Pet expression package and pet model generation method, device, equipment and medium

Abstract

The present disclosure provides a method, apparatus, device, and medium for generating pet emoji packages and pet models, relating to the field of artificial intelligence, specifically large models, deep learning, cloud computing, and other technical fields. The specific implementation scheme comprises: obtaining a first emoji package theme sent by a client; generating at least one pet emoji package under the first emoji package theme based on the pet model associated with the client and the first emoji package theme; wherein the pet model corresponds to a target pet and is generated based on at least one pet photo showing the target pet sent by the client; the target pet is shown in the first pet emoji package; and each pet emoji package is sent to the client.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of AI (Artificial Intelligence), in particular to the technical fields of large models, deep learning, cloud computing, and the like, and more particularly to a pet sticker and pet model generation method, device, equipment and medium. BACKGROUND

[0002] When using a social platform (or social media, social application), users often use stickers to chat with friends to enhance emotional expression and increase the fun of interaction. Among them, pet stickers such as cats and dogs are very popular among users, so how to make pet stickers is very important. SUMMARY

[0003] The present disclosure provides a pet sticker and pet model generation method, device, equipment and medium.

[0004] According to an aspect of the present disclosure, a pet sticker generation method is provided, comprising:

[0005] Obtaining a first sticker theme sent by a client;

[0006] Generating at least one pet sticker under the first sticker theme according to a pet model associated with the client and the first sticker theme; wherein the pet model corresponds to a target pet and is generated according to at least one pet photo sent by the client, the pet photo showing the target pet; the first pet sticker shows the target pet;

[0007] Sending each pet sticker to the client.

[0008] According to another aspect of the present disclosure, a pet model generation method is provided, comprising:

[0009] Obtaining at least one pet photo; wherein the target pet shown in the at least one pet photo has different shooting angles;

[0010] Verifying the at least one pet photo based on a set verification rule;

[0011] Generating a pet model corresponding to the target pet according to the pet photo that passes the verification.

[0012] According to still another aspect of the present disclosure, another pet sticker generation method is provided, comprising:

[0013] send a first sticker theme to a server; wherein the first sticker theme is used to generate at least one first pet sticker under the first sticker theme based on a pet model associated with the client; wherein the pet model corresponds to a target pet and is generated according to at least one pet photo sent by the client, the pet photo showing the target pet; and the first pet sticker shows the target pet.

[0014] receive the first pet stickers sent by the server.

[0015] According to yet another aspect of the present disclosure, a pet sticker generation device is provided, comprising:

[0016] an obtaining module configured to obtain a first sticker theme sent by a client;

[0017] a generating module configured to generate at least one pet sticker under the first sticker theme according to a pet model associated with the client and the first sticker theme; wherein the pet model corresponds to a target pet and is generated according to at least one pet photo sent by the client, the pet photo showing the target pet; and the first pet sticker shows the target pet.

[0018] a sending module configured to send the pet stickers to the client.

[0019] According to another aspect of the present disclosure, a pet model generation device is provided, comprising:

[0020] an obtaining module configured to obtain at least one pet photo; wherein the target pet shown in the at least one pet photo is taken from different angles;

[0021] a verifying module configured to verify the at least one pet photo based on a set verification rule;

[0022] a generating module configured to generate a pet model corresponding to the target pet according to the pet photo that passes the verification.

[0023] According to still another aspect of the present disclosure, another pet sticker generation device is provided, comprising:

[0024] a sending module configured to send a first sticker theme to a server; wherein the first sticker theme is used to generate at least one first pet sticker under the first sticker theme based on a pet model associated with the client; wherein the pet model corresponds to a target pet and is generated according to at least one pet photo sent by the client, the pet photo showing the target pet; and the first pet sticker shows the target pet.

[0025] A receiving module is configured to receive each of the first pet emoticons sent by the server.

[0026] According to still another aspect of the present disclosure, an electronic device is provided, comprising:

[0027] at least one processor; and

[0028] a memory in communication with the at least one processor; wherein

[0029] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the pet emoticon generation method according to the above-mentioned aspect of the present disclosure, or perform the pet model generation method according to the above-mentioned another aspect of the present disclosure, or perform the pet emoticon generation method according to the above-mentioned still another aspect of the present disclosure.

[0030] According to still another aspect of the present disclosure, a non-transitory computer-readable storage medium of computer instructions is provided, the computer instructions being used to cause the computer to perform the pet emoticon generation method according to the above-mentioned aspect of the present disclosure, or perform the pet model generation method according to the above-mentioned another aspect of the present disclosure, or perform the pet emoticon generation method according to the above-mentioned still another aspect of the present disclosure.

[0031] According to still another aspect of the present disclosure, a computer program product is provided, comprising a computer program, the computer program being executed by a processor to implement the pet emoticon generation method according to the above-mentioned aspect of the present disclosure, or to implement the pet model generation method according to the above-mentioned another aspect of the present disclosure, or to implement the pet emoticon generation method according to the above-mentioned still another aspect of the present disclosure.

[0032] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0033] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0034] Figure 1 a flowchart of the pet emoticon generation method provided by the first embodiment of the present disclosure;

[0035] Figure 2 a flowchart of the pet emoticon generation method provided by the second embodiment of the present disclosure;

[0036] Figure 3A schematic diagram of a making method of a pet sticker provided by an embodiment of the present disclosure is shown.

[0037] Figure 4 A schematic diagram of a making method of a pet sticker provided by an embodiment of the present disclosure is shown.

[0038] Figure 5 A schematic diagram of a pet sticker under a New Year theme provided by an embodiment of the present disclosure is shown.

[0039] Figure 6 A schematic diagram of a making method of a pet model provided by an embodiment of the present disclosure is shown.

[0040] Figure 7 A schematic diagram of a making method of a pet model provided by an embodiment of the present disclosure is shown.

[0041] Figure 8 A schematic diagram of a making method of a pet sticker provided by an embodiment of the present disclosure is shown.

[0042] Figure 9 A schematic diagram of a making method of a pet sticker provided by an embodiment of the present disclosure is shown.

[0043] Figure 10 A schematic diagram of a sharing method of a pet sticker provided by an embodiment of the present disclosure is shown.

[0044] Figure 11 A schematic diagram of a making method of a pet sticker provided by an embodiment of the present disclosure is shown.

[0045] Figure 12 A schematic diagram of a making device of a pet sticker provided by an embodiment of the present disclosure is shown.

[0046] Figure 13 A schematic diagram of a making device of a pet model provided by an embodiment of the present disclosure is shown.

[0047] Figure 14 A schematic diagram of a making device of a pet sticker provided by an embodiment of the present disclosure is shown.

[0048] Figure 15 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0049] Exemplary embodiments of the present disclosure are described herein with reference to the accompanying drawings, which are included to provide a thorough understanding of embodiments of the present disclosure and are not intended to be inclusive of all embodiments. Accordingly, persons of ordinary skill in the art will recognize that there are numerous variations and modifications that can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. As well, for clarity and the convenience, descriptions of well-known functions and constructions are omitted herein.

[0050] Pet expression packages such as kittens, puppies, etc. are very popular among users. The current pet expression package production methods generally include the following two types:

[0051] 1. Using a social platform (or social media, social application) to directly add pet pictures as pet expression packages;

[0052] 2. Using a professional expression package making tool to make pet expression packages. After the pet expression package is made, the user can upload the pet expression package to various social platforms.

[0053] The source of the user's pet expression package is also divided into two categories: 1. Directly use the pet expression package provided by the social platform; 2. Use personal pet pictures to make pet expression packages.

[0054] In the above process, the process from making pet expression packages to using pet expression packages is long and the effect is general. Especially when the user wants to use personal pets to make expression packages, the cost is high, which depends on good pet photo materials, learning of the corresponding production tool, inability to batch processing, and the degree of beauty is limited by personal aesthetic ability.

[0055] Therefore, in view of at least one of the above problems, the present disclosure provides a pet expression package and pet model generation method, device, equipment and medium.

[0056] The pet expression package and pet model generation method, device, equipment and medium of the embodiments of the present disclosure are described below with reference to the accompanying drawings. Before specifically describing the embodiments of the present disclosure, in order to facilitate understanding, first introduce the commonly used technical terms:

[0057] Large model refers to a machine learning model with large-scale parameters and complex computational structure, usually constructed by deep neural networks, with tens of billions or even hundreds of billions of parameters. The purpose of designing a large model is to improve the expression ability and prediction performance of the model, which can handle more complex tasks and data. Large models have wide applications in various fields, including natural language processing, computer vision, speech recognition and recommendation systems, etc.

[0058] Figure 1 The flowchart of the pet expression package generation method provided by Embodiment One of the present disclosure.

[0059] The pet sticker generation method of the embodiments of the present disclosure can be applied to a server.

[0060] As shown in Figure 1 The pet sticker generation method can include the following steps:

[0061] In step S101, a first sticker theme sent by a client is obtained.

[0062] The client refers to a software program or the like running on an electronic device to provide services for users. For example, the client can be a network disk client.

[0063] The electronic device can be any device with computing capability, such as a personal computer, a mobile terminal, and the like. The mobile terminal can be a mobile phone, a tablet computer, a personal digital assistant, a wearable device, and the like, which has various operating systems, touch screens, and / or display screens.

[0064] The first sticker theme refers to a sticker theme selected by a user. The first sticker theme includes, but is not limited to, the following themes: a New Year theme (or a Spring Festival theme), a working person theme, a daily theme, and the like.

[0065] In the embodiments of the present disclosure, a user who logs in to the client can select a sticker theme (referred to as a first sticker theme in the present disclosure) from at least one sticker theme. The client can send the first sticker theme to the server in response to the selection operation of the user. Correspondingly, the server can receive the first sticker theme sent by the client.

[0066] In step S102, at least one pet sticker under the first sticker theme is generated according to a pet model associated with the client and the first sticker theme. The pet model corresponds to a target pet and is generated according to at least one pet photo sent by the client, which shows the target pet. The first pet sticker shows the target pet.

[0067] The species category to which the target pet belongs includes, but is not limited to, a cat, a dog, a mouse (such as a hamster, a golden bear, and the like), a bird (such as a parrot, a pigeon, and the like), a snake, a lizard, a fish, and the like.

[0068] In the embodiments of the present disclosure, each pet model corresponds to a pet (referred to as a target pet in the present disclosure). The pet model can be generated according to at least one pet photo sent by the client, which shows the target pet.

[0069] In the embodiments of the present disclosure, the server can obtain a pet model associated with the client, and generate at least one pet sticker under the first sticker theme according to the pet model and the first sticker theme, wherein each first pet sticker displays a target pet.

[0070] In step S103, the server sends the pet stickers to the client.

[0071] In the embodiments of the present disclosure, after generating the pet stickers under the first sticker theme, the server can send the pet stickers under the first sticker theme to the client.

[0072] The method for generating pet stickers according to the embodiments of the present disclosure can automatically generate at least one pet sticker under the first sticker theme required by the user based on the pet model associated with the client by the server. On the one hand, the user does not need to use professional tools to make pet stickers, which can reduce the operation steps of the user and improve the user experience. On the other hand, a plurality of pet stickers can be generated at one time, which can improve the generation efficiency of pet stickers. In addition, the generated pet stickers display the target pet (such as a real pet raised by the user) required by the user, which can meet the personalized generation requirement of pet stickers of the user.

[0073] It should be noted that in the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information are all carried out on the premise of obtaining the consent of the user, and all comply with the relevant legal regulations and do not violate public order and good customs.

[0074] In order to clearly illustrate how to generate at least one pet sticker under the first sticker theme in the above embodiments, the present disclosure further provides a method for generating pet stickers.

[0075] Figure 2 The flowchart of the method for generating pet stickers provided in Embodiment Two of the present disclosure.

[0076] As shown in Figure 2 The method for generating pet stickers can be applied to a server, which includes the following steps:

[0077] In step S201, the server obtains a first sticker theme sent by the client.

[0078] The explanation of step S201 can refer to the related description in any embodiment of the present disclosure, which will not be repeated here.

[0079] In step S202, at least one sticker picture displaying a target pet is generated according to a pet model associated with the client.

[0080] The pet model corresponds to the target pet and is generated based on at least one pet photo showing the target pet sent by the client.

[0081] In an embodiment of the present disclosure, the server may obtain a pet model associated with the client, and generate at least one emoticon picture showing a target pet based on the pet model.

[0082] As an example, a large model may be used to generate at least one emoticon picture showing the target pet based on the pet model.

[0083] Step S203: Acquire multiple props associated with the first emoticon package theme.

[0084] The types of props include, but are not limited to, the following: text, stickers, filters, backgrounds, animations, etc. This allows for image processing of emoticon images based on different types of props, enhancing the content richness and aesthetics of the resulting pet emoticon package and improving the user experience.

[0085] In an embodiment of the present disclosure, multiple props under different emoticon package themes can be generated in advance, and a correspondence or association relationship between the emoticon package themes and the props can be established. Therefore, in the present disclosure, the server can query the above-mentioned association relationship based on the first emoticon package theme to determine the multiple props associated with the first emoticon package theme.

[0086] Step S204: performing image processing on at least one emoticon package picture based on the multiple props to obtain at least one pet emoticon package under the first emoticon package theme.

[0087] Among them, the first pet emoticon package displays the target pet.

[0088] In an embodiment of the present disclosure, the server may perform image processing on at least one emoticon package image based on multiple props to obtain at least one pet emoticon package under the first emoticon package theme. For example, for any emoticon package image, at least one prop may be superimposed on the emoticon package image to obtain a pet emoticon package under the first emoticon package theme.

[0089] As an example, taking the first emoticon package theme as the New Year's greeting theme, users can Figure 3 Make a pet emoticon package in the following way:

[0090] 1. Users can click Figure 3 (a) In the client side homepage creative template list, a certain emoticon package template (referred to as emoticon package theme template in this disclosure) is selected. For example, the user clicks on the "New Year emoticon package" (or Spring Festival emoticon package) shown in area 31 in 3 (a), and then can enter the following Figure 3(b) the production page shown.

[0091] 2. The user can continue to click Figure 3 the "Make Immediately" button in (b) to make each pet sticker under the New Year theme.

[0092] 3. The client can send the New Year theme to the server to query the pet model associated with the client by the server, and make each pet sticker under the New Year theme based on the pet model and the New Year theme.

[0093] 4. During the process of making pet stickers on the server, the client can display a countdown page (such as Figure 3 (c) shown), wherein the countdown page is used to indicate the remaining generation time (or called remaining production time) of the pet sticker.

[0094] 5. After the server generates the pet sticker, the pet sticker can be sent to the client for display, as shown in Figure 3 (d).

[0095] 6. The client can add the above pet sticker to the first sticker theme in the album, as shown in Figure 3 (e).

[0096] Step S205, send each pet sticker to the client.

[0097] The explanation of step S205 can refer to the related description in any embodiment of the present disclosure, which will not be repeated here.

[0098] The pet sticker generation method of the embodiments of the present disclosure can generate a batch of sticker pictures based on the pet model, and perform image processing on the batch of sticker pictures based on a plurality of props associated with the first sticker theme required by the user. Not only can the pet sticker be made in batches, but also the pet sticker includes props associated with the first sticker theme required by the user, so that the pet sticker can meet the actual drawing needs of the user and improve the user experience.

[0099] In order to clearly illustrate how to generate at least one pet sticker under the first sticker theme in the above embodiments, the present disclosure further provides a pet sticker generation method.

[0100] Figure 4 The flowchart of the pet sticker generation method provided in the third embodiment of the present disclosure.

[0101] As shown in Figure 4 , the pet sticker generation method can be applied to the server, comprising the following steps:

[0102] Step S401, acquire the first sticker theme sent by the client.

[0103] The explanation of step S401 can refer to the relevant description in any embodiment of the present disclosure, which will not be repeated here.

[0104] In any embodiment of the present disclosure, the client can display at least one sticker theme template, for example, Figure 3 In (a), the client side homepage creative template list displays a plurality of sticker theme templates, including "New Year's Greetings Sticker", "Working Stickers" (not shown in 3(a)), "Daily Stickers" (not shown in 3(a)), and the like.

[0105] The user can select a target sticker theme template from at least one sticker theme template, so that in the present disclosure, the sticker theme associated with the target sticker theme template can be the first sticker theme required by the user.

[0106] That is, in the present disclosure, the client can determine the first sticker theme associated with the target sticker theme template in response to the user triggering the selection operation of the target sticker theme template in at least one sticker theme template.

[0107] Then, the client can send the first sticker theme to the server, and correspondingly, the server can receive the first sticker theme sent by the client.

[0108] Step S402, determine the pet model specified by the client from a plurality of pet models associated with the client.

[0109] Different pet models correspond to different target pets, and each pet model is generated according to a pet photo showing the corresponding target pet.

[0110] For example, assuming that the user who logs in the client raises a plurality of target pets (such as the user raises different breeds of puppies, the user raises different breeds of cats, the user raises both cats and dogs, etc.), the user can upload pet photos corresponding to the target pets through the client, so that the server can generate a pet model corresponding to each target pet according to the pet photo corresponding to the target pet.

[0111] In an embodiment of the present disclosure, the server can determine the pet model specified by the client from a plurality of pet models associated with the client. For example, the server can take the pet model currently selected by the user on the client side as the specified pet model.

[0112] It should be noted that in the case where the pet model associated with the client is multiple, the user logged in the client can select the specified pet model by manually switching the pet model.

[0113] In step S403, at least one pet sticker under the first sticker theme is generated according to the specified pet model and the first sticker theme.

[0114] In the embodiments of the present disclosure, the server can generate at least one pet sticker under the first sticker theme according to the pet model specified by the client and the first sticker theme, wherein the pet sticker displays a target pet corresponding to the pet model specified by the client.

[0115] As an example, the server can generate at least one sticker picture displaying a target pet corresponding to the specified pet model according to the specified pet model, and perform image processing on the at least one sticker picture based on a plurality of props associated with the first sticker theme, to obtain at least one pet sticker under the first sticker theme.

[0116] In step S404, the pet stickers are sent to the client.

[0117] The explanation of step S404 can refer to the related description in any embodiment of the present disclosure, which will not be repeated here.

[0118] It should be noted that the same sticker theme supports generating stickers corresponding to pets of different species or different breeds.

[0119] As an example, taking the first sticker theme as a New Year theme (or a Spring Festival theme) as an example, the pet stickers under the New Year theme (or the Spring Festival theme) generated can be added to the New Year theme (or the Spring Festival theme) in the album, for example, there are Spring Festival stickers in the album, and the above pet stickers can be added to the Spring Festival stickers, for example, when the target pet is a dog (such as a Corgi), each pet sticker generated can be as shown in the Spring Festival stickers in (a). Figure 5 When the target pet is a cat, each pet sticker generated can be as shown in the Spring Festival stickers in (b). Figure 5

[0120] The pet sticker generation method of the embodiments of the present disclosure, in the case where the number of pet models associated with the client is multiple, generates pet stickers only according to the pet model specified by the user in the plurality of pet models, which can meet the actual drawing needs of the user.

[0121] ​To clearly illustrate how the pet model associated with the client is made in any embodiment of the present disclosure, the present disclosure also proposes a pet model generation method.

[0122] Figure 6 A flowchart of the pet model generation method provided in Embodiment Four of the present disclosure is shown.

[0123] The pet model generation method of the embodiments of the present disclosure can be applied to the server.

[0124] As shown in Figure 6 The pet model generation method can include the following steps:

[0125] Step S601: Obtain at least one pet photo; wherein the target pet shown in each of the at least one pet photo is taken from a different perspective.

[0126] The species category to which the target pet belongs includes but is not limited to cats, dogs, mice (such as hamsters, golden bears, etc.), birds (such as parrots, pigeons, etc.), snakes, lizards, fish, etc.

[0127] In the embodiments of the present disclosure, in order to improve the generation effect of the pet model, the server can generate a pet model according to pet photos taken from different perspectives. First, the server can obtain at least one pet photo; wherein the same pet (referred to as a target pet in the present disclosure) is shown in each pet photo, and the target pet shown in different pet photos is taken from different perspectives.

[0128] As an example, the server can receive at least one pet photo sent by the client.

[0129] For example, the pet photo uploaded by the client can include a front-facing photo of the target pet, multiple side-facing photos of the target pet (taken from different perspectives), and a back-facing photo of the target pet.

[0130] Step S602: Verify the at least one pet photo based on a set verification rule.

[0131] The set verification rule refers to a pre-set verification rule.

[0132] In the embodiments of the present disclosure, the server can verify the at least one pet photo based on the set verification rule.

[0133] In any one embodiment of the present disclosure, the verification method of the pet photo may, for example, be:

[0134] 1. For any one pet photo, the server can perform target detection on the pet photo based on a target detection algorithm to obtain the species category to which the target pet in the pet photo belongs.

[0135] The species category to which the target pet belongs includes, but is not limited to, cats, dogs, mice (such as hamsters, chipmunks, etc.), birds (such as parrots, pigeons, etc.), snakes, lizards, fish, and the like.

[0136] 2. In a case where the species category of the pet photo matches the set species category, the server can detect whether the face of the target pet in the pet photo is clear, and whether the target pet in the pet photo is blocked, to obtain a detection result.

[0137] The set species category is a pre-set species category, such as a cat or a dog.

[0138] In the embodiments of the present disclosure, in a case where the species category to which the target pet in the pet photo belongs matches the set species category, the server can further identify or detect, based on an image recognition algorithm, whether the face of the target pet in the pet photo is clear, and whether the target pet in the pet photo is blocked, to obtain a detection result.

[0139] 3. The server can determine whether the pet photo passes the verification according to the detection result.

[0140] For example, in a case where the detection result indicates that the face of the target pet is clear, and the detection result indicates that the target pet is not blocked, the server can determine that the pet photo passes the verification; and in a case where the detection result indicates that the face of the target pet is not clear, and / or the detection result indicates that the target pet is blocked, the server can determine that the pet photo does not pass the verification.

[0141] Therefore, generating a pet model only based on a pet photo with a clear face and no blockage can improve the quality of the pet model, so that generating a pet sticker based on a high-quality pet model can make the face of the target pet in the pet sticker clear and without blockage, thereby improving the generation quality and aesthetics of the pet sticker and further improving the user experience.

[0142] In any one of the embodiments of the present disclosure, the server determines whether the pet photo passes the verification according to the detection result, for example, in the following manner:

[0143] A. In a case where the detection result indicates that the face of the target pet is not clear, and / or the detection result indicates that the target pet is blocked, the server can directly determine that the pet photo does not pass the verification.

[0144] B. In a case where the detection result indicates that the face of the target pet is clear, and the target pet is not blocked, the server can further determine whether the area ratio of the target pet in the pet photo is within a set ratio interval, to obtain a determination result.

[0145] wherein the proportion interval is a pre-set value interval, for example, the lower limit of the value of the proportion interval can be 20%, 25%, etc., and the upper limit of the value of the proportion interval can be 50%, 60%, etc.

[0146] In the embodiments of the present disclosure, in the case that the detection result indicates that the face of the target pet is clear and the detection result indicates that the target pet does not exist occlusion, the server can further calculate the area proportion of the target pet in the pet photo (i.e., calculate the ratio between the area of the target pet in the pet photo and the total area of the pet photo), and determine whether the area proportion of the target pet is within the set proportion interval to obtain a determination result.

[0147] C, the server can determine whether the pet photo passes the verification according to the determination result.

[0148] For example, in the case that the determination result indicates that the area proportion of the target pet is within the set proportion interval, the server can determine that the pet photo passes the verification; and in the case that the determination result indicates that the area proportion of the target pet is not within the set proportion interval (for example, the area proportion of the target pet is less than the lower limit of the value of the proportion interval, or the area proportion of the target pet is greater than the upper limit of the value of the proportion interval), the server can determine that the pet photo does not pass the verification.

[0149] Therefore, only pet photos with clear faces, no occlusion, and moderate subjects are used to generate pet models, which can further improve the generation quality of pet models, so that pet stickers based on high-quality pet models can make the faces of target pets in the pet stickers clear, without occlusion and moderate subjects, thereby improving the generation quality and aesthetics of pet stickers and further improving the user experience.

[0150] Step S603: generating a pet model corresponding to the target pet according to the pet photo that passes the verification.

[0151] In the embodiments of the present disclosure, the server can generate a pet model corresponding to the target pet according to the pet photo that passes the verification.

[0152] As an example, the server can use the LoRA (Low-Rank Adaptation) training method based on the Stable Deffusion platform to generate a pet model corresponding to the target pet by taking the pet photos of multiple shooting angles uploaded by the client as training data and passing the LoRA training platform deployed in the cloud, wherein each target pet corresponds to one pet model, i.e., the pet model and the target pet are in a one-to-one correspondence.

[0153] As an application scenario, taking the species category to which the target pet belongs as a cat and taking a network disk client as the client, a user can generate a pet model corresponding to the pet cat in the manner shown in Figure 7

[0154] 1. The user can click the “Select Photo” button in (a) to upload a clear photo of the front of the target pet, and then can enter the photo album selection page shown in (b). Figure 7 Figure 7

[0155] 2. The user can click the “Network Disk Photo Album” control in (b) to select a clear photo of the front of the target pet from the network disk photo album, or the user can click the “Mobile Phone Photo Album” control in (b) to select a clear photo of the front of the target pet from the mobile phone photo album. For example, the photos in the mobile phone photo album can be as shown in (c). Figure 7 Figure 7 Figure 7

[0156] 3. Assuming that the user selects the pet photo in the first row and the second column in (c) and clicks the “Confirm Upload” button, the uploaded clear photo of the front can continue to be identified and verified through the identification page shown in (d). Figure 7 Figure 7

[0157] 4. After the clear photo of the front is verified, the user can click the “Continue to Select X Photos” button in the page shown in (e) to upload pet photos taken from other perspectives. Figure 7

[0158] 5. After the user has uploaded pet photos taken from other perspectives (as shown in (f)), the pet photos can be verified or audited, and pet photos that fail the verification (i.e., that fail the audit) can be marked so that the user deletes the pet photos that fail the verification and / or clicks the “Supplement Photos” button in the page shown in (f) to continue to upload pet photos taken from other perspectives. Figure 7 Figure 7

[0159] 6. In the case where the user does not need to supplement photos, the user can click the “Generate Immediately” button in the page shown in (f) to generate the pet model. Figure 7

[0160] 7. During the generation of the pet model on the server, the client can display the countdown page shown in (g), which is used to indicate the remaining generation time of the pet model. Figure 7

[0161] ​​​​​​​​​​​​​8, the generated pet model can be displayed on a webpage as Figure 8 (h) the pet information page shown.

[0162] The pet model generation method of the embodiments of the present disclosure verifies each pet photo, and generates a pet model corresponding to a target pet only according to the pet photos that pass the verification, which can improve the generation quality of the pet model. In addition, different pet photos are taken from different perspectives, and the pet model is generated based on pet photos taken from different perspectives, which can make the pet sticker generated based on the pet model show the target pet from different perspectives, improve the distinction between different pet stickers (i.e. the difference between the contents of the pictures), and further improve the user experience.

[0163] The above is each method embodiment executed by the server, and the present disclosure further provides a method embodiment executed by the client.

[0164] Figure 8 The flowchart of the pet sticker generation method provided in the fifth embodiment of the present disclosure.

[0165] As shown in Figure 5 , the pet sticker generation method can be applied to the client, including the following steps:

[0166] Step S801, send a first sticker theme to the server; wherein the first sticker theme is used to generate at least one first pet sticker under the first sticker theme based on a pet model associated with the client; wherein the pet model corresponds to a target pet and is generated according to at least one pet photo sent by the client, which shows the target pet; the target pet is shown in the first pet sticker.

[0167] Step S802, receive each first pet sticker sent by the server.

[0168] It should be noted that the explanation and description of each method embodiment executed by the server in the foregoing embodiments also apply to this embodiment, and the implementation principle is similar, which will not be repeated here.

[0169] In any one embodiment of the present disclosure, after receiving the first pet sticker, the client can display each first pet sticker, and / or add each first pet sticker to the first sticker theme in the album.

[0170] As an example, taking the first sticker theme as a New Year theme (or called a Spring Festival theme) as an example, the first pet sticker under the generated New Year theme (or Spring Festival theme) can be added to the New Year theme (or Spring Festival theme) in the album, for example, there are Spring Festival stickers in the album, and the first pet sticker can be added to the Spring Festival sticker, for example, when the target pet is a dog (such as a Corgi), each first pet sticker generated can be as shown in the Spring Festival sticker under (a). Figure 5 When the target pet is a cat, each first pet sticker generated can be as shown in the Spring Festival sticker under (b). Figure 7

[0171] In this way, the user can intuitively view each first pet sticker under the first sticker theme, so that the user can use the first pet sticker conveniently.

[0172] In any one of the embodiments of the present disclosure, before the client receives each first pet sticker sent by the server, the client can also display a countdown page, wherein the countdown page is used to indicate the remaining generation time of the first pet sticker.

[0173] In this way, during the user's waiting for the first pet sticker, a countdown page is provided to inform the user of the remaining time, which not only can reduce the user's anxiety, but also can avoid the situation that the user repeatedly requests the server during the generation of the pet sticker, that is, avoid the repeated request situation, and reduce the load of the server.

[0174] In any one of the embodiments of the present disclosure, after the client sends the first sticker theme to the server, if the client does not receive the first pet sticker sent by the server for a long time, the client can prompt the user that the first pet sticker generation fails and the reason for the failure.

[0175] For example, the sending time of the first sticker theme is marked as a target time, if the client does not receive the first pet sticker sent by the server within a set period of time after the target time, the client can generate and display prompt information. Wherein the prompt information is used to indicate that the first pet sticker generation fails and the reason for the failure.

[0176] Wherein, the length of the set period is pre-set.

[0177] For example, the client can display the prompt information through a pop-up window, wherein the prompt information is used to indicate that the first pet sticker generation fails and the reason for the failure, for example, the reason for the failure can be "due to network exception, this generation fails, please try later".

[0178] ​Thus, in the case that the client does not receive the first pet sticker package sent by the server for a long time, the user is prompted that the first pet sticker package fails to be generated and the reason for the failure, so that the user can generate the pet sticker package again according to the prompt information, and the effectiveness and success rate of the user obtaining the pet sticker package are improved.

[0179] In any one of the embodiments of the present disclosure, the user can also update the pet model according to the user's own needs, for example, the user can update the pet model by using the latest pet photo showing the target pet.

[0180] As an example, the client can update at least one pet photo associated with the pet model in response to the user triggering an update operation on the pet model, where the update includes but is not limited to adding a new pet photo and deleting an original pet photo. Then, the client can send the updated pet photo to the server, so that the server updates the pet model according to the updated pet photo.

[0181] For example, taking the species category of the target pet as a cat, and taking the client as a network disk client, the user can update the pet model by clicking the "Make it look more like my pet" button in (h). For example, the user can delete and add pet photos, and then the client can re-upload the updated pet photos to the server, so that the server updates the pet model. Figure 9

[0182] Thus, the pet model associated with the client can be dynamically maintained to meet the user's latest drawing needs.

[0183] The pet sticker package generation method of the embodiments of the present disclosure can automatically generate at least one pet sticker package under the first sticker package theme required by the user based on the pet model associated with the client by the server. On the one hand, the user does not need to use professional sticker package making tools to make pet sticker packages, which can reduce the user's operation steps and improve the user's experience. On the other hand, multiple pet sticker packages can be generated at one time, which can improve the generation efficiency of pet sticker packages. On the other hand, the generated pet sticker package shows the target pet (such as the real pet raised by the user) required by the user, which can meet the user's personalized pet sticker package generation needs.

[0184] In any one of the embodiments of the present disclosure, the client can also share the pet sticker package generated by the server in a social application. In order to clearly illustrate how the client shares the pet sticker package in any one of the embodiments of the present disclosure, the present disclosure also proposes a pet sticker package generation method.

[0185] Figure 9 ​A flowchart of the method for generating a pet sticker provided in Embodiment Six of the present disclosure is shown.

[0186] As shown in Figure 10 , the client can share the pet sticker by the following steps.

[0187] In Step S901, a second sticker theme is determined from at least one sticker theme in the album in response to a selection operation.

[0188] In the embodiments of the present disclosure, the client can determine a sticker theme (denoted as a second sticker theme in the present disclosure) required by the user from the sticker themes in the album in response to a selection operation triggered by the user.

[0189] For example, taking a network disk client as an example, the user can select a second sticker theme from the sticker themes in the album of the network disk.

[0190] In Step S902, a second pet sticker is determined from the pet stickers under the second sticker theme.

[0191] In the embodiments of the present disclosure, the client can display the pet stickers under the second sticker theme, so that the user can select a pet sticker (denoted as a second pet sticker in the present disclosure) required by the user from the pet stickers under the second sticker theme. Accordingly, the client can select or determine the second pet sticker from the pet stickers under the second sticker theme in response to a selection operation triggered by the user.

[0192] In Step S903, the second pet sticker is shared to a target social application in response to a sharing operation on the second pet sticker.

[0193] The target social application can be a social application selected by the user, or the target social application can also be a default social application.

[0194] In the embodiments of the present disclosure, the client can also share the second pet sticker to the target social application in response to a sharing operation on the second pet sticker triggered by the user.

[0195] In any one of the embodiments of the present disclosure, the sharing manner of the second pet sticker can be, for example:

[0196] 1. The client can display a sharing page in response to a sharing operation on the second pet sticker triggered by the user, wherein at least one chat object (such as a friend or a group of the user) in the target social application is displayed in the sharing page.

[0197] 2、The client can determine or select a target chat object from the at least one chat object in response to a user triggered selection operation.

[0198] 3、The client can invoke a dialog box between the target chat object in the target social application, and share the second pet sticker pack to the target chat object through the dialog box.

[0199] As an example, taking the second sticker pack theme as a New Year theme, the species category to which the target pet belongs as a dog, and the client as a network disk client, the user can share a pet sticker pack under the New Year theme in the manner as shown in Figure 10 .

[0200] 1、After the user clicks a pet sticker pack (such as the pet sticker pack shown in Figure 10 (a)) under the New Year theme in the network disk album, the user can click the "Share with friends" button in Figure 10 (a) to enter the sharing page as shown in Figure 10 (b).

[0201] 2、Suppose the user clicks a target chat object (such as Zhang San) in Figure 10 (b), a dialog box between Zhang San in the target social application can be invoked (as shown in Figure 10 (c)).

[0202] 3、The pet sticker pack shown in Figure 10 (a) can be shared to Zhang San through the dialog box, for example, the pet sticker pack received by Zhang San can be displayed in the chat interface as shown in Figure 11 (d).

[0203] Thus, the second pet sticker pack can be shared to a specific chat object in the target social application according to actual needs of the user, satisfying actual sharing needs of the user.

[0204] The pet sticker pack generation method of the embodiments of the present disclosure can implement sharing of pet sticker packs made by the server to the target social application, satisfying actual social needs of the user.

[0205] In order to clearly illustrate the above-mentioned embodiments, the present disclosure further provides a pet sticker pack generation method.

[0206] Figure 11 A flowchart of the pet sticker pack generation method provided by the seventh embodiment of the present disclosure.

[0207] As shown in Figure 3 , the pet sticker pack generation method can be applied to a client, including the following steps:

[0208] Step S1101, in response to the selection operation on the target sticker theme template in the at least one sticker theme template, determining a first sticker theme associated with the target sticker theme template.

[0209] In the embodiments of the present disclosure, the client can display at least one sticker theme template, wherein each sticker theme template can be associated with a sticker theme. For example, Figure 7 (a) The client side home page creative template list displays a plurality of sticker theme templates, including "New Year's greetings sticker", "worker sticker", (3(a) not shown), "daily sticker" (3(a) not shown), and the like.

[0210] In the embodiments of the present disclosure, the user can select a sticker theme template (referred to as a target sticker theme template in the present disclosure) from at least one sticker theme template, so that in the present disclosure, the sticker theme associated with the target sticker theme template can be used as the first sticker theme required by the user.

[0211] That is, in the present disclosure, the client can determine the sticker theme associated with the target sticker theme template in response to the selection operation of the target sticker theme template triggered by the user in the at least one sticker theme template, and use it as the first sticker theme.

[0212] Step S1102, sending the first sticker theme to the server, wherein the first sticker theme is used to generate at least one first pet sticker under the first sticker theme based on the pet model associated with the client.

[0213] Wherein the pet model corresponds to the target pet and is generated according to at least one pet photo sent by the client, which displays the target pet; the first pet sticker displays the target pet.

[0214] Step S1103, receiving each first pet sticker sent by the server.

[0215] The explanation and description of steps S1102 and S1103 can be referred to the related description in any embodiment of the present disclosure, which will not be repeated here.

[0216] The pet sticker generation method of the embodiments of the present disclosure can realize that the user selects a sticker theme template required by himself from each sticker theme template displayed by the client, and uses the sticker theme associated with the sticker theme template as the first sticker theme, so that the server can automatically generate each pet sticker under the first sticker theme to meet the actual drawing needs of the user.

[0217] In any embodiment of the present disclosure, a large model can be used to quickly generate a set of emoticons of a user's real pet (i.e., a batch of pet emoticon packages) to meet the user's personalized mapping needs. For example, the following parts can be used to generate a personalized set of emoticons:

[0218] The first step is to generate a pet model. For example, using the LoRA training method based on the Stable Deffusion platform, user-uploaded pet photos can be used as training data. After passing through the cloud-deployed LoRA training platform, the corresponding pet model is generated; each pet corresponds to a pet model.

[0219] The process of uploading pet photos mainly includes the following two steps:

[0220] 1) Upload a photo of your pet’s face;

[0221] 2) Upload photos of your pet from multiple angles.

[0222] Furthermore, the uploaded pet photos can also be verified. If the species category of the subject in the pet photo matches the set species category, the face is clear, there is no obstruction, and the subject is moderate, the pet photo is determined to have passed the verification, so that the pet model can be generated subsequently based only on the pet photos that have passed the verification.

[0223] During the pet model generation process, the remaining generation time of the pet model can be prompted through the countdown page. For example, the remaining generation time can be updated every 5 seconds. The countdown can decrease or remain unchanged, and cannot jump.

[0224] Among them, after the pet model is generated, the user can be reminded through the relevant service number of the client (such as XX pet service number).

[0225] After the pet model is generated, the user can click Figure 3 Click the "More like my pet" button in (h) to update the pet model. For example, you can delete or add previously saved pet photos, so that a new pet model can be generated based on the updated pet photos.

[0226] It should be noted that if the user wants to update the pet model again later, the user can upload new pet photos.

[0227] The second part generates pet emoji base images (referred to as emoji pictures in this disclosure) according to the emoji theme. For example, emoji pictures showing pets can be generated in batches based on the emoji theme and pet models associated with the emoji theme template selected by the user.

[0228] The third part is to superimpose the props and the captions on the sticker picture to generate a complete pet sticker. For example, the corresponding props and captions can be superimposed on the sticker picture by means of image synthesis to finally generate a complete pet sticker.

[0229] The user can generate the pet sticker in the sticker theme associated with the sticker template by clicking the sticker template in the list of creative templates on the home page in (a). Figure 3

[0230] The data hierarchy of the pet sticker is: set theme (i.e., sticker theme) and sticker. The set theme is, for example, [New Year Set], [Daily Set], etc.

[0231] The theme picture under the set theme can be configured, and the cover under the set theme can display the specific pet sticker under the current theme. For example, the pet sticker can be displayed in a grid form.

[0232] It should be noted that the pet sticker under multiple set themes supports switching. The user can click the different header theme pictures to display the cover under the corresponding set theme.

[0233] As an example, the generation process of the pet sticker can include the following two steps:

[0234] Step 1: generating a sticker picture based on a pet model;

[0235] Step 2: adding props, captions, etc. to the sticker picture according to the set theme and then performing image synthesis.

[0236] During the generation process of the pet sticker, a countdown page and a quit reminder can be displayed, and when the pet sticker fails to be generated, a pop-up window can be used to display a prompt message, for example, “This generation fails due to network anomalies. Please try again later.” The user can click the “I know” button to return to the template detail page as shown in (a). Figures 1 to 4

[0237] After the pet sticker is generated, the pet sticker can be automatically added to the corresponding set theme in the album. The same set theme supports the generation of pet stickers of different species.

[0238] The fourth part is to share the pet sticker.

[0239] The user can share the generated pet sticker to a target social application. For example, the interaction process can be: the user clicks the “Share with friends” button, displays a sharing page, initiates a dialog box, shares the pet sticker based on the dialog box, and the user can long press the pet sticker to add the pet sticker to his / her own sticker.​​

[0240] Corresponding to the pet sticker generation method provided by the above-mentioned Figures 1 to 4 The pet sticker generation method provided by the above-mentioned Figure 12 Corresponding to the pet sticker generation method provided by the above-mentioned

[0241] Figure 12 A structural schematic diagram of the pet sticker generation device provided by the eighth embodiment of the present disclosure.

[0242] As Figure 6 shown, the pet sticker generation device 1200 can be applied to a server, and includes an acquisition module 1210, a generation module 1220, and a sending module 1230.

[0243] The acquisition module 1210 is configured to acquire a first sticker theme sent by a client.

[0244] The generation module 1220 is configured to generate at least one pet sticker under the first sticker theme according to a pet model associated with the client and the first sticker theme, wherein the pet model corresponds to a target pet and is generated according to at least one pet photo sent by the client and showing the target pet, and the first pet sticker shows the target pet.

[0245] The sending module 1230 is configured to send each pet sticker to the client.

[0246] In a possible implementation manner of the present disclosure, the generation module 1220 is configured to: generate at least one sticker picture showing the target pet according to the pet model; acquire a plurality of props associated with the first sticker theme; and perform image processing on the at least one sticker picture based on the plurality of props to obtain at least one pet sticker under the first sticker theme.

[0247] In a possible implementation manner of the present disclosure, the type of the prop includes at least one of the following: text; sticker; filter; background; and dynamic effect.

[0248] In a possible implementation of the embodiment of the present disclosure, the number of pet models associated with the client is multiple, and different pet models correspond to different target pets; the generation module 1220 is configured to: determine a pet model specified by the client from the multiple pet models; and generate at least one pet sticker under the first sticker theme according to the specified pet model and the first sticker theme; and the pet sticker displays the target pet corresponding to the specified pet model.

[0249] The pet sticker generation apparatus of the embodiment of the present disclosure can automatically generate at least one pet sticker under the first sticker theme required by the user based on the pet model associated with the client by the server, on the one hand, without the need for the user to use professional sticker making tools to make pet stickers, which can reduce the operation steps of the user and improve the user experience, on the other hand, multiple pet stickers can be generated at one time, which can improve the generation efficiency of the pet stickers, and on the other hand, the generated pet sticker displays the target pet (such as a real pet raised by the user) required by the user, which can meet the personalized pet sticker generation requirement of the user.

[0250] The pet model generation method provided in the above Figure 6 The pet model generation apparatus is provided in the embodiment of the present disclosure, and the pet model generation method provided in the above Figure 13 The pet model generation method provided in the above

[0251] Figure 13 The pet model generation apparatus provided in the ninth embodiment of the present disclosure is shown in the structural schematic diagram.

[0252] As Figures 8 to 11 shown, the pet model generation apparatus 1300 can include an acquisition module 1310, a verification module 1320, and a generation module 1330.

[0253] The acquisition module 1310 is configured to receive at least one pet photo sent by the client; and the target pet displayed in the at least one pet photo has different shooting angles.

[0254] The verification module 1320 is configured to verify the at least one pet photo based on a set verification rule.

[0255] The generation module 1330 is configured to generate a pet model according to the pet photo that passes the verification.

[0256] In a possible implementation manner of the embodiment of the present disclosure, the verification module 1320 is configured to: for any pet photo, performing target detection on any pet photo to obtain a species category to which a target pet in any pet photo belongs; in a case where the species category of any pet photo matches a set species category, detecting whether a face of the target pet in any pet photo is clear and detecting whether the target pet in any pet photo is occluded to obtain a detection result; and determining whether any pet photo passes verification according to the detection result.

[0257] In a possible implementation manner of the embodiment of the present disclosure, the verification module 1320 is configured to: in a case where the detection result indicates that the face of the target pet is not clear and / or the detection result indicates that the target pet is occluded, determining that any pet photo fails to pass verification; in a case where the detection result indicates that the face of the target pet is clear and the target pet is not occluded, judging whether an area proportion of the target pet in any pet photo is within a set proportion interval to obtain a judgment result; and determining whether any pet photo passes verification according to the judgment result.

[0258] In a possible implementation manner of the embodiment of the present disclosure, the verification module 1320 is configured to: in a case where the judgment result indicates that the area proportion is within the proportion interval, determining that any pet photo passes verification; and in a case where the judgment result indicates that the area proportion is not within the proportion interval, determining that any pet photo fails to pass verification.

[0259] The generation apparatus of the pet model in the embodiment of the present disclosure verifies each pet photo, and generates a pet model corresponding to a target pet only according to pet photos that pass verification, which can improve the generation quality of the pet model. In addition, different pet photos are taken from different perspectives, and the pet model is generated based on pet photos taken from different perspectives, which can make the pet sticker generated based on the pet model display the target pet from different perspectives, improve the distinction (i.e., the difference) between different pet stickers, and further improve the user experience.

[0260] The generation apparatus of the pet sticker provided in the embodiment of the present disclosure corresponds to the generation method of the pet sticker provided in the embodiment of the present disclosure. Figures 8 to 11 The generation apparatus of the pet sticker provided in the embodiment of the present disclosure corresponds to the generation method of the pet sticker provided in the embodiment of the present disclosure. Figure 14 Therefore, the implementation manners of the generation method of the pet sticker are also applicable to the generation apparatus of the pet sticker provided in the embodiment of the present disclosure, which will not be described in detail in the embodiment of the present disclosure.

[0261] Figure 14 A structural schematic diagram of the generation apparatus of the pet sticker provided in the tenth embodiment of the present disclosure.

[0262] As Figure 15 shown, the pet sticker generation apparatus 1400 can be applied to a client, including: a sending module 1410 and a receiving module 1420.

[0263] The sending module 1410 is configured to send a first sticker theme to a server; the first sticker theme is used to generate at least one first pet sticker under the first sticker theme based on a pet model associated with the client; the pet model corresponds to a target pet and is generated according to at least one pet photo sent by the client, the pet photo showing the target pet; and the first pet sticker shows the target pet.

[0264] The receiving module 1420 is configured to receive each first pet sticker sent by the server.

[0265] In a possible implementation of the present disclosure, the pet sticker generation apparatus 1400 can further include:

[0266] A processing module is configured to display each first pet sticker; and / or add each first pet sticker to the first sticker theme in an album.

[0267] In a possible implementation of the present disclosure, the pet sticker generation apparatus 1400 can further include:

[0268] A determining module is configured to determine a second sticker theme from at least one sticker theme in the album and determine a second pet sticker from each pet sticker under the second sticker theme in response to a selection operation.

[0269] A sharing module is configured to share the second pet sticker to a target social application in response to a sharing operation on the second pet sticker.

[0270] In a possible implementation of the present disclosure, the sharing module is configured to: display a sharing page in response to the sharing operation on the second pet sticker; display at least one chat object in the target social application in the sharing page; determine a target chat object from the at least one chat object in response to a selection operation; and initiate a dialogue box between the target chat object in the target social application and share the second pet sticker to the target chat object through the dialogue box.

[0271] In a possible implementation of the present disclosure, the pet sticker generation apparatus 1400 can further include:

[0272] A display module is configured to display a countdown page; the countdown page is used to indicate a remaining generation time of the first pet sticker.

[0273] In a possible implementation of the embodiment of the present disclosure, the sending time of the first sticker theme is the target time, and the apparatus further includes:

[0274] The display module is configured to, in a case where the first pet sticker is not received from the server within a set time period after the target time, generate and display prompt information.

[0275] The prompt information is used to indicate that the first pet sticker fails to be generated and a reason for the failure.

[0276] In a possible implementation of the embodiment of the present disclosure, the pet sticker generation apparatus 1400 further includes:

[0277] The update module is configured to, in response to an update operation on the pet model, update at least one pet photo associated with the pet model.

[0278] The sending module is further configured to send the updated pet photo to the server, and the updated pet photo is used to update the pet model.

[0279] In a possible implementation of the embodiment of the present disclosure, the client displays at least one sticker theme template, and each sticker theme template is associated with a sticker theme. The sending module 1410 is configured to, in response to a selection operation on a target sticker theme template in the at least one sticker theme template, determine a first sticker theme associated with the target sticker theme template, and send the first sticker theme to the server.

[0280] The pet sticker generation apparatus of the embodiment of the present disclosure can automatically generate at least one pet sticker under a first sticker theme required by a user based on a pet model associated with the client by the server. On the one hand, the user does not need to use a professional sticker making tool to make a pet sticker, which can reduce the operation steps of the user and improve the user experience. On the other hand, a plurality of pet stickers can be generated at one time, which can improve the generation efficiency of the pet sticker. In addition, the generated pet sticker displays a target pet (such as a real pet raised by the user) required by the user, which can meet the generation requirement of the user for the personalized pet sticker.

[0281] To implement the above-mentioned embodiments, the present disclosure further provides an electronic device, which can include at least one processor, and a memory connected with the at least one processor in communication. The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the pet sticker generation method or the pet model generation method proposed in any one of the embodiments of the present disclosure.

[0282] To achieve the above-mentioned embodiments, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make a computer execute the pet sticker generation method or the pet model generation method proposed in any one of the above-mentioned embodiments of the present disclosure.

[0283] To achieve the above-mentioned embodiments, the present disclosure further provides a computer program product, which comprises a computer program, and the computer program, when executed by a processor, implements the pet sticker generation method or the pet model generation method proposed in any one of the above-mentioned embodiments of the present disclosure.

[0284] According to embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0285] Figure 15 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown.

[0286] The electronic device can include a server, a client in the above-mentioned embodiments. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0287] As shown in ​ Device 1500 includes a computing unit 1501 that can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 1502 or a computer program loaded into a RAM (Random Access Memory) 1503 from a storage unit 1507. Various programs and data required for the operation of device 1500 can also be stored in the RAM 1503. The computing unit 1501, the ROM 1502, and the RAM 1503 are connected to each other through a bus 1504. An I / O (Input / Output) interface 1505 is also connected to the bus 1504.

[0288] A plurality of components in the device 1500 are connected to the I / O interface 1505, including: an input unit 1506, such as a keyboard, a mouse, etc.; an output unit 1507, such as various types of displays, speakers, etc.; a storage unit 1508, such as a magnetic disk, an optical disk, etc.; and a communication unit 1509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1509 allows the device 1500 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0289] The computing unit 1501 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1501 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 1501 performs various methods and processes described above, such as the generation method of the pet sticker or the generation method of the pet model. For example, in some embodiments, the generation method of the pet sticker or the generation method of the pet model described above can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 1508. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 1500 via the ROM 1502 and / or the communication unit 1509. When the computer program is loaded into the RAM 1503 and executed by the computing unit 1501, one or more steps of the generation method of the pet sticker or the generation method of the pet model described above can be performed. Alternatively, in other embodiments, the computing unit 1501 can be configured to perform the generation method of the pet sticker or the generation method of the pet model described above by any other appropriate means, such as by means of firmware.

[0290] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a Field Programmable Gate Array (FPGA), an Application-Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a System on a Chip (SOC), a Complex Programmable Logic Device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0291] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general or special purpose computer, such that the program code, when executed by the processor or controller, causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0292] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include a linearly-programmed electronic storage, a portable computer diskette, a hard disk, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory), or flash memory, an optical fiber, a CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0293] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0294] The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, and a blockchain network.

[0295] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service (Virtual Private Server). The server can also be a server of a distributed system, or a server combined with a blockchain.

[0296] It should be noted that artificial intelligence is a discipline that studies enabling computers to simulate some thinking processes and intelligent behaviors of people (such as learning, reasoning, thinking, planning, etc.), and has both hardware and software technologies. Artificial intelligence hardware technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing, etc.; artificial intelligence software technology mainly includes computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, knowledge graph technology, etc. several major directions.

[0297] According to the technical scheme of the embodiment of the present disclosure, at least one pet sticker under the first sticker theme required by the user can be automatically generated by the server based on the pet model associated with the client. On the one hand, the user does not need to use professional sticker making tools to make pet stickers, which can reduce the operation steps of the user and improve the user experience. On the other hand, a plurality of pet stickers can be generated at one time, which can improve the generation efficiency of pet stickers. On the other hand, the generated pet stickers display the target pet (such as a real pet raised by the user) required by the user, which can meet the personalized pet sticker generation needs of the user.

[0298] It should be understood that the steps can be reordered, added, or deleted using the various forms of the flow shown above. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical scheme of the present disclosure can be achieved, which is not limited herein.

[0299] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating a pet expression package, characterized in that: The method is applied to the server, and includes: Obtaining a first emoticon package theme sent by the client, where the first emoticon package theme is selected by the user from a homepage creative template list on the client side; Querying a pet model associated with the client; generating at least one emoticon package picture showing a target pet based on the pet model and the first emoticon package theme; wherein the pet model corresponds to the target pet and is generated based on at least one pet photo showing the target pet sent by the client; and the target pet is shown in the first pet emoticon package; Obtain multiple props associated with the first emoticon package theme; Based on the multiple props, performing image processing on the at least one emoticon package picture to obtain at least one pet emoticon package under the first emoticon package theme; Sending each pet expression package to the client; The method comprises: Obtaining at least one pet photo; wherein the target pet shown in the at least one pet photo is shot from a different perspective; For any pet photo, perform target detection on the pet photo to obtain the species category of the target pet in the pet photo; When the species category of any one of the pet photos matches the set species category, detecting whether the face of the target pet in any one of the pet photos is clear, and detecting whether the target pet in any one of the pet photos is blocked, and obtaining a detection result; Determining whether any of the pet photos passes verification based on the detection result; A pet model corresponding to the target pet is generated based on the verified pet photos as training data, wherein the verified pet photos refer to pet photos with clear faces and no occlusion.

2. The method according to claim 1, wherein The type of the prop includes at least one of the following: Word; sticker; Filters; background; Animation.

3. The method according to any one of claims 1 to 2, wherein There are multiple pet models associated with the client, and different pet models correspond to different target pets; The step of generating at least one pet emoticon package under the first emoticon package theme according to the pet model associated with the client and the first emoticon package theme includes: Determining the pet model specified by the client from the plurality of pet models; Generate at least one pet emoticon package under the first emoticon package theme according to the specified pet model and the first emoticon package theme; The pet emoticon package displays a target pet corresponding to the designated pet model.

4. The method according to claim 1, wherein Determining whether any of the pet photos passes verification based on the detection result includes: If the detection result indicates that the face of the target pet is unclear, and / or the detection result indicates that the target pet is obscured, determining that any one of the pet photos fails verification; When the detection result indicates that the face of the target pet is clear and there is no occlusion of the target pet, determining whether the area ratio of the target pet in any one of the pet photos is within a set ratio range, and obtaining a determination result; According to the judgment result, it is determined whether any of the pet photos passes the verification.

5. The method according to claim 4, wherein Determining whether any of the pet photos passes verification based on the judgment result includes: If the judgment result indicates that the area ratio is within the ratio range, determining that any one of the pet photos passes the verification; If the judgment result indicates that the area ratio is not within the ratio range, it is determined that any one of the pet photos has failed the verification.

6. A method for generating a pet expression package, characterized in that: The method is applied to a client, and includes: In response to a selection operation of a target emoji package theme template from at least one emoji package theme template, determining a first emoji package theme associated with the target emoji package theme template; wherein the client displays at least one emoji package theme template, and each emoji package theme template is associated with an emoji package theme; Sending a first emoticon package theme to a server, so that the server queries a pet model associated with the client, and generating at least one emoticon package picture showing a target pet based on the pet model and the first emoticon package theme, and obtaining a plurality of props associated with the first emoticon package theme, and performing image processing on the at least one emoticon package picture based on the plurality of props to obtain at least one pet emoticon package under the first emoticon package theme; wherein the pet model corresponds to the target pet and is generated based on at least one pet photo showing the target pet sent by the client; and the target pet is shown in the first pet emoticon package; Receiving each of the first pet expression packages sent by the server; The pet model is generated by the server through the following steps: Obtaining at least one pet photo; wherein the target pet shown in the at least one pet photo is shot from a different perspective; For any pet photo, perform target detection on the pet photo to obtain the species category of the target pet in the pet photo; When the species category of any one of the pet photos matches the set species category, detecting whether the face of the target pet in any one of the pet photos is clear, and detecting whether the target pet in any one of the pet photos is blocked, and obtaining a detection result; Determining whether any of the pet photos passes verification based on the detection result; A pet model corresponding to the target pet is generated based on the verified pet photos as training data, wherein the verified pet photos refer to pet photos with clear faces and no occlusion.

7. The method according to claim 6, wherein: The method further comprises: Displaying each of the first pet emoticons; and / or, Add each of the first pet emoticon packages to the first emoticon package theme in the album.

8. The method according to claim 7, wherein: The method further comprises: In response to the selection operation, determining a second emoticon package theme from at least one emoticon package theme in the album; Determine a second pet emoticon package from each pet emoticon package under the second emoticon package theme; In response to a sharing operation on the second pet emoticon package, the second pet emoticon package is shared to a target social application.

9. The method according to claim 8, wherein The step of sharing the second pet emoticon package to a target social application in response to a sharing operation on the second pet emoticon package includes: In response to a sharing operation on the second pet emoticon package, displaying a sharing page; wherein the sharing page displays at least one chat object in the target social application; In response to the selection operation, determining a target chat object from the at least one chat object; Invoke a dialog box between the target social application and the target chat object, and share the second pet emoticon package with the target chat object through the dialog box.

10. The method according to any one of claims 6 to 9, wherein: Before receiving the first pet expression packages sent by the server, the method further includes: Display a countdown page; wherein, the countdown page is used to indicate the remaining generation time of the first pet emoticon package.

11. The method according to any one of claims 6 to 9, wherein: The sending time of the first emoticon package theme is the target time, and the method further includes: If the first pet emoticon package sent by the server is not received within a set period after the target time, generating and displaying a prompt message; The prompt information is used to indicate that the generation of the first pet emoticon package failed and the reason for the failure.

12. The method according to any one of claims 6 to 9, wherein: The method further comprises: In response to an update operation on the pet model, updating the at least one pet photo associated with the pet model; Sending updated pet photos to the server; wherein the updated pet photos are used to update the pet model.

13. A device for generating pet emoticon packages, characterized in that: The device is provided at the server end and includes: An acquisition module, configured to acquire a first emoticon package theme sent by a client, wherein the first emoticon package theme is selected by a user from a homepage creative template list on a client side; A generation module is configured to query a pet model associated with the client; generate at least one emoticon package picture showing a target pet based on the pet model and the first emoticon package theme; wherein the pet model corresponds to the target pet and is generated based on at least one pet photo showing the target pet sent by the client; the target pet is shown in the first pet emoticon package; obtain a plurality of props associated with the first emoticon package theme; and perform image processing on the at least one emoticon package picture based on the plurality of props to obtain at least one pet emoticon package under the first emoticon package theme; A sending module, configured to send each pet expression package to the client; The device further comprises: An acquisition module is configured to acquire at least one pet photo; wherein the target pet shown in the at least one pet photo is shot from a different perspective; a verification module for performing target detection on any pet photo to obtain the species category of the target pet in the pet photo; if the species category of the pet photo matches a set species category, detecting whether the face of the target pet in the pet photo is clear and whether there is any occlusion in the pet photo to obtain a detection result; and determining whether the pet photo passes verification based on the detection result; The generation module is used to generate a pet model corresponding to the target pet based on the verified pet photo.

14. The device according to claim 13, wherein The type of the prop includes at least one of the following: Word; sticker; Filters; background; Animation.

15. The device according to any one of claims 13-14, wherein There are multiple pet models associated with the client, and different pet models correspond to different target pets; The generating module is used to: Determining the pet model specified by the client from the plurality of pet models; Generate at least one pet emoticon package under the first emoticon package theme according to the specified pet model and the first emoticon package theme; The pet emoticon package displays a target pet corresponding to the designated pet model.

16. The device according to claim 13, wherein The verification module is used to: If the detection result indicates that the face of the target pet is unclear, and / or the detection result indicates that the target pet is obscured, determining that any one of the pet photos fails verification; When the detection result indicates that the face of the target pet is clear and there is no occlusion of the target pet, determining whether the area ratio of the target pet in any one of the pet photos is within a set ratio range, and obtaining a determination result; According to the judgment result, it is determined whether any of the pet photos passes the verification.

17. The device according to claim 16, wherein The verification module is used to: If the judgment result indicates that the area ratio is within the ratio range, determining that any one of the pet photos passes the verification; If the judgment result indicates that the area ratio is not within the ratio range, it is determined that any one of the pet photos has failed the verification.

18. A device for generating pet emoticon packages, characterized in that: The device is provided at the client end and includes: A sending module, configured to determine a first emoji package theme associated with the target emoji package theme template in response to a selection operation on a target emoji package theme template in at least one emoji package theme template; wherein the client displays at least one emoji package theme template, and each emoji package theme template is associated with an emoji package theme; send the first emoji package theme to a server, so that the server queries a pet model associated with the client, and generates at least one emoji package picture showing a target pet based on the pet model and the first emoji package theme, and obtains a plurality of props associated with the first emoji package theme, and performs image processing on the at least one emoji package picture based on the plurality of props to obtain at least one pet emoji package under the first emoji package theme; wherein the pet model corresponds to the target pet, and is generated based on at least one pet photo showing the target pet sent by the client; the target pet is displayed in the first pet emoji package; A receiving module, configured to receive each of the first pet expression packages sent by the server; The pet model is generated by the server through the following steps: Obtaining at least one pet photo; wherein the target pet shown in the at least one pet photo is shot from a different perspective; For any pet photo, perform target detection on the pet photo to obtain the species category of the target pet in the pet photo; When the species category of any one of the pet photos matches the set species category, detecting whether the face of the target pet in any one of the pet photos is clear, and detecting whether the target pet in any one of the pet photos is blocked, and obtaining a detection result; Determining whether any of the pet photos passes verification based on the detection result; A pet model corresponding to the target pet is generated based on the verified pet photos as training data, wherein the verified pet photos refer to pet photos with clear faces and no occlusion.

19. The device according to claim 18, wherein The device further comprises: A processing module is used to display each of the first pet emoticon packages; and / or add each of the first pet emoticon packages to the first emoticon package theme in the album.

20. The device according to claim 19, wherein The device further comprises: a determination module for determining, in response to a selection operation, a second emoticon package theme from at least one emoticon package theme in the album, and determining a second pet emoticon package from each pet emoticon package under the second emoticon package theme; The sharing module is configured to share the second pet emoticon package to a target social application in response to a sharing operation on the second pet emoticon package.

21. The device according to claim 20, wherein The sharing module is used to: In response to a sharing operation on the second pet emoticon package, displaying a sharing page; wherein the sharing page displays at least one chat object in the target social application; In response to the selection operation, determining a target chat object from the at least one chat object; Invoke a dialog box between the target social application and the target chat object, and share the second pet emoticon package with the target chat object through the dialog box.

22. The device according to any one of claims 18 to 21, wherein The device further comprises: A display module is used to display a countdown page; wherein the countdown page is used to indicate the remaining generation time of the first pet emoticon package.

23. The device according to any one of claims 18 to 21, wherein: The sending time of the first emoticon package theme is the target time, and the device further includes: a display module, configured to generate and display a prompt message if the first pet emoticon package sent by the server is not received within a set period of time after the target time; The prompt information is used to indicate that the generation of the first pet emoticon package failed and the reason for the failure.

24. The device according to any one of claims 18 to 21, wherein The device further comprises: an updating module, configured to update the at least one pet photo associated with the pet model in response to an update operation on the pet model; The sending module is further used to send updated pet photos to the server; wherein the updated pet photos are used to update the pet model.

25. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for generating a pet emoticon package described in any one of claims 1-5, or execute the method for generating a pet emoticon package described in any one of claims 6-12.

26. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable the computer to execute the method for generating a pet emoticon package according to any one of claims 1-5, or to execute the method for generating a pet emoticon package according to any one of claims 6-12.

27. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for generating a pet emoticon package according to any one of claims 1 to 5, or implements the steps of the method for generating a pet emoticon package according to any one of claims 6 to 12.

Images