Emoticon package generation method, device and equipment and computer readable storage medium

Abstract

The application discloses an expression package generation method, which comprises the following steps: obtaining a target picture and identifying the target picture; analyzing the identification result of the target picture; selecting a target expression according to the identification result; and generating an expression package based on the target expression. The application further discloses an expression package generation device, equipment and computer readable storage medium. The application combines the target expression with the target picture according to the target expression selected by a user and the target expression selected by the user by obtaining the target picture selected by the user, identifying the target picture, and generating an expression package according to the identification result of the target picture. The application realizes high expression package production efficiency, makes the generated expression package more diversified, and meets the customized needs of users.

Description

Technical Field

[0001] This invention relates to the field of communication software, and more particularly to methods, apparatus, devices, and computer-readable storage media for generating emoticons. Background Technology

[0002] With the development of technology and the rapid popularization of smart devices (such as smartphones and personal computers), all kinds of software have sprung up like mushrooms after rain, such as emoji creation software (or emoji creation plugins installed in other software).

[0003] Existing emoji creation software requires users to first take a picture or download it to their local device, then select the image and edit it to generate an emoji. Some emoji creation software allows users to batch generate multiple emojis using only a single background image and different text descriptions. However, editing images on a device presents a high learning curve for users, resulting in low emoji creation efficiency. Using only a single background image to batch generate multiple emojis also leads to a lack of variety in the generated emojis, failing to meet users' diverse and customized emoji creation needs. Summary of the Invention

[0004] The main objective of this invention is to provide a method for generating emojis, which aims to solve the technical problems of existing emoji creation methods having high learning costs and producing only a single type of emoji, failing to meet users' diverse and customized emoji creation needs.

[0005] Furthermore, to achieve the above objectives, the present invention also provides a method for generating emojis, the method comprising the following steps:

[0006] Acquire the target image and perform recognition on the target image;

[0007] Analyze the recognition results of the target image;

[0008] Based on the recognition results, select a target expression;

[0009] Based on the target expression, an emoji pack is generated.

[0010] Optionally, the step of obtaining the target image includes:

[0011] Before generating an emoji, output the image selection interface;

[0012] When it is detected that a user has launched the camera based on the image selection interface, the first image generated after the camera takes a picture is acquired, and the first image is used as the target image; or

[0013] When it is detected that a user has opened a local photo library based on the image selection interface, the second image selected by the user in the local photo library is used as the target image.

[0014] Optionally, after the steps of acquiring the target image and recognizing the target image, the method further includes:

[0015] If the recognition result of the target image is a portrait image, then the portrait information of the portrait image is obtained;

[0016] Based on the portrait information, select the facial expressions corresponding to the portrait information from a preset database, and combine the facial expressions to form a subset of facial expressions, wherein the facial expressions belong to the matched expressions.

[0017] Optionally, after the steps of acquiring the target image and recognizing the target image, the method further includes:

[0018] If the recognition result of the target image is not a portrait image, then the subject information of the target image is obtained;

[0019] Based on the subject information, select the subject expression corresponding to the subject information from the preset database, and combine the subject expressions to form a subject expression subset, wherein the subject expression belongs to the matching expression.

[0020] Optionally, if the recognition result of the target image is a portrait image, then after the step of obtaining the portrait information of the portrait image, the method includes:

[0021] Select a first person expression corresponding to the portrait image from the preset database, combine the first person expressions to form a subset of first person expressions, and extract at least one of the following from the portrait information: race information, age information, ethnicity information, and country information;

[0022] Based on the racial and / or ethnic information, a second character expression is selected from the preset database, and the second character expressions are combined to form a subset of second character expressions; or,

[0023] Based on the racial information and / or the national information, select third-person facial expressions from the preset database, and combine the third-person facial expressions to form a subset of third-person facial expressions; or,

[0024] Based on at least one of the racial information, national information, and age information, a fourth character expression is selected from the preset database, and the fourth character expressions are combined to form a subset of fourth character expressions.

[0025] Optionally, the step of selecting the subject expression corresponding to the subject information from a preset database based on the subject information, and combining the subject expressions to form a subset of subject expressions includes:

[0026] Extract the main image subject and / or similar subjects from the subject information;

[0027] Based on the image subject, select a first subject expression from a preset database, and combine the first subject expressions to form a first subject expression subset; and / or,

[0028] Based on the similar subjects, a second subject expression is selected from the preset database, and the second subject expressions are combined to form a subset of the second subject expressions.

[0029] Optionally, the step of acquiring the target image and recognizing the target image includes:

[0030] After obtaining the target image, when a first operation is received from the user based on the target image, the target image is identified, wherein the first operation is at least one of the following: gesture operation, click operation, button operation, and voice operation.

[0031] In addition, to achieve the above objectives, the present invention also provides an emoji generation device, which includes: a memory, a processor, and an emoji generation program stored in the memory and executable on the processor. When the emoji generation program is executed by the processor, it implements the steps of the emoji generation method described above.

[0032] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium storing an emoji generation program, which, when executed by a processor, implements the steps of the emoji generation method described above.

[0033] This invention discloses a method, apparatus, device, and computer-readable storage medium for generating emojis. In this embodiment, when a user starts the emoji generation program, the program first acquires and recognizes the target image selected by the user. The program is pre-connected to a (cloud) database containing many emojis. Based on the recognition results of the target image, the program further selects multiple matching emojis from the database that correspond to the recognition results. These matching emojis are also output for the user to choose from. The user can select their preferred target emoji based on the matching emojis. Finally, the program combines the target emoji with the target image to generate an emoji. Because the recognition of the target image, the output of the emoji subset, and the generation of the emoji are all completed automatically by the emoji generation program, high emoji production efficiency is achieved. Furthermore, because the program intelligently recommends a series of emojis based on the recognition results, the generated emojis are more diverse, meeting the user's customization needs. Attached Figure Description

[0034] Figure 1 A schematic diagram of the hardware structure of one embodiment of the emoji generation device provided in this invention;

[0035] Figure 2 This is a flowchart illustrating the first embodiment of the emoji generation method of the present invention;

[0036] Figure 3 This is a schematic diagram of the emoji echelon in the first embodiment of the emoji generation method of the present invention;

[0037] Figure 4 This is a flowchart illustrating the second embodiment of the emoji generation method of the present invention;

[0038] Figure 5 This is a schematic diagram of the image selection interface in the second embodiment of the emoticon generation method of the present invention;

[0039] Figure 6 This is a flowchart illustrating the third embodiment of the emoji generation method of the present invention;

[0040] Figure 7 This is a schematic diagram of the main facial expression in the third embodiment of the emoji generation method of the present invention.

[0041] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0042] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0043] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0044] The emoji generation terminal (also called a terminal, device, or terminal device) in this embodiment of the invention can be a PC, or a mobile terminal device with display function such as a smartphone, tablet computer, or portable computer.

[0045] like Figure 1 As shown, the terminal may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0046] Optionally, the terminal may also include a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, and so on. Sensors may include light sensors, motion sensors, and other sensors. Specifically, light sensors may include ambient light sensors and proximity sensors. The ambient light sensor can adjust the display brightness according to the ambient light level, while the proximity sensor can turn off the display and / or backlight when the mobile terminal is moved to the ear. As a type of motion sensor, a gravity accelerometer can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity, and can be used for applications that identify the mobile terminal's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition functions (such as pedometers, taps), etc. Of course, the mobile terminal may also be equipped with other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, which will not be elaborated here.

[0047] Those skilled in the art will understand that Figure 1 The terminal structure shown does not constitute a limitation on the terminal and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0048] like Figure 1 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an emoji generation program.

[0049] exist Figure 1 In the terminal shown, the network interface 1004 is mainly used to connect to the backend server and communicate with the backend server; the user interface 1003 is mainly used to connect to the client (user terminal) and communicate with the client; and the processor 1001 can be used to call the emoticon generation program stored in the memory 1005. When the emoticon generation program is executed by the processor, it implements the operations in the emoticon generation method provided in the following embodiments.

[0050] Based on the above-mentioned device hardware structure, an embodiment of the emoji generation method of the present invention is proposed.

[0051] Reference Figure 2 In a first embodiment of the emoji generation method of the present invention, the emoji generation method includes:

[0052] Step S10: Obtain the target image and identify the target image.

[0053] In this embodiment, the emoji generation method is applied to an emoji generation device, which includes devices such as smartphones and personal computers that can install emoji creation programs (plugins). In this embodiment, the emoji generation device is pre-installed with an emoji generation program that supports the emoji generation method, or other software (such as instant messaging software such as WeChat and QQ) with built-in emoji generation plugins. In the following description, the emoji generation device is illustrated using a smartphone as an example, and the emoji creation program is illustrated using WeChat as an example.

[0054] When a user wants to create an emoji based on an image, the first step is to select the image (i.e., the target image in this embodiment). There are many ways to select an image: the user can manually turn on the camera, or the emoji generator can automatically turn on the camera. In this emoji generator, the front camera is activated by default. The user can manually switch to the rear camera, or the emoji generator can be set to default to the rear camera. Once the camera is activated, the user can take a picture. Alternatively, the image can be downloaded from the internet using a smartphone, transferred from another device to the smartphone, or sent by a friend on WeChat, etc. The specific method for obtaining the target image will not be detailed in this embodiment. After obtaining the target image, the emoji generator will recognize its content. The recognition method can be existing facial recognition methods. Specifically, the image can be scanned to obtain the subject information, and then the type of subject (a person or another object) can be determined.

[0055] Step S20: Analyze the recognition results of the target image.

[0056] To support the emoji generation method in this embodiment, the emoji generation program connects to a (cloud) database containing various types of emojis. Emoji classification tags can include accessories, text, expressions, ethnic characteristics, and local celebrities. It is understood that the initial identification of the target image can result in either portrait images or non-portrait images. When the target image is identified as a portrait image, the database will contain many emojis that can be matched with it, forming a large set. This large set can be further subdivided into smaller sets based on the emoji classification tags. Therefore, portrait images can be further identified to obtain more portrait information, such as skin color, ethnicity, and country. For example, if the further identification result of the target image is an Indian portrait, the database will contain some emojis that can be matched with Indian portraits. These emojis are small sets within the large set, which can be represented as emoji subsets.

[0057] Step S30: Select a target expression based on the recognition result.

[0058] As we know, when a user selects a target image, the emoji generation program will recognize the target image. The recognition result can be a portrait image or a non-portrait image. Further recognition can be performed if the target image is identified as either a portrait or a non-portrait image. For example, if the recognition result is a portrait image, more detailed recognition results can be obtained, such as skin color and ethnicity. Based on different recognition results, the database will output different matching emojis for the user to choose from. Figure 3 The above, Figure 3 Each small square on the right corresponds to an emoji. Users select their preferred emoji, which becomes the target emoji. Therefore, when a user clicks... Figure 3 The "More" option will also display more emojis for users to choose from.

[0059] Step S40: Generate an emoji pack based on the target expression.

[0060] In this embodiment, the target expression refers to the fact that after the recognition result of the target image is obtained, the program selects multiple expressions from the database, classifies these expressions as subsets, and outputs these subsets, such as... Figure 3 As shown, Figure 3 The pending emoji queues in the database are the preset database, with the first to fourth queues being subsets of these emojis. If a user browses these output emojis and selects one, this selected emoji becomes the target emoji in this embodiment. The emoji generation program will then combine the target emoji with the target image to generate an emoji pack.

[0061] Specifically, the detailed steps of step S10 also include:

[0062] Step a1: After obtaining the target image, when a first operation is received from the user based on the target image, the target image is identified. The first operation is at least one of the following: gesture operation (which may be a touch gesture operation or an air gesture operation), click operation, button operation, and voice operation.

[0063] In this embodiment, gesture operations refer to a series of operations performed by the user on the target image using their fingers, including (single) tap, (double) tap, long press, (any direction) swipe, and tap; click operations refer to a series of operations performed by the user on the floating button on the smartphone screen using their fingers. It is understood that the interface on the smartphone screen during a click operation can be the display interface of the target image, and click operations include single tap, double tap, long press, and drag; button operations refer to a series of operations performed by the user on the buttons on the smartphone, including but not limited to volume buttons, home button, and screen-off button, or any combination of these buttons, and button operations include single tap, double tap, long press, and pressing different buttons simultaneously; voice operations refer to a series of operations performed by the user on the target image using their voice, including various voice commands, such as "make an emoji." The purpose of operating on the image can be to recognize the target image.

[0064] In this embodiment, when a user starts the emoji generation program, the program first acquires the target image selected by the user and performs recognition on it. The program is pre-connected to an emoji database (i.e., a preset database). Based on the recognition results of the target image, the program further selects multiple matching emojis from the preset database that correspond to the recognition results. These matching emojis are then combined into multiple emoji subsets. The user can choose their preferred emoji based on the name of the emoji subset. Finally, the program combines the selected emoji with the target image to generate an emoji. Because the recognition of the target image, the output of the emoji subsets, and the generation of the emoji are all completed automatically by the program, high emoji production efficiency is achieved. Furthermore, because the program intelligently recommends a series of emojis based on the recognition results, the generated emojis are diversified, meeting the user's customization needs.

[0065] Furthermore, referring to Figure 4 Based on the above embodiments of the present invention, a second embodiment of the emoticon generation method of the present invention is proposed.

[0066] This embodiment is a refinement of step S10 in the first embodiment. The difference between this embodiment and the above-described embodiments of the present invention is as follows:

[0067] Step S11: Before generating an emoji, output the image selection interface.

[0068] Step S12: When it is detected that the user has launched the camera based on the image selection interface, acquire the first image generated after the camera takes a picture, and use the first image as the target image. Alternatively,

[0069] Step S13: When it is detected that the user opens the local gallery based on the image selection interface, the second image selected by the user in the local gallery is used as the target image.

[0070] In this embodiment, the condition for triggering the creation of emojis can be either a user's active click or an automatic trigger when the emoji generation program detects downloaded or received images. The image selection interface refers to an interactive interface displayed on the smartphone's screen after the emoji generation program is launched. This interface may include buttons to open the camera or to navigate to the phone's photo album, such as... Figure 5 As shown, when a user selects the corresponding operation button, the smartphone will activate the corresponding function. It is understood that when the user selects the button to open the camera, the emoji generation program will default to opening the smartphone's front-facing camera. The user can manually adjust to the rear camera, or set the rear camera to be enabled by default in the emoji creation program. After the camera is opened, the image taken by the user is the first image in this application. When the user selects the button to open the phone's photo album, the emoji generation program will redirect to the phone's photo album (i.e., the local gallery in this embodiment) for the user to browse. The image selected by the user while browsing the phone's photo album is the second image in this embodiment. It is understood that images obtained through other means (such as those downloaded while browsing the internet) are generally automatically saved to the local gallery.

[0071] In this embodiment, the first step in generating an emoji is to acquire the target image. This embodiment provides all possible ways to acquire images through a smartphone, fully ensuring the diversity of image sources and the flexibility and variability of the emoji.

[0072] Furthermore, referring to Figure 6 Based on the above embodiments of the present invention, a third embodiment of the emoticon generation method of the present invention is proposed.

[0073] This embodiment is a step following step S10 in the first embodiment. The difference between this embodiment and the above embodiments of the present invention is as follows:

[0074] Step S50: If the recognition result of the target image is a portrait image, then obtain the portrait information of the portrait image.

[0075] Step S60: Based on the portrait information, select the facial expressions corresponding to the portrait information from a preset database, and combine the facial expressions to form a subset of facial expressions, wherein the facial expressions belong to the matched expressions.

[0076] In this embodiment, "portrait image" refers to the recognition result of the emoji generation program on a target image containing a clearly visible human image (including a face photo, half-body photo, or full-body photo). The number of human images in the target image is not limited; only clearly visible human images are required. This is to ensure more accurate recognition results. "Portrait information" in this embodiment refers to the further acquisition of information about the human image by the emoji generation program when the target image is identified as a portrait image. For example, if the portrait image is a frontal view, the program can acquire the person's skin color, face shape, and other facial features. Then, based on these features, the program can intelligently calculate the person's age, ethnicity, race, and country. This information is collectively referred to as portrait information. Figure 3 As shown, when the recognition result of the target image is a portrait image, and the portrait information of the portrait image has been obtained, the emoji generation program will select the human expression corresponding to the portrait information from the preset database. That is, when the recognition result of the target image is a portrait image, the matching expression selected by the emoji generation program from the preset database is the human expression in this embodiment. Figure 3 The right side of the image displays the queue of expressions to be processed, which contains all the character expressions. These expressions are then categorized and grouped according to facial information to form multiple subsets of character expressions (such as...). Figure 3 (The first to fourth tiers of expressions), for example, based on the racial, age and national information of a person calculated by intelligence, a portion of the expressions can be selected from all the expressions to form the fourth tier of expressions.

[0077] Specifically, the steps following step S10 also include:

[0078] Step S70: If the recognition result of the target image is not a portrait image, then obtain the subject information of the target image.

[0079] Step S80: Based on the subject information, select the subject expression corresponding to the subject information from the preset database, and combine the subject expressions to form a subject expression subset, wherein the subject expression belongs to the matching expression.

[0080] When the target image does not contain a human figure, or only contains a blurry human figure, the emoji generation program will determine that the target image is not a human figure and will obtain the main subject of the target image. Based on the main subject, it will then determine the main subject information of the target image, which may include the main subject and / or similar subjects. For example... Figure 7As shown, if the emoji generation program determines that the target image is not a human portrait and obtains that the main subject of the target image is a bear, then the main subject of the target image can be any type of bear, and similar subjects can be pandas or other subjects similar to bears. When the target image is not a human portrait and the main subject information of the target image has been obtained, the emoji generation program will select the main emoji corresponding to the main subject information from a preset database. That is, when the target image is not a human portrait, the matching emoji selected by the emoji generation program from the preset database is the main emoji in this embodiment. Figure 7 The queue of expressions to be processed shown on the right is the complete set of main expressions. These main expressions are categorized and grouped according to their subject information to form multiple subsets of main expressions (such as...). Figure 7 (The first and second tiers in the image), for example, based on the main subject of the image, a portion of the main subject expressions can be selected and combined to form the first subject tier.

[0081] Specifically, the steps following step S21 also include:

[0082] Step b1: Select a first human expression corresponding to the portrait image from the preset database, combine the first human expressions to form a first human expression subset, and extract at least one of the following from the portrait information: race information, age information, ethnicity information, and country information.

[0083] Step b2: Based on the racial and / or ethnic information, select a second character expression from the preset database, and combine the second character expressions to form a subset of second character expressions. Alternatively,

[0084] Step b3: Based on the racial information and / or the national information, select third-person facial expressions from the preset database, and combine the third-person facial expressions to form a subset of third-person facial expressions. Alternatively,

[0085] Step b4: Select a fourth character expression from the preset database based on at least one of the ethnicity information, the country information, and the age information, and combine the fourth character expressions to form a subset of fourth character expressions.

[0086] like Figure 3 As shown, the first to fourth subsets of character expressions in this embodiment are... Figure 3The first to fourth tiers in the image are named accordingly. In this embodiment, the first to fourth character expressions correspond to the first to fourth character expression subsets. For example, the first character expression is an expression in the first tier. In this embodiment, the first character expression subset is a collection of expressions (i.e., the first tier) that are paired with different expressions, accessories, and text for the characters in the image. The expressions in this first character expression subset are highly adaptable and applicable to most portrait images, so they are placed in the first tier. It can be seen that the emoji generation program can also flexibly adjust the position of each character expression subset based on the obtained user preferences. In this embodiment, the second character expression subset is... Figure 3 The second echelon consists of several categories. The second echelon can contain expressions reflecting the ethnic characteristics of the person in the image. Therefore, based on the person's ethnicity and race, corresponding expressions are selected from a pre-defined database and combined to form the second echelon. The third echelon can contain expressions representing well-known figures from the person's country (or region). Similarly, based on the person's ethnicity and country, corresponding expressions are selected from a pre-defined database and combined to form the third echelon. The fourth echelon can contain frequently used expressions on social media platforms (the internet) corresponding to the person's age in their country (or region). Therefore, based on the person's ethnicity, country, and age, corresponding expressions are selected from a pre-defined database and combined to form the fourth echelon. It is understood that the number of echelons can be flexibly adjusted according to the classification criteria. In this embodiment, the number, order, and content of the echelons are merely illustrative examples.

[0087] Specifically, the steps following step S23 also include:

[0088] Step c1: Extract the main image subject and / or similar subjects from the subject information.

[0089] Step c2: Based on the subject of the image, select a first subject expression from a preset database and combine the first subject expressions to form a first subject expression subset.

[0090] Step c3: Select a second subject expression from the preset database based on the similar subjects, and combine the second subject expressions to form a subset of second subject expressions.

[0091] like Figure 7 As shown, the first and second subsets of main facial expressions in this embodiment are... Figure 7The first and second tiers in the image are named accordingly. In this embodiment, the first and second subject expressions correspond to subsets of the first and second subject expressions, respectively. The first subject expression in this embodiment is formed by anthropomorphizing or cartoonizing the subject in the image (including but not limited to animals, objects, and other items), and then adding corresponding props, text, accessories, and geometric elements. The set of first subject expressions is the collection of all first subject expressions; therefore, it is necessary to select the corresponding expression from a preset database based on the image subject. The second subject expression in this embodiment is formed by anthropomorphizing or cartoonizing a subject similar to the subject in the image, and then adding corresponding props, text, accessories, and geometric elements. The set of second subject expressions is the collection of all second subject expressions; therefore, it is necessary to select the corresponding expression from a preset database based on similar subjects.

[0092] In this embodiment, the emoji generation program outputs a series of emoji tiers based on the recognition results, making the generated emojis more diverse and meeting the user's customization needs.

[0093] Furthermore, this invention also proposes an emoji generation device, which includes:

[0094] An acquisition module is used to acquire a target image and identify the target image;

[0095] The selection module is used to select matching expressions from a preset database based on the recognition results of the target image, and combine the matching expressions to form an expression subset;

[0096] The generation module is used to receive the target emoji selected by the user based on the emoji subset and generate an emoji pack.

[0097] Optionally, the acquisition module includes:

[0098] The output unit is used to output an image selection interface before generating an emoji.

[0099] The first acquisition unit is configured to acquire a first image generated after the camera takes a picture when it detects that a user has launched the camera based on the image selection interface, and use the first image as the target image; or

[0100] The detection unit is used to select the second image selected by the user in the local image library as the target image when it detects that the user has opened the local image library based on the image selection interface.

[0101] Optionally, the emoji generation device further includes:

[0102] The second acquisition unit is used to acquire the portrait information of the portrait image if the recognition result of the target image is a portrait image.

[0103] The first selection unit is used to select a human expression corresponding to the human image information from a preset database based on the human image information, and combine the human expressions to form a subset of human expressions, wherein the human expressions belong to the matched expressions.

[0104] Optionally, the emoji generation device further includes:

[0105] The third acquisition unit is used to acquire the main body information of the target image if the recognition result of the target image is not a portrait image.

[0106] The second selection unit is used to select a subject expression corresponding to the subject information from a preset database based on the subject information, and combine the subject expressions to form a subject expression subset, wherein the subject expression belongs to the matching expression.

[0107] Optionally, the emoji generation device further includes:

[0108] The first extraction unit is used to select a first human expression corresponding to the portrait image from a preset database, combine the first human expressions to form a subset of first human expressions, and extract at least one of race information, age information, ethnicity information and country information from the portrait information;

[0109] The first combining unit is configured to select a second character expression from the preset database based on the racial information and / or ethnic information, and combine the second character expressions to form a subset of second character expressions; or,

[0110] The second combining unit is used to select a third person's facial expression from the preset database based on the ethnicity information and / or the country information, and combine the third person's facial expressions to form a subset of third person's facial expressions; or,

[0111] The third combination unit is used to select a fourth character expression from the preset database based on at least one of the ethnicity information, the country information, and the age information, and combine the fourth character expressions to form a subset of fourth character expressions.

[0112] Optionally, the second selection unit includes:

[0113] The second extraction unit is used to extract the main image subject and / or similar subjects from the main subject information;

[0114] The third selection unit is configured to select a first subject expression from a preset database based on the subject of the image, and combine the first subject expressions to form a subset of first subject expressions; and / or,

[0115] The fourth selection unit is used to select a second subject expression from the preset database based on the similar subjects, and combine the second subject expressions to form a subset of the second subject expressions.

[0116] Optionally, the acquisition module further includes:

[0117] An operation unit is used to acquire a target image and, upon receiving a first operation performed by a user based on the target image, to recognize the target image. The first operation includes at least one of the following: a gesture operation (which may be a touch gesture operation or an air gesture operation), a click operation, a button operation, and a voice operation.

[0118] The methods executed by the above-mentioned program modules can be referred to in the various embodiments of the method of the present invention, and will not be repeated here.

[0119] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0120] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0121] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, tablet computer, etc.) to execute the methods described in the various embodiments of the present invention.

[0122] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. An expression package generation method, characterized by, The expression package generation method comprises the following steps: Obtaining a target picture and identifying the target picture; Analyzing the identification result of the target picture; According to the identification result, a target expression is selected; Based on the target expression, an expression package is generated; After the step of obtaining a target picture and identifying the target picture, the following steps are further included: If the target picture does not contain a portrait or only contains an unclear portrait, the subject information of the target picture is obtained; The picture subject and / or similar subject in the subject information are extracted, which includes but is not limited to animals, plants and other objects; According to the picture subject, a first subject expression is selected from a preset database, and the first subject expression is combined to form a first subject expression subset, wherein the first subject expression is an expression formed by personifying or cartoonizing the picture subject and adding at least one of corresponding props, scripts, accessories and geometric elements; and / or, According to the similar subject, a second subject expression is selected from the preset database, and the second subject expression is combined to form a second subject expression subset, wherein the second subject expression is an expression formed by personifying or cartoonizing the similar subject and adding at least one of corresponding props, scripts, accessories and geometric elements. 2.The sticker generation method of claim 1, wherein, The step of obtaining a target picture comprises: Before generating an expression package, outputting a picture selection interface; When detecting that the user starts a camera based on the picture selection interface, obtaining a first picture generated after the camera takes a picture, and taking the first picture as the target picture; or When detecting that the local gallery is opened based on the picture selection interface, taking a second picture selected by the user in the local gallery as the target picture. 3.The sticker generation method of claim 1, wherein, The step of obtaining a target picture and identifying the target picture comprises: After obtaining the target picture, when receiving a first operation made by the user based on the target picture, identifying the target picture, wherein the first operation is at least one of a gesture operation, a click operation, a key operation and a voice operation.

4. An expression package generation device characterized by comprising: The expression package generation device comprises a memory, a processor and an expression package generation program stored on the memory and executable on the processor, and the expression package generation program is executed by the processor to implement the steps of the expression package generation method according to any one of claims 1 to 3.

5. A computer readable storage medium, characterized in that, The computer readable storage medium stores an expression package generation program, and the expression package generation program is executed by the processor to implement the steps of the expression package generation method according to any one of claims 1 to 3.

Images