Processing method, intelligent terminal and storage medium

Abstract

The invention provides a processing method, an intelligent terminal and a storage medium. The processing method comprises the following steps: generating a target image according to acquired image description information and target features; based on this, the target feature can include information such as regions for identifying different cultural backgrounds, and the method can adapt to the text and image demands of users with different cultural backgrounds by taking the obtained target feature as one of the reference dimensions for image generation, thereby improving the user experience.

Description

Technical Field

[0001] The present application relates to the field of human-computer interaction, and specifically to a processing method, an intelligent terminal and a storage medium. Background Art

[0002] A text-generated image is an image generated based on the text content entered by the user using artificial intelligence (AI) technology. Users can quickly customize images through the corresponding text-generated image model to meet their diverse needs.

[0003] In the process of conceiving and implementing this application, the inventors found that there are at least the following problems: people in different regions have different cultural backgrounds, and they expect different images to be generated for the same text description, and their standards for judging the beauty and taboos of images are also different. Users need to add specific words to the text description to generate image content that conforms to the user's cultural background, which will undoubtedly affect the user experience.

[0004] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the invention

[0005] In response to the above technical problems, the present application provides a processing method, an intelligent terminal and a storage medium, which can adapt to the cultural image needs of users with different cultural backgrounds and improve the user experience.

[0006] A processing method provided in an embodiment of the present application includes the following steps:

[0007] Generate a target image based on the acquired image description information and target features.

[0008] Optionally, the method further includes: acquiring a target style;

[0009] The target image is displayed according to the target style.

[0010] Optionally, the method for acquiring the target style includes at least one of the following:

[0011] Acquire an alternative style associated with the target feature as a target style;

[0012] In response to a user operation, selecting a target style from a plurality of candidate styles;

[0013] Generating a target style according to the text content input by the user;

[0014] Determine the target style based on user history information.

[0015] Optionally, generating a target style according to the text content input by the user includes:

[0016] Identifying target features from the text content input by the user;

[0017] Acquire at least one candidate style according to the target feature;

[0018] Determine or get the target style from among the alternative styles.

[0019] Optionally, determining or acquiring the target style from the candidate styles includes: taking the candidate style with the highest ranking as the target style, or selecting and adjusting the candidate style according to a user instruction, and taking the adjusted candidate style as the target style.

[0020] Optionally, the target feature includes at least one of geographical location, language, architecture, clothing and facial features.

[0021] Optionally, the method for acquiring the target feature includes at least one of the following:

[0022] Enable positioning to obtain current geographical information to obtain target features;

[0023] Recognizing target features from the text content input by the user;

[0024] Get the target features entered by the user in the preset interface.

[0025] Optionally, the method further includes:

[0026] In response to the partition display, determining a target partition from at least two partitions;

[0027] Generate a comparison image based on the text content input by the user and the reference features;

[0028] The target image is displayed in the target partition, and the comparison image is displayed in other partitions.

[0029] Optionally, generating a target image includes:

[0030] In response to obtaining the text content input by the user, calling the preset AI model;

[0031] In response to acquiring the target feature, calling the sub-model corresponding to the target feature;

[0032] The sub-model and the preset AI model are integrated to generate a target image.

[0033] The present application also provides an intelligent terminal, comprising: a memory and a processor, wherein a processing program is stored in the memory, and when the processing program is executed by the processor, the steps of any of the above processing methods are implemented.

[0034] The present application also provides a storage medium storing a computer program, wherein the computer program implements the steps of any of the above processing methods when executed by a processor.

[0035] As described above, the technical solution of the present application includes: generating a target image according to the acquired image description information and target features. The target features may include information such as regions for identifying different cultural backgrounds. Here, the present application uses the acquired target features as one of the reference dimensions for image generation, which can meet the cultural image needs of users with different cultural backgrounds and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments of the present application, and together with the specification, are used to explain the principles of the present application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.

[0037] Figure 1 A schematic diagram of the hardware structure of a mobile terminal for implementing various embodiments of the present application;

[0038] Figure 2 A communication network system architecture diagram provided for an embodiment of the present application;

[0039] Figure 3 A flowchart of a processing method provided in the first embodiment of the present application;

[0040] Figure 4 A schematic diagram of a Wenshengtu AI interface provided in an embodiment of the present application;

[0041] Figure 5a and Figure 5b A schematic diagram of two target images generated for an embodiment of the present application;

[0042] Figure 6 A schematic diagram of a process for generating a target image provided by an embodiment of the present application;

[0043] Figure 7 A flowchart of a processing method provided in the second embodiment of the present application;

[0044] Figure 8 A flowchart of a processing method provided in the third embodiment of the present application;

[0045] Fig. 9 Based on Figure 8The processing method shown is a schematic diagram showing the target image and the comparison image.

[0046] The realization of the purpose, functional features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings have shown clear embodiments of this application, which will be described in more detail later. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0047] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0048] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0049] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in this article, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this article, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination". Furthermore, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising" and "including" indicate that there are the described features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or", "and / or", "including at least one of the following" etc. used in this application can be interpreted as inclusive, or mean any one or any combination. For example, “comprising at least one of the following: A, B, C” means “any of the following: A; B; C; A and B; A and C; B and C; A and B and C”, and for another example, “A, B or C” or “A, B and / or C” means “any of the following: A; B; C; A and B; A and C; B and C; A and B and C”. An exception to this definition will only occur when a combination of elements, functions, steps or operations are inherently mutually exclusive in some manner.

[0050] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are displayed in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and it can be performed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0051] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0052] It should be noted that, in this article, step codes such as S11, S12, etc. are used for the purpose of expressing the corresponding content more clearly and concisely, and do not constitute a substantial limitation on the sequence. When implementing it specifically, those skilled in the art may execute S12 first and then S11, etc., but these should all be within the scope of protection of this application.

[0053] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0055] The smart terminal may be implemented in various forms. For example, the smart terminal described in this application may include smart terminals such as mobile phones, tablet computers, laptop computers, PDAs, portable media players (PMPs), navigation devices, wearable devices, smart bracelets, pedometers, etc., as well as fixed terminals such as digital TVs and desktop computers.

[0056] The following description will be made by taking a mobile terminal as an example, and those skilled in the art will understand that, in addition to components specifically used for mobile purposes, the construction according to the embodiments of the present application can also be applied to fixed-type terminals.

[0057] See also Figure 1 , which is a schematic diagram of the hardware structure of a mobile terminal for implementing various embodiments of the present application, the mobile terminal 100 may include: RF (Radio Frequency, radio frequency) unit 101, WiFi module 102, audio output unit 103, A / V (audio / video) input unit 104, sensor 105, display unit 106, user input unit 107, interface unit 108, memory 109, processor 110, and power supply 111 and other components. Those skilled in the art can understand that Figure 1 The structure of the mobile terminal shown in the figure does not constitute a limitation on the mobile terminal. The mobile terminal may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0058] Combine the following Figure 1 The following is a detailed introduction to the various components of the mobile terminal:

[0059] The radio frequency unit 101 can be used for receiving and sending signals during information transmission or communication. Specifically, after receiving the downlink information of the base station, it is sent to the processor 110 for processing; in addition, the uplink data is sent to the base station. Generally, the radio frequency unit 101 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc. In addition, the radio frequency unit 101 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communications can use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA2000 (Code Division Multiple Access 2000), WCDMA (Wideband Code Division Multiple Access), TD-SCDMA (Time Division-Synchronous Code Division Multiple Access), FDD-LTE (Frequency Division Duplexing-Long Term Evolution), TDD-LTE (Time Division Duplexing-Long Term Evolution), 5G and 6G, etc.

[0060] WiFi is a short-range wireless transmission technology. Mobile terminals can help users send and receive emails, browse web pages, and access streaming media through WiFi module 102. It provides users with wireless broadband Internet access. Figure 1 The WiFi module 102 is shown, but it is understandable that it is not an essential component of the mobile terminal and can be omitted as needed without changing the essence of the invention.

[0061] The audio output unit 103 can convert the audio data received by the RF unit 101 or the WiFi module 102 or stored in the memory 109 into an audio signal and output it as sound when the mobile terminal 100 is in a call signal reception mode, a talk mode, a recording mode, a voice recognition mode, a broadcast reception mode, etc. Moreover, the audio output unit 103 can also provide audio output related to a specific function performed by the mobile terminal 100 (for example, a call signal reception sound, a message reception sound, etc.). The audio output unit 103 may include a speaker, a buzzer, etc.

[0062] The A / V input unit 104 is used to receive audio or video signals. The A / V input unit 104 may include a graphics processor (GPU) 1041 and a microphone 1042, and the graphics processor 1041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The processed image frame can be displayed on the display unit 106. The image frame processed by the graphics processor 1041 can be stored in the memory 109 (or other storage medium) or sent via the radio frequency unit 101 or the WiFi module 102. The microphone 1042 can receive sound (audio data) via the microphone 1042 in a telephone call mode, a recording mode, a voice recognition mode, and other operating modes, and can process such sound into audio data. The processed audio (voice) data can be converted into a format output that can be sent to a mobile communication base station via the radio frequency unit 101 in the case of a telephone call mode. The microphone 1042 can implement various types of noise elimination (or suppression) algorithms to eliminate (or suppress) noise or interference generated in the process of receiving and sending audio signals.

[0063] The mobile terminal 100 also includes at least one sensor 105, such as a light sensor, a motion sensor, and other sensors. Optionally, the light sensor includes an ambient light sensor and a proximity sensor. Optionally, the ambient light sensor can adjust the brightness of the display panel 1061 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 1061 and / or the backlight when the mobile terminal 100 is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can be configured on the mobile phone, such as fingerprint sensors, pressure sensors, iris sensors, molecular sensors, gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be repeated here.

[0064] The display unit 106 is used to display information input by the user or information provided to the user. The display unit 106 may include a display panel 1061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0065] The user input unit 107 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the mobile terminal. Optionally, the user input unit 107 may include a touch panel 1071 and other input devices 1072. The touch panel 1071, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 1071 or near the touch panel 1071 using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a pre-set program. The touch panel 1071 may include two parts: a touch detection device and a touch controller. Optionally, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 110, and can receive and execute the command sent by the processor 110. In addition, the touch panel 1071 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 1071, the user input unit 107 may further include other input devices 1072. Optionally, the other input devices 1072 may include, but are not limited to, one or more of a physical keyboard, a function key (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, etc., which are not specifically limited here.

[0066] Optionally, the touch panel 1071 may cover the display panel 1061. When the touch panel 1071 detects a touch operation on or near it, it transmits the information to the processor 110 to determine the type of touch event. Then, the processor 110 provides corresponding visual output on the display panel 1061 according to the type of touch event. Figure 1 In the figure, the touch panel 1071 and the display panel 1061 are used as two independent components to implement the input and output functions of the mobile terminal. However, in some embodiments, the touch panel 1071 and the display panel 1061 can be integrated to implement the input and output functions of the mobile terminal, which is not limited here.

[0067] The interface unit 108 serves as an interface through which at least one external device can be connected to the mobile terminal 100. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, etc. The interface unit 108 may be used to receive input (e.g., data information, power, etc.) from an external device and transmit the received input to one or more elements within the mobile terminal 100 or may be used to transmit data between the mobile terminal 100 and an external device.

[0068] The memory 109 can be used to store software programs and various data. The memory 109 can mainly include a program storage area and a data storage area. Optionally, the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 109 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0069] The processor 110 is the control center of the mobile terminal. It uses various interfaces and lines to connect various parts of the entire mobile terminal. It executes various functions of the mobile terminal and processes data by running or executing software programs and / or modules stored in the memory 109, and calling data stored in the memory 109, so as to monitor the mobile terminal as a whole. The processor 110 may include one or more processing units; preferably, the processor 110 may integrate an application processor and a modem processor. Optionally, the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 110.

[0070] The mobile terminal 100 may also include a power supply 111 (such as a battery) for supplying power to various components. Preferably, the power supply 111 may be logically connected to the processor 110 via a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system.

[0071] although Figure 1 Not shown, the mobile terminal 100 may further include a Bluetooth module, etc., which will not be described in detail here.

[0072] In order to facilitate understanding of the embodiments of the present application, the communication network system on which the mobile terminal of the present application is based is described below.

[0073] See also Figure 2 , Figure 2 A communication network system architecture diagram is provided for an embodiment of the present application, wherein the communication network system is an LTE system of universal mobile communication technology, and the LTE system includes a UE (User Equipment) 201, an E-UTRAN (Evolved UMTS Terrestrial Radio Access Network) 202, an EPC (Evolved Packet Core) 203 and an operator's IP service 204, which are connected in sequence for communication.

[0074] Optionally, UE201 may be the above-mentioned terminal 100, which will not be described in detail here.

[0075] E-UTRAN 202 includes eNodeB 2021 and other eNodeBs 2022 , etc. Optionally, eNodeB 2021 may be connected to other eNodeBs 2022 via a backhaul (eg, an X2 interface), and eNodeB 2021 is connected to EPC 203 , and eNodeB 2021 may provide UE 201 with access to EPC 203 .

[0076] EPC203 may include MME (Mobility Management Entity) 2031, HSS (Home Subscriber Server) 2032, other MMEs 2033, SGW (Serving Gate Way) 2034, PGW (PDN Gate Way) 2035 and PCRF (Policy and Charging Rules Function) 2036, etc. Optionally, MME 2031 is a control node that processes signaling between UE 201 and EPC 203, and provides bearer and connection management. HSS 2032 is used to provide some registers to manage functions such as home location register (not shown in the figure), and store some user-specific information such as service features and data rates. All user data can be sent through SGW2034, PGW2035 can provide IP address allocation and other functions for UE 201, PCRF2036 is the policy and charging control policy decision point for service data flow and IP bearer resources, which selects and provides available policy and charging control decisions for the policy and charging execution function unit (not shown in the figure).

[0077] The IP service 204 may include the Internet, an intranet, an IMS (IP Multimedia Subsystem) or other IP services.

[0078] Although the above introduction takes the LTE system as an example, those skilled in the art should know that the present application is not only applicable to the LTE system, but also to other wireless communication systems, such as GSM, CDMA2000, WCDMA, TD-SCDMA, 5G and future new network systems (such as 6G), etc., without limitation here.

[0079] Based on the above-mentioned mobile terminal hardware structure and communication network system, various embodiments of the present application are proposed.

[0080] First embodiment

[0081] See also Figure 3 , is a flowchart of a processing method provided in an embodiment of the present application. The processing method (hereinafter referred to as "the method") may be executed by at least one of a smart terminal such as a mobile phone, a processor with an image generation function, a storage medium, etc. The method includes step S11.

[0082] S11: Generate a target image according to the acquired image description information and target features.

[0083] The image description information is used to describe at least the content of the image to be generated (i.e., the target image), for example, which objects are included in the image to be generated, including but not limited to people, plants, animals, etc. These elements constitute the basic content of the target image. The acquisition method of the image description information includes but is not limited to: user input, and the user input method can be, for example, Figure 4 The text input on the interface can come from at least one of manual input, copy and paste, text recognition of clipped images, and voice input. The image description information at this time can be regarded as what is commonly referred to as "text content input by the user". Here, the processing method can also be called the text-to-image method.

[0084] The target feature includes, but is not limited to, regional information and features of the object to be generated in the image description information, such as at least one of the user's age, emotion, clothing color, etc. Through the target feature, different cultural backgrounds can be identified. For ease of description, the following description takes regional information as an example.

[0085] The regional information includes but is not limited to: geographical location, and at least one of language, architecture, clothing, and facial features, wherein at least one of language, architecture, clothing, and facial features can be used to identify regional information to reflect different cultural backgrounds. Taking geographical location as an example, people in different regions, provinces, and countries have different cultural backgrounds, which include but are not limited to clothing, diet, etc.

[0086] The processing method of the present application can be implemented based on an AI model, and the AI ​​model can be expressed in an execution subject such as a smart terminal as follows: Figure 4 An application program in the application interface shown, the application program may be called an AI program, Figure 4The application interface shown can be called an AI interface. The presentation form of the application is not limited to the APP installed on the smart terminal, but can also be a user-defined function description, including but not limited to a code, script or program that describes the need to perform a certain function; and at least one of the following: widgets, which can be used to make up for the main application (such as the APP on the main page) that cannot display the functions that the user cares about in a timely manner; shortcut function icons, which can be specifically displayed on the desktop as icons, symbols, folders, etc. similar to APP icons, for example, multiple regional icons can be displayed in a file, and each icon corresponds to a region; character segments, pictures, videos, audio and other media files displayed on the page in the form of icons. For the sake of ease of explanation and understanding, the application interface of the application example is selected for description below, for example, the accompanying drawings are all described using the APP interface as an example.

[0087] For example, for scenarios applicable to smart terminals, this example is equivalent to adding a sub-model (which may be called a "sub-AI model") function to the smart terminal. The sub-model function is equivalent to implanting text content about the target features in the original AI model of the smart terminal (which may be called a "preset AI model"), so that the target features can be used as reference dimensions when generating images. The implementation method of this function includes but is not limited to: taking a smart phone as an example, pre-programming a script or application and installing it in the operating system of the smart phone, thereby adding a "sub-model" option to the settings interface of the smart phone; then, by sliding the slider to turn the option on or off, the function can be turned on or off accordingly. Alternatively, the smart terminal can be separately configured as follows: Figure 4 An option is set on the interface shown. After opening the interface, the option can be turned on and off, and detailed settings including the target features corresponding to the option can be performed.

[0088] In other examples, the “sub-model” option can be set in the “settings” interface of the smart terminal, for example, it can be set in the “settings” interface to Figure 4 The interface for setting the application shown.

[0089] Optionally, the method for obtaining the regional information includes at least one of the following:

[0090] Method 1: Enable positioning to obtain the current region information to obtain target features.

[0091] by Figure 4 Taking the interface shown as an example, once the user turns on the "sub-model" option, the smart terminal will automatically turn on the positioning function to obtain the current geographical location and obtain regional information.

[0092] In actual scenarios, the automatic activation of the positioning function of the smart terminal will not violate the settings of the operating system. For example, if the operating system of the smart terminal has disabled the positioning function, even if the user Figure 4 If the "Sub-model" option is turned on in the interface shown in the figure, the smart terminal will not automatically turn on the positioning function. An optional prompt box "Positioning function is turned off, please go to the settings interface to turn it on" will be popped up to remind the user; for example, if the positioning function is turned on in the operating system of the smart terminal, but the positioning function is pre-set Figure 4 The application corresponding to the interface shown is not allowed to call user trips during operation, that is, the Figure 4 If the positioning function is turned off when the interface is opened, the smart terminal will not automatically turn on the positioning function, and the prompt box may pop up to remind the user. The current region information is obtained only after the user turns on the positioning function.

[0093] When the user does not input other information except the region information as the target feature this time, the obtained region information is directly used as the target feature. When the user also inputs other information except the region information this time, the obtained region information and other information are used together as the target feature.

[0094] Method 2: Obtain the target features input by the user in the preset interface.

[0095] In one example, the preset interface is Figure 4 The AI ​​interface shown has an input window, for example, a text input window, where the user inputs geographical information as a target feature through text input; for another example, the input window can be a voice input window, where the user inputs target features including geographical information through speaking.

[0096] The specific form of the input window and the way the user inputs the regional information are not limited to the above, and can be determined according to the adaptability of the actual scene requirements. For example, the smart terminal can establish a matching connection with other terminals and input the target features through other terminals. At this time, the input window of the smart terminal may not be displayed, or the AI ​​interface of the smart terminal does not display the input window, but displays a preset icon or dialog box to indicate that "the smart terminal is currently inputting the target features through other terminals".

[0097] Mode 3: Identify and obtain target features from the text content input by the user.

[0098] For example, the text content input by the user is "party of an African women in iro and buba", where iro and buba are local African costumes. The identified regional information is Africa and cultural background information related to Africa. The final output result can be as follows: Figure 5a The target image shown, in which the facial features, body shape, clothing and other elements of the African woman are consistent with the recognized regional information.

[0099] For another example, the text content input by the user is "park the xxx sports car at yy square", where "yy" is a local building, and the recognized regional information is India and cultural background information related to India. The final output result can be as follows: Figure 5b The target image shown, in which the buildings and characters displayed are consistent with the cultural background of India.

[0100] Method 4: Obtain target features from historical information.

[0101] Continue reading Figure 4 to Figure 5b As shown, the AI ​​interface may display a "historical information" option, which records the most recent or most recent preset regional information before this time.

[0102] When the user does not input other information except the region information as the target feature this time, in one example, the most recent region information is used as the region information this time. In other examples, the region information that appears the most times in the most recent preset times or the most times in the most recent preset time period can be obtained as the region information this time. When the user inputs other information except the region information as the target feature this time, the obtained region information and other information are used together as the target feature.

[0103] It should be understood that the historical information of this option can also record the most recent or most recent preset multiple generated images before this time. In this regard, the present application is equivalent to adding geographical information to the generated historical images. It should be noted that the geographical information added by this application is not the geographical, time and other information when the traditional image is generated. The geographical, time and other information when the traditional image is generated is the geographical, time and other information of the smart terminal at the moment the image is generated, which has nothing to do with the content of the image generation. The historical information of this option in the present application is related to the generated content of the historical image, and is not necessarily related to the location and time of the smart terminal.

[0104] In actual scenarios, the historical information of this option can be hidden and displayed. Figure 4 After selecting the "History Information" option, the AI ​​interface changes from Figure 4The interface shown switches to display multiple historical images. When the user performs a preset operation, such as clicking to select a historical image and then sliding up, the smart terminal responds to the preset operation and displays the added regional information below the historical image. The user clicks on the added regional information, and the AI ​​interface can pop up an option box to allow the user to use the added regional information as the regional information for this time through the "Regional Information" menu in the option box. Of course, the option box can also be provided with menus such as "Download", "Share", and "Edit". Optionally, the AI ​​interface also displays the geographical and time information of the smart terminal at the moment the historical image was generated.

[0105] It should be noted that the embodiments of the present application include multiple situations and multiple methods for a certain technical feature. Unless otherwise specified, it means that the corresponding technical feature can be implemented by combining any part of the methods. Through the combination scheme, the corresponding technical feature can be implemented more accurately and / or intelligently, thereby improving the accuracy of the implementation of the technical feature and the user experience.

[0106] For example, the present application may combine the above-mentioned method 2 and method 3. The intelligent terminal automatically acquires the regional information through method 3, and then manually selects the automatically acquired regional information through method 2, which can more accurately reflect the user's actual image generation intention.

[0107] Based on the above, the target feature of the present application may include regional information. By using the acquired regional information as one of the reference dimensions for image generation, the requirements of the Wensheng map for users with different cultural backgrounds can be met, thereby improving the user experience. At the same time, the execution subject of the method of the present application has a regional perception function when performing Wensheng map, and can optimize Wensheng map for the Wensheng background of different regions.

[0108] In one example of the present application, the target features including the regional information can be independently acquired by a separate AI model. To distinguish it from the original AI model of the smart terminal, the separate AI model is called a sub-model and the original AI model of the smart terminal is called a preset AI model. The algorithms used by the two AI models can be the same or different. Optionally, the sub-model has a smaller amount of computation and a higher model training accuracy for target features including regional information. The sub-model can be installed and trained separately. For example, images and related text descriptions are collected according to the cultural backgrounds of different regions, and then a preset AI model is fine-tuned with the collected images and text descriptions to generate sub-models under various cultural backgrounds, and the regional information applicable to the sub-model is marked. Here, Figure 6 As shown, the step S11 generates a target image, including the following steps S111 to S113.

[0109] S111: In response to obtaining the text content input by the user, calling a preset AI model;

[0110] S112: In response to acquiring the target feature, calling the sub-model corresponding to the target feature;

[0111] S113: Integrate the sub-model and the preset AI model to generate a target image.

[0112] By creating and training separate AI models for different target features, the AI ​​model has high portability and specificity. It not only has a wide range of usage scenarios and is flexibly applicable to different smart terminals, but also ensures that the text and image results can better meet the personalized needs of users.

[0113] Second embodiment

[0114] See also Figure 7 , is a flow chart of a processing method provided in the second embodiment of the present application. The processing method includes the following steps S21 to S23.

[0115] S21: Generate a target image according to the acquired image description information and target features;

[0116] S22: Get target style;

[0117] S23: Displaying the target image according to the target style.

[0118] In other words, the second embodiment also obtains the target style and uses the target style as one of the reference dimensions for generating the image. The so-called target style refers to one or more candidate styles selected by the user and used to perform the Vincent map. The so-called style refers to the representative appearance of the image as a whole, which can be regarded as the effect display of the object in the target image, and may not necessarily be associated with the aforementioned regional information. Figure 4 As shown, the AI ​​interface can display alternative styles such as "Smart Selection", "Traditional Style", "Movie", "Photography", "Game", "Surreal", "Cyberpunk", and "2D". Of course, there will also be a "More Styles" option to fold other alternative styles that cannot be displayed at once. Users can click the "More Styles" option to display these folded alternative styles on the AI ​​interface.

[0119] The same features of the second embodiment as those of the first embodiment can be found in the foregoing description and will not be described in detail here.

[0120] Optionally, the method for acquiring the target style includes at least one of the following:

[0121] Method 1: Obtain an alternative style associated with a target feature as a target style.

[0122] Taking the target feature as regional information as an example, the association relationship can be a cultural style that is well known to the public in a certain region. Taking the regional information as Japan as an example, the alternative style of "two-dimensional" can be selected as the target style; taking the regional information as Germany as an example, the alternative style of "cyberpunk" can be selected as the target style; taking the regional information as Hainan as an example, the alternative style of "sea view style" can be selected as the target style.

[0123] For another example, the association relationship may be the style corresponding to the regional information when generating the historical image. Taking the regional information A obtained during this cultural image generation as an example, if the historical image was previously generated using the regional information A as a reference dimension (i.e., the target image generated before this time), the target style when the historical image was generated may be directly selected as the target style for this cultural image generation.

[0124] It should be noted that a single region information may be associated with multiple candidate styles. This application may sort these candidate styles according to the degree of association. The greater the degree of association, the higher the ranking, so that the candidate style with the highest ranking is used as the target style. For example, if there are two or more candidate styles ranked at the top, these two or more candidate styles can be used as target styles, that is, there are multiple target styles, so that a target image can be generated according to each target style according to the text content input by the user and the regional information obtained, and finally multiple target images are obtained.

[0125] Method 2: In response to a user operation, a target style is selected from a plurality of candidate styles.

[0126] Combination Figure 4 As shown, in one example, the user can click on an alternative style in the AI ​​interface, including clicking on an alternative style collapsed by a "more styles" option, as a target style.

[0127] Combination Figure 4 As shown, in other examples, the user can click the "More Styles" option in the AI ​​interface to edit and generate a style, such as the "Impressionism" style, as the target style. The so-called editing includes editing the alternative styles collapsed by the "More Styles" option, and can also include reintroducing styles other than the alternative styles collapsed by the "More Styles" option.

[0128] Method 3: Generate a target style according to the text content input by the user.

[0129] In one example, the text content input by the user may directly include character information identifying a certain style. For example, for the text content "Park the xxx sports car at the yy square to generate a game wallpaper", the target style may be determined to be "game" based on "game wallpaper"; for another example, for the text content "party of an african women in iro and buba, Anime and Manga", the target style may be determined to be "two-dimensional" based on "Anime and Manga".

[0130] In another example, the smart terminal may first identify regional information (i.e., target features) from the text content input by the user, and then generate at least one alternative style based on the identified regional information, for example, generating alternative styles based on the association relationship of the aforementioned target style acquisition method 1, and then determining or acquiring the target style from the alternative styles. For example, determining the target style from the alternative styles includes: taking the top-ranked alternative style as the target style; acquiring the target style from the alternative styles includes: when the user is not satisfied with the displayed alternative styles, one or more alternative styles can be selected and adjusted according to user instructions, and finally the adjusted alternative style is used as the target style. That is, this example allows the user to adjust the alternative styles to generate a new style as the target style, thereby further meeting the user's personalized image generation needs.

[0131] Method 4: Determine the target style based on user history information.

[0132] For example, the user's image may be captured by a camera or other means to identify the user's style, and a style corresponding to the user's style may be selected as the target style; for another example, the target style previously selected by the user may be directly used as the target style of the target object this time.

[0133] In this second embodiment, by taking the target style as one of the reference dimensions for generating images, the diversity of the Vincent map can be improved, and the alternative styles can be adjusted according to the regional information, that is, different style options are provided for different regions and cultural backgrounds, so that the Vincent map is more in line with the regional culture.

[0134] Third embodiment

[0135] See also Figure 8 , is a flow chart of a processing method provided in the third embodiment of the present application. The processing method includes the following steps S31 to S34.

[0136] S31: Generate a target image according to the text content input by the user and the acquired regional information;

[0137] S32: In response to the partition display, determining a target partition from at least two partitions;

[0138] S33: generating a comparison image according to the text content input by the user and the reference features;

[0139] S34: Displaying the target image in the target partition, and displaying the comparison image in other partitions.

[0140] The same features of the third embodiment as those of the first embodiment may be found in the foregoing description. For example, the features of step S31 correspond to the same features of step S11 of the first embodiment, and are not described in detail here.

[0141] Optionally, the target partition is a partition facing the user's viewing angle. The partition is obtained by dividing the screen of the smart terminal; taking the smart terminal with a folding screen as an example, the two split screens that are folded from a straight screen to two split screens facing back to back can be called two partitions, and at this time, one of the split screens faces the user's eyes, which can be called the target partition; taking the smart terminal with a scroll screen as an example, the target partition can be the expanded part when the scroll screen switches from a wound state to a partially expanded state, and the unexpanded part can be called other partitions; taking the smart terminal with a straight screen as an example, the operating system divides the display area of ​​the straight screen into multiple partitions, and these partitions can be displayed with visible dividing lines or without visible dividing lines. Display the dividing lines visible to the naked eye. At this time, the dividing lines between the partitions are shown as the logical dividing lines divided by the operating system background. Then, one of the partitions is determined as the target partition according to the preset rules. Optionally, the preset rules can be at least one of the following: select the one with the largest display area as the target partition; select a partition selected by the user operation as the target partition; select a partition located in a fixed position as the target partition according to the placement state of the smart terminal. For example, when the smart terminal is in portrait mode, the partition at the bottom is the target partition. When the smart terminal switches to landscape mode, the partition closest to the short side of the straight screen is the target partition. The specific form of the preset rules is not limited in this application.

[0142] In an example of step S32, the preset rule may be one or more rules, which may be special rules for implementing the present application, and are different from existing rules for triggering the smart terminal to display partitions, so as to at least avoid any rule from conflicting with existing rules for executing other functions (including personalized rules set by the user). For example, step S32 is only executed when entering the preset mode and / or turning on the preset function option, so as to avoid conflicting with existing rules for executing other functions. Figure 4 The AI ​​interface shown in the figure has the "Sub-model" option turned on, and only then will the preset rule be considered valid and the corresponding steps be triggered. Here, users can implement the same rule to perform different functions more conveniently and quickly, that is, reuse the rules that perform other functions. For example, when the "Sub-model" option is turned on, Fig. 9As shown, the partition facing the user's eyes is detected and can be used as the target partition. As the user flips the smart terminal, another partition faces the user's eyes, and the other partition is used as the target partition. When this option is not turned on, even if the user flips the smart terminal, the other partition cannot be used as the target partition. At this time, the target partition is still the partition before the flip.

[0143] In another example, the preset rule is not an existing rule for executing other functions, but is only a special rule for this application. If it is detected that the preset rule is a special rule for this application, the current interface is not considered and step S32 is directly triggered. Optionally, this application can combine the preset rule with the current interface to determine whether to trigger step S32. For example, if the current interface is open as Figure 4 The AI ​​interface shown, once the preset rule is detected, triggers the execution of step S32; if the current interface is other interfaces (non-AI interface), even if it is detected that the current situation of the smart terminal meets the preset rule, it does not trigger the execution of step S32, but executes the existing function corresponding to the operation included in the preset rule.

[0144] In the step S33, the reference dimensions of the generated comparison image and the target image are different, and the difference lies only in the target features, such as only in the geographical information, and the other reference dimensions can be exactly the same.

[0145] Taking the region information as the facial feature as an example, the text content input by the user is "a man smiling on the Great Wall". If the region information for generating the target image is China, then according to the processing method of the first or second embodiment, the final generated image is: Fig. 9 The target image with a Chinese man shown in ; if the reference region information is the United States, the final generated Fig. 9 The comparison image of an American man is shown in . Different regional information reflects different cultural backgrounds. By comparing the images displayed in different areas, users can more intuitively perceive the differences in the same text description when facing different regional cultures.

[0146] An embodiment of the present application further provides an intelligent terminal, including a memory and a processor, wherein a processing program is stored in the memory, and when the processing program is executed by the processor, the steps of the processing method in any of the above embodiments are implemented.

[0147] An embodiment of the present application further provides a storage medium on which a processing program is stored. When the processing program is executed by a processor, the steps of the processing method in any of the above embodiments are implemented.

[0148] In the embodiments of the smart terminal and storage medium provided in the present application, all technical features of any of the above-mentioned processing method embodiments may be included, and therefore have corresponding beneficial effects. The expanded and explained contents of the specification are basically the same as those of the embodiments of the above-mentioned methods and will not be repeated here.

[0149] The embodiment of the present application further provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer executes the methods in the above various possible implementation modes.

[0150] An embodiment of the present application also provides a chip, including a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a device equipped with the chip executes the methods in various possible implementation modes as described above.

[0151] It is understood that the above scenarios are only examples and do not constitute a limitation on the application scenarios of the technical solutions provided in the embodiments of the present application. The technical solutions of the present application can also be applied to other scenarios. For example, it is known to those skilled in the art that with the evolution of the system architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0152] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0153] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs.

[0154] The units in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0155] In the present application, the same or similar terminology concepts, technical solutions and / or application scenario descriptions are generally described in detail only the first time they appear. When they appear again later, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of the present application, for the same or similar terminology concepts, technical solutions and / or application scenario descriptions that are not described in detail later, reference can be made to the previous related detailed descriptions.

[0156] In the present application, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0157] The various technical features of the technical solution of the present application can be arbitrarily combined. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present application.

[0158] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, a controlled terminal, or a network device, etc.) to execute the method of each embodiment of the present application.

[0159] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. Computer instructions can be stored in a storage medium, or transmitted from one storage medium to another storage medium. For example, computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. Available media can be magnetic media, (e.g., floppy disk, storage disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid-state storage disk Solid State Disk (SSD)), etc.

[0160] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A processing method, characterized in that: Includes steps: Generate a target image based on the acquired image description information and target features.

2. The method according to claim 1, characterized in that: The method further comprises: Get the target style; The target image is displayed according to the target style.

3. The method according to claim 2, characterized in that The method for obtaining the target style includes at least one of the following: Acquire an alternative style associated with the target feature as a target style; In response to a user operation, selecting a target style from a plurality of candidate styles; Generating a target style according to the text content input by the user; Determine the target style based on user history information.

4. The method according to claim 3, characterized in that Generating a target style according to the text content input by the user includes at least one of the following: Identifying target features from the text content input by the user; Acquire at least one candidate style according to the target feature; Determine or get the target style from among the alternative styles.

5. The method according to any one of claims 1 to 4, characterized in that The target feature includes at least one of geographical location, language, architecture, clothing and facial features.

6. The method according to any one of claims 1 to 4, characterized in that The method for obtaining the target feature includes at least one of the following: Enable positioning to obtain current geographical information to obtain target features; Recognizing target features from the text content input by the user; Get the target features entered by the user in the preset interface.

7. The method according to any one of claims 1 to 4, characterized in that Also includes: In response to the partition display, determining a target partition from at least two partitions; Generate a comparison image based on the text content input by the user and the reference features; The target image is displayed in the target partition, and the comparison image is displayed in other partitions.

8. The method according to any one of claims 1 to 4, characterized in that Generating a target image comprises: In response to obtaining the text content input by the user, calling the preset AI model; In response to acquiring the target feature, calling the sub-model corresponding to the target feature; The sub-model and the preset AI model are integrated to generate a target image.

9. An intelligent terminal, characterized in that: include: A memory and a processor, wherein a processing program is stored on the memory, and when the processing program is executed by the processor, the steps of the processing method according to any one of claims 1 to 8 are implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the processing method according to any one of claims 1 to 8.

Images