Video generation method and electronic device

Abstract

A video generation method and an electronic device. The method comprises: an electronic device displays a video creation window. In response to an operation of a user selecting a target theme card from among a plurality of theme cards, the electronic device displays an operation window of a target video theme, wherein when characters corresponding to at least one face group all lack naming data, the operation window comprises a first video creation entry, and when at least one character in the characters corresponding to the at least one face group has naming data, the operation window comprises a second video creation entry. In response to an operation on the first video creation entry, the electronic device displays a first selection window comprising a face image of at least one character. In response to an operation of the user selecting the face image, the electronic device generates a video of the character corresponding to the face image selected by the user. Alternatively, in response to an operation on the second video creation entry, the electronic device generates a video of the character corresponding to the second video creation entry.

Description

Video generation method and electronic device Technical Field

[0001] The embodiments of the present application relate to the technical field of electronic devices, and in particular to a video generation method and electronic device. Background Art

[0002] With the continuous development of electronic devices, they have become an indispensable part of people's work and life. The camera function of electronic devices can contribute to the convenience of consumers' lives. For example, consumers can use camera apps to capture photos and warm moments in their daily work and life, or use camera apps to shoot videos to record life moments.

[0003] Summary of the Invention

[0004] The embodiments of the present application provide a video generation method and an electronic device for solving the problem that current video synthesis operations are cumbersome and result in low convenience.

[0005] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0006] In a first aspect, a video generation method is provided. The video generation method is applied to an electronic device, the electronic device including multiple portrait materials and at least one face group divided into the multiple portrait materials based on facial images. The portrait materials within a face group contain faces of the same person. The method includes: the electronic device displays a video creation window; the video creation window displays multiple theme cards, with different theme cards corresponding to different video themes. In response to a user selecting a target theme card from the multiple theme cards, the electronic device displays an operation window for a target video theme. When all the people corresponding to at least one face group lack naming data, the operation window includes a first video creation entry; when at least one of the people corresponding to the at least one face group has naming data, the operation window includes a second video creation entry; the target video theme is the video theme corresponding to the target theme card. In response to the operation on the first video creation entry, the electronic device displays a first selection window, the first selection window including at least one person's facial image. In response to the user selecting a facial image, the electronic device generates a video of the person corresponding to the user-selected facial image. Alternatively, in response to the operation on the second video creation entry, the electronic device generates a video of the person corresponding to the second video creation entry.

[0007] The video production window can include theme cards corresponding to various video themes, such as personal photos, family photos, growth themes, warm moments, cute pets, etc.

[0008] The video creation entries included in the target video theme's operation window correspond to one or more face groups. The number of face groups associated with each video creation entry varies across different video themes. For example, in the personal portrait operation window, each video creation entry corresponds to only one face group. For another example, in the family photo operation window, each video creation entry corresponds to multiple face groups. For another example, in the warm moments operation window, each video creation entry corresponds to one or more face groups.

[0009] By selecting a video corresponding to a second face group, users can quickly and easily find portrait materials corresponding to one or more second face groups. Alternatively, if the face group the user wants to synthesize doesn't have named data, users can further identify the portrait materials for the first face group by selecting a video corresponding to the first face group, ensuring that no individual face group is missed.

[0010] The video generation method provided in this application utilizes the varying facial features of different people to map portrait materials to the face groups in which the face images appear, based on the face images appearing in each portrait material. Furthermore, the method employs a design in which each video creation entry corresponds to one or more face groups, and the face groups corresponding to different video creation entries are not identical. This allows the video generation method to use a single video creation entry to simultaneously locate portrait materials corresponding to one or more face groups, thereby improving the efficiency of identifying portrait materials in a composite video and, consequently, the efficiency of video generation.

[0011] In a possible implementation of the first aspect, the operation window includes a second video creation entry, including: the operation window includes 1 first video creation entry and N second video creation entries; the first video creation entry corresponds to a character who lacks naming data, each second video creation entry corresponds to a character who has naming data, and the characters corresponding to different second video creation entries are not exactly the same; N is a positive integer greater than 1.

[0012] In this embodiment, the video theme's operation window simultaneously displays a first video creation entry and N second video creation entries. Therefore, the user can select the first video creation entry in the video theme's operation window to select footage from the first face group, which lacks naming data, as the material for the composite video; or select the second video creation entry in the video theme's operation window to select footage from the second face group, which has naming data, as the material for the composite video. This improves the user's video synthesis efficiency.

[0013] In another possible implementation of the first aspect, in response to a user selecting a facial image, the electronic device generates a video of a person corresponding to the facial image selected by the user, including:

[0014] The electronic device generates a video in response to the user's operation on Q facial images in the first selection window; the video screen simultaneously displays the characters corresponding to the Q facial images, where Q is a positive integer and the value of Q is associated with the target video theme.

[0015] When the video creation entry clicked by the user corresponds to a first face group with multiple missing naming data, the electronic device displays multiple first face groups through a first selection window for the user to select Q first face groups.

[0016] Different video themes correspond to different Q values. For example, if the video theme is a personal portrait, Q is 1. For another example, if the video theme is a family photo, Q is greater than 1. For another example, if the video theme is a heartwarming moment, Q can be 1 or greater than 1.

[0017] In another possible implementation of the first aspect, in response to a user selecting a facial image, the electronic device generates a video of a person corresponding to the facial image selected by the user, including: in response to the user selecting the facial image in a first selection window, the electronic device displays a third selection window. The third selection window displays multiple portrait materials to be selected, each of which is an intersection of portrait materials corresponding to the facial image selected by the user in the first selection window, and the portrait materials include pictures and / or videos. In response to the user selecting one or more portrait materials to be selected in the third selection window, the electronic device generates the video.

[0018] In this embodiment, after the user selects a face group, a third selection window displays multiple portrait materials corresponding to that face group. The user can then select one or more portrait materials to include in the composite video, allowing the user to freely select the materials used in the composite video, increasing the user's flexibility in video synthesis.

[0019] In another possible implementation of the first aspect, the first selection window further includes naming controls, each naming control corresponding to a person in a face image;

[0020] After displaying the first selection window, the method further includes:

[0021] The electronic device displays a name editing window in response to a user selecting a name control;

[0022] When the electronic device receives the naming data edited by the user through the naming editing window, it returns to the first selection window and uses the naming data as the naming data of the person corresponding to the naming control selected by the user.

[0023] In the case where a face group in the album application lacks naming data, the user can operate the naming control in the first selection window to add naming data to the face group, so that the first face group with the added naming data becomes the second face group later.

[0024] In another possible implementation of the first aspect, the electronic device displaying a name editing window in response to a user selecting a name control includes: the electronic device displaying the name editing window in response to the user selecting the name control. After the electronic device receives the name data edited by the user through the name editing window, the method further includes the photo album application using the name data as the name data of the person corresponding to the name control selected by the user.

[0025] During the video synthesis process, the user operates the naming control, and the album application displays a naming editing window, thereby adding naming data to the face group in the album application.

[0026] In another possible implementation of the first aspect, the name editing window includes a name input area. The name input area is used for a user to input sub-data of a person's name, where the name sub-data is part of the naming data. The album application uses the name data as the naming data of the person corresponding to the naming control selected by the user, including: the album application uses the name sub-data as the naming data of the person corresponding to the naming control selected by the user.

[0027] In another possible implementation of the first aspect, the name editing window includes a relationship input area. The relationship input area is used for a user to input sub-data of a relationship between a person and an owner of the electronic device, where the relationship sub-data is part of the naming data. The album application uses the naming data as the naming data of the person corresponding to the naming control selected by the user, including: the album application uses the relationship sub-data as the naming data of the person corresponding to the naming control selected by the user.

[0028] In this embodiment, the naming of each character is determined from two perspectives, namely, the name of the character and the relationship between the character and the owner of the electronic device. This can avoid the problem of incorrect selection of face groups due to two people having the same name, and improve the accuracy of character naming.

[0029] In another possible implementation of the first aspect, in response to a user selecting a second video creation entry, the electronic device generates a video of a person corresponding to the second video creation entry selected by the user, including: the electronic device displays a third selection window in response to the user selecting the second video creation entry; the third selection window displays a plurality of portrait materials to be selected, each of the portrait materials to be selected being an intersection of portrait materials of the person corresponding to the second video creation entry selected by the user, the portrait materials including pictures and / or videos. The electronic device generates the video in response to the user selecting one or more portrait materials to be selected.

[0030] In this embodiment, after the user selects the second video creation entry corresponding to the second face group, the electronic device can display multiple portrait materials corresponding to the second face group. The user can then select one or more portrait materials to be included in the synthesized video from the multiple portrait materials, thereby allowing the user to freely select the materials used in the synthesized video, thereby increasing the user's freedom in video synthesis.

[0031] In another possible implementation of the first aspect, the third selection window displays multiple portrait materials to be selected, including: the electronic device arranges multiple portrait materials to be selected in the third selection window according to the order of the portrait material acquisition time periods; wherein the number of portrait materials to be selected displayed in each acquisition time period is positively correlated with the number of portrait materials captured by the electronic device during the acquisition time period.

[0032] For example, in a video titled "Growth," the number of selectable portrait materials corresponding to each acquisition period can be positively correlated with the amount of material captured by the electronic device during that acquisition period. For example, if the amount of material captured in August is high and the amount of material captured in September is low within the same year, the third selection window can display more material captured in August and less material captured in September. This helps users select more material related to their growth process and create videos that better fit the theme of growth.

[0033] In another possible implementation of the first aspect, the first video creation entry includes first recommendation text, which is preset recommendation text corresponding to the video theme. And / or, the second video creation entry includes second recommendation text, which includes naming data of a character corresponding to the second video creation entry.

[0034] By including the naming data of the second face group in the recommended text of the second video creation entry, users can understand the characters corresponding to each second video creation entry, making it easier for users to select character materials more accurately and improving the efficiency of synthesizing videos.

[0035] In another possible implementation of the first aspect, the topic card displays preset recommendation text corresponding to the video topic.

[0036] In another possible implementation of the first aspect, the first video creation entry includes a first example image. The first example image is an example image corresponding to the subject of the video. And / or, the second video creation entry includes a second example image, which includes a portrait of a person corresponding to the second video creation entry.

[0037] In another possible implementation of the first aspect, the operation window includes a second video creation item, and the target theme card includes a second example image of the second video creation item.

[0038] By displaying the portrait material of the second face group as the theme image in the theme card, it can be used as a material selection sample to attract users to select a synthetic video produced by the theme.

[0039] In another possible implementation of the first aspect, before the operation window displays the operation window of the target video theme, the method further includes: the electronic device obtaining at least one face group corresponding to multiple portrait materials in the album application.

[0040] In another possible implementation of the first aspect, before the electronic device displays the video production window, the method further includes: the electronic device launching a voice assistant application in response to a user input operation. The voice assistant application displays the video production window.

[0041] In this embodiment, the video production window can be provided by a voice assistant application. It can be understood that the video generation method can be implemented by voice interaction between the user and the voice assistant application.

[0042] In a second aspect, the present application provides an electronic device. The electronic device includes a processor, a memory, and a display screen. The processor is coupled to the memory and the display screen, respectively. The memory is configured to store computer program code. The computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device performs any of the methods described in the first aspect.

[0043] The beneficial effects of the second aspect can refer to the beneficial effects of the first aspect and will not be described in detail here.

[0044] In a third aspect, the present application provides a computer-readable storage medium. The computer-readable storage medium includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes any one of the methods in the first aspect.

[0045] The beneficial effects of the third aspect can refer to the beneficial effects of the first aspect and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] FIG1 is a schematic diagram of an interface interaction of a photo album application in some embodiments;

[0047] FIG2 is a schematic diagram of window interactions displayed by a voice assistant application in some embodiments;

[0048] FIG3 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application;

[0049] FIG4 is an architecture diagram of a software system of an electronic device provided in an embodiment of the present application;

[0050] FIG5 is an architecture diagram of another software system of an electronic device provided in an embodiment of the present application;

[0051] FIG6 is a flow chart of a video generation and synthesis method provided by an embodiment of the present application;

[0052] FIG7 is a schematic diagram of the interaction of the voice conversation window in the process corresponding to FIG6;

[0053] FIG8 is a schematic diagram of the interaction of the video production window in the process corresponding to FIG6;

[0054] FIG9 is a schematic diagram of multiple theme cards in the video production window shown in FIG8 ;

[0055] FIG10 is a schematic diagram of the switching display operation window of the personal photo video production window in the process corresponding to FIG6;

[0056] FIG11 is a schematic diagram of the operation window switching displaying the first selection window in the process corresponding to FIG6;

[0057] FIG12 is a schematic diagram showing one of selecting a face group through the first selection window;

[0058] FIG13 is a second schematic diagram of selecting a face group through the first selection window;

[0059] FIG14 is a schematic diagram of selecting a face group through the operation window;

[0060] FIG15 is a schematic diagram of the first selection window or the operation window switching to display the third selection window in the process corresponding to FIG6;

[0061] FIG16 is a schematic diagram showing a method of selecting a portrait material to be selected through the third selection window;

[0062] FIG17 is a second schematic diagram of selecting a portrait material to be selected through the third selection window;

[0063] FIG18 is a schematic diagram of switching to display a composite video through a third selection window in the process corresponding to FIG6 ;

[0064] FIG19 is a schematic diagram of adding naming data to a character through the first selection window;

[0065] 20 to 24 are partial interaction diagrams of the process of FIG. 6 corresponding to the family photo video theme;

[0066] Figures 25 to 29 are partial interactive diagrams of the process of Figure 6 corresponding to the theme of the warm moment video;

[0067] Figures 30 to 34 are partial interactive diagrams of the process corresponding to Figure 6 for the growth-themed video theme;

[0068] FIG35 is a schematic diagram of the hardware structure of the chip system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application. Among them, in the description of the embodiments of the present application, the terms used in the following embodiments are only for the purpose of describing specific embodiments, and are not intended to be used as limitations on the present application. As used in the specification and claims of the present application, the singular expressions "a", "", "above", "the" and "this" are intended to also include expressions such as "one or more", unless there is a clear contrary indication in the context. It should also be understood that in the following embodiments of the present application, "at least one", "one or more" refer to one or more (including two). The term "and / or" is used to describe the association relationship of associated objects, indicating that three relationships can exist; for example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship.

[0070] References to "one embodiment" or "some embodiments" etc. described in this specification mean that the specific features, structures or characteristics described in conjunction with the embodiment are included in one or more embodiments of the present application. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. appearing in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in another way. The term "connected" includes direct and indirect connections, unless otherwise stated. "First" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated.

[0071] In the embodiments of this application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplarily" or "for example" is intended to present the relevant concepts in a concrete manner.

[0072] Before introducing the embodiments of the present application, a brief introduction to the relevant technical terms involved in the embodiments of the present application is first given here.

[0073] 1. Face clustering

[0074] To illustrate with images, face clustering refers to dividing a large number of face images into different face groups based on the facial images that appear in multiple portrait images (images containing facial images are called portrait images) according to a preset similarity index. It can be understood that the portrait materials within each face group contain the face of the same person, and different face groups correspond to the faces of different people. In addition, since portrait videos (videos containing facial images are called portrait videos) are also composed of multiple frames, face clustering can also be performed on videos to divide different face groups.

[0075] In the future, portrait pictures and portrait videos will be collectively referred to as portrait materials.

[0076] Each face group corresponds to multiple portrait materials of the same person. Each portrait material contains the face image of that person, and may also contain the face images of other people. It can be understood that when a portrait image (such as a group photo) contains multiple face images, this portrait image can correspond to multiple face groups, and this image can also be called the intersection of the portrait materials of multiple face groups; alternatively, this portrait image can correspond to a group of multiple people in a group photo.

[0077] 2. Album application (also known as gallery application)

[0078] An album application is an application that can store portrait materials or other images and videos taken or downloaded by users. Users can use the album application to view, edit, take screenshots, and share portrait materials. The album application can be a system application.

[0079] Furthermore, some photo album applications may include face clustering capabilities. For example, the photo album application can analyze multiple stored images / videos and identify portrait materials containing at least one face from the multiple images. After processing using portrait clustering, multiple face groups can be displayed in the photo album application. Each face group corresponds to a specific person's face. By selecting a face group, multiple portrait materials containing the person corresponding to that face group can be found.

[0080] Figure 1 shows a schematic diagram of the interface interaction of person information in a photo album application displayed on the screen. Referring to Figure 1 , Figure 1 (a) shows the creation interface of the photo album application, which displays portrait display content, for example, the portrait display content includes facial images of multiple people. Of course, the creation interface may also include other display content such as location display content, puzzle tools, editing tools, etc., which are not limited here. After the user clicks on the portrait display content, the photo album application of the electronic device may display a personal page as shown in Figure 1 (b) or (c). The personal page displays multiple face groups 10 formed by face clustering of multiple portrait materials. Each face group 10 in the personal page corresponds to a person. Each face group 10 is displayed by a face image 11, representing the person whose face image 11 corresponds to each face group 10. The multiple portrait materials within a face group 10 all include facial images of the same person.

[0081] The album application can also add naming data 12 for the person corresponding to each face group 10. The user can set naming data for the person corresponding to each face group 10 to distinguish different face groups 10. The naming data can include name sub-data such as the name and nickname of the person corresponding to the face group 10, and can also include relationship sub-data such as the relationship between the person corresponding to the face group 10 and the user, such as a relative or friend relationship. It can also include both name sub-data and relationship sub-data, or even more information, which is not limited in the embodiments of the present application.

[0082] In Figure 1(b), each face group 10 corresponding to a person lacks named data, and a "Add Name" button is displayed to encourage the user to name the person. In Figure 1(c), some face groups 10 have named data 12, while others lack named data. Hereinafter, the face groups 10 corresponding to the people lacking named data are referred to as first face groups 10a, and the face groups corresponding to the people with named data are referred to as second face groups 10b.

[0083] Furthermore, for the person named by the user, the album application can also perform face clustering on the portrait material with multiple face images to form a third face group (group photo group) 10c.

[0084] Based on this, the user can also slide the personal page, or click "Group Photo" on the personal page, so that the electronic device's album application displays the group photo page as shown in (d) in Figure 1. The group photo page can display at least one third face group 10c.

[0085] Each third face group 10c is displayed by displaying a group photo containing facial images of multiple people corresponding to the third face group 10c. Thus, the group photo can represent the multiple people corresponding to each third face group 10c. Third face group 10c corresponds to portrait material in an album application where multiple faces appear simultaneously in multiple photos. For example, if person A and person B have multiple group photos, a group of photos of person A and person B can be formed.

[0086] The photo album application may also add naming data 12 for each third face group 10 c . The user may set the naming data 12 for each third face group 10 c to distinguish different face groups 10 .

[0087] Understandably, if a third face group 10c corresponds to Person 1 and Person 2, then this third face group 10c corresponds to multiple portrait materials in the album application that simultaneously include the facial images of Person 1 and Person 2. Furthermore, the intersection of the portrait materials in Person 1's face group 10 and the portrait materials in Person 2's face group 10 also corresponds to portrait materials in the album application that simultaneously include the facial images of Person 1 and Person 2. Therefore, the portrait materials in the third face group 10c corresponding to Person 1 and Person 2 can be considered equivalent to the intersection of the portrait materials in Person 1's face group 10 and the portrait materials in Person 2's face group 10.

[0088] 3. Synthetic video function

[0089] The composite video feature allows an electronic device to create a video from multiple user-selected materials. These materials can be images, videos, and more. During playback, the composite video displays each material, along with accompanying animations and music.

[0090] For the principles and methods of synthesizing videos, reference may be made to the descriptions of other prior arts, and the embodiments of the present application will not elaborate on them.

[0091] 4. Voice Assistant App

[0092] A voice assistant application is an application used by electronic devices to provide voice interaction functions to users. For example, the voice assistant can collect the voice of the user, convert it into voice commands, and then input it into the system chip (SoC, also known as system-on-chip) of the electronic device, so that the electronic device can execute the user's intention accordingly; and the voice assistant can also convert the output message of the electronic device into text sentences and play it to the user in the form of voice. In this way, the voice assistant application can realize voice communication between the electronic device and the user. The voice assistant application can be a system application.

[0093] Figure 2 shows a schematic diagram of the window interaction corresponding to the voice assistant application displayed on the screen. After the voice assistant application obtains the opening permission of the electronic device, the user can wake up the voice assistant application by issuing a preset voice command or action (such as long pressing the lock screen button). After the voice assistant application is turned on, as shown in Figure 2, the voice assistant window 20 will be displayed on the display screen of the electronic device accordingly.

[0094] The voice assistant window 20 may include a voice conversation window 21. The voice conversation window 21 may display a first conversation message 211. The first conversation message 211 may display text corresponding to the voice spoken by the user. Exemplarily, the voice assistant application collects the voice emitted by the user, performs audio-to-text processing (including voice recognition processing), and then displays the corresponding text through the first conversation message 21. The voice conversation window 21 may also display a second conversation message 212. The second conversation message 212 may display text corresponding to the voice played by the voice assistant application to the user. Exemplarily, the voice assistant application converts the output message into a text sentence and displays it through the second conversation message 22. In addition, the voice assistant application also drives the speaker of the electronic device to play the corresponding voice message after the text-to-speech processing.

[0095] The voice assistant window 20 may also include other windows. Specifically, the number of windows of the voice assistant window 20 may depend on the number of functions integrated into the voice assistant application. For example, when the voice assistant application integrates the above-mentioned video synthesis function, the voice assistant window 20 may also include a video production window.

[0096] It should be noted that the window mentioned herein may be a half-screen window, a full-screen window, or a window of other sizes. In addition, in actual application scenarios, the window may be presented in the form of a page, an interface, or the like. It is understandable that the window represents various ways of being presented on a display screen, and the embodiments of the present application are not limited thereto.

[0097] The following describes the solution of the embodiment of this application:

[0098] An electronic device provided in an embodiment of the present application includes the aforementioned photo album application. The photo album application may store multiple images, including at least one portrait image of a human face. Furthermore, the electronic device may also include the aforementioned video synthesis function. It is understood that the electronic device can synthesize a video based on multiple materials.

[0099] The electronic devices provided in the embodiments of the present application may include, but are not limited to, smartphones, tablet computers, laptops, handheld computers, netbooks, personal digital assistants (PDAs), wearable electronic devices, virtual reality devices, electric vehicles, and other devices that have their own display screens and data processing functions.

[0100] For ease of understanding, the following electronic devices are described using smartphones as an example, but this should not be regarded as a limitation on the application scenarios and devices of electronic devices.

[0101] Figure 3 shows a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present application. As shown in Figure 3, a smartphone 300 may include: a processor 310, an internal memory 320, a universal serial bus (USB) interface 330, a charging management module 340, a power management module 341, a battery 342, an antenna 1, an antenna 2, a mobile communication module 351, a wireless communication module 352, a camera 360, an audio module 370, a speaker 370A, a receiver 370B, a microphone 370C, an earphone jack 370D, a sensor module 380, and a display 390, etc.

[0102] It should be understood that the structure illustrated in this embodiment does not constitute a specific limitation on smartphones. In other embodiments, smartphones may include more or fewer components than illustrated, or may combine or separate certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0103] The processor 310 may include one or more processing units. For example, the processor 310 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). The different processing units may be independent devices or integrated into one or more processors.

[0104] The controller may be the nerve center and command center of the smartphone 300. The controller may generate an operation control signal based on the instruction operation code and the timing signal to complete the control of instruction fetching and execution.

[0105] Processor 310 may also include a memory for storing instructions and data. In some embodiments, the memory in processor 310 is a cache memory. This memory can store instructions or data that have just been used or are being recycled by processor 310. If processor 310 needs to use the same instruction or data again, it can directly retrieve it from the memory. This avoids duplicate accesses, reduces processor 310 latency, and thus improves system efficiency.

[0106] In some embodiments, the processor 310 may include one or more interfaces. The interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM interface, and / or a USB interface.

[0107] The internal memory 320 can be used to store computer executable program code, which includes instructions. The processor 310 executes various functional applications and data processing of the smartphone 300 by running the instructions stored in the internal memory 320. The internal memory 320 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system, an application required for at least one function (such as the above-mentioned album application, voice assistant application), etc. The data storage area can store data created during the use of the smartphone 300 (such as pictures and videos stored by the user in the album application), etc. In addition, the internal memory 320 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0108] USB interface 330 is an interface that complies with USB standards and specifications, and may be a Mini USB interface, a Micro USB interface, a USB Type-C interface, or the like. USB interface 330 can be used to connect a charger to charge smartphone 300, or to transfer data between smartphone 300 and peripheral devices. It can also be used to connect headphones to play audio. This interface can also be used to connect other electronic devices, such as tablets.

[0109] The charging management module 340 is configured to receive charging input from a charger. The charger can be either a wireless charger or a wired charger. The power management module 341 is configured to connect the battery 342, the charging management module 340, and the processor 310. The power management module 341 receives input from the battery 342 and / or the charging management module 340 to power the processor 310, the internal memory 320, the external memory, the display 390, the mobile communication module 351, and the wireless communication module 352.

[0110] The wireless communication function of the smart phone 300 can be implemented through the antenna 1, the antenna 2, the mobile communication module 351, the wireless communication module 352, etc. The antenna 1 and the antenna 2 are used to transmit and receive electromagnetic wave signals.

[0111] The mobile communication module 351 can provide a solution for cellular communications (such as 2G / 3G / 4G / 5G) used in smartphones. The mobile communication module 351 may include at least one filter, a switch, a power amplifier, a low-noise amplifier (LNA), etc. The mobile communication module 351 can receive electromagnetic waves from antenna 1, filter and amplify the received electromagnetic waves, and transmit them to the baseband processor for demodulation. The mobile communication module 351 can also amplify the signals modulated by the baseband processor and convert them into electromagnetic waves for radiation via antenna 1.

[0112] The wireless communication module 352 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the smartphone 300. The wireless communication module 352 can be one or more devices that integrate at least one communication processing module. The wireless communication module 352 receives electromagnetic waves via the antenna 2, frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 310. The wireless communication module 352 can also receive the signal to be sent from the processor 310, frequency modulate and amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.

[0113] Electronic device 100 implements display functionality through a GPU, display screen 390, and an application processor. A GPU is a microprocessor for image processing that connects display screen 390 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering and synthesis. Processor 310 may include one or more GPUs that execute program instructions to generate or modify display information.

[0114] Display screen 390 is used to display images, videos, and the like. Display screen 390 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a MiniLED, a MicroLED, a Micro-oLed, or a quantum dot light-emitting diode (QLED). In some embodiments, smartphone 300 may include one or N display screens 390, where N is a positive integer greater than one.

[0115] The smartphone 300 can implement a shooting function through an ISP, a camera 360, a video codec, a GPU, a display 390, and an application processor.

[0116] The ISP processes data from the camera 360. For example, when the shutter is opened to take a photo, light passes through the lens and is transmitted to the camera's photosensitive element. The light signal is converted into an electrical signal, which is then passed to the ISP for processing and transformed into a visible image. The ISP can also perform algorithmic optimization on image noise and brightness. It can also optimize parameters such as exposure and color temperature of the captured scene. In some embodiments, the ISP can be located within the camera 360.

[0117] The camera 360 is used to capture still images or videos. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, and then passes the electrical signal to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV or other format. In some embodiments, the smartphone 300 may include 1 or N cameras 360, where N is a positive integer greater than 1.

[0118] The digital signal processor is used to process digital signals. In addition to processing digital image signals, it can also process other digital signals. For example, when the smartphone 300 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy.

[0119] Video codecs are used to compress or decompress digital video. Smartphone 300 may support one or more video codecs. This allows smartphone 300 to play or record videos in various encoding formats, such as Moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, and MPEG4.

[0120] The NPU is a neural network (NN) computing processor. Drawing on the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it rapidly processes input information and can continuously self-learn. The NPU enables applications such as intelligent cognition in smartphones 300.

[0121] For example, the NPU can analyze multiple pictures in the photo album application stored in the internal memory 320 and identify the faces in the pictures. For another example, the NPU can recognize the voice of the user collected by the voice assistant application and obtain the text corresponding to the voice.

[0122] The smartphone can implement audio functions such as music playback and recording through the audio module 270, speaker 270A, receiver 270B, microphone 270C, headphone jack 270D, and application processor. In some embodiments, during a call using a cellular network or satellite network, the smartphone can collect the user's voice through the microphone 270C and play the voice from the other party through the speaker 270A, receiver 270B, or headphones connected to the headphone jack 270D.

[0123] In some embodiments, the voice assistant application can use microphone 270C to collect the user's voice and receive user input commands; and the voice assistant application can use speaker 270A to play the voice to the user to output voice messages to the user, thereby realizing voice interaction between the smartphone 300 and the user. Of course, in other embodiments, after the user plugs in headphones to the headphone jack 270D, the voice assistant application can also use the microphone and speaker on the headphones to interact with the user by voice.

[0124] The software system of the electronic device can adopt a layered architecture, event-driven architecture, micro-core architecture, micro-service architecture, or cloud architecture. TM Taking the system as an example, the software structure of the terminal is illustrated.

[0125] FIG4 is an architecture diagram of a software system of an electronic device provided in an embodiment of the present application; FIG5 is an architecture diagram of another software system of an electronic device provided in an embodiment of the present application.

[0126] As shown in Figures 4 and 5, the layered architecture can divide the software system of the electronic device into several layers, each with a clear role and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android TM The system is divided into three layers, from top to bottom: application layer, application framework layer and kernel layer.

[0127] It should be understood that the software system layers of the electronic device shown in Figures 4 and 5 are merely exemplary. In actual implementation, the software system of the electronic device may include more or fewer layers. For example, between the application framework layer and the kernel layer, a system library may be included; for another example, between the application framework layer and the kernel layer, a hardware abstraction layer may be included.

[0128] Among them, the application layer can include a series of application packages, such as call applications, SMS applications, browser applications, voice assistant applications, album applications and other system applications; it can also include third-party applications downloaded and installed by users themselves.

[0129] Since the voice assistant application and the photo album application are both system applications, if the photo album application has the face clustering capability, as shown in Figure 4, the voice assistant application can directly obtain at least one face group of multiple pictures in the album from the photo album application.

[0130] The application framework layer provides an application programming interface (API) and programming framework for applications in the application layer. The application framework layer includes some predefined functions.

[0131] The application framework layer may include a notification manager, a window manager, a resource manager, a content provider, and a view system.

[0132] As shown in Figure 5, the application framework layer can also include a smart middle platform. The smart middle platform can provide APIs and programming frameworks for voice assistant applications. The smart middle platform can also be connected to the photo album application.

[0133] If the album application has the ability to cluster faces, the smart middle platform can obtain at least one face group from multiple pictures in the album from the album application and then forward it to the voice assistant application.

[0134] If the photo album application does not have the ability to cluster faces, the smart middle platform can analyze multiple pictures in the photo album application to obtain at least one face group in the multiple pictures in the photo album application. Then, the at least one face group is sent to the voice assistant application.

[0135] The kernel layer is the layer between hardware and software. The kernel layer may include display drivers, camera drivers, audio drivers, etc. It should be noted that in the embodiment of the present application, when performing the video synthesis process, the kernel layer is mainly used to transmit the display data of the upper layer (the layer above the kernel layer) to the display screen.

[0136] Based on the hardware structure and software architecture of the smartphone described above, the specific process of video synthesis in the embodiments of this application is described in detail below. The following description uses the example of integrating the video synthesis function into a voice assistant application; it should be understood that in other feasible embodiments, the video synthesis function can also be an application independent of the voice assistant application, and the embodiments of this application are not limited to this.

[0137] It should be noted that since the video synthesis function is integrated into the voice assistant application, the instructions or operations entered by the user into the smartphone during the process can be considered to be completed by the user speaking. In addition, since the screen also displays the voice assistant window during the operation of the voice assistant application, the instructions or operations entered by the user into the smartphone during the process can also be considered to be completed by the user touching the screen with their finger.

[0138] FIG6 shows a flow chart of a video generation method provided in an embodiment of the present application; FIG7 to FIG18 show interactive schematic diagrams of the display screen of the electronic device during the execution of FIG6.

[0139] As shown in FIG6 , the video generation method provided in the embodiment of the present application includes S11 - S19 .

[0140] S11: The user inputs a first operation for a composite video function to the electronic device.

[0141] For example, when the voice assistant application is turned on in the electronic device, the user can send a voice message to the smartphone saying "I want to synthesize a video" as the first operation input to the voice assistant application for the synthesized video function. Of course, this operation is not limited to specific words in the voice message. Other voice messages that can make the voice assistant application recognize the synthesized video function can be considered as input operations for the synthesized video function. For example, the voice message can also be "create a video" or "I want to make a video".

[0142] It is understandable that the subsequent different voice inputs by the user to the voice assistant application are not limited to the specific vocabulary of the voice, and will not be repeated hereafter.

[0143] S12: The voice assistant application displays a video production window on the display screen in response to the first operation.

[0144] As shown in Figure 7, after receiving the first operation, the voice assistant can display the first conversation message 213 corresponding to the first operation in the voice conversation window 21, and in response to the first operation, display the second conversation message 214 used to reply to the first conversation message 213 in the voice conversation window 21, and play the voice of the second conversation message 214 through the speaker.

[0145] After displaying the second conversation message 214, the voice assistant application may display a video production window 22 in the voice assistant window 20, as shown in FIG8 . The video production window 22 may display multiple theme cards 221, each theme card 221 corresponding to a video theme, and different theme cards 221 corresponding to different video themes.

[0146] In one possible implementation, the interface in FIG8 can be accessed in other ways, and the present application is not limited to the above-described methods. For example, after accessing the dialogue, recommendation, and other functions in other ways, manually switching to the "Smart Video" function (video production window 22).

[0147] The theme card 221 may include at least one of theme material 2211, theme name 2212, and theme recommendation text 2213. It is understandable that the theme card 221 may include one or more of theme material 2211, theme name 2212, and theme recommendation text 2213.

[0148] Theme material 2211 can be a representative picture or video that can represent the theme of the video corresponding to theme card 221, and is used to intuitively display the video theme to the user. For example, theme material 2211 can be a picture or video preset by the electronic device for each video theme; or theme material 2211 can also be a picture or video stored in the album application that matches the video theme.

[0149] The theme name 2212 can be a text description that can represent the video theme corresponding to the theme card 221, which is convenient for users to understand and locate the theme content corresponding to each theme card 221, such as "Personal Photo", "Growth Theme", "Family Photo", etc. as shown in Figure 8. It is not limited to the example shown in Figure 8, for example, it can also be "Daily Vlog", "Travel Vlog", "Birthday Party", etc.

[0150] The theme recommendation text 2213 may be a text for attracting users to try the video theme to which it belongs. For example, the theme recommendation text 2213 may be a recommendation text preset by the electronic device for each video theme.

[0151] 8 and 9 , a plurality of topic cards 221 may be displayed in the video production window 22. In some examples, 12, 24, or even more topic cards 221 may be displayed in the video production window 22. In other examples, fewer topic cards 221 may be displayed in the video production window 22.

[0152] S13: The user inputs a second operation on the target theme card to the electronic device.

[0153] For example, when the electronic device displays the video creation window 22, the user can send a voice message to the smartphone saying "I choose personal photo" or click on the theme card 221 corresponding to "Personal Photo" as the user inputting a second operation for the personal photo card (target theme card) into the voice assistant application. The second operation can also be for other video themes such as growth themes, family photos, etc., and the personal photo is used as an example for explanation here.

[0154] For ease of understanding, the process of S11-S19 in this embodiment is described using a personal photo as the target subject. It should be noted that because a personal photo is only for one person, this embodiment does not utilize the third face group 10c in the photo album application. The description will only be based on the first face group 10a and the second face group 10b.

[0155] S14: The electronic device responds to the user's second operation on the target theme card and displays an operation window for the target video theme. For example, the electronic device responds to the user's operation on the personal photo card and displays an operation window for the personal photo.

[0156] Before displaying the personal photo and video theme operation window, the electronic device's voice assistant application can obtain at least one face group corresponding to multiple portrait materials in the album application. As previously explained, the multiple face groups obtained by performing face clustering based on multiple face images can be completed by the album application or the smart middleware, and will not be repeated here.

[0157] It should be noted that the voice assistant application may obtain at least one face group corresponding to the multiple portrait materials in the album application before S14 or even before S11; or it may be completed after receiving the second operation and before the operation window of the target video theme is displayed. The embodiments of the present application are not limited to this.

[0158] For example, the photo album application provides at least one face group to the voice assistant application. The at least one face group may include the first face group 10a but not the second face group 10b, or may include the second face group 10b but not the first face group 10a, or may include both the first face group 10a and the second face group 10b.

[0159] If at least one face group includes the first face group 10a but does not include the second face group 10b, the operation window displayed by the electronic device may include a first video creation entry corresponding to the first face group 10a. If at least one face group includes the second face group 10b but does not include the first face group 10a, the operation window displayed by the electronic device may include a second video creation entry corresponding to the second face group 10b. If both the first face group 10a and the second face group 10b are included, the operation window displayed by the electronic device may include only the second video creation entry corresponding to the second face group 10b, or may include both the second video creation entry corresponding to the second face group 10b and the first video creation entry corresponding to the first face group 10a.

[0160] As shown in FIG. 6 , in some examples, in order to distinguish whether the operation window has a second video creation entry, S14 may include S141 - S143 .

[0161] S141: The electronic device determines whether at least one face group includes a second face group.

[0162] S141 is equivalent to determining whether there is a person with naming data among the persons corresponding to at least one face group.

[0163] In a case where at least one face group does not include the second face group, and the characters corresponding to at least one face group are all missing naming data, the electronic device executes S142.

[0164] In a case where the at least one face group includes the second face group, and at least one person among the persons corresponding to the at least one face group has naming data, the electronic device executes S143.

[0165] S142: The electronic device displays an operation window of the target video theme, where the operation window includes a first video creation item.

[0166] In the case where each of the multiple face groups acquired by the voice assistant application is the first face group 10a (none of the characters corresponding to the face groups include naming data, as shown in FIG1(b)), the voice assistant application responds to the user's second operation on the personal photo card by switching the electronic device's display from the video creation window 22 shown in FIG10(a) to the personal photo operation window 23 shown in FIG10(b), which includes a video creation entry (first video creation entry) 231a. The first video creation entry 231a is associated with multiple characters that lack naming data.

[0167] The first video creation entry 231 a may include at least one of an entry material 2311 and / or an entry recommendation text 2312 .

[0168] Since the first video creation entry 231a is associated with a person who lacks naming data and has no naming data, the entry material 2311 displayed by the first video creation entry 231a can be the same as the theme material 2211 displayed by the theme card 221 of the personal photo, both of which are pictures or videos preset by the electronic device for personal photos.

[0169] Similarly, the entry recommendation text 2312 displayed in the first video creation entry 231a may be the same as the theme recommendation text 2213 displayed in the theme card 221 of the personal photo, both of which are recommendation texts preset by the electronic device for the personal photo.

[0170] In the case where the operation window of the target video theme is displayed as shown in FIG10( b ), as shown in FIG6 , S15 in the process may include S151 - S154 .

[0171] S151: The user inputs a third operation of creating an entry for the first video to the electronic device.

[0172] The user can send a voice message of "generate a personal photo collection video" to the smartphone or click on the first video creation entry 231a as a third operation input by the user to the voice assistant application for the first video creation entry 231a.

[0173] S152: The electronic device displays a first selection window in response to the user's third operation on the first video creation item.

[0174] In some feasible implementations, after the user inputs a third operation to the electronic device, the electronic device's display switches from the personal portrait operation window 23 shown in FIG. 11(a) to the display shown in FIG. 11(b). Based on the user's voice, the voice assistant application can display a first conversation message 211a corresponding to the voice in the personal portrait operation window 23. The first conversation message 211a can be displayed below the first video creation entry 231a. The interface shown in FIG. 11(a) and the interface shown in FIG. 10(b) are the same interface.

[0175] In some feasible implementations, in response to the first conversation message 211a, as shown in FIG11(b), the voice assistant application may display a second conversation message 212a for the first conversation message 211a before displaying the first selection window 24, in response to the first conversation message 211a. The first selection window 24 may then be displayed below the second conversation message 212a.

[0176] The voice assistant application in the electronic device responds to the user's third operation for creating entry 231a for the first video, as shown in Figure 11(b), and the display screen displays a first selection window 24. The first selection window 24 can be a separate display window, or the first selection window 24 can be displayed within the personal photo operation window 23, which is not limited in the embodiments of the present application. For ease of explanation, the first selection window 24 and other displayed windows are shown as being displayed within the operation window 23 in the subsequent figures. In actual scenarios, the other displayed windows can also be separate display windows.

[0177] First selection window 24 may include one or more facial images 11, with different facial images 11 corresponding to different people and first face groups 10a. The people corresponding to the facial images in first selection window 24 lack naming data. Therefore, as shown in FIG11(b), first selection window 24 may also display the text "Add Name" below the facial image 11 to encourage the user to name the person.

[0178] The number of facial images 11 displayed in the first selection window 24 can be M. M can be a positive integer such as 1, 2, 3, 4, etc., and is not limited in the embodiments of the present application. For example, the number M of facial images 11 displayed in the first selection window 24 shown in FIG11(b) can be less than or equal to the number K of the first facial groups 10a in the album application shown in FIG1(b).

[0179] In some examples, when M=K, the first selection window 24 may display all facial images 11 of the first face group 10 a .

[0180] In some other examples, when M<K, the first selection window 24 may display a portion of the facial images 11 of the first face group 10 a.

[0181] For example, the voice assistant application can pre-acquire the number of portrait materials included in each first face group 10a and identify M first face groups 10a whose number of portrait materials exceeds a preset material threshold. When the voice assistant application displays the first selection window 24, the facial images 11 of the M first face groups 10a with the larger number of materials are displayed in the first selection window 24.

[0182] As another example, the voice assistant application can pre-acquire the number of portrait materials included in each first face group 10a and determine the M first face groups 10a with the largest number of portrait materials. When the voice assistant application displays the first selection window 24, the facial images 11 of the M first face groups 10a with the largest number of materials are displayed in the first selection window 24.

[0183] For another example, the voice assistant application can pre-acquire the number of newly added portrait materials for each first face group 10a in the recent period (e.g., within two days or within a week), and determine the M first face groups 10a with the largest number of newly added portrait materials. When the voice assistant application displays the first selection window 24, the facial images 11 of the M first face groups 10a with the largest number of newly added materials are displayed in the first selection window 24.

[0184] Of course, the voice assistant application may also have other ways to select the facial images 11 of the M first face group 10a displayed in the first selection window 24, and the embodiments of the present application are not limited to this.

[0185] S153: The user inputs a fourth operation on a face image to the electronic device.

[0186] As shown in FIG12(a), the interface shown in FIG12(a) is the same interface as that shown in FIG11(b). The first selection window 24 may further include a plurality of first selection controls 242. The plurality of first selection controls 242 correspond one-to-one to the plurality of facial images 11, and each first selection control 242 is located in the display area of ​​the facial image 11. Each first selection control 242 corresponds to two display states. Specifically, the first selection control 242 may include a selected display state and an unselected display state. In terms of the display content of the display screen, the selected display state has an additional "√" selection mark compared to the unselected display state.

[0187] If the user performs a fourth operation on the first selection control 242 in the unselected display state, the first selection control 242 will be displayed in the selected display state.

[0188] In addition, the first selection window 24 also includes a plurality of arrangement numbers 243. The plurality of arrangement numbers 243 correspond one-to-one to the plurality of facial images 11, and each arrangement number 243 is located in the display area of ​​the facial image 11. The plurality of arrangement numbers 243 are different from each other and can be used to distinguish different facial images 11.

[0189] In this way, the user can send a voice message of "select the first one" to the smartphone or click on the first selection control 242 corresponding to the first facial image 11, as the user inputs the fourth operation for the 1 facial image 11 to the voice assistant application. At this time, the display screen of the electronic device will switch from displaying the first selection window 24 in Figure 12 (a) to displaying as shown in Figure 12 (b), and the first selection control 242 corresponding to the facial image 11 with the arrangement number 1 will be displayed from an unselected display state to a selected display state. If the user selects the first selection control corresponding to another facial image 11, the electronic device controls the first selection control corresponding to the facial image 11 with the arrangement number 1 to be displayed in an unselected state. In other words, the user can only select one facial image 11 to generate a personal portrait.

[0190] The first selection window 24 may further include a first expansion control 241. The first expansion control 241 may be displayed below the M first face groups 10a. The user may operate the first expansion control 241 when the first selection window 24 does not contain a facial image of a person that the user wants to select.

[0191] In some examples, if a user operates on the first extended control 241, the display screen of the electronic device switches from the first selection window 24 shown in Figure 13(a) to the selection interface 24a shown in Figure 13(b). The selection interface 24a may include the facial image 11 displayed in the first selection window 24, as well as more facial images 11, thereby increasing the number of facial images 11 displayed. Each facial image 11 in the selection interface 24a corresponds to a person and a first facial group 10a, and different facial images 11 correspond to different people and first facial groups 10a. The interface shown in Figure 13(a) and the interface shown in Figure 11(b) are the same interface.

[0192] Each facial image 11 in the selection interface 24a also corresponds to a first selection control 242, which has the same function as the first selection control 242 in the first selection window 24 and is not further described here. Similarly, if the user selects a facial image 11 and then selects the first selection control 241 corresponding to another facial image 11, the first selection control corresponding to the previously selected facial image 11 will be displayed as unselected.

[0193] The selection interface 24a may include a first cancel control 24a1. If the user does not find the facial image for which they want to generate a video in the selection interface 24a, or if the user enters the selection interface 24a by accidentally touching the first expansion control 242 in the first selection window 24, the user may operate the first cancel control 24a1 to exit the selection interface 24a and return to the first selection window 24.

[0194] The selection interface 24a may also include selection information 24a2. When a user selects a facial image 11, causing the first selection control 242 for that facial image 11 to be displayed as selected, the selection information 24a2 displays the number of facial images 11 selected in the selection interface 24a. For example, after the user selects a facial image 11 from the selection interface 24a, the selection interface displayed on the display screen switches from FIG. 13(b) to FIG. 13(c), with the first selection control 242 for the selected facial image 11 displayed as selected, and the selection information 24a1 displays "1 item selected."

[0195] Because the video theme is a personal portrait, only one face image 11 will be selected for the personal portrait. Therefore, in the selection interface 24a corresponding to the personal portrait, the selection information 24a1 will only indicate two situations: "not selected" and "one item selected".

[0196] Selection interface 24a may also include a confirmation control 24a3. After the user has selected facial image 11 from selection interface 24a, the user may operate confirmation control 24a3 to confirm the selection of facial image 11 in selection interface 24a. The display screen switches from the selection interface shown in FIG13(c) to the first selection window 24 shown in FIG13(d). At this point, the facial image 11 selected in selection interface 24a appears in first selection window 24, and the corresponding first selection control 242 is displayed as selected.

[0197] When the user does not select the face image 11, the confirmation control 24a3 may be displayed in gray, and the electronic device does not perform any steps when the user clicks the confirmation control 24a3.

[0198] Furthermore, in the first selection window 24 shown in FIG. 13( d ), the first expansion control 241 may also display the number of selected facial images 11 and the total number of facial images to prompt the user of the number of characters selected.

[0199] At this time, the first selection window 24 shown in (d) of FIG13 is substantially the same as the first selection window 24 shown in (b) of FIG12 , that is, the selection of the facial image 11 is completed in both first selection windows 24 through the fourth operation.

[0200] S154: The user inputs a fifth operation to the electronic device for one facial image. For example, the user inputs a fifth operation to the electronic device for the facial image 11 selected in the first selection window 24.

[0201] As shown in FIG12( a ), the first selection window 24 may further include a first selection confirmation control 244. The user may operate the first selection confirmation control 244 as the user inputting a first selection confirmation operation for one first face group 10a to the voice assistant application.

[0202] Alternatively, the user can make a voice call of "selected" to the smartphone or click the first selection confirmation control 244 in the first selection window 24 as the fifth operation input by the user to the voice assistant application for the face image 11 selected in the first selection window 24.

[0203] In some feasible implementations, after the user inputs the fifth operation to the electronic device, the display screen of the electronic device switches from the first selection window 24 shown in FIG. 12( b) to the display screen shown in FIG. 12( c), and the voice assistant application can display a first conversation message 211 b corresponding to the user's voice in the personal photo operation window 23 based on the user's voice. The first conversation message 211 b can be displayed below the first selection window 24.

[0204] In some feasible implementations, the electronic device responds to the first conversation message 211b, as shown in (c) in Figure 12, and the voice assistant application may display a second conversation message 212b for the first conversation message 211b before executing S16 to answer the first conversation message 211b.

[0205] The electronic device responds to the user's first selection confirmation operation on a facial image and then executes S16. For example, the electronic device responds to the user's fifth operation on facial image 11 arranged in sequence number 1 in first selection window 24, determines the person corresponding to the personal portrait and first facial group 10a, and then executes S16.

[0206] The above is the specific process of S14 and S15 when the at least one face group acquired by the voice assistant application in S14 only includes the first face group 10a.

[0207] S143: The electronic device displays an operation page of the target video theme, where the operation page includes a second video creation entry.

[0208] Among the multiple face groups 10 acquired by the voice assistant application, the multiple face groups 10 include a second face group 10b (at least one of the multiple characters corresponding to the face group includes naming data, as shown in (c) in Figure 1).

[0209] In some examples, the voice assistant application responds to the user's second operation on the personal photo card, and the electronic device's display switches from the video creation window 22 shown in FIG. 10( a ) to a personal photo operation window 23 shown in FIG. 10( c ), which displays N (N is a positive integer greater than 1) video creation entries (second video creation entries) 231 b. Each second video creation entry 231 b is associated with a second face group 10 b having naming data, and different second video creation entries 231 b correspond to different second face groups 10 b.

[0210] Exemplarily, when all characters corresponding to at least one face group have naming data, the voice assistant application responds to the user's second operation on the personal photo card, and the display screen of the electronic device switches from the video production window 22 shown in Figure 10 (a) to the operation window 23 including N second video creation entries 231b as shown in Figure 10 (c).

[0211] The number N of the second video creation entries 231 b displayed in the personal photo operation window 23 may be less than or equal to the number P of the second face groups 10 b in the album application.

[0212] In some examples, when N=P, the N second video creation entries 231 b displayed in the operation window 23 may correspond to all second face groups 10 b .

[0213] In other examples, when N < P, the N second video creation entries 231b displayed in the operation window 23 may correspond to a portion of the second face group 10b. In this case, the operation window 23 may also display a second expansion control (not shown). After the user operates the second expansion control, the operation window 23 may expand and display more second video creation entries 231b, allowing the user to more comprehensively select a second video creation entry 231b through the operation window 23.

[0214] The second video creation entry 231 b may include at least one of an entry material 2311 and / or an entry recommendation text 2312 .

[0215] Because the second video creation entry 231b is associated with the second face group 10b, each second video creation entry 231b can display the portrait material from the corresponding second face group 10 as entry material 2311. In this case, the subject material 2211 displayed in the target subject card 221 can be a material pre-set on the electronic device or a picture or video stored in the photo album application. For example, the subject material displayed in the target subject card 221 can be the entry material 2311 displayed in any second video creation entry 231b in the personal portrait operation window 23.

[0216] Similarly, the item recommendation text 2312 displayed in the second video creation item 231b may include the naming data 12 in the corresponding second face group 10b. For example, the second video creation item 231b corresponding to the second face group 10b with the naming data "Xiao Yang" may include the item recommendation text 2312 of "Generate a photo collection video of Xiao Yang."

[0217] In the case where the operation window 23 of the target video theme is displayed as shown in (c) of FIG. 10 , as shown in FIG. 6 , S15 in the process may include S155 .

[0218] S155: The user inputs a sixth operation of creating an entry for the second video to the electronic device.

[0219] As shown in FIG. 10( c ), the personal photo operation window 23 has N video creation entries (second video creation entries) 231 b .

[0220] Taking the second video creation entry 231b including the entry recommendation text 2312 as an example, the user can send a voice message of "Generate Xiaohua's photo collection video" to the electronic device or click on the corresponding second video creation entry 231b, as the user inputs the sixth operation of the second second video creation entry 231b in the operation window 23 of the personal photo as shown in (c) in Figure 10 to the voice assistant application.

[0221] Because each second video creation entry 231b in the personal portrait operation window 23 shown in FIG10(c) corresponds to a person with named data, the sixth operation on the second second video creation entry 231b can determine the second face group 10b corresponding to the personal portrait, which is actually similar to determining the first face group 10a corresponding to the first video creation entry 231a using the method described above in S151-S154. Therefore, after S155, the electronic device can execute S16.

[0222] In some feasible implementations, after the user inputs the second selection operation to the electronic device, the electronic device's display screen switches from the personal portrait operation window 23 shown in FIG. 14(a) to the one shown in FIG. 14(b). Based on the user's voice, the voice assistant application can display a first conversation message 211c corresponding to the voice in the personal portrait operation window 23. The first conversation message 211c can be displayed below the N video creation entries 231b.

[0223] In some feasible implementations, the electronic device responds to the first conversation message 211c, as shown in (b) in FIG14 , and the voice assistant application may display a second conversation message 212c for the first conversation message 211c to answer the first conversation message 211c before executing S16.

[0224] The above is the specific process of S14-S15 when the at least one face group acquired by the voice assistant application in S14 only includes the second face group 10b.

[0225] In other examples, the voice assistant application responds to the user's second operation on the personal photo card, and the electronic device's display screen switches from the video creation window 22 shown in Figure 10 (a) to the operation window 23 shown in Figure 10 (d), which includes N second video creation entries 231b and one first video creation entry 231a. Each second video creation entry 231b is associated with a person with naming data, and different second video creation entries 231b correspond to different people. The first video creation entry 231a is associated with multiple people without naming data.

[0226] Exemplarily, among the characters corresponding to at least one face group, some characters have naming data and other characters lack naming data, the voice assistant application responds to the user's second operation on the personal photo card, and the display screen of the electronic device switches from the video production window 22 shown in Figure 10 (a) to the operation window 23 shown in Figure 10 (d), including N second video creation entries 231b and 1 first video creation entry 231a.

[0227] The process for selecting the first video creation item 231a in the operation window 23 shown in FIG10(d) can refer to the description of S151-S154 above. The process for selecting the second video creation item 231b in the operation window 23 shown in FIG10(d) can refer to the description of S155 above. Furthermore, the operation window 23 shown in FIG10(d) also includes the second extended control described above, which has the same function and effect, and will not be further described here.

[0228] After finishing S15, the electronic device may execute S16.

[0229] S16: The electronic device displays a third selection window.

[0230] It can be understood that when the display screen of the electronic device is displaying the first selection window 24 as shown in Figure 15 (a), after responding to the fifth operation to determine the person corresponding to the theme of the personal photo video, the display screen can switch to display the third selection window 25 as shown in Figure 15 (c). Alternatively, when the display screen of the electronic device is displaying the personal photo operation window 23 as shown in Figure 15 (b), after responding to the sixth operation to determine the person corresponding to the theme of the personal photo video, the display screen can switch to display the third selection window 25 as shown in Figure 15 (c). The interface shown in Figure 15 (a) is the same interface as the interface shown in Figure 12 (c), and the interface shown in Figure 15 (b) is the same interface as the interface shown in Figure 14 (b).

[0231] The third selection window 25 may display multiple portrait materials 251 for selection. The portrait materials 251 for selection may be images or videos, and the embodiments of the present application are not limited thereto. It should be noted that the multiple portrait materials 251 for selection displayed in the third selection window 25 all include portrait materials of the same person (corresponding to the second face group 10b or the first face group 10a). In addition to the facial images corresponding to the face group, the portrait materials may also include facial images of other people.

[0232] In some examples, the number of portrait materials 251 to be selected displayed in the third selection window 25 may be a fixed number. For example, the number of portrait materials 251 to be selected displayed in the third selection window 25 may be 3, 4, 6, 8, 9, etc., which is not limited here. In other examples, there may be a smaller number of portrait materials 251 to be selected for a person, in which case the third selection window 25 may display all portrait materials.

[0233] The third selection window 25 may display a third selection control 252. Multiple third selection controls 252 correspond one-to-one to multiple selectable portrait materials 251, and each third selection control 252 is located in the display area of ​​a selectable portrait material 251. The function of the third selection control 252 on the selectable portrait material 251 is the same or similar to the function of the first selection control 242 on the first face group 10a, and will not be further described here.

[0234] The multiple portrait materials 251 to be selected in the third selection window 25 can be arranged in chronological order, or can be arranged in descending order of aesthetic scores after aesthetic scores are performed on each portrait material to be selected, or can be arranged in other ways, which are not limited in the embodiments of the present application.

[0235] In addition, the multiple portrait materials 251 to be selected in the third selection window 25 can display all portrait materials that meet the conditions in the album, or can also display some portrait materials. For example, the voice assistant application can perform deduplication processing on the portrait images in the album before displaying them. For another example, the voice assistant application can perform aesthetic scoring on each material and display portrait images with aesthetic scores above a preset scoring threshold.

[0236] S17: The user inputs a seventh operation to the electronic device for one or more portrait materials to be selected.

[0237] For example, the user can speak "Select All" to the smartphone or manually select each of the candidate portrait materials 251 in the third selection window 25 as the user inputs the seventh operation to the voice assistant application for one or more candidate portrait materials 251. At this time, the display screen of the electronic device switches from the third selection window 25 shown in Figure 16 (a) to that shown in Figure 16 (b), and the third selection control 252 located on each material 251 will change from an unselected display state to a selected display state. The interface shown in Figure 16 (a) is the same interface as the interface shown in Figure 15 (c).

[0238] When the third selection window 25 displays only a portion of the portrait materials 251 to be selected, the third selection window 25 may further include a third expansion control 253. The third expansion control 253 may be displayed below the plurality of portrait materials 251 to be selected. The user may operate the third expansion control 253 to display more portrait materials 251 to be selected on the screen of the electronic device.

[0239] In some examples, if the user operates the third extended control 253 in the third selection window 25, the display screen of the electronic device switches from the third selection window 25 shown in FIG17(a) to the character material interface corresponding to a character (or face group 10) shown in FIG17(b). The character material interface can display the character material to be selected displayed in the third selection window 25, as well as more character materials to be selected, thereby increasing the number of character materials to be selected. The character materials to be selected in the character material interface 25a are all portrait materials 251 to be selected that contain the same character (corresponding to the second face group 10b, or corresponding to the first face group 10a). The interface shown in FIG17(a) is the same interface as that shown in FIG15(c).

[0240] Each candidate portrait material 251 in the character material interface 25a also corresponds to a third selection control 252, which has the same function as the first selection control 242 in the first selection window 24 and is not further described here. The user can select one or more candidate portrait materials 251 in the character material interface 25a, and the third selection control 252 of the selected candidate portrait material 251 will be displayed as selected.

[0241] The character material interface 25a may include a second cancel control 25a1. If the user does not find the candidate portrait material 251 for which they want to generate a video in the character material interface 25a, or if the user enters the character material interface 25a by accidentally touching the third expansion control 252 in the third selection window 25, the user can operate the second cancel control 25a1 to exit the character material interface 25a and return to the third selection window 25.

[0242] The character material interface 25a may also include selection information 25a2. When the user selects a candidate portrait material 251 and the second selection control 252 of the candidate portrait material 251 is displayed as a selected display state, the selection information 25a2 will display the number of candidate portrait materials 251 selected in the character material interface 25a. For example, after the user selects multiple candidate portrait materials 251 from the character material interface 25a, the character material interface 25a displayed on the display screen switches from FIG. 17 (b) to FIG. 17 (c), and the second selection control 252 of the selected candidate portrait material 251 is displayed as a selected display state, and the selection information 25a1 displays "T items selected", where T is the number of character materials displayed as selected in the character material interface 25a.

[0243] The character material interface 25a may also include a confirmation control 25a3. After the user has selected the candidate portrait material 251 from the character material interface 25a, the user may operate the confirmation control 25a3 to confirm the selection of the candidate portrait material 251 in the character material interface 25a. The display screen switches from the selection interface shown in FIG. 17(c) to the first selection window 24 shown in FIG. 17(d). At this point, the candidate portrait material 251 selected in the character material interface 25a appears in the third selection window 25, and the corresponding third selection control 252 is displayed as selected.

[0244] In the case that the user has not selected the portrait material 251 to be selected, the confirmation control 25a3 may be displayed in gray, and when the user clicks the confirmation control 25a3, the electronic device does not perform any steps.

[0245] Furthermore, in the third selection window 25 shown in FIG. 17 ( d ), the third extended control 252 may also display the number of selected portrait materials 251 and the total number of portrait materials 251 to prompt the user to select the number of portrait materials 251 to be selected.

[0246] In some feasible implementations, the character material interface 25a shown in FIG17(c) may further include an add control 25a4. The user may operate the add control 25a4 to further select other character portrait materials from the album, or select other non-portrait materials, which are not limited here.

[0247] At this time, the third selection window 25 shown in (d) of FIG17 is substantially the same as the third selection window 25 shown in (b) of FIG16 , that is, the selection of the portrait material 251 to be selected is completed in both third selection windows 25 through the seventh operation.

[0248] S18: The user inputs an eighth operation on one or more portrait materials to be selected to the electronic device. For example, the user inputs a third selection confirmation operation on the selected portrait material to be selected 251 to the electronic device.

[0249] As shown in FIG. 16( b ), the third selection window 25 may further include a third selection confirmation control 254 .

[0250] The user can send a voice message of "selected" to the smartphone or click the third selection confirmation control 254 as the eighth operation input by the user to the voice assistant application for the selected multiple candidate portrait materials 251.

[0251] In some feasible implementations, after the user inputs the eighth operation to the electronic device, as shown in FIG16( b ), the voice assistant application may display a first conversation message 211 d corresponding to the user's voice in the personal photo operation window 23 based on the user's voice. The first conversation message 211 d may be displayed below the third selection window 25.

[0252] S19: The electronic device generates a video in response to the user's eighth operation on one or more portrait materials to be selected.

[0253] The electronic device responds to the user's eighth operation on one or more portrait materials 251 to be selected, and after determining multiple selected materials, it can generate a video based on the aforementioned synthetic video function, which will not be repeated here.

[0254] After the electronic device generates the video, the electronic device's display switches from the third selection window 25 shown in FIG. 18(a) to the personal portrait video operation window 23 shown in FIG. 18(b), which displays the synthesized video 26. The interface shown in FIG. 18(a) is the same as the interface shown in FIG. 16(b).

[0255] In some feasible implementations, in response to the first conversation message 211d, as shown in FIG18(b), the voice assistant application may display a second conversation message 212d for the first conversation message 211d before displaying the video 26, in response to the first conversation message 211d. The video 26 may then be displayed below the second conversation message 212d.

[0256] In this way, the video generation method provided by the embodiment of the present application utilizes the different characteristics of facial features of different people, and can correspond the portrait material to the face group in which the face image appears based on the face image appearing in each portrait material. Furthermore, it is combined with a design in which each video creation entry corresponds to one or more people, and the people corresponding to different video creation entries are not exactly the same. In this way, the video generation method can use a second video creation entry to find the portrait material corresponding to one or more people at one time, thereby improving the efficiency of determining the portrait material in the synthesized video, and thus improving the efficiency of generating the video.

[0257] FIG19 also shows a schematic diagram of adding named data in a face group in the video synthesis process.

[0258] As can be seen from S11-S19 above, whether at least one face group in the album application includes named data has a significant impact on the above process. Typically, adding named data to a face group in an album application requires opening the album application on the electronic device's desktop, then finding the corresponding face group and adding the named data, which is a relatively cumbersome operation. In the embodiments of the present application, a path for adding named data for face groups is added to the video synthesis process, making it more convenient to add named data for face groups.

[0259] When the electronic device displays the first selection window 24 as shown in FIG. 19( a), the text "Add Name" can serve as a naming control. The user can perform a ninth operation on one or more naming controls in the first selection window 24. When the user performs the ninth operation on the naming control (target naming control) of the second facial image 11, the voice assistant application responds to the ninth operation and switches the display screen of the electronic device from FIG. 19( a) to the naming editing window 27 as shown in FIG. 19( b). The interface shown in FIG. 19( a) is the same interface as the vegetarian interface in FIG. 11( b).

[0260] The name editing window 27 may include a person name column 271. The user may edit the name, nickname, or nickname of the second face image 11 corresponding to the first selection window 24 in the person name column 271 as the name sub-data of the person corresponding to the second face group 10.

[0261] The name editing window 27 may also include a relationship control 272. There may be multiple relationship controls 272, each corresponding to a piece of relationship sub-data representing the relationship between the person and the electronic device owner. A relationship control 272 may correspond to relationship sub-data representing a kinship relationship. For example, relationship sub-data representing the person is the electronic device owner's father, or relationship sub-data representing the person is the electronic device owner's grandmother. A relationship control 272 may also represent relationship sub-data representing a workplace relationship. For example, relationship sub-data representing the person is the electronic device owner's colleague.

[0262] The user can select a relationship control 272 from the plurality of relationship controls 272 through a selection operation. In response to the selection operation, the electronic device determines the relationship sub-data of the person corresponding to the second facial image 11.

[0263] It should be noted that (b) in FIG. 19 may also include a control for customizing the relationship. In response to the user clicking the control for customizing the relationship and the relationship sub-data input by the user, the electronic device may determine the relationship between the character and the owner of the electronic device.

[0264] It should be noted that the user can operate on either or both the character name field 271 and the relationship control 272, and this is not limited in the embodiments of the present application. If the user only operates on the character name field 271, the name sub-data can be used as the naming data for the face group 10. If the user only operates on the relationship control 272, the relationship sub-data can be used as the naming data for the face group 10. If the user operates on both the character name field 271 and the relationship control 272, either the name sub-data or the relationship sub-data can be used as the naming data for the face group 10.

[0265] The name editing window 27 may also include a name confirmation control 273. After the user completes editing the name sub-data in the person name column 271 and / or operates the relationship control 272 to confirm the relationship sub-data, the user can operate the name confirmation control 273 to complete the editing process of the name data. In response to the user's operation of the name confirmation control 273, the electronic device's display screen switches from FIG. 19 (b) to the first selection window 24 shown in FIG. 19 (c). At this point, the first selection window 24 displays the name data of the person corresponding to the second facial image 11.

[0266] In some examples, the naming editing window 27 shown in (b) of Figure 19 can be a window provided by the voice assistant application. After the voice assistant application obtains the naming data through the naming editing window 27, it can provide the naming data to the album application, so that the album application can synchronously add the naming data of the face group 10.

[0267] In other examples, the name editing window 27 shown in FIG. 19( b) may be a window provided by an album application. After obtaining the name data through the name editing window 27, the album application directly adds the name data of the face group 10 within the album application. The name data may also be provided to the voice assistant application, so that the first selection window 24 can synchronously display the name data of the face group 10.

[0268] The above S11-S19 are all explained by taking the personal photo video theme as the target video theme as an example.

[0269] The following description takes a family photo video theme as an example of a target video theme.

[0270] Please refer to FIG. 6 . The video generation method provided in the embodiment of the present application includes steps S11 to S19 .

[0271] S11: The user inputs a first operation for a composite video function to the electronic device.

[0272] S12: The voice assistant application displays a video production window on the display screen in response to the first operation.

[0273] In this embodiment, the specific process of S11-S12 can refer to the description of S11-S12 in the personal photo video theme, which will not be repeated here.

[0274] S13: The user inputs a second operation for the family photo theme card into the electronic device.

[0275] For example, when the electronic device displays the video production window 22, the user can send a voice message "I choose family photo" to the smartphone, or the user can click on the theme card 221 corresponding to "Family Photo" as the user inputs a second operation for the family photo card to the voice assistant application.

[0276] S14: The electronic device responds to the user's second operation on the family photo theme card and displays an operation window for the family photo video theme. For example, the electronic device responds to the user's operation on the family photo card and displays an operation window for the family photo theme.

[0277] Before displaying the family photo video theme, the voice assistant application of the electronic device can obtain at least one face group corresponding to multiple images in the photo album application. For example, the photo album application provides at least one face group to the voice assistant application. The at least one face group may include the first face group 10a but not the second face group 10b, the second face group 10b but not the first face group 10a, or both the first face group 10a and the second face group 10b.

[0278] If at least one face group includes the first face group 10a but does not include the second face group 10b, the operation window displayed by the electronic device may include a first video creation entry corresponding to the first face group 10a. If at least one face group includes the second face group 10b but does not include the first face group 10a, the operation window displayed by the electronic device may include a second video creation entry corresponding to the second face group 10b. If both the first face group 10a and the second face group 10b are included, the operation window displayed by the electronic device may include only the second video creation entry corresponding to the second face group 10b, or may include both the second video creation entry corresponding to the second face group 10b and the first video creation entry corresponding to the first face group 10a.

[0279] As shown in FIG. 6 , in some examples, in order to distinguish whether the operation window has a second video creation entry, S14 may include S141 - S143 .

[0280] S141: The electronic device determines whether at least one face group includes a second face group.

[0281] S141 is equivalent to determining whether there is a person with naming data among the persons corresponding to at least one face group.

[0282] In a case where at least one face group does not include the second face group, and the characters corresponding to at least one face group are all missing naming data, the electronic device executes S142.

[0283] In a case where the at least one face group includes the second face group, and at least one person among the persons corresponding to the at least one face group has naming data, the electronic device executes S143.

[0284] S142: The electronic device displays an operation page of the video theme, where the operation page includes a first video creation entry.

[0285] In the case where each of the multiple face groups acquired by the voice assistant application is a first face group 10a (the characters corresponding to the face groups do not include naming data, as shown in FIG1(b)), the voice assistant application responds to the user's second operation on the family photo card by switching the electronic device's display from the video creation window 22 shown in FIG20(a) to an operation window 23 of the family photo, as shown in FIG20(b), displaying a video creation entry (first video creation entry) 231a. The first video creation entry 231a is associated with the multiple first face groups 10a.

[0286] In the case where the operation window of the target video theme is displayed as shown in FIG10( b ), as shown in FIG6 , S15 in the process may include S151 - S154 .

[0287] S151: The user inputs a third operation of creating an entry for the first video to the electronic device.

[0288] The user can send a voice message of "generate a family photo video" to the smartphone or click on the first video creation entry 231a as the user inputting a third operation (first selection operation) for the first video creation entry 231a to the voice assistant application.

[0289] S152: The electronic device displays a first selection window in response to the user's third operation on the first video creation item.

[0290] In response to the user's first selection operation for creating entry 231a for the first video, the voice assistant application on the electronic device switches the display of the electronic device from the operation window 23 for the family photo shown in FIG21(a) to the first selection window 24 shown in FIG21(b). The interface shown in FIG21(a) is the same as the interface shown in FIG20(b).

[0291] First selection window 24 may include one or more facial images 11, with different facial images 11 corresponding to different characters and first facial groups 10a, and each character does not include naming data 12. As shown in FIG21(b), if a character does not include naming data 12, the text "Add Name" is displayed below facial image 11 to encourage the user to name the character.

[0292] In this embodiment, the text "Add Name" in the first selection window 24 can also be used as a naming control to perform the process of adding naming data to the first face group 10a. The process of adding naming data is basically the same as the process shown in Figure 19 and will not be repeated here.

[0293] S153: The user inputs a fourth operation for at least two face groups 10 to the electronic device.

[0294] As shown in FIG21(b), the first selection window 24 may further include multiple first selection controls 242. The multiple first selection controls 242 correspond one-to-one to the multiple facial images 11, and each first selection control 242 is located in the display area of ​​the facial image 11. The user can send a voice message "Select all" to the smartphone or click on the selection controls 242 corresponding to the multiple facial groups 10 as the user inputs a fourth operation for the multiple first facial groups 10a to the voice assistant application. At this time, the display screen of the electronic device displays the display shown in FIG21(b), with the first selection controls 242 corresponding to all the first facial groups 10a in the first selection window 24 changing from an unselected display state to a selected display state.

[0295] It should be noted that the first selection window 24 shown in FIG. 21( b ) may also include the aforementioned first expansion control 241. The user may operate the first expansion control 241 to enter a selection interface and select multiple facial images 11 in the first face group 10a. The user is required to select two or more people in the selection interface. If the number of people selected by the user is less than two, the electronic device that determines the user's operation does not execute any steps.

[0296] S154: The user inputs a fifth operation to the electronic device for at least two first face groups. For example, the user inputs a first selection confirmation operation to the electronic device for all first face groups 10a in FIG. 21(b).

[0297] 21( b ), the first selection window 24 may further include a first selection confirmation control 244. The user may operate the first selection confirmation control 244 as the user inputting a first selection confirmation operation for the selected at least two first face groups 10a to the voice assistant application.

[0298] Alternatively, the user can send a "selected" voice to the smartphone or manually click on the facial images 11 displayed by multiple first face groups 10a as the user inputs a first selection confirmation operation for at least two selected first face groups 10a to the voice assistant application.

[0299] The electronic device responds to the user's first selection confirmation operation on at least two first face groups 10a and then executes S16. For example, the electronic device responds to the user's first selection confirmation operation on all first face groups 10a in the first selection window 24 and determines the face group 10 corresponding to the family photo and then executes S16.

[0300] The above is the specific process of S14 and S15 when the at least one face group acquired by the voice assistant application in S14 only includes the first face group 10a.

[0301] S143: The electronic device displays an operation page of the second video theme, where the operation page includes a second video creation entry.

[0302] Among the multiple face groups 10 acquired by the voice assistant application, the multiple face groups 10 include a second face group 10b (at least one of the multiple characters corresponding to the face group includes naming data, as shown in (c) in Figure 1).

[0303] In some examples, the voice assistant application responds to the user's second operation on the family photo card, and the electronic device's display screen switches from the video creation window 22 shown in FIG. 20( a ) to an operation window 23 of the family photo, as shown in FIG. 20( c ), which displays N (N is a positive integer greater than 1) video creation entries (second video creation entries) 231 b. Each second video creation entry 231 b is associated with at least two characters having naming data, and different second video creation entries 231 b correspond to different characters.

[0304] For example, one second video creation entry 231b is associated with three second face groups 10b: a child, a father, and a mother. Another second video creation entry 231b is associated with two second face groups 10b: a child and a father. Another second video creation entry 231b is associated with two second face groups 10b: a child and a mother. Each of these three second video creation entries 231b is associated with at least two second face groups 10b with named data, and the second face groups 10b corresponding to the three second video creation entries 231b are not identical.

[0305] Exemplarily, when all characters corresponding to at least one face group have naming data, the voice assistant application responds to the user's second operation on the personal photo card, and the display screen of the electronic device switches from the video production window 22 shown in Figure 20 (a) to the operation window 23 including N second video creation entries 231b as shown in Figure 20 (c).

[0306] In the case where the operation window 23 of the target video theme is displayed as shown in (c) of FIG. 20 , as shown in FIG. 6 , S15 in the process may include S155 .

[0307] S155: The user inputs a sixth operation of creating an entry for the target video to the electronic device.

[0308] As shown in FIG. 20( c ), the operation window 23 for the family photo has N video creation entries (second video creation entries) 231 b .

[0309] Taking the example of second video creation entry 231b including entry recommendation text 2312, the user can send a voice message to the electronic device saying "generate a video of the child and mother" or click on the corresponding second video creation entry as the sixth operation input to the voice assistant application for the second second video creation entry 231b in the operation window 23 for the family photo shown in FIG20(c). The display screen of the electronic device switches from the operation window 23 for the family photo shown in FIG22(a) to the display shown in FIG22(b), indicating that the electronic device has determined the second video creation entry 231b selected by the user.

[0310] Since each second video creation entry 231b in the family photo operation window 23 shown in FIG22(a) corresponds to a second face group 10b of at least two people, the second selection operation on the second second video creation entry 231b can determine the second face group 10b of at least two people corresponding to the family photo, which is actually equivalent to determining that the first face group 10a of at least two people corresponding to the first video creation entry 231a is similar in the manner of S151-S154 described above. Therefore, after S155, the electronic device can execute S16.

[0311] The above is the specific process of S14-S15 when the at least one face group acquired by the voice assistant application in S14 only includes the second face group 10b.

[0312] In other examples, the voice assistant application responds to the user's second operation on the family photo card, and the electronic device's display screen switches from the video creation window 22 shown in Figure 20 (a) to the operation window 23 shown in Figure 20 (d), which includes N second video creation entries 231b and one first video creation entry 231a. Each second video creation entry 231b is associated with at least two characters with naming data, and different second video creation entries 231b correspond to different characters. The first video creation entry 231a is associated with multiple characters without naming data.

[0313] Exemplarily, among the characters corresponding to at least one face group, some characters have naming data and other characters lack naming data, the voice assistant application responds to the user's second operation on the family photo card, and the display screen of the electronic device switches from the video production window 22 shown in Figure 20 (a) to the operation window 23 shown in Figure 20 (d), including N second video creation entries 231b and 1 first video creation entry 231a.

[0314] It should be noted that the face group 10 corresponding to the second video creation entry 231 b only has the second face group 10 b and does not correspond to the first face group 10 a .

[0315] The process of the user selecting the first video creation entry 231a in the operation window 23 as shown in (d) in Figure 20 can refer to the description of S151-S154 above; the process of the user selecting the second video creation entry 231b in the operation window 23 as shown in (d) in Figure 20 can refer to the description of S155 above, which will not be repeated here.

[0316] In addition, since family photos correspond to multiple people, the third face group can be suitable for family photo video themes. For example, when using the third face group 10c to determine the face group 10 corresponding to the composite video, the first face group 10a and the second face group 10b may not be needed.

[0317] For example, if the electronic device includes multiple persons with named data 12 among the multiple persons corresponding to at least one face group 10 obtained from the photo album application, the multiple persons with named data 12 may be combined to form multiple third face groups 10c. The creation window 23 may display second video creation entries 231b, each second video creation entry 231b corresponding to a third face group 10c.

[0318] Of course, the production window 23 may also display the first video creation entry 231 a on the basis of displaying the second video creation entry 231 b , where the first video creation entry 231 a corresponds to a plurality of characters that are missing naming data.

[0319] It should be noted that the third face groups 10c corresponding to the second video creation entries 231b all correspond to persons with named data.

[0320] After determining the face group, the electronic device may execute S16.

[0321] S16: The electronic device displays a third selection window.

[0322] It is understandable that when the display screen of the electronic device displays the first selection window 24 shown in FIG. 23( a ), after the first face group 10a corresponding to the family photo video theme is determined in response to the first selection confirmation operation, the display screen may switch to display the third selection window 25 shown in FIG. 23( c ). Alternatively, when the display screen of the electronic device displays the operation window 23 for family photos shown in FIG. 23( b ), after the at least two second face groups 10b corresponding to the family photo video theme are determined in response to the second selection operation, the display screen may switch to display the third selection window 25 shown in FIG. 23( c ).

[0323] The third selection window 25 may display multiple portrait materials 251 for selection. The portrait materials 251 for selection may be images or videos, and the embodiments of the present application are not limited thereto. It should be noted that the multiple portrait materials 251 for selection displayed in the third selection window 25 are all intersections of portrait materials of the same number (e.g., two, three, etc.) of people (the second face group 10b corresponding to the second selection operation, or the first face group 10a corresponding to the first selection confirmation operation).

[0324] Taking the second video creation entry 231b corresponding to the second face group 10b1 of person 1, the second face group 10b2 of person 2 and the second face group 10b3 of person 3 as an example, each selected portrait material 251 in the third selection window 25 is the intersection of the portrait material of the second face group 10b1, the portrait material of the second face group 10b2 and the portrait material of the third face group 10b3. It can be understood that each selected portrait material 251 simultaneously contains the facial image of person 1, the facial image of person 2 and the facial image of person 3.

[0325] S17: The user inputs a seventh operation to the electronic device for one or more portrait materials to be selected.

[0326] For example, the user can speak "Select All" to the smartphone as the seventh operation input to the voice assistant application for one or more portrait materials 251 to be selected. At this time, the display screen of the electronic device switches from the third selection window 25 shown in Figure 16 (a) to that shown in Figure 16 (b), and the third selection control 252 located on each material 251 is displayed from an unselected display state to a selected display state.

[0327] It should be noted that the first selection window 24 shown in FIG23(c) may also include the third extension control 252. The user may operate the third extension control 252 to enter the character material interface and select multiple character materials to be selected.

[0328] S18: The user inputs an eighth operation on one or more portrait materials to be selected to the electronic device. For example, the user inputs an eighth operation on the selected portrait material to the electronic device.

[0329] As shown in FIG. 23( c ), the third selection window 25 may further include a third selection confirmation control 254 .

[0330] The user can send a voice message "selected" to the smartphone or manually click the third selection confirmation control 254 as the eighth operation input by the user to the voice assistant application for the selected multiple candidate portrait materials 251.

[0331] In some feasible implementations, after the user inputs the eighth operation to the electronic device, as shown in FIG24(a), the voice assistant application may display a first conversation message 211d corresponding to the user's voice in the family photo operation window 23 based on the user's voice. The first conversation message 211d may be displayed below the third selection window 25.

[0332] S19: The electronic device generates a video in response to the user's eighth operation on one or more portrait materials to be selected.

[0333] After the electronic device responds to the user's eighth operation on one or more portrait materials to be selected 251 and determines multiple selected portrait materials, it can synthesize the video based on the aforementioned video synthesis function, which will not be repeated here.

[0334] After the electronic device synthesizes the video, the display screen of the electronic device switches from the third selection window 25 shown in Figure 24 (a) to the family photo video operation window 23 shown in Figure 24 (b), and the synthesized video 26 is displayed in the family photo video operation window 23.

[0335] The above S11-S19 are all described by taking the family photo video theme as the target video theme as an example.

[0336] The following explanation is made by taking the warm moment video theme as the target video theme.

[0337] Please refer to FIG. 6 . The video generation method provided in the embodiment of the present application includes steps S11 to S19 .

[0338] S11: The user inputs a first operation for a composite video function to the electronic device.

[0339] S12: The voice assistant application displays a video production window on the display screen in response to the first operation.

[0340] In this embodiment, the specific process of S11-S12 can refer to the description of S11-S12 in the personal photo video theme, which will not be repeated here.

[0341] S13: The user inputs a second operation for the warm moment theme card to the electronic device.

[0342] For example, when the electronic device displays the video production window 22, the user can send a voice message "I choose warm moments" to the smartphone, or the user can click on the theme card 221 corresponding to "Warm Moments" as the user inputs a second operation for the warm moment card to the voice assistant application.

[0343] S14: The electronic device responds to the user's second operation on the Warm Moment theme card by displaying an operation window for the Warm Moment video theme. For example, the electronic device responds to the user's operation on the Warm Moment theme card by displaying the Warm Moment operation window.

[0344] Before displaying the operation window for the Warm Moments video theme, the voice assistant application of the electronic device can obtain at least one face group corresponding to multiple images in the photo album application. For example, the photo album application provides at least one face group to the voice assistant application. The at least one face group may include the first face group 10a but not the second face group 10b, the second face group 10b but not the first face group 10a, or both the first face group 10a and the second face group 10b.

[0345] If at least one face group includes the first face group 10a but does not include the second face group 10b, the operation window displayed by the electronic device may include a first video creation entry corresponding to the first face group 10a. If at least one face group includes the second face group 10b but does not include the first face group 10a, the operation window displayed by the electronic device may include a second video creation entry corresponding to the second face group 10b. If both the first face group 10a and the second face group 10b are included, the operation window displayed by the electronic device may include only the second video creation entry corresponding to the second face group 10b, or may include both the second video creation entry corresponding to the second face group 10b and the first video creation entry corresponding to the first face group 10a.

[0346] As shown in FIG. 6 , in some examples, in order to distinguish whether the operation window has a second video creation entry, S14 may include S141 - S143 .

[0347] S141: The electronic device determines whether at least one face group includes a second face group.

[0348] S141 is equivalent to determining whether there is a person with naming data among the persons corresponding to at least one face group.

[0349] In a case where at least one face group does not include the second face group, and the characters corresponding to at least one face group are all missing naming data, the electronic device executes S142.

[0350] In a case where the at least one face group includes the second face group, and at least one person among the persons corresponding to the at least one face group has naming data, the electronic device executes S143.

[0351] S142: The electronic device displays an operation page of the video theme, where the operation page includes a first video creation entry.

[0352] In the case where each of the multiple face groups acquired by the voice assistant application is a first face group 10a (the characters corresponding to the face groups do not include naming data, as shown in FIG1(b)), the voice assistant application responds to the user's second operation on the warm moment card by switching the display of the electronic device from the video creation window 22 shown in FIG25(a) to the warm moment operation window 23 shown in FIG25(b) , which includes a video creation entry (first video creation entry) 231a. The first video creation entry 231a is associated with the multiple first face groups 10a.

[0353] In the case where the operation window of the target video theme is displayed as shown in FIG. 20( b ), as shown in FIG. 6 , S15 in the process may include S151 - S154 .

[0354] S151: The user inputs a third operation of creating an entry for the first video to the electronic device.

[0355] The user may send a voice message "generate a video of a warm moment" to the smartphone or click on the first video creation entry 231a as a third operation input by the user to the voice assistant application for the first video creation entry 231a.

[0356] S152: The electronic device displays a first selection window in response to the user's third operation on the first video creation item.

[0357] The voice assistant application in the electronic device responds to the user's third operation to create entry 231a for the first video, and the display screen of the electronic device switches from the operation window 23 of the warm moment shown in Figure 26 (a) to the first selection window 24 as shown in Figure 26 (b).

[0358] First selection window 24 may include one or more facial images 11, with different facial images 11 corresponding to different characters and first facial groups 10a, and each character does not include naming data 12. As shown in FIG21(b), if a character does not include naming data 12, the text "Add Name" is displayed below facial image 11 to encourage the user to name the character.

[0359] In this embodiment, the text "Add Name" in the first selection window 24 can also be used as a naming control to perform the process of adding naming data to the first face group 10a. The process of adding naming data is basically the same as the process shown in Figure 19 and will not be repeated here.

[0360] S153: The user inputs a fourth operation for at least one face group 10 to the electronic device.

[0361] As shown in FIG26(b), the first selection window 24 may further include multiple first selection controls 242. The multiple first selection controls 242 correspond one-to-one to the multiple facial images 11, and each first selection control 242 is located in the display area of ​​the facial image 11. The user can speak "Select the first and third" to the smartphone or click the selection controls 242 corresponding to the first and third facial groups 10, as the user inputs a fourth operation for the multiple first facial groups 10a to the voice assistant application. At this point, the display screen of the electronic device displays the display shown in FIG26(b), with the first selection controls 242 corresponding to all the first facial groups 10a in the first selection window 24 changing from an unselected display state to a selected display state.

[0362] It should be noted that the first selection window 24 shown in FIG. 26( b ) may also include the aforementioned first expansion control 241. The user may operate the first expansion control 241 to enter a selection interface and select multiple facial images 11 from the first face group 10a. The user is required to select at least one person in the selection interface. If the number of people selected by the user is less than one, the electronic device that determines the user's operation does not execute any steps.

[0363] S154: The user inputs a fifth operation to the electronic device for at least one first face group. For example, the user inputs a first selection confirmation operation to the electronic device for the first and third first face groups 10a and 10a in FIG26(b).

[0364] As shown in FIG26( b ), the first selection window 24 may further include a first selection confirmation control 244. The user may operate the first selection confirmation control 244 as a fifth operation inputted to the voice assistant application for the selected at least one first face group 10a.

[0365] Alternatively, the user may utter a voice message “selected” to the smartphone as a fifth operation inputted by the user to the voice assistant application for the selected at least one first face group 10 a.

[0366] The electronic device responds to the user's first selection confirmation operation on at least one first face group 10a and then executes S16. For example, the electronic device responds to the user's fifth operation on the first and third first face groups 10a in the first selection window 24, determines the face group 10 corresponding to the tender moment, and then executes S16.

[0367] The above is the specific process of S14 and S15 when the at least one face group acquired by the voice assistant application in S14 only includes the first face group 10a.

[0368] S143: The electronic device displays an operation page of the target video theme, where the operation page includes a second video creation entry.

[0369] Among the multiple face groups 10 acquired by the voice assistant application, the multiple face groups 10 include a second face group 10b (at least one of the multiple characters corresponding to the face group includes naming data, as shown in (c) in Figure 1).

[0370] In some examples, in response to the user's second operation on a warm moment card, the voice assistant application switches the display screen of the electronic device from the video creation window 22 shown in FIG. 25( a ) to an operation window 23 showing a family photo including N (N is a positive integer greater than 1) video creation entries (second video creation entries) 231 b, as shown in FIG. 25( c ). Each second video creation entry 231 b is associated with at least one person having naming data, and different second video creation entries 231 b correspond to different people.

[0371] For example, one second video creation entry 231b is associated with three second face groups 10b: a child, a father, and a mother. Another second video creation entry 231b is associated with two second face groups 10b: a child and a father. Another second video creation entry 231b is associated with two second face groups 10b: a child and a mother. Each of these three second video creation entries 231b is associated with at least one second face group 10b with named data, and the second face groups 10b corresponding to the three second video creation entries 231b are not identical.

[0372] Exemplarily, when all characters corresponding to at least one face group have naming data, the voice assistant application responds to the user's second operation on the personal photo card, and the display screen of the electronic device switches from the video production window 22 shown in Figure 25 (a) to the operation window 23 including N second video creation entries 231b as shown in Figure 25 (c).

[0373] In the case where the operation window 23 of the target video theme is displayed as shown in (c) of FIG. 25 , as shown in FIG. 6 , S15 in the process may include S155 .

[0374] S155: The user inputs a sixth operation of creating an entry for the target video to the electronic device.

[0375] As shown in FIG. 25( c ), the operation window 23 of the tender moment has N video creation entries (second video creation entries) 231 b .

[0376] Taking the second video creation entry 231b including the entry recommendation text 2312 as an example, the user can send a voice message to the electronic device saying "Create a heartwarming video of a child and his father playing" or click on the corresponding video creation entry as the user inputs the sixth operation (second selection operation) to the voice assistant application for the second second video creation entry 231b in the operation window 23 of the warm moment shown in Figure 25 (c). The display screen of the electronic device switches from the operation window 23 of the warm moment shown in Figure 27 (a) to the display shown in Figure 27 (b), and the electronic device determines the second video creation entry 231b selected by the user.

[0377] Because each second video creation entry 231b in the operation window 23 for the tender moment shown in FIG27(a) corresponds to at least one second face group 10b, the second selection operation on the second second video creation entry 231b can determine at least one second face group 10b corresponding to the tender moment, which is actually similar to the method of determining at least one first face group 10a corresponding to the first video creation entry 231a in the above-mentioned steps S151-S154. Therefore, after S155, the electronic device can execute S16.

[0378] The above is the specific process of S14-S15 when the at least one face group acquired by the voice assistant application in S14 only includes the second face group 10b.

[0379] In other examples, the voice assistant application responds to the user's second operation on the warm moment card, and the display screen of the electronic device switches from the video creation window 22 shown in Figure 25 (a) to the operation window 23 shown in Figure 25 (d), which includes N second video creation entries 231b and 1 first video creation entry 231a. Each second video creation entry 231b is associated with at least one character with naming data, and different second video creation entries 231b correspond to different characters. The first video creation entry 231a is associated with multiple characters without naming data.

[0380] Exemplarily, among the characters corresponding to at least one face group, some characters have naming data and other characters lack naming data, the voice assistant application responds to the user's second operation on the warm moment card, and the display screen of the electronic device switches from the video production window 22 shown in Figure 25 (a) to the operation window 23 shown in Figure 25 (d), including N second video creation entries 231b and 1 first video creation entry 231a.

[0381] It should be noted that the face group 10 corresponding to the second video creation entry 231 b only has the second face group 10 b and does not correspond to the first face group 10 a .

[0382] The process of the user selecting the first video creation entry 231a in the operation window 23 as shown in (d) of Figure 25 can refer to the description of S151-S154 above; the process of the user selecting the second video creation entry 231b in the operation window 23 as shown in (d) of Figure 25 can refer to the description of S155 above, which will not be repeated here.

[0383] In addition, since tender moments can correspond to multiple characters, the third face group can be suitable for tender moment video themes. For example, when the third face group 10c is used to determine the face group 10 corresponding to the composite video, the first face group 10a and the second face group 10b may not be needed.

[0384] For example, if the electronic device includes multiple persons with named data 12 among the multiple persons corresponding to at least one face group 10 obtained from the photo album application, the multiple persons with named data 12 may be combined to form multiple third face groups 10c. The creation window 23 may display second video creation entries 231b, each second video creation entry 231b corresponding to a third face group 10c.

[0385] Of course, the production window 23 may also display the first video creation entry 231 a on the basis of displaying the second video creation entry 231 b , where the first video creation entry 231 a corresponds to a plurality of characters that are missing naming data.

[0386] It should be noted that the third face group 10c corresponding to the second video creation entry 231b all corresponds to a person with named data. After determining the face group, the electronic device may execute S16.

[0387] S16: The electronic device displays a third selection window.

[0388] It is understandable that when the display screen of the electronic device displays the first selection window 24 as shown in FIG. 28( a ), after the first face group 10a corresponding to the tender moment video theme is determined in response to the first selection confirmation operation, the display screen of the electronic device may switch to display the third selection window 25 as shown in FIG. 28( c ). Alternatively, when the display screen of the electronic device displays the operation window 23 of the tender moment as shown in FIG. 28( b ), after the at least one second face group 10b corresponding to the tender moment video theme is determined in response to the second selection operation, the display screen of the electronic device may switch to display the third selection window 25 as shown in FIG. 28( c ).

[0389] The third selection window 25 may display multiple portrait materials 251 for selection. The portrait materials 251 for selection may be images or videos, and the embodiments of the present application are not limited thereto. It should be noted that the multiple portrait materials 251 for selection displayed in the third selection window 25 are all portrait materials of the same face group 10; or, the multiple portrait materials 251 for selection displayed in the third selection window 25 are all the intersection of portrait materials of the same multiple people (the second face group 10b corresponding to the second selection operation, or the first face group 10a corresponding to the first selection confirmation operation).

[0390] S17: The user inputs a seventh operation to the electronic device for one or more portrait materials to be selected.

[0391] For example, the user can speak "Select All" to the smartphone as the seventh operation input to the voice assistant application for one or more portrait materials 251 to be selected. At this time, the display screen of the electronic device switches from the third selection window 25 shown in Figure 16 (a) to that shown in Figure 16 (b), and the third selection control 252 located on each material 251 is displayed from an unselected display state to a selected display state.

[0392] It should be noted that the third selection window 25 shown in FIG28(c) may also include the third extension control 252. The user may operate the third extension control 252 to enter the character material interface and select multiple character materials to be selected.

[0393] S18: The user inputs an eighth operation on one or more portrait materials to be selected to the electronic device. For example, the user inputs an eighth operation on the selected material to the electronic device.

[0394] As shown in FIG. 28( c ), the third selection window 25 may further include a third selection confirmation control 254 .

[0395] The user may utter a voice message “selected” to the smartphone as an eighth operation inputted by the user to the voice assistant application regarding the selected plurality of candidate portrait materials 251 .

[0396] In some feasible implementations, after the user inputs the eighth operation to the electronic device, as shown in FIG29(a), the voice assistant application may display a first conversation message 211d corresponding to the user's voice in the warm moment operation window 23 based on the user's voice. The first conversation message 211d may be displayed below the third selection window 25.

[0397] S19: The electronic device creates a video in response to the user's third selection confirmation operation on one or more portrait materials to be selected.

[0398] The electronic device responds to the user's third selection confirmation operation for one or more portrait materials 251 to be selected, and after determining multiple selected portrait materials, it can synthesize the video based on the aforementioned synthetic video function, which will not be repeated here.

[0399] After the electronic device synthesizes the video, the display screen of the electronic device switches from the third selection window 25 shown in Figure 29 (a) to the video operation window 23 of the warm moment shown in Figure 29 (b), and the synthesized video 26 is displayed in the video operation window 23 of the warm moment.

[0400] The above S11-S19 are all explained by taking the warm moment video theme as the target video theme as an example.

[0401] The following is an example of taking the growth-themed video theme as the target video theme.

[0402] Please refer to FIG. 6 . The video generation method provided in the embodiment of the present application includes steps S11 to S19 .

[0403] S11: The user inputs a first operation for a composite video function to the electronic device.

[0404] S12: The voice assistant application displays a video production window on the display screen in response to the first operation.

[0405] In this embodiment, the specific process of S11-S12 can refer to the description of S11-S12 in the personal photo video theme, which will not be repeated here.

[0406] S13: The user inputs a second operation on the growth theme card to the electronic device.

[0407] For example, when the electronic device displays the video production window 22, the user can send a voice message "I choose the growth theme" to the smartphone, or the user can click on the theme card 221 corresponding to the "Growth Theme" as the user inputs a second operation for the growth theme card (target theme card) to the voice assistant application.

[0408] S14: The electronic device responds to the user's second operation on the growth theme card and displays an operation window for the warm moment video theme. For example, the electronic device responds to the user's operation on the growth theme card and displays an operation window for the growth theme.

[0409] Before displaying the operation window for the growth-themed video, the voice assistant application of the electronic device can obtain at least one face group corresponding to multiple images in the photo album application. For example, the photo album application provides at least one face group to the voice assistant application. The at least one face group may include the first face group 10a but not the second face group 10b, or may include the second face group 10b but not the first face group 10a.

[0410] Before displaying the operation window for the growth-themed video, the voice assistant application of the electronic device can obtain at least one face group corresponding to multiple images in the photo album application. For example, the photo album application provides at least one face group to the voice assistant application. The at least one face group may include the first face group 10a but not the second face group 10b, the second face group 10b but not the first face group 10a, or both the first face group 10a and the second face group 10b.

[0411] If at least one face group includes the first face group 10a but does not include the second face group 10b, the operation window displayed by the electronic device may include a first video creation entry corresponding to the first face group 10a. If at least one face group includes the second face group 10b but does not include the first face group 10a, the operation window displayed by the electronic device may include a second video creation entry corresponding to the second face group 10b. If both the first face group 10a and the second face group 10b are included, the operation window displayed by the electronic device may include only the second video creation entry corresponding to the second face group 10b, or may include both the second video creation entry corresponding to the second face group 10b and the first video creation entry corresponding to the first face group 10a.

[0412] As shown in FIG. 6 , in some examples, in order to distinguish whether the operation window has a second video creation entry, S14 may include S141 - S143 .

[0413] S141: The electronic device determines whether at least one face group includes a second face group.

[0414] S141 is equivalent to determining whether there is a person with naming data among the persons corresponding to at least one face group.

[0415] In a case where at least one face group does not include the second face group, and the characters corresponding to at least one face group are all missing naming data, the electronic device executes S142.

[0416] In a case where the at least one face group includes the second face group, and at least one person among the persons corresponding to the at least one face group has naming data, the electronic device executes S143.

[0417] S142: The electronic device displays an operation page of the video theme, where the operation page includes a first video creation entry.

[0418] In the case where each of the multiple face groups acquired by the voice assistant application is a first face group 10a (the characters corresponding to the face groups do not include naming data, as shown in FIG1(b)), the voice assistant application responds to the user's second operation on the growth theme card, and the electronic device's display screen switches from the video creation window 22 shown in FIG30(a) to an operation window 23 of the growth theme, as shown in FIG30(b), which displays a video creation entry (first video creation entry) 231a. The first video creation entry 231a is associated with multiple first face groups 10a.

[0419] In the case where the operation window of the target video theme is displayed as shown in (b) of FIG. 30 , as shown in FIG. 6 , S15 in the process may include S151 - S154 .

[0420] S151: The user inputs a third operation of creating an entry for the first video to the electronic device.

[0421] The user may send a voice message of "make a happy growth video" to the smartphone or click on the first video creation entry 231a as a third operation inputted by the user to the voice assistant application for the first video creation entry 231a.

[0422] S152: The electronic device displays a first selection window in response to the user's first selection operation for creating an entry for a target video.

[0423] The voice assistant application in the electronic device responds to the user's third operation to create an entry 231a for the first video, and the display screen of the electronic device switches from the operation window 23 of the growth theme shown in Figure 31 (a) to the first selection window 24 as shown in Figure 31 (b).

[0424] First selection window 24 may include one or more facial images 11, with different facial images 11 corresponding to different characters and first facial groups 10a, and each character does not include naming data 12. As shown in FIG21(b), if a character does not include naming data 12, the text "Add Name" is displayed below facial image 11 to encourage the user to name the character.

[0425] In this embodiment, the text "Add Name" in the first selection window 24 can also be used as a naming control to perform the process of adding naming data to the first face group 10a. The process of adding naming data is basically the same as the process shown in Figure 19 and will not be repeated here.

[0426] In the growth theme, the characters displayed in the first selection window 24 need to include children.

[0427] S153: The user inputs a fourth operation for at least one face group 10 to the electronic device.

[0428] As shown in FIG31(b), the first selection window 24 may further include multiple first selection controls 242. The multiple first selection controls 242 correspond one-to-one to the multiple facial images 11, and each first selection control 242 is located in the display area of ​​the facial image 11. The user can send a voice message to the smartphone saying "select the second and fourth" or click on the selection controls 242 corresponding to the multiple facial images 11, as the user inputs a fourth operation for the two first face groups 10a to the voice assistant application. At this time, the display screen of the electronic device displays the image shown in FIG31(b), with the first selection controls 242 corresponding to the second first face group 10a and the fourth first face group 10a in the first selection window 24 changing from an unselected display state to a selected display state.

[0429] It should be noted that the first selection window 24 shown in FIG. 31( b ) may also include the aforementioned first expansion control 241. The user may operate the first expansion control 241 to enter a selection interface and select multiple facial images 11 from the first face group 10a. The user is required to select at least one person in the selection interface. If the number of people selected by the user is less than one, the electronic device that determines the user's operation does not execute any steps.

[0430] The first face group 10 a selected by the user in the first selection window 24 needs to include at least one first face group 10 a of a child.

[0431] S154: The user inputs a fifth operation to the electronic device for at least one first face group. For example, the user inputs a first selection confirmation operation to the electronic device for the second first face group 10a and the fourth first face group 10a in FIG31(b).

[0432] As shown in FIG31( b ), the first selection window 24 may further include a first selection confirmation control 244. The user may operate the first selection confirmation control 244 as a fifth operation inputted to the voice assistant application for the selected at least one first face group 10a.

[0433] Alternatively, the user may utter a voice message “selected” to the smartphone as a fifth operation inputted by the user to the voice assistant application for the selected at least one first face group 10 a.

[0434] The electronic device responds to the user's first selection confirmation operation on at least one first face group 10a and then executes S16. For example, the electronic device responds to the user's fifth operation on the second and fourth first face groups 10a in the first selection window 24, determines the face group 10 corresponding to the growth theme, and then executes S16.

[0435] The above is the specific process of S14 and S15 when the at least one face group acquired by the voice assistant application in S14 only includes the first face group 10a.

[0436] S143: The electronic device displays an operation page of the target video theme, where the operation page includes a second video creation entry.

[0437] Among the multiple face groups 10 acquired by the voice assistant application, the multiple face groups 10 include a second face group 10b (at least one of the multiple characters corresponding to the face group includes naming data, as shown in (c) in Figure 1).

[0438] In some examples, in response to the user's second operation on the growth-themed card, the voice assistant application switches the display screen of the electronic device from the video creation window 22 shown in FIG. 30( a ) to an operation window 23 of the growth-themed card, as shown in FIG. 30( c ), which displays N (N is a positive integer greater than 1) video creation entries (second video creation entries) 231 b. Each second video creation entry 231 b is associated with at least one second face group 10 b having naming data, and different second video creation entries 231 b correspond to different second face groups 10 b.

[0439] Exemplarily, when all characters corresponding to at least one face group have naming data, the voice assistant application responds to the user's second operation on the personal photo card, and the display screen of the electronic device switches from the video production window 22 shown in (a) of Figure 30 to the operation window 23 including N second video creation entries 231b as shown in (c) of Figure 30.

[0440] In the case where the operation window 23 of the target video theme is displayed as shown in (c) of FIG. 30 , as shown in FIG. 6 , S15 in the process may include S155 .

[0441] S155: The user inputs a sixth operation (second selection operation) of creating an entry for the target video to the electronic device.

[0442] As shown in FIG. 30( c ), the operation window 23 of the growth theme has N video creation entries (second video creation entries) 231 b .

[0443] Taking the example of a second video creation entry 231b including entry recommendation text 2312, the user can send a voice message to the electronic device saying "generate a growth video of the child and mother" or click on the corresponding first video creation entry as the sixth operation inputted by the user to the voice assistant application for the second second video creation entry 231b in the growth-themed operation window 23 shown in FIG30(c). The display screen of the electronic device switches from the growth-themed operation window 23 shown in FIG32(a) to the display shown in FIG32(b), indicating that the electronic device has determined the second video creation entry 231b selected by the user.

[0444] It should be noted that each second video creation entry 231b corresponds to at least one second face group 10b for children, and may also correspond to a second face group 10b for adults. The entry material 2311 of the second video creation entry 231b may include portrait images of one or more people, where the portrait images must include a child's face. The entry recommendation text 2312 may include the naming data of one or more people, where the naming data must include the naming data of a child.

[0445] Since each second video creation entry 231b in the operation window 23 of the growth theme shown in FIG32(a) corresponds to at least one second face group 10b, the second selection operation on the second second video creation entry 231b can determine at least one second face group 10b corresponding to the growth theme, which is actually similar to the method of determining at least one first face group 10a corresponding to the first video creation entry 231a in the above-mentioned steps S151-S154. Therefore, after S155, the electronic device can execute S16.

[0446] The above is the specific process of S14-S15 when the at least one face group acquired by the voice assistant application in S14 only includes the second face group 10b.

[0447] In other examples, the voice assistant application responds to the user's second operation on the growth theme card, and the display screen of the electronic device switches from the video production window 22 shown in Figure 30 (a) to the operation window 23 shown in Figure 30 (d), which includes N second video creation entries 231b and 1 first video creation entry 231a. Each second video creation entry 231b is associated with at least one character with naming data, and different second video creation entries 231b correspond to different characters. The first video creation entry 231a is associated with multiple characters without naming data.

[0448] Exemplarily, among the characters corresponding to at least one face group, some characters have naming data and other characters lack naming data, the voice assistant application responds to the user's second operation on the warm moment card, and the display screen of the electronic device switches from the video production window 22 shown in Figure 30 (a) to the operation window 23 shown in Figure 30 (d), including N second video creation entries 231b and 1 first video creation entry 231a.

[0449] It should be noted that the face group 10 corresponding to the second video creation entry 231 b only has the second face group 10 b and does not correspond to the first face group 10 a .

[0450] The process of the user selecting the first video creation entry 231a in the operation window 23 as shown in (d) in Figure 30 can refer to the description of S151-S154 above; the process of the user selecting the second video creation entry 231b in the operation window 23 as shown in (d) in Figure 30 can refer to the description of S155 above, which will not be repeated here.

[0451] In addition, since the growth theme can correspond to multiple characters, the third face group can be applied to the growth theme video theme. For example, when the third face group 10c is used to determine the face group 10 corresponding to the synthesized video, the first face group 10a and the second face group 10b may not be needed.

[0452] For example, if the electronic device includes multiple persons with named data 12 among the multiple persons corresponding to at least one face group 10 obtained from the photo album application, the multiple persons with named data 12 may be combined to form multiple third face groups 10c. The creation window 23 may display second video creation entries 231b, each second video creation entry 231b corresponding to a third face group 10c.

[0453] Of course, the production window 23 may also display the first video creation entry 231 a on the basis of displaying the second video creation entry 231 b , where the first video creation entry 231 a corresponds to a plurality of characters that are missing naming data.

[0454] It should be noted that the third face group 10c corresponding to the second video creation entry 231b all corresponds to a person with named data. After determining the face group, the electronic device may execute S16.

[0455] S16: The electronic device displays a third selection window.

[0456] It can be understood that when the display screen of the electronic device displays the first selection window 24 as shown in Figure 33 (a), after the first face group 10a corresponding to the growth-themed video theme is determined in response to the first selection confirmation operation, the display screen can switch to display the third selection window 25 as shown in Figure 33 (c). Alternatively, when the display screen of the electronic device displays the growth-themed operation window 23 as shown in Figure 33 (b), after the at least one second face group 10b corresponding to the growth-themed video theme is determined in response to the second selection operation, the display screen can switch to display the third selection window 25 as shown in Figure 33 (c).

[0457] The third selection window 25 may display a plurality of portrait materials 251 to be selected. The portrait material 251 to be selected may be a picture or a video, and the embodiments of the present application do not limit this. It should be noted that the plurality of portrait materials 251 to be selected displayed in the third selection window 25 are all portrait materials of the same face group 10; or, the plurality of portrait materials 251 to be selected displayed in the third selection window 25 are all the intersection of portrait materials of the same plurality of persons (the second face group 10b corresponding to the second selection operation, or the first face group 10a corresponding to the first selection confirmation operation). Moreover, each portrait material 251 to be selected needs to include a facial image of a child.

[0458] In the third selection window 25 shown in FIG. 33( c ), a plurality of portrait materials 251 to be selected are arranged in the order of the acquisition period of the materials. It can be understood that they are arranged in the order of time from the youngest child to the older child.

[0459] In some examples, in the third selection window 25 shown in FIG33(c), the number of selectable portrait materials 251 corresponding to each acquisition period is positively correlated with the number of materials captured by the electronic device during the acquisition period. For example, if the number of materials captured in August is large and the number of materials captured in September is small in the same year, the third selection window 25 shown in FIG33(c) may display more materials captured in August and less materials captured in September. This can help users select more materials in the growth process and generate videos that are more in line with the theme of growth.

[0460] S17: The user inputs a seventh operation to the electronic device for one or more portrait materials to be selected.

[0461] For example, the user can speak "Select All" to the smartphone as the seventh operation input to the voice assistant application for one or more portrait materials 251 to be selected. At this time, the display screen of the electronic device switches from the third selection window 25 shown in Figure 17 (a) to that shown in Figure 17 (b), and the third selection control 252 located on each material 251 is displayed from an unselected display state to a selected display state.

[0462] It should be noted that the third selection window 25 shown in FIG33( c ) may also include the third extension control 252. The user may operate the third extension control 252 to enter the character material interface and select multiple character materials to be selected.

[0463] S18: The user inputs an eighth operation on one or more portrait materials to be selected to the electronic device. For example, the user inputs an eighth operation on the selected material to the electronic device.

[0464] As shown in FIG. 33( c ), the third selection window 25 may further include a third selection confirmation control 254 .

[0465] The user may utter a voice message “selected” to the smartphone as a third selection confirmation operation inputted to the voice assistant application by the user for the selected plurality of candidate human portrait materials 251 .

[0466] In some feasible implementations, after the user inputs the third selection confirmation operation into the electronic device, as shown in FIG34(a), the voice assistant application may display a first conversation message 211d corresponding to the user's voice in the growth-themed operation window 23 based on the user's voice. The first conversation message 211d may be displayed below the third selection window 25.

[0467] S19: The electronic device creates a video in response to the user's third selection confirmation operation on one or more portrait materials to be selected.

[0468] The electronic device responds to the user's third selection confirmation operation for one or more portrait materials 251 to be selected, and after determining multiple selected portrait materials, it can synthesize the video based on the aforementioned synthetic video function, which will not be repeated here.

[0469] After the electronic device synthesizes the video, the display screen of the electronic device switches from the third selection window 25 shown in Figure 34 (a) to the growth-themed video operation window 23 shown in Figure 34 (b), and the synthesized video 26 is displayed in the growth-themed video operation window 23.

[0470] The above S11-S19 are all explained by taking the growth-themed video theme as the target video theme as an example.

[0471] The above describes the specific process of the video generation method in detail by taking the video themes of "personal portrait", "family photo", "warm moment" and "growth theme" as examples. The video synthesis process of other video themes can refer to the description of the above four examples and will not be repeated here.

[0472] An embodiment of the present application also provides a chip system (e.g., a system on a chip (SoC)). As shown in Figure 35, the chip system includes at least one processor 701 and at least one interface circuit 702. The processor 701 and the interface circuit 702 can be interconnected via lines. For example, the interface circuit 702 can be used to receive signals from other devices (e.g., a memory of an electronic device). For another example, the interface circuit 702 can be used to send signals to other devices (e.g., a processor 701 or a camera of an electronic device). Exemplarily, the interface circuit 702 can read instructions stored in the memory and send the instructions to the processor 701. When the instructions are executed by the processor 701, the electronic device can execute the various steps in the above embodiments. Of course, the chip system can also include other discrete components, which is not specifically limited in the embodiment of the present application.

[0473] An embodiment of the present application also provides a computer-readable storage medium, which includes computer instructions. When the computer instructions are executed on the above-mentioned electronic device, the electronic device executes the various functions or steps executed by the electronic device in the above-mentioned method embodiment.

[0474] The present application also provides a computer program product, which, when executed on a computer, enables the computer to execute the functions or steps executed by the electronic device in the above method embodiment. For example, the computer may be the above electronic device.

[0475] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0476] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0477] The units described as separate components may or may not be physically separate, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0478] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0479] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0480] The above content is only a specific embodiment of this application, but the scope of protection of this application is not limited to this. Any changes or replacements within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A video generation method, characterized in that, Applied to an electronic device, the electronic device includes multiple personal video materials and at least one face group divided according to face images, and the personal video materials within one face group contain the faces of the same person; the method includes: The electronic device displays a video production window; multiple theme cards are displayed in the video production window, and different theme cards correspond to different video themes; The electronic device, in response to the user's operation of selecting a target theme card from the multiple theme cards, displays an operation window for the target video theme; wherein, when there is no naming data for the people corresponding to the at least one face group, the operation window includes a first video creation entry, and when there is at least one person with naming data among the people corresponding to the at least one face group, the operation window includes a second video creation entry; the target video theme is the video theme corresponding to the target theme card; The electronic device, in response to the operation on the first video creation entry, displays a first selection window, and the first selection window includes the face images of at least one person; The electronic device, in response to the user's operation of selecting a face image, generates a video of the person corresponding to the selected face image; Or, The electronic device, in response to the operation on the second video creation entry, generates a video of the person corresponding to the second video creation entry.

2. The method according to claim 1, wherein The operation window includes a second video creation entry, including: The operation window includes 1 first video creation entry and N second video creation entries; the first video creation entry corresponds to the person without naming data, and each second video creation entry corresponds to a person with naming data, and the people corresponding to different second video creation entries are not completely the same; N is a positive integer greater than 1.

3. The method according to claim 1 or 2, characterized in that, The electronic device, in response to the user's operation of selecting a face image, generates a video of the person corresponding to the selected face image, including: The electronic device, in response to the user's operation on Q face images in the first selection window, generates a video; the video screen simultaneously displays the people corresponding to the Q face images, Q is a positive integer, and the value of Q is associated with the target video theme.

4. The method according to any one of claims 1 to 3, characterized in that The electronic device, in response to the user's operation of selecting a face image, generates a video of the person corresponding to the selected face image, including: The electronic device, in response to the user's operation of selecting a face image in the first selection window, displays a third selection window; the third selection window displays multiple candidate personal video materials, and each candidate personal video material is the intersection of the personal video materials corresponding to the face images selected by the user in the first selection window, and the personal video materials include pictures and / or videos; The electronic device, in response to the user's operation of selecting one or more of the candidate personal video materials in the third selection window, generates a video.

5. The method according to any one of claims 1-4, characterized in that, The first selection window further includes naming controls, and each naming control corresponds to the person of a face image; After displaying the first selection window, the method further includes: In response to an operation in which the user selects a naming control, the electronic device displays a naming edit window; When the electronic device receives naming data edited by the user through the naming edit window, the electronic device returns the first selection window and uses the naming data as the naming data of the person corresponding to the naming control selected by the user.

6. The method according to claim 5, wherein The electronic device responding to an operation in which the user selects a naming control and displaying a naming edit window includes: In response to an operation in which the user selects a naming control, the photo album application displays a naming edit window; After the electronic device receives the naming data edited by the user through the naming edit window, the method further includes: The photo album application uses the naming data as the naming data of the person corresponding to the naming control selected by the user.

7. The method according to claim 5 or 6, characterized in that, The naming edit window includes a name input area for the user to input name sub-data of a person, and the name sub-data belongs to the naming data; The photo album application using the naming data as the naming data of the person corresponding to the naming control selected by the user includes: The photo album application uses the name sub-data as the naming data of the person corresponding to the naming control selected by the user; and / or The naming edit window includes a relationship input area for the user to input relationship sub-data between the person and the owner of the electronic device, and the relationship sub-data belongs to the naming data; The photo album application using the naming data as the naming data of the person corresponding to the naming control selected by the user includes: The photo album application uses the relationship sub-data as the naming data of the person corresponding to the naming control selected by the user.

8. The method according to any one of claims 1-7, characterized in that, The electronic device generating a video of the person corresponding to the second video creation entry selected by the user in response to an operation in which the user selects the second video creation entry includes: In response to an operation in which the user selects the second video creation entry, the electronic device displays a third selection window; the third selection window displays a plurality of candidate person materials, and each candidate person material is the intersection of the person materials of the person corresponding to the second video creation entry selected by the user, and the person materials include pictures and / or videos; In response to an operation in which the user selects one or more of the candidate person materials, the electronic device generates a video.

9. The method according to claim 4 or 8, characterized in that, The third selection window displaying a plurality of candidate person materials includes: The electronic device arranges a plurality of candidate person materials in the third selection window in the order of the time periods when the person materials are acquired; wherein, the number of candidate person materials displayed in each acquisition time period is positively correlated with the number of person materials photographed by the electronic device during the acquisition time period.

10. The method according to any one of claims 1-9, characterized in that The first video creation entry includes a first recommended text, and the first recommended text is a preset recommended text corresponding to the video theme; and / or The second video creation entry includes a second recommended text, and the second recommended text includes the naming data of the person corresponding to the second video creation entry.

11. The method according to any one of claims 1-10, characterized in that, The theme card displays a preset recommended text corresponding to the video theme.

12. The method according to any one of claims 1-11, characterized in that, The first video creation entry includes a first example image, and the first example image is an example image corresponding to the video theme; and / or The second video creation entry includes a second example image, and the second example image includes human pixel material of the person corresponding to the second video creation entry.

13. The method according to claim 12, wherein The operation window includes the second video creation entry; The target theme card includes a second example image of one of the second video creation entries.

14. The method according to any one of claims 1 to 13, characterized in that, Before the operation window for the target video theme is displayed, the method further includes: The electronic device obtains at least one face group corresponding to multiple pieces of human pixel material in the album application.

15. The method according to any one of claims 1-14, characterized in that, Before the electronic device displays the video production window, the method further includes: The electronic device responds to a user input operation and launches the voice assistant application; The voice assistant application displays the video production window.

16. An electronic device, characterized in that, The electronic device includes: a processor, a memory, and a display screen, and the processor is respectively coupled to the memory and the display screen; the memory is used to store computer program code; the computer program code includes computer instructions, and when the processor executes the above computer instructions, the electronic device executes the method according to any one of claims 1-15.

17. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes computer instructions, and when the computer instructions run on the electronic device, the electronic device executes the method according to any one of claims 1-15.

18. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, the steps of the method according to any one of claims 1-15 are implemented.

Images