Personalized skin generation method and device, electronic equipment and computer program product

Abstract

The invention provides a personalized skin generation method and device, electronic equipment and a computer program product, and the method can obtain a skin generation demand of a system interface, the skin generation demand comprises a skin content description statement, the skin content description statement is expanded according to a scene described by the skin content description statement, and the skin content description statement is generated according to the expanded skin content description statement. According to the method, the skin content cue word is obtained, and the system interface skin meeting the skin generation requirement is generated at least according to the skin content cue word, so that the system interface skin can be generated according to the requirement of the user, and the requirement of the user for personalized dress-up is met.

Description

Technical Field

[0001] The present application relates to the technical field of skin generation, and in particular to a personalized skin generation method, device, electronic device and computer program product. Background Art

[0002] Software system interface is an important tool for users to interact with the digital world. With the rapid development of the Internet, the demand for personalized software system interface is growing. Although there are many kinds of software system interface skins on the market, they are often limited to established templates and cannot meet users' needs for personalized dressing. Summary of the invention

[0003] In view of this, the present application proposes a personalized skin generation method, device, electronic device and computer program product to solve the problem that although there are many types of software system interface skins on the current market, they are often limited by established templates and cannot meet users' needs for personalized dressing.

[0004] The technical solutions proposed in this application are as follows:

[0005] In a first aspect, an embodiment of the present application provides a personalized skin generation method, comprising:

[0006] Acquire the skin generation requirement of the system interface; the skin generation requirement includes a skin content description statement;

[0007] Expanding the skin content description sentence according to the scene described by the skin content description sentence to obtain skin content prompt words;

[0008] At least according to the skin content prompt word, a system interface skin that meets the skin generation requirements is generated.

[0009] Furthermore, in the above method, the step of expanding the skin content description sentence according to the scene described by the skin content description sentence to obtain the skin content prompt words includes:

[0010] According to the scene described by the skin content description sentence and the skin style requirements of each functional area in the system interface, the skin content description sentence is expanded to obtain the skin content prompt words corresponding to each functional area.

[0011] Furthermore, in the above method, the function area includes a background area and an option area;

[0012] The skin content description statement is expanded according to the scene described by the skin content description statement and the skin style requirements of each functional area in the system interface to obtain the skin content prompt words corresponding to each functional area, including:

[0013] According to the scene described by the skin content description sentence, the elements in the skin content description sentence are expanded to obtain the skin content prompt words corresponding to the background area;

[0014] According to the scene described by the skin content description sentence, an element description sentence associated with the scene is generated as the skin content prompt word corresponding to the option area.

[0015] Furthermore, in the above method, the elements in the skin content description sentence are expanded according to the scene described by the skin content description sentence to obtain the skin content prompt words corresponding to the background area, including:

[0016] Inputting the skin content description sentence and the first expanded prompt word into a large language model, so that the large language model expands the elements in the skin content description sentence according to the scene described by the skin content description sentence to obtain the skin content prompt word corresponding to the background area;

[0017] The first expansion prompt word is used to instruct the large language model to perform a task of expanding elements in the skin content description sentence according to the scenario described by the skin content description sentence.

[0018] Furthermore, in the above method, generating an element description sentence associated with the scene as the skin content prompt word corresponding to the option area according to the scene described by the skin content description sentence includes:

[0019] Inputting the skin content description sentence and the second expanded prompt word into a large language model, so that the large language model generates an element description sentence associated with the scene as the skin content prompt word corresponding to the option area according to the scene described by the skin content description sentence;

[0020] The second extended prompt word is used to instruct the large language model to perform a task of generating an element description sentence associated with the scene according to the scene described by the skin content description sentence; wherein each option area corresponds to a skin content prompt word.

[0021] Furthermore, in the above method, the skin generation requirement also includes a skin style requirement, and the step of generating a system interface skin that meets the skin generation requirement at least according to the skin content prompt word includes:

[0022] According to the skin style requirement and the skin content prompt word, a system interface skin that meets the skin generation requirement is generated.

[0023] Furthermore, in the above method, generating a system interface skin that meets the skin generation requirement according to the skin style requirement and the skin content prompt word includes:

[0024] Generate skin pictures for each functional area in the system interface according to the skin style requirements and the skin content prompt words;

[0025] The skin images of each functional area are combined according to the structure of the system interface to obtain a system interface skin that meets the skin generation requirements.

[0026] Furthermore, in the above method, generating skin images of each functional area in the system interface according to the skin style requirements and the skin content prompt words includes:

[0027] The skin style requirement and the skin content prompt word are input into a pre-trained skin generation model, so that the skin generation model generates skin pictures for each functional area in the system interface according to the skin style requirement and the skin content prompt word.

[0028] Furthermore, in the above method, the skin generation model is trained using the ip-adapter solution with sample skin style requirements as training samples and with the goal of generating a system interface skin that meets the sample skin style requirements.

[0029] In a second aspect, an embodiment of the present application provides a personalized skin generation device, comprising:

[0030] An acquisition module, used for acquiring skin generation requirements of a system interface; the skin generation requirements include skin content description statements;

[0031] An expansion module, used to expand the skin content description sentence according to the scene described by the skin content description sentence to obtain skin content prompt words;

[0032] A generation module is used to generate a system interface skin that meets the skin generation requirements at least according to the skin content prompt word.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0034] A memory and a processor; wherein the memory is used to store programs; and the processor is used to implement any of the methods described above by running the programs in the memory.

[0035] In a fourth aspect, an embodiment of the present application provides a computer program product, the computer program product comprising a computer program, and when the computer program is executed by a processor, the computer program implements any one of the above methods. Optionally, the computer program can be stored in a readable storage medium of a computer device or in the cloud; the processor of the computer device reads the computer program from the readable storage medium or the cloud.

[0036] The personalized skin generation method proposed in the present application can obtain the skin generation requirements of the system interface, wherein the skin generation requirements include skin content description sentences, and the skin content description sentences are expanded according to the scenarios described by the skin content description sentences to obtain skin content prompt words. At least based on the skin content prompt words, a system interface skin that meets the skin generation requirements is generated. In this way, the system interface skin can be generated according to the user's needs to meet the user's needs for personalized dressing. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application 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, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0038] Figure 1 It is a schematic diagram of an application scenario of the personalized skin generation method provided in an embodiment of the present application.

[0039] Figure 2 It is a flow chart of a personalized skin generation method provided in an embodiment of the present application.

[0040] Figure 3 It is a schematic diagram of the keyboard skin quality provided in the embodiment of the present application.

[0041] Figure 4 It is a flowchart of generating a keyboard skin provided in an embodiment of the present application.

[0042] Figure 5 It is a structural schematic diagram of a personalized skin generation device provided in an embodiment of the present application.

[0043] Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] The software system interface is the portal of the software system and an important tool for users to interact with the digital world. With the rapid development of the Internet, people's demand for personalized software system interfaces is growing. Although there are many types of software system interface skins on the market, the existing skins are all made by designers and put on the shelves. Users have limited choices among skins and it is difficult to accurately find the skin they want, which makes it difficult to meet users' needs for personalized dressing.

[0046] Based on this, the present application proposes a personalized skin generation method, device, electronic device and computer program product. The technical solution automatically generates a personalized skin matching the text content input by the user, thereby achieving the effect of satisfying the user's demand for personalized dressing.

[0047] Figure 1 The embodiment shown shows a feasible application scenario of the personalized skin generation method, such as Figure 1 In the scenario shown, a client and a server are set up.

[0048] The client can be an electronic device with network access capability. Specifically, for example, the client can be a desktop computer, a tablet computer, a laptop computer, a smart phone, a digital assistant, a smart wearable device, a shopping guide terminal, a television, etc. Among them, the smart wearable device includes but is not limited to a smart bracelet, a smart watch, a smart glasses, a smart helmet, a smart necklace, etc. Alternatively, the client can also be software that can run in an electronic device.

[0049] The server can be an electronic device with certain computing and processing capabilities. It can have a network communication module, a processor, and a memory, etc. Of course, the server can also refer to software running in an electronic device. The server can also be a distributed server, which can be a system with multiple processors, memories, network communication modules, etc. operating in collaboration. Alternatively, the server can also be a server cluster formed by several servers. Alternatively, with the development of science and technology, the server can also be a new technical means that can realize the corresponding functions of the implementation method of the specification. For example, it can be a new form of "server" based on quantum computing.

[0050] The client and the server can communicate through the target network. The target network can be any type of network. For example, the target network can be a network that can be subdivided into multiple subnetworks. The target network or the multiple subnetworks contained in the target network can be at least one of a cellular mobile network (such as 2G, 3G, 4G or 5G), ZIGBEE, WIFI, Bluetooth, or any combination of at least one of these networks and other networks.

[0051] In the above feasible application scenario, the client obtains the skin generation requirements of the system interface, which includes a skin content description statement, and then sends the skin generation requirements to the server. The server obtains the skin generation requirements from the client, expands the skin content description statement according to the scenario described by the skin content description statement in the skin generation requirements, obtains the skin content prompt words, and generates a system interface skin that meets the skin generation requirements at least based on the skin content prompt words, and then sends the system interface skin to the client, and the client configures the system interface skin as the system interface skin. With this setting, the system interface skin can be generated according to the user's needs to meet the user's needs for personalized dressing.

[0052] Furthermore, the embodiment of the present application proposes a personalized skin generation method, which can be executed by an electronic device, which can be any device with data and instruction processing functions, for example, a notebook computer, a tablet computer, a desktop computer, a mobile device (for example, a mobile phone, a personal digital assistant, a dedicated messaging device) and other types of user terminals or a combination of any two or more of these electronic devices; it can also be a server, for example, the server in the above embodiment. See Figure 2 As shown, the method includes:

[0053] S101, obtaining skin generation requirements for the system interface.

[0054] The above-mentioned system interface refers to the interface for which a personalized skin needs to be generated. Among them, any system that has an interactive interface with a user, the interface of the system can be used as the system interface of this embodiment, and the skin is generated according to the personalized skin generation method of this embodiment. The type of the system is not limited in this embodiment. For example, the system can be a small program, an application (Application, APP), computer software, a website, etc., which is not limited in this embodiment. APP includes various applications installed on the client, such as input method APP, etc., which is not limited in this embodiment.

[0055] The above-mentioned skin generation requirements include skin content description sentences, which are generally input by users. Among them, the skin content description sentence refers to a sentence describing the user's requirements for the skin, such as the style of the skin, the content of the picture, etc., which is not limited in this embodiment. Exemplarily, the skin content description sentence is "a girl, autumn countryside".

[0056] In the embodiment of the present application, the format of the skin content description sentence is not limited. The skin content description sentence can be a text format content input by the user, or a voice format content. However, it should be noted that if the skin content description sentence is a voice format content, the voice format content needs to be converted into text first.

[0057] S102: Expand the skin content description sentence according to the scene described by the skin content description sentence to obtain skin content prompt words.

[0058] There are generally many locations in the system interface where skins need to be generated, and each functional area of ​​the system interface needs to generate corresponding skins. In some embodiments, the functional area of ​​the system interface includes a background area and multiple option areas, and skins need to be generated for both the background area and the multiple option areas. It should be noted that the option area refers to an area with different functions in the system interface, such as an area for displaying different content, and an area that can execute various functions after clicking. Exemplarily, the option area in the input method APP refers to each key in the keyboard. The skin of the input method APP includes the keyboard background skin and the skin of each key in the keyboard. Generally, a nine-key input method keyboard includes about 20 keys, while a twenty-six-key input method keyboard contains more keys, generally about 30.

[0059] If the skin content description sentence input by the user provides less information, directly generating the skin according to the skin content description sentence will result in less generated skin content or more repetitive content, affecting the generated skin effect.

[0060] Based on this, in this embodiment, after obtaining the skin content description sentence, the skin content description sentence is first expanded. In order to make the expanded content consistent with the skin content description sentence, the skin content description sentence needs to be expanded according to the scene described by the skin content description sentence to obtain the skin content prompt words. That is to say, when expanding the skin content description sentence, the content corresponding to the expanded sentence should be the content in the scene described by the skin content description sentence. For example, if the skin content description sentence is "cool and refreshing in summer", then the content corresponding to the expanded sentence should be the content in the summer cooling scene, such as iced watermelon, ice cream, swimming pool, etc., and down jackets, stoves, etc. should not appear.

[0061] When the skin content description statement is expanded, the expanded content should not only conform to the scene described by the content description statement, but also contain sufficient content to be used as material to generate skins corresponding to the background area and each option area. In some embodiments, both the background and each option area are expanded to obtain skin content prompt words for the background and skin content prompt words for each option area.

[0062] In some embodiments, a large language model can be used to expand the skin content description sentence according to the scene described by the skin content description sentence to obtain skin content prompt words. A large number of skin content description sentences can be obtained as training samples, and then the skin content description sentences can be manually expanded according to the scene described by the skin content description sentence to obtain skin content prompt words as training labels. Exemplarily, the skin content description sentence can be manually expanded for the background area to obtain the skin content prompt words for the background area, and the skin content description sentence can be manually expanded for each option area to obtain the skin content prompt words for each option area. Then, the large language model is fine-tuned in a supervised manner using the above-mentioned training samples and training labels until the large language model meets expectations. Among them, the large language model can adopt a mature large language model in the prior art, which is not limited in this embodiment.

[0063] The skin content description sentence is input into the fine-tuned large language model to obtain the skin content prompt words output by the large language model, including skin content prompt words for the background and skin content prompt words for each option area.

[0064] S103: Generate a system interface skin that meets skin generation requirements at least according to the skin content prompt word.

[0065] Then, the system interface skin is generated at least according to the skin content prompt words. In some embodiments, a pre-trained image generation model can be used to generate the system interface skin according to the skin content prompt words.

[0066] The skin resources of the system interface can be obtained, and then the skin content prompt words of these skin resources can be manually annotated. The manually annotated skin content prompt words are used as training samples, and the corresponding skin resources are used as training labels to train the image generation model.

[0067] The specific training process is to input the training sample into the image generation model to obtain the prediction result of the image generation model, and obtain the loss of the image generation model by comparing the prediction result of the image generation model with the training sample. The parameters of the image generation model are adjusted with the goal of reducing the loss of the image generation model. Then the above process is repeated until the image generation model meets expectations. In this way, the image generation model has the ability to generate skin images corresponding to the background area and each option area according to the skin content prompt word. At the same time, in the generated skin image, the skin image size of the background area meets the skin size requirements of the background area in the system interface, and the skin image size of each option area meets the skin size requirements of each option area in the system interface. The image generation model can adopt a text-to-image generation model (Text-to-Image model, T2I) and the like, which is not limited in this embodiment.

[0068] The skin content prompt words for the background and the skin content prompt words for each option area are input into the trained image generation model to obtain the skin image for the background area and the skin image for each option area output by the image generation model. Then, the skin image for the background area and the skin image for each option area are arranged and combined according to the positional relationship between the background area and the option areas to obtain the system interface skin that meets the skin generation requirements.

[0069] In the above embodiment, the skin generation requirements of the system interface can be obtained, wherein the skin generation requirements include skin content description sentences, the skin content description sentences are expanded according to the scenarios described by the skin content description sentences, and skin content prompt words are obtained. At least based on the skin content prompt words, a system interface skin that meets the skin generation requirements is generated. In this way, the system interface skin can be generated according to the user's needs to meet the user's needs for personalized dressing.

[0070] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment are to expand the skin content description sentence according to the scene described by the skin content description sentence to obtain the skin content prompt word, which may specifically include the following steps:

[0071] According to the scenario described by the skin content description sentence and the skin style requirements of each functional area in the system interface, the skin content description sentence is expanded to obtain the skin content prompt words corresponding to each functional area.

[0072] As described in the above embodiment, the system interface includes multiple function areas, wherein the function area includes a background area and multiple option areas.

[0073] In this embodiment, skin style requirements are set for each functional area. The skin style requirements for each functional area specify the style type of the skin of each functional area, such as the number of elements that the skin of each functional area should contain. The skin style requirements can be set according to actual needs and are not limited in this embodiment. For example, the skin style requirement for the background area can be that the skin corresponding to the background area should contain multiple elements, and the skin style requirement for the option area can be that each option area should contain one element. Among them, the elements in this embodiment refer to entity elements.

[0074] According to the scenario described by the skin content description sentence and the skin style requirements of each functional area in the system interface, the skin content description sentence is expanded to obtain more standardized skin content prompt words corresponding to each functional area, and the generated skin image is more in line with the system interface.

[0075] In some embodiments, the skin content description statement and the skin style requirements for each functional area can be input into a fine-tuned large language model, so that the large language model can expand the skin content description statement according to the scenario described by the skin content description statement and the skin style requirements for each functional area in the system interface, and obtain the skin content prompt words corresponding to each functional area.

[0076] It should be noted that when fine-tuning the large language model, a large number of skin content description sentences and skin style requirements for each functional area can be obtained as training samples, and then the skin content description sentences are manually expanded according to the skin content description sentences and the skin style requirements for each functional area to obtain skin content prompt words as training labels. Then, the large language model is fine-tuned in a supervised manner using the above training samples and training labels until the large language model meets expectations.

[0077] In the above embodiment, the skin content description statement can also be expanded according to the skin style requirements of each functional area in the system interface, so that the skin content prompt words corresponding to each functional area are more standardized and the generated skin image is more in line with the system interface.

[0078] As an optional implementation, another embodiment of the present application discloses that the function area of ​​the above embodiment includes a background area and an option area. The steps of the above embodiment are to expand the skin content description statement according to the scene described by the skin content description statement and the skin style requirements of each function area in the system interface to obtain the skin content prompt words corresponding to each function area, which may specifically include the following steps:

[0079] According to the scene described by the skin content description sentence, the elements in the skin content description sentence are expanded to obtain the skin content prompt words corresponding to the background area; according to the scene described by the skin content description sentence, an element description sentence associated with the scene is generated as the skin content prompt words corresponding to the option area.

[0080] In this embodiment, the skin style requirement of the skin image of the background area is that the skin image of the background area includes the scene described by the skin content description sentence, and the scene includes multiple elements. Therefore, it is necessary to expand the elements in the skin content description sentence according to the skin style requirement and the scene described by the skin content description sentence to obtain the skin content prompt words corresponding to the background area, so as to generate a skin image that meets the requirements according to the skin content prompt words. For example, the skin content description sentence is "a girl, autumn countryside", and the corresponding generated background area skin content prompt words are "a girl wearing a yellow hat, pigtails, and an overalls skirt, looking into the distance in the autumn countryside, surrounded by golden plants, and there are a few small houses in the distance."

[0081] The skin style requirement for the skin image in the option area is that the skin image in each option area contains an element in the scene described by a skin content description sentence. Therefore, it is necessary to generate an element description sentence associated with the scene as the skin content prompt word corresponding to the option area according to the skin style requirement and the scene described by the skin content description sentence, so as to generate a skin image that meets the requirements according to the skin content prompt word. One of the option areas corresponds to one element. For example, if the skin content description sentence is "a girl, autumn countryside" and it is required to generate element description sentences for three option areas, the corresponding generated option area skin content prompt words are "a pumpkin", "a chicken" and "a basket".

[0082] In the above embodiment, the skin content description statement can be expanded according to the skin style requirements, so that the skin content prompt words corresponding to each functional area are more standardized, and the skin image generated according to the skin content prompt words is more in line with the system interface.

[0083] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment are to expand the elements in the skin content description sentence according to the scene described by the skin content description sentence to obtain the skin content prompt words corresponding to the background area, which may specifically include the following steps:

[0084] The skin content description sentence and the first expanded prompt word are input into the large language model, so that the large language model expands the elements in the skin content description sentence according to the scene described by the skin content description sentence to obtain the skin content prompt word corresponding to the background area.

[0085] The first expansion prompt word is used to instruct the large language model to perform the task of expanding the elements in the skin content description sentence according to the scene described by the skin content description sentence. It can be understood that the first expansion prompt word corresponds to the skin style requirement of the background area, that is, the large language model needs to expand the elements in the skin content description sentence according to the scene described by the skin content description sentence, so that the skin image of the background area includes the scene described by the skin content description sentence, and the scene includes multiple elements.

[0086] In a specific embodiment, the first extended prompt word includes "As a prompt master with rich associative ability, you can quickly complete the elements that should be included in any input scene or picture to make the picture elements richer."

[0087] The above skin content description sentence and the first expanded prompt word are input into the large language model, so that the large language model expands the elements in the skin content description sentence according to the scene described by the skin content description sentence to obtain the skin content prompt word corresponding to the background area.

[0088] In addition to fine-tuning the large language model in a supervised manner according to the above embodiment, a large number of skin content description sentences and first expansion prompt words can also be obtained, and then the skin content description sentences are manually expanded according to the skin content description sentences and the first expansion prompt words to obtain skin content prompt words. The skin content description sentences, the first expansion prompt words and the obtained skin content prompt words are input into the large language model, so that the large language model can learn and then have the ability to generate skin content prompt words corresponding to the background area according to the skin content description sentences and the first expansion prompt words.

[0089] In the above embodiment, the large language model can be used to quickly and accurately generate the skin content prompt words corresponding to the background area according to the skin content description sentence and the first expanded prompt words.

[0090] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment generate an element description sentence associated with the scene as a skin content prompt word corresponding to the function item according to the scene described by the skin content description sentence, which may specifically include the following steps:

[0091] The skin content description sentence and the second expanded prompt word are input into the large language model, so that the large language model generates an element description sentence associated with the scene as the skin content prompt word corresponding to the option area according to the scene described by the skin content description sentence.

[0092] The second extended prompt word is used to instruct the large language model to perform the task of generating an element description sentence associated with the scene according to the scene described by the skin content description sentence; wherein each option area corresponds to a skin content prompt word. It can be understood that the second extended prompt word corresponds to the skin style requirement of the option area, that is, the large language model should generate an element description sentence associated with the scene as the skin content prompt word corresponding to the function item according to the scene described by the skin content description sentence, so that the skin image of each option area contains an element in the scene described by the skin content description sentence.

[0093] In a specific embodiment, the second extended prompt word includes "As a prompt master with rich associative ability, you can quickly associate N closely related objects with any input scene or picture and output entity nouns to help me broaden my thinking. According to the picture or scene description I provide, output N entity nouns related to it to promote the user's divergent thinking and creativity." N is the number of option areas.

[0094] In some embodiments, in order to enable the large language model to understand the task more clearly, more specific content may be set in the second expansion prompt, such as requiring the specific format of the element description sentence, the size of the element, etc. in the second expansion prompt.

[0095] For example, if the number of option areas is 9, the second extended prompt word may include:

[0096] As a hint master, your task is to output 9 relevant entity nouns based on the description I input. Please strictly output appropriate entity nouns according to the requirements in {}. The following are the relevant requirements:

[0097] {

[0098] 1. Generate a subject that matches the described picture or scene. The subject must be logically related to the input and have an observable regular shape, such as an apple, a puppy, a table, a lamp, a shell, and other solid objects. Avoid generating objects without a fixed shape, such as sunlight, rivers, streams, wind, lakes, and the sky. Avoid generating some abstract concepts, such as a painting or a scene;

[0099] 2. The output format is {quantifier}+{entity noun}, for example, {"a piece of xx", "a flower of xx", "a piece of xx", "a piece of xx"}; avoid adding other modifying words;

[0100] 3. The volume of the object must be less than 20 cubic meters.

[0101] }

[0102] Here are a few examples and the input and output formats:

[0103] Input: {a desk lamp, warm light, minimalist style}

[0104] Output: {a table, a chair, a book, a vase, a mug, a lamp, an alarm clock, a plant, a pair of glasses}

[0105] Input: {a girl, surfing at the beach, half-length portrait, Disney style}

[0106] Output: {a shell, a small fish, a conch, a starfish, a surfboard, a seagull, a jellyfish, a boat, a pair of sunglasses}

[0107] Input: {a fawn, forest, illustration style}

[0108] Output: {a flower, a stone, a clover, a mushroom, a leaf, a pine cone, a hazelnut, a squirrel, a butterfly}

[0109] Input: {moon, night, dream style}

[0110] Output: {a star, a cloud, a lantern, an owl, an epiphyllum, a bottle of red wine, a crescent moon, a shooting star, a butterfly}

[0111] Input: {a tiger, cute, grassland, anime style}

[0112] Output: {a lamb, a stone, a deer, a flower, a clover, a rabbit, a green leaf, a grass, a haystack}

[0113] Input: {a girl, magical, cute, 2D style}

[0114] Output: {a staff, a cat, a magic stone, a wizard's hat, a fairy, a magic wand, a fireball, a dragon, a magic book}

[0115] The skin content description sentence and the second expanded prompt word are input into the large language model, so that the large language model generates an element description sentence associated with the scene as the skin content prompt word corresponding to the option area according to the scene described by the skin content description sentence.

[0116] In addition to fine-tuning the large language model in a supervised manner as described in the above embodiment, a large number of skin content description sentences and second expanded prompt words can also be obtained, and then the skin content description sentences are manually expanded according to the skin content description sentences and the second expanded prompt words to obtain skin content prompt words. Then, the skin content description sentences, the second expanded prompt words and the obtained skin content prompt words are input into the large language model, so that the large language model can learn and then have the ability to generate skin content prompt words corresponding to the option area according to the skin content description sentences and the second expanded prompt words.

[0117] In the above embodiment, the large language model can be used to quickly and accurately generate the skin content prompt word corresponding to the option area according to the skin content description sentence and the second expanded prompt word.

[0118] As an optional implementation, another embodiment of the present application discloses that the skin generation requirement in the above embodiment also includes a skin style requirement. The steps in the above embodiment generate a system interface skin that meets the skin generation requirement based on at least the skin content prompt word, which may specifically include the following steps:

[0119] According to the skin style requirements and skin content prompt words, a system interface skin that meets the skin generation requirements is generated.

[0120] Skin generation requirements also include skin style requirements. That is, in addition to entering skin content prompts, users can also enter skin style requirements, which indicate the style of the skin required by the user. The addition of skin style requirements makes the user's requirements more obvious and specific, and the generated system interface skin is more specific and meets the user's requirements.

[0121] In this embodiment, a system interface skin that meets the skin generation requirements is generated based on the skin style requirements and the skin content prompt words. Specifically, the skin style requirements and the skin content prompt words can be input into the trained image generation model, so that the skin image for the background area and the skin images for each option area are output in the image generation model. Then, the skin image of the background area and the skin images of each option area are arranged and combined according to the positional relationship between the background area and each option area, so as to obtain a system interface skin that meets the skin generation requirements.

[0122] It should be noted that when training the image generation model, in addition to using the manually annotated skin content prompt words as training samples according to the above embodiment, it is also necessary to manually annotate the style of the skin resources and add the style corresponding to the skin resources to the training samples. Then, the image generation model is trained according to the training method described in the above embodiment. The skin style requirements and skin content prompt words are input into the trained image generation model to obtain the skin images for the background area and the skin images for each option area output by the image generation model.

[0123] In the above embodiment, skin style requirements are added. According to the skin style requirements and skin content prompt words, the generated system interface skin is more specific and more in line with the user's requirements.

[0124] Optionally, the steps of the above embodiment may include: splicing the skin content description sentence and the skin style requirements to obtain a revised skin content description sentence, and then expanding the skin content description sentence according to the scene described by the revised skin content description sentence and the skin style requirements of each functional area in the system interface to obtain the skin content prompt words corresponding to each functional area. Then, based at least on the skin content prompt words, a system interface skin that meets the skin generation requirements is generated.

[0125] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment generate a system interface skin that meets the skin generation requirements according to the skin style requirements and the skin content prompt words, which may specifically include the following steps:

[0126] According to the skin style requirements and skin content prompt words, skin pictures of each functional area in the system interface are generated; according to the structure of the system interface, the skin pictures of each functional area are combined to obtain a system interface skin that meets the skin generation requirements.

[0127] The skin style requirements and skin content prompt words are input into the image generation model trained in the above steps to obtain the skin images for the background area and the skin images for each option area output by the image generation model.

[0128] Then, according to the structure of the system interface, the skin images of each functional area are combined to obtain a system interface skin that meets the skin generation requirements. The structure of the system interface includes the positional relationship between the background area and each option area. According to the positional relationship between the background area and each option area, the skin image of the background area and the skin image of each option area are arranged and combined to obtain a system interface skin that meets the skin generation requirements.

[0129] It should be noted that sometimes the image generated by the large language model has a background. In order to make the skin image of each option area clearer and eliminate the interference of the background image, the background of the skin image of each option area can be removed. For example, the matting algorithm can be used to perform a cutout operation on the skin image of each option area, remove the background of the skin image of each option area, and arrange and combine the skin image of the background area and the skin images of each option area after the cutout processing according to the positional relationship between the background area and each option area to obtain a system interface skin that meets the skin generation requirements.

[0130] In addition to using the image generation model trained in the above embodiment to generate the image of the background area and the skin images of each option area, as an optional implementation method, another embodiment of the present application discloses that the steps of the above embodiment generate skin images of each functional area in the system interface according to the skin style requirements and the skin content prompt words, which may specifically include the following steps:

[0131] The skin style requirements and skin content prompt words are input into the pre-trained skin generation model, so that the skin generation model generates skin images for each functional area in the system interface according to the skin style requirements and skin content prompt words.

[0132] In the embodiment of the present application, a skin generation model is pre-trained, and the skin generation model can generate skin images of each functional area in the system interface according to the skin style requirements and skin content prompt words. The skin generation model uses the sample skin style requirements as training samples and aims to generate system interface skins that meet the sample skin style requirements, and is trained using the ip-adapter solution.

[0133] Specifically, a large number of skin resources can be obtained, and the style of each skin resource can be manually annotated. It should be noted that after the skin resources are obtained, these skin resources can be divided into high-end resources, low-end resources and mid-range resources according to their quality, and high-end skin resources can be selected for model training to ensure the effect of the skin image generated by the skin generation model. In some embodiments, if the system interface is the keyboard of the input method APP, then in the skin resources corresponding to the keyboard of the input method APP, Figure 3 Image a in corresponds to high-end resources, Figure 3 Image b in corresponds to the mid-range resource, Figure 3 Image c in corresponds to the low-end resource.

[0134] The manually annotated styles are used as training samples, and the corresponding skin resources are used as training labels to train the skin generation model. To ensure consistency between option areas, the ip-adapter solution is used for training, and the style input is unified, so that skin images corresponding to multiple option areas with consistent styles can be generated under the same skin content prompt words. The image generation model can adopt the T2I model, etc., which is not limited in this embodiment.

[0135] In some embodiments, multiple style types are set in advance, such as cute cartoon style, anime style, two-dimensional style, hand-painted style, fantasy style, etc., which are not limited in this embodiment. When manually annotating skin resources, select the corresponding style from the multiple style types set in advance for annotation, so that the skin generation model can have the ability to generate skin images that meet the style requirements. At the same time, in the generated skin image, the skin image size of the background area meets the skin size requirements of the background area in the system interface, and the skin image size of each option area meets the skin size requirements of each option area in the system interface. When the user enters the skin style requirements, he also needs to select from the multiple style types set in advance.

[0136] In the above embodiment, the skin generation model is used to quickly and accurately generate skin images that meet user needs. Since the skin images of each functional area are generated based on the same skin content prompt word, and the skin images of each option area can be generated separately, the overall skin effect and details are guaranteed, while ensuring the richness and exquisiteness of the generated skin.

[0137] In a specific embodiment, the system interface is a nine-key keyboard of an input method APP, and the skin generation requirement is a keyboard skin generation requirement. Figure 4 As shown, the method for generating a personalized skin of the keyboard may include:

[0138] Gets the skin content description statement and skin style requirements for the keyboard skin.

[0139] For example, the skin content description sentence is "A girl, autumn countryside", and the user selects the style he needs from "cute cartoon style, anime style, two-dimensional style, hand-painted style, fantasy style, illustration style, and painted style" as the skin style requirement, and the skin style requirement selected by the user is "illustration style".

[0140] The skin content description sentence and the first expanded prompt word are input into the large language model, so that the large language model expands the elements in the skin content description sentence according to the scene described by the skin content description sentence, and obtains the skin content prompt word corresponding to the background area. Exemplarily, the skin content prompt word corresponding to the background area includes "a girl wearing a yellow hat, pigtails, and an overalls skirt, looking into the distance in the autumn countryside, surrounded by golden plants, and there are several small houses in the distance."

[0141] The skin content description sentence and the second expanded prompt word are input into the large language model, so that the large language model generates an element description sentence associated with the scene as the skin content prompt word corresponding to the option area according to the scene described by the skin content description sentence. Exemplarily, there are 9 skin content prompt words corresponding to the option area, namely "a pumpkin, a chicken, a scarecrow, an apple tree, a bottle of juice, a small house, a pair of boots, a hat, and a basket". Among them, the option area corresponds to the keyboard key.

[0142] Then the skin style requirements and skin content prompt words are input into the pre-trained skin generation model, so that the skin generation model generates skin images for each functional area in the system interface according to the skin style requirements and skin content prompt words, including a skin image corresponding to the background area and skin images corresponding to the 9 option areas.

[0143] Then, the matting algorithm is used to perform a matting operation on the skin image corresponding to the option area, and the independent area of ​​the skin image of each keyboard key is accurately extracted. After the matting is completed, the skin image of the keyboard key is synthesized with the skin image of the background area to form a complete keyboard skin, such as Figure 4 shown.

[0144] Corresponding to the above-mentioned personalized skin generation method, the embodiment of the present application also discloses a personalized skin generation device, see Figure 5 As shown, the device comprises:

[0145] The acquisition module 100 is used to acquire the skin generation requirements of the system interface; the skin generation requirements include skin content description statements;

[0146] An expansion module 110 is used to expand the skin content description sentence according to the scene described by the skin content description sentence to obtain skin content prompt words;

[0147] The generating module 120 is used to generate a system interface skin that meets the skin generation requirements at least according to the skin content prompt words.

[0148] As an optional implementation, another embodiment of the present application discloses that the expansion module 110 in the above embodiment is specifically used for:

[0149] According to the scenario described by the skin content description sentence and the skin style requirements of each functional area in the system interface, the skin content description sentence is expanded to obtain the skin content prompt words corresponding to each functional area.

[0150] As an optional implementation, another embodiment of the present application discloses that the function area of ​​the above embodiment includes a background area and an option area; the expansion module 110 of the above embodiment is specifically used for:

[0151] According to the scene described by the skin content description sentence, the elements in the skin content description sentence are expanded to obtain the skin content prompt words corresponding to the background area; according to the scene described by the skin content description sentence, an element description sentence associated with the scene is generated as the skin content prompt words corresponding to the function item.

[0152] As an optional implementation, another embodiment of the present application discloses that the expansion module 110 in the above embodiment is specifically used for:

[0153] The skin content description sentence and the first expansion prompt word are input into the large language model so that the large language model expands the elements in the skin content description sentence according to the scene described by the skin content description sentence to obtain the skin content prompt word corresponding to the background area; the first expansion prompt word is used to instruct the large language model to perform the task of expanding the elements in the skin content description sentence according to the scene described by the skin content description sentence.

[0154] As an optional implementation, another embodiment of the present application discloses that the expansion module 110 in the above embodiment is specifically used for:

[0155] The skin content description sentence and the second extended prompt word are input into the large language model so that the large language model generates an element description sentence associated with the scene as the skin content prompt word corresponding to the option area according to the scene described by the skin content description sentence; the second extended prompt word is used to instruct the large language model to perform the task of generating an element description sentence associated with the scene according to the scene described by the skin content description sentence; wherein each option area corresponds to a skin content prompt word.

[0156] As an optional implementation, another embodiment of the present application discloses that the skin generation requirement of the above embodiment also includes a skin style requirement, and the generation module 120 of the above embodiment is specifically used for:

[0157] According to the skin style requirements and skin content prompt words, a system interface skin that meets the skin generation requirements is generated.

[0158] As an optional implementation, another embodiment of the present application discloses that the skin generation requirement of the above embodiment also includes a skin style requirement, and the generation module 120 of the above embodiment is specifically used for:

[0159] According to the skin style requirements and skin content prompt words, skin pictures of each functional area in the system interface are generated; according to the structure of the system interface, the skin pictures of each functional area are combined to obtain a system interface skin that meets the skin generation requirements.

[0160] As an optional implementation, another embodiment of the present application discloses that the skin generation requirement of the above embodiment also includes a skin style requirement, and the generation module 120 of the above embodiment is specifically used for:

[0161] The skin style requirements and skin content prompt words are input into the pre-trained skin generation model, so that the skin generation model generates skin images for each functional area in the system interface according to the skin style requirements and skin content prompt words.

[0162] As an optional implementation method, another embodiment of the present application discloses that the skin generation model is trained using the sample skin style requirements as training samples and is aimed at generating a system interface skin that meets the sample skin style requirements, using the ip-adapter solution.

[0163] Specifically, the device provided in this embodiment belongs to the same application concept as the method provided in the above embodiment of this application, can execute the method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of the execution method. For the technical details not fully described in this embodiment, please refer to the specific processing content of the method provided in the above embodiment of this application, which will not be repeated here.

[0164] The functions implemented by the above modules can be implemented by the same or different processors respectively, and the embodiments of the present application are not limited thereto.

[0165] It should be understood that the units in the above devices can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device, wherein the processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory in the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits, and the functions of some or all units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD, taking FPGA as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by the configuration file, so as to realize the functions of some or all of the above units. All units of the above devices can be implemented in the form of a processor calling software, or in the form of hardware circuits, or in part by a processor calling software, and the remaining part is implemented in the form of hardware circuits.

[0166] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and run instructions, such as a CPU, a microprocessor, a GPU, or a DSP; in another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0167] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0168] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a SOC. The SOC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0169] An embodiment of the present application further provides a control device, which includes a processor and an interface circuit. The processor in the control device is connected to an input-output component through the interface circuit of the control device.

[0170] The input-output component specifically refers to a hardware component that enables a user to input information and output information to the user, such as a microphone, keyboard, handwriting tablet, touch screen, display, speaker, printer, etc.

[0171] The above-mentioned interface circuit can be any interface circuit that can realize the data communication function, for example, it can be a USB interface circuit, a Type-C interface circuit, a serial port circuit, a PCIE circuit, etc.

[0172] The processor in the control device is a circuit with signal processing capability, which satisfies the user's demand for personalized dressing by executing any of the personalized skin generation methods described in the above embodiments. The specific implementation of the processor can refer to the above processor implementation, and the embodiments of this application are not strictly limited.

[0173] When the control device is applied to a device with a human-computer interaction function, the input and output components of the control device may be input components and output components on the device, such as a microphone, a keyboard, a handwriting tablet, a touch screen, a display, an audio player, etc. At the same time, the processor of the control device may be a CPU or GPU, etc. provided by the device, and the interface circuit of the control device may be an interface circuit between the information input component of the device and a processor such as a CPU or GPU.

[0174] Corresponding to the above-mentioned personalized skin generation method, the present application embodiment also discloses an electronic device, see Figure 6 As shown, the electronic device includes:

[0175] Memory 200 and processor 210;

[0176] The memory 200 is connected to the processor 210 and is used to store programs;

[0177] The processor 210 is used to implement the personalized skin generation method disclosed in any of the above embodiments by running the program stored in the memory 200.

[0178] Specifically, the electronic device may further include: a bus, a communication interface 220 , an input device 230 and an output device 240 .

[0179] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are connected to each other via a bus.

[0180] A bus may include a pathway that transfers information between components of a computer system.

[0181] The processor 210 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0182] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0183] The memory 200 stores a program for executing the technical solution of the present application, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes computer operation instructions. More specifically, the memory 200 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0184] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0185] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0186] The communication interface 220 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0187] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement the various steps of the personalized skin generation method provided in the above embodiments of the present application.

[0188] In addition to the above methods and devices, the embodiments of the present application may also be a computer program product, which includes a computer program. When the computer program is executed by a processor, the personalized skin generation method provided by any of the above embodiments of the present application may be executed. Optionally, the computer program may be stored in a readable storage medium or in the cloud of a computer device; the processor of the computer device reads the computer program from the readable storage medium or the cloud.

[0189] 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 application, 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 the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0190] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK).

[0191] In addition, the embodiment of the present application 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 each step of the personalized skin generation method provided in the above embodiment.

[0192] The computer readable storage medium may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, 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.

[0193] Specifically, the specific working contents of each part of the above-mentioned electronic device, computer program product and storage medium, as well as the specific processing contents when the computer program product or the computer program on the above-mentioned storage medium is executed by the processor, can all be found in the contents of the various embodiments of the above-mentioned personalized skin generation method, and will not be repeated here.

[0194] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0195] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0196] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0197] The modules and sub-modules in the devices and terminals in the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0198] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, such as multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0199] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0200] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0201] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0202] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0203] Finally, it should be noted that, in this article, relational terms such as first and second, etc. 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", "comprises" 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 "including a..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0204] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. 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 application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A personalized skin generation method, characterized in that: include: Get the skin generation requirements of the system interface; The skin generation requirement includes a skin content description statement; Expanding the skin content description sentence according to the scene described by the skin content description sentence to obtain skin content prompt words; At least according to the skin content prompt word, a system interface skin that meets the skin generation requirements is generated.

2. The method according to claim 1, characterized in that The step of expanding the skin content description sentence according to the scene described by the skin content description sentence to obtain the skin content prompt words includes: According to the scene described by the skin content description sentence and the skin style requirements of each functional area in the system interface, the skin content description sentence is expanded to obtain the skin content prompt words corresponding to each functional area.

3. The method according to claim 2, characterized in that The function area includes a background area and an option area; The skin content description statement is expanded according to the scene described by the skin content description statement and the skin style requirements of each functional area in the system interface to obtain the skin content prompt words corresponding to each functional area, including: According to the scene described by the skin content description sentence, the elements in the skin content description sentence are expanded to obtain the skin content prompt words corresponding to the background area; According to the scene described by the skin content description sentence, an element description sentence associated with the scene is generated as the skin content prompt word corresponding to the option area.

4. The method according to claim 3, characterized in that The step of expanding the elements in the skin content description sentence according to the scene described by the skin content description sentence to obtain the skin content prompt words corresponding to the background area includes: Inputting the skin content description sentence and the first expanded prompt word into a large language model, so that the large language model expands the elements in the skin content description sentence according to the scene described by the skin content description sentence to obtain the skin content prompt word corresponding to the background area; The first expansion prompt word is used to instruct the large language model to perform a task of expanding elements in the skin content description sentence according to the scenario described by the skin content description sentence.

5. The method according to claim 3, characterized in that: The step of generating, according to the scene described by the skin content description sentence, an element description sentence associated with the scene as a skin content prompt word corresponding to the option area comprises: Inputting the skin content description sentence and the second expanded prompt word into a large language model, so that the large language model generates an element description sentence associated with the scene as the skin content prompt word corresponding to the option area according to the scene described by the skin content description sentence; The second extended prompt word is used to instruct the large language model to perform a task of generating an element description sentence associated with the scene according to the scene described by the skin content description sentence; wherein each option area corresponds to a skin content prompt word.

6. The method according to claim 1, characterized in that The skin generation requirement also includes a skin style requirement, and generating a system interface skin that meets the skin generation requirement at least according to the skin content prompt word includes: According to the skin style requirement and the skin content prompt word, a system interface skin that meets the skin generation requirement is generated.

7. The method according to claim 6, characterized in that The step of generating a system interface skin that meets the skin generation requirement according to the skin style requirement and the skin content prompt word includes: Generate skin pictures for each functional area in the system interface according to the skin style requirements and the skin content prompt words; The skin images of each functional area are combined according to the structure of the system interface to obtain a system interface skin that meets the skin generation requirements.

8. The method according to claim 7, characterized in that Generating skin images for each functional area in the system interface according to the skin style requirements and the skin content prompt words includes: The skin style requirement and the skin content prompt word are input into a pre-trained skin generation model, so that the skin generation model generates skin pictures for each functional area in the system interface according to the skin style requirement and the skin content prompt word.

9. The method according to claim 8, characterized in that The skin generation model is trained by using the sample skin style requirement as a training sample and generating a system interface skin that meets the sample skin style requirement through the ip-adapter solution.

10. A personalized skin generation device, characterized in that: include: Acquisition module, used to obtain the skin generation requirements of the system interface; The skin generation requirement includes a skin content description statement; An expansion module, used to expand the skin content description sentence according to the scene described by the skin content description sentence to obtain skin content prompt words; A generation module is used to generate a system interface skin that meets the skin generation requirements at least according to the skin content prompt words.

11. An electronic device, characterized in that: include: Memory and processor; Wherein, the memory is used to store programs; The processor is used to implement the method according to any one of claims 1 to 9 by running the program in the memory.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images