Video generation method, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a video generation method, electronic equipment and a storage medium, which are applied to the technical field of terminals, and the method comprises the following steps: receiving a first operation triggered by a user to generate a target video corresponding to a target theme; in response to the first operation, displaying an interface of a voice assistant comprising at least one candidate object corresponding to the keyword of the target theme; receiving a second operation of the user on a target object in the at least one candidate object; in response to the second operation, a first material corresponding to the target object is displayed in an interface of the voice assistant, and the first material is an image or a video found by the voice assistant from an image library; receiving a third operation triggered by the user to generate the target video; and in response to the third operation, displaying a thumbnail of a target video in an interface of the voice assistant, the target video being generated according to the first material corresponding to the target object. Therefore, the video of the theme expected by the user can be quickly generated, the step of generating the video is simplified, and the user experience is better.

Description

[0001] This application claims the priority of the Chinese patent application filed with the State Intellectual Property Office on October 27, 2023, with application number 202311418278.6 and invention name “A video production method and electronic device based on large models”, all contents of which are incorporated by reference in this application. Technical Field

[0002] The embodiments of the present application relate to the field of terminal technology, and in particular to a video generation method, an electronic device, and a storage medium. Background Art

[0003] With the rapid popularity of short videos, users have an increasing need to quickly generate videos on electronic devices (such as mobile phones, tablets, etc.). However, the steps for users to generate videos based on images in the gallery are cumbersome and cannot quickly generate videos of the user's desired subject. Summary of the invention

[0004] The embodiments of the present application provide a video generation method, an electronic device, and a storage medium, which can quickly generate a video on a subject desired by a user, simplify the steps of generating a video, and provide a better user experience.

[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, which is applied to an electronic device including a voice assistant. The video generation method may include:

[0007] Receive a first operation triggered by a user to generate a target video corresponding to a target topic; in response to the first operation, display the interface of the voice assistant, the interface of the voice assistant includes at least one candidate object corresponding to the keyword of the target topic; receive a second operation of the user on a target object among the at least one candidate object; in response to the second operation, display a first material corresponding to the target object in the interface of the voice assistant, the first material being an image or video found by the voice assistant from the gallery of the electronic device; receive a third operation triggered by the user to generate a target video; in response to the third operation, display a thumbnail of the target video in the interface of the voice assistant, the target video being generated based on the first material corresponding to the target object.

[0008] It can be understood that the electronic device receives the user's instructions to generate the target video, and the voice assistant interacts with the user. The entire interactive process of generating the target video can be displayed in the voice assistant's interface, which not only simplifies the steps of generating the video, but also helps to improve the user experience.

[0009] In a possible implementation manner of the first aspect, during the process of displaying the first material corresponding to the target object in the first interface, the video generation method may further include:

[0010] Receive the user's fourth operation; in response to the fourth operation, display the target material after material processing of the first material corresponding to the target object in the interface of the voice assistant, where the material processing includes at least one of adding material, replacing material, deleting material or changing the order of materials.

[0011] It can be understood that after the first material corresponding to the target object is displayed in the voice assistant interface, the electronic device can add, replace, delete, change the order of the material, etc. to the first material, so that the target material after material processing is the material that satisfies the user.

[0012] In another possible implementation manner of the first aspect, the video generating method may further include:

[0013] If the user's fourth operation indicates the amount of material processing to be performed on the first material, the material processing is performed according to the indicated amount; if the user's fourth operation does not indicate the amount of material processing to be performed on the first material, the material processing is performed on the first material using a preset amount, and the preset amount is less than the quantity threshold; wherein, when the voice or text semantics corresponding to the fourth operation does not indicate the amount of material processing to be performed on the first material, the preset amount is the amount of the gear corresponding to the voice or text semantics, and different gears correspond to different amounts.

[0014] It can be understood that, when the electronic device receives a clear instruction from the user on the amount of materials to be processed, the indicated amount is used to process the materials. For example, the user voice instructs "delete ten drawing materials", and the electronic device deletes ten materials from the first material. In the case where the user instruction operation received by the electronic device does not indicate the amount of materials to be processed, a preset amount of the first material is used for material processing. For example, if the user's voice instruction is "delete most of the materials", the electronic device can delete half of the materials in the first material. For another example, if the user's voice instruction is "add a small amount of the second daughter's drawing materials", the electronic device can find the second daughter's drawing materials and add the second daughter's drawing materials to the first material, and the amount added is less than 30% of the amount of the first material.

[0015] In another possible implementation of the first aspect, the material processing is adding material, and the target material displayed in the interface of the voice assistant includes the total material after adding the second material to the target object, and the total material includes the first material and the second material.

[0016] It can be understood that the electronic device adds the second material to the first material in response to the user's operation, and the total material after adding is displayed in the interface of the voice assistant.

[0017] In another possible implementation manner of the first aspect, the material processing is adding material, and the video generation method may further include:

[0018] In response to the fourth operation, a first prompt message is displayed in the interface of the voice assistant, and the first prompt message is used to prompt that the total number of materials corresponding to the target object has reached an upper limit.

[0019] That is to say, when the electronic device receives an operation instructing the user to add materials, and the total number of materials corresponding to the target material reaches the upper limit, the voice assistant interface can prompt the user by displaying a prompt message.

[0020] In another possible implementation manner of the first aspect, the video generating method may further include:

[0021] Receive the user's fifth operation; in response to the fifth operation, display the third material in the interface of the voice assistant, the third material including the material after deleting part of the material in the total material and then adding the fourth material.

[0022] It can be understood that when the number of total materials corresponding to the target object reaches an upper limit, the electronic device can respond to the user's operation, delete part of the total materials, and then add other materials.

[0023] In another possible implementation of the first aspect, the material processing is replacement material, and the target material displayed in the interface of the voice assistant includes a sixth material obtained by replacing part of the material in the target object with the fifth material, and the sixth material includes the fifth material and part of the first material.

[0024] That is to say, the electronic device can replace part of the materials of the target object in response to the user's operation, so that the materials of the target object after replacement are all materials that satisfy the user.

[0025] In another possible implementation manner of the first aspect, the material processing is to delete the material, and the target material displayed in the interface of the voice assistant includes part of the first material after the material is deleted.

[0026] That is to say, when the target material displayed in the voice assistant interface is material that the user does not like, the electronic device can delete part of the target material in response to the user's operation, so that the deleted materials are all materials that the user is satisfied with.

[0027] In another possible implementation of the first aspect, the material processing is to change the order of the materials, and the target material displayed in the interface of the voice assistant includes a seventh material, the materials included in the seventh material are the same as the materials in the first material, and the order of the materials in the seventh material is different from the order of the materials in the first material.

[0028] That is to say, the electronic device can adjust the order of the materials of the target object in response to the user's operation, so that the video generated according to the adjusted material can better meet the user's needs and improve the user's experience.

[0029] In another possible implementation manner of the first aspect, the video generating method may further include:

[0030] Receive a sixth operation from the user; in response to the sixth operation, edit the object name of at least one candidate object displayed in the interface of the voice assistant, where the editing includes adding a name, modifying a name, or deleting a name.

[0031] In another possible implementation manner of the first aspect, the video generating method may further include:

[0032] Receive a seventh operation from a user; in response to the seventh operation, display a target interface, the target interface including at least one candidate object and other candidate objects; receive a second operation from a user on a target object among at least one candidate object, including: receive a second operation from a user on a target object among the candidate objects on the target interface.

[0033] In another possible implementation manner of the first aspect, the video generating method may further include:

[0034] If a deletion operation of the target video is received from the user, then in response to the deletion operation, the thumbnail of the target video is not displayed in the interface of the voice assistant; if a sharing operation of the target video is received from the user, then in response to the sharing operation, the sharing interface is displayed in the interface of the voice assistant.

[0035] That is to say, the electronic device can delete, share, and perform other operations on the generated target video in response to the user's trigger operation. As a result, the user does not need to download the target video to the local electronic device for storage to delete or share the target video, thereby improving the user experience.

[0036] If a template change operation of the target video is received from the user, the video after the template change is displayed in the interface of the voice assistant in response to the template change operation; if a duration adjustment operation of the target video is received from the user, the video after the duration adjustment is displayed in the interface of the voice assistant in response to the duration adjustment operation.

[0037] In another possible implementation manner of the first aspect, the first operation is a voice instruction operation, and after receiving the first operation of a user triggering generation of a target video corresponding to the target theme, the method may further include:

[0038] Perform semantic analysis on the first voice information of the first operation instruction; if the semantics corresponding to the first voice information are identified, determine the keywords corresponding to the target subject according to the identified semantics; if the semantics corresponding to the first voice information are not identified, or no candidate object matching the keyword is identified from the gallery, display a second prompt message in the interface of the voice assistant, and the second prompt message is used to prompt the adjustment of the voice instruction operation.

[0039] It can be understood that after the electronic device receives the operation of generating a video indicated by the user's voice, the electronic device performs semantic analysis on the received user's voice information. The electronic device can determine whether to recognize the keywords corresponding to the target topic based on the semantic analysis result.

[0040] In another possible implementation manner of the first aspect, after receiving a second operation of the user on a target object among the at least one candidate object, the video generation method may further include:

[0041] Perform semantic analysis on the second voice information of the second operation indication; if the semantics corresponding to the second voice information is not identified, or the target object matching the semantics corresponding to the second voice information is not identified from at least one candidate object, display a third prompt message in the interface of the voice assistant, and the third prompt message is used to prompt the user to select other candidate objects.

[0042] In another possible implementation of the first aspect, the candidate object is a person, and the image of the candidate object is displayed on the interface of the voice assistant, and the image of the candidate object includes a portrait; the target topic includes keywords related to the person.

[0043] In a second aspect, the present application provides an electronic device comprising: one or more processors; a memory; wherein one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the electronic device, enable the electronic device to perform a video generation method as described in any one of the above-mentioned first aspects.

[0044] In a third aspect, the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on an electronic device, the electronic device executes the video generation method as described in any one of the first aspects.

[0045] In a fourth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the video generation method as described in any one of the first aspects.

[0046] It can be understood that the electronic device described in the second aspect, the computer storage medium described in the third aspect, and the computer program product described in the fourth aspect are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0048] Figure 2 A software structure diagram of an electronic device provided in an embodiment of the present application;

[0049] Figure 3 An example of entering the intelligent interactive interface provided in the embodiment of the present application Figure 1 ;

[0050] Figure 4 An example of entering the intelligent interactive interface provided in the embodiment of the present application Figure 2 ;

[0051] Figure 5 An example of entering the intelligent interactive interface provided in the embodiment of the present application Figure 3 ;

[0052] Figure 6 An example of entering the intelligent interactive interface provided in the embodiment of the present application Figure 4 ;

[0053] Figure 7 An example of entering the intelligent interactive interface provided in the embodiment of the present application Figure 5 ;

[0054] Figure 8 An example of entering the intelligent interactive interface provided in the embodiment of the present application Figure 6 ;

[0055] Fig. 9 An example of a video generation method provided in an embodiment of the present application Figure 1 ;

[0056] Fig.10 An example of a video generation method provided in an embodiment of the present application Figure 2 ;

[0057] Fig.11 Example of editing the name of a portrait provided in the embodiment of the present application Figure 3 ;

[0058] Fig.12 An example diagram of adding material provided in an embodiment of the present application;

[0059] Fig.13 Another example diagram of adding materials provided in an embodiment of the present application;

[0060] Fig.14 An example diagram of a replacement material provided in an embodiment of the present application;

[0061] Fig.15 An example diagram of deleting material provided in an embodiment of the present application;

[0062] Fig.16 An example diagram of changing the order of materials provided in an embodiment of the present application;

[0063] Fig.17 An example diagram of editing a target video provided in an embodiment of the present application;

[0064] Fig.18 An example diagram of video generation provided in an embodiment of the present application;

[0065] Fig.19 Another example diagram of editing a target video provided in an embodiment of the present application;

[0066] Fig. 20 Another example diagram of editing a target video provided in an embodiment of the present application;

[0067] Fig.21 This is another example diagram of editing a target video provided in an embodiment of the present application. DETAILED DESCRIPTION

[0068] The technical solution in the embodiment of the present application will be described below in conjunction with the drawings in the embodiment of the present application. In the description of the embodiment of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0069] In the following, the terms "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 the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0070] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0071] The embodiment of the present application provides a video generation method, which is applied to an electronic device including a voice assistant, and the method includes: the voice assistant receives a first operation of a user; in response to the first operation, a first interface including at least one candidate object is displayed, and the voice assistant receives a second operation of the user on a target object in at least one candidate object; in response to the second operation, a first material corresponding to the target object is displayed in the first interface, and the first material is an image or video found by the voice assistant from the gallery of the electronic device; the voice assistant receives a third operation of the user triggering the generation of a target video; in response to the third operation, a thumbnail of the target video is displayed in the first interface, and the target video is generated according to the first material corresponding to the target object. Thus, the voice assistant can quickly generate the video desired by the user in response to the user's triggering operation, and improves the efficiency of video generation.

[0072] The first operation and the second operation of the user mentioned above may be manual triggering operations of the user or voice instruction operations of the user, which are not limited here.

[0073] Exemplarily, the video generation method provided in the embodiments of the present application can be applied to mobile phones, tablet computers, personal computers (PCs), personal digital assistants (PDAs), smart watches, netbooks, wearable electronic devices, augmented reality (AR) devices, virtual reality (VR) devices, vehicle-mounted devices, smart cars and other electronic devices with display screens, and the embodiments of the present application do not impose any restrictions on this.

[0074] like Figure 1 As shown, Figure 1 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0075] The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0076] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0077] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (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), etc. Different processing units may be independent devices or integrated into one or more processors.

[0078] The controller may be the nerve center and command center of the electronic device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

[0079] The processor 110 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0080] The charging management module 140 is used to receive charging input from a charger.

[0081] The power management module 141 is used to connect the battery 142 , the charging management module 140 and the processor 110 .

[0082] The wireless communication function of the electronic device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

[0083] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve the utilization of antennas. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.

[0084] The mobile communication module 150 can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the electronic device 100. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, and filter, amplify, and process the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the same device as at least some of the modules of the processor 110.

[0085] The wireless communication module 160 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 electronic device 100. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates the frequency of the electromagnetic wave signal and performs filtering, and sends the processed signal to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, modulate the frequency of it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.

[0086] In some embodiments, the antenna 1 of the electronic device 100 is coupled to the mobile communication module 150, and the antenna 2 is coupled to the wireless communication module 160, so that the electronic device 100 can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology, etc. GNSS may include the global positioning system (GPS), the global navigation satellite system (GLONASS), the Beidou navigation satellite system (BDS), the quasi-zenith satellite system (QZSS) and / or the satellite based augmentation system (SBAS).

[0087] The electronic device 100 implements the display function through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

[0088] The display screen 194 is used to display images, videos, etc. The display screen 194 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 or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1.

[0089] In an embodiment of the present application, the display screen 194 is used to display the display interface of the voice assistant. When the user interacts with the voice assistant to control the voice assistant to perform a certain function, the electronic device 100 receives the user's operation on the display interface of the voice assistant. In response to the user's operation, the display screen 194 displays the corresponding execution result.

[0090] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement a data storage function, such as storing music, video and other files in the external memory card.

[0091] The internal memory 121 can be used to store computer executable program codes, and the executable program codes include instructions. The processor 110 executes various functional applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121. The internal memory 121 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the electronic device 100 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 121 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.

[0092] The electronic device 100 can implement audio functions such as music playing and recording through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone jack 170D, and the application processor.

[0093] The audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. The audio module 170 can also be used to encode and decode audio signals. In some embodiments, the audio module 170 can be arranged in the processor 110, or some functional modules of the audio module 170 can be arranged in the processor 110.

[0094] The speaker 170A, also called a "speaker", is used to convert an audio electrical signal into a sound signal. The electronic device 100 can listen to music or listen to a hands-free call through the speaker 170A.

[0095] The receiver 170B, also called a "earpiece", is used to convert audio electrical signals into sound signals. When the electronic device 100 receives a call or voice message, the voice can be received by placing the receiver 170B close to the human ear.

[0096] Microphone 170C, also called "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can speak by putting their mouth close to microphone 170C to input the sound signal into microphone 170C. The electronic device 100 can be provided with at least one microphone 170C. In other embodiments, the electronic device 100 can be provided with two microphones 170C, which can not only collect sound signals but also realize noise reduction function. In other embodiments, the electronic device 100 can also be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify the sound source, realize directional recording function, etc.

[0097] Exemplarily, after the microphone 170C of the electronic device receives the voice information of the user's voice instruction to start the voice assistant, the electronic device starts the voice assistant. During the process of the user's voice interaction with the voice assistant, the microphone 170C can receive the voice information of the user's voice instruction to the voice assistant to perform a certain function.

[0098] The earphone interface 170D is used to connect a wired earphone and can be a USB interface 130 or a 3.5 mm open mobile terminal platform (OMTP) standard interface or a cellular telecommunications industry association of the USA (CTIA) standard interface.

[0099] The software system of the electronic device may adopt a layered architecture, an event-driven architecture, a micro-core architecture, a micro-service architecture, or a cloud architecture. The embodiment of the present invention takes the Android system of the layered architecture as an example to exemplify the software structure of the electronic device.

[0100] Figure 2 A software structure diagram of an electronic device provided in an embodiment of the present application.

[0101] It is understandable that the layered architecture divides the software into several layers, each with clear roles and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system may include an application layer (abbreviated as application layer), an application framework layer (abbreviated as framework layer), a system library, and a kernel layer.

[0102] The above-mentioned application layer may include a series of application packages.

[0103] like Figure 2 As shown, the application package may include system applications. System applications refer to applications that are set in the electronic device before leaving the factory. For example, the system applications may include programs such as voice assistant, camera, gallery, calendar, music, short message, memo, and weather.

[0104] In an embodiment of the present application, the voice assistant receives the interactive operation between the user and the voice assistant, and in response to the user's operation, displays the recommended candidate topics in the intelligent interactive interface of the voice assistant. The candidate topics include at least one topic recommended by the voice assistant based on the image recognition results of the image library.

[0105] The gallery stores multiple images, and the gallery can perform image recognition processing on the stored multiple images. For example, the gallery performs clustering processing on the multiple images so that the voice assistant can generate at least one candidate theme based on the image recognition results of the gallery.

[0106] It should be explained that in this application, the use of the voice assistant to generate at least one candidate theme based on the image recognition results of the gallery is only an example. In this solution, any application or module that can obtain images stored in the electronic device can perform the image recognition process, which is not limited here. The application package can also include third-party applications, which refer to applications that users install after downloading the installation package from the application store (or application market). For example, map applications, food delivery applications, reading applications (such as e-books), social applications, and travel applications.

[0107] The application framework layer provides an application programming interface (API) and a programming framework for the application programs in the application layer. The application framework layer includes some predefined functions.

[0108] like Figure 2 As shown, the application framework layer may include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, and the like.

[0109] The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.

[0110] Content providers are used to store and retrieve data and make it accessible to applications. The data can include videos, images, audio, calls made and received, browsing history and bookmarks, phone books, etc.

[0111] The view system includes visual controls, such as controls for displaying text, controls for displaying images, etc. The view system can be used to build applications. A display interface can be composed of one or more views. For example, a display interface including a text notification icon can include a view for displaying text and a view for displaying images.

[0112] The phone manager is used to provide communication functions for electronic devices, such as the management of call status (including answering, hanging up, etc.).

[0113] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0114] The notification manager allows applications to display notification information in the status bar. It can be used to convey notification-type messages and can disappear automatically after a short stay without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as notifications of applications running in the background, or a notification that appears on the screen in the form of a dialog window. For example, a text message is displayed in the status bar, a reminder sound is emitted, the phone vibrates, the indicator light flashes, etc.

[0115] Android Runtime includes core libraries and virtual machines. Android Runtime is responsible for scheduling and management of the Android system.

[0116] The core library consists of two parts: one part is the function that needs to be called by the Java language, and the other part is the Android core library.

[0117] The application layer and the application framework layer run in a virtual machine. The virtual machine executes the Java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform functions such as object life cycle management, stack management, thread management, security and exception management, and garbage collection.

[0118] The system library may include multiple functional modules, such as surface manager, media library, 3D graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL), etc.

[0119] The surface manager is used to manage the display subsystem and provide the fusion of two-dimensional and three-dimensional layers for multiple applications.

[0120] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

[0121] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

[0122] A 2D graphics engine is a drawing engine for 2D drawings.

[0123] The kernel layer is the layer between hardware and software. The kernel layer includes at least display driver, camera driver, audio driver and sensor driver.

[0124] In an embodiment of the present application, the electronic device receives a trigger operation of a user on an icon of a voice assistant, and in response to the trigger operation of the user, the display driver controls the display screen to display the display interface of the voice assistant.

[0125] Based on the above hardware architecture and software architecture, the video generation method provided in the embodiment of the present application is introduced below by taking the electronic device as a mobile phone as an example.

[0126] In one possible case of an embodiment of the present application, the mobile phone receives an operation of triggering the user to start the voice assistant, and in response to the user's triggering operation, the mobile phone starts the voice assistant. After the mobile phone receives an operation of triggering the user to enter the intelligent interaction interface, in response to the user's triggering operation, the mobile phone displays the intelligent interaction interface. The intelligent interaction interface is an interface provided by the voice assistant to interact with the user. For example, the user can manually trigger or voice-trigger the control of the voice assistant to execute corresponding instructions in the intelligent interaction interface. Using the intelligent film-making function of the voice assistant, users can create videos in the intelligent interaction interface.

[0127] In one possible case, the mobile phone receives an operation of the user controlling the voice assistant to generate a target video corresponding to the target theme on the intelligent interaction interface. In response to the user's triggering operation, the voice assistant finds at least one image corresponding to the target theme and displays at least one image corresponding to the target theme on the intelligent interaction interface. The voice assistant receives an operation of the user triggering the generation of the target video. In response to the user's triggering operation, the voice assistant generates a target video corresponding to the target theme based on at least one image corresponding to the target theme and displays a thumbnail of the target video on the intelligent interaction interface.

[0128] Among them, the target theme can be any theme, and the type of the target theme is not limited in the embodiment of the present application. For example, the target theme can be "generate a video of a child dancing", "generate a video of a child smiling", "generate a video of a pet playing", "generate a video of a weekend trip", etc. The object type and number of objects corresponding to the target theme are also not limited in this scheme. For example, the object type of the target theme can be a person, a pet, a place, etc. The number of objects can be one or more. At least one image corresponding to the target theme is an image recommended for display to the intelligent interactive interface of the voice assistant after the gallery performs image recognition processing on all images in the gallery. All images in the gallery can be target images of interest to the user. For example, the images in the gallery can be images taken by a mobile phone camera; or, images received in real time or in advance by the mobile phone from other electronic devices; or, images downloaded in real time or in advance from the network by the mobile phone, etc. In the embodiment of the present application, the images in the gallery are not limited to the above-mentioned acquisition method, and the acquisition method of the images in the gallery is not limited in the embodiment of the present application.

[0129] There are many ways for users to trigger the entry into the intelligent interactive interface.

[0130] In one embodiment, the user can wake up the voice assistant by voice, long pressing the power button, etc., and then trigger the intelligent interaction interface through the display interface of the voice assistant. For example, when the mobile phone is displaying the main interface, after the mobile phone receives the user's voice to wake up the voice assistant, it displays the intelligent interaction interface in response to the user's operation. Figure 3 Interface 300 shown in (a) of FIG. 1 . For example, after the mobile phone receives the voice message "Xiao Y Xiao Y" indicated by the user's voice to wake up the voice assistant, it displays Figure 3 Alternatively, after the mobile phone detects that the user has long pressed the power button 301, it displays Figure 3 Then, after receiving the user's voice instruction "generate a video of a child dancing from childhood to adulthood", the mobile phone displays Figure 3 The interface 302 shown in (b) in the figure switches to Figure 3 The intelligent interactive interface 303 shown in (c).

[0131] It can be understood that the voice assistant can provide users with a variety of functions, including the function of generating videos in this application. The display interfaces of different functions of the voice assistant are different. In addition, the voice assistant can provide users with an entrance to the display interface of the corresponding function through a menu to trigger the mobile phone to display the interface of the corresponding function.

[0132] For example, after the user triggers the voice assistant through voice instructions, the mobile phone displays the interface of the voice assistant's conversation function by default, which includes a menu (such as Figure 3 The menu includes the entrances to various functions, such as "dialogue", "recommendation", "smart film", "text creation", etc. After the voice assistant receives the user's left and right sliding or voice instructions, it can switch to display the interface corresponding to each function. It should be explained that due to the limited size of the display screen, Figure 3 The entrances to the functions in the area 304 shown in (c) are only examples, and the user can display the entrance controls of other functions by sliding left and right.

[0133] In one possible case, if the voice assistant determines that the gallery has clustered multiple images in the gallery into people, the intelligent interaction interface of the voice assistant displays at least one clustered person image. For example, Figure 3 The intelligent interactive interface 303 shown in (c) displays images of three children.

[0134] It needs to be explained that Figure 3 The interface displayed on the mobile phone and the various interfaces of the voice assistant shown in the figure are only described as examples, and the user's triggering operation on the mobile phone is also only used as an example, and this is not limited in the embodiments of the present application.

[0135] In another embodiment, the user can start the voice assistant by triggering the voice assistant icon on the mobile phone desktop, and then trigger the intelligent interaction interface through the display interface of the voice assistant. Figure 4 In (a), the mobile phone displays a main interface 401, which includes a voice assistant icon 402. After the mobile phone receives a trigger operation of the user on the voice assistant icon 402, it displays Figure 4 After receiving the user's operation of sliding right on the recommendation interface 403, the mobile phone displays the following in response to the user's triggering operation: Figure 4 The intelligent interactive interface 404 shown in (c).

[0136] In another embodiment, the user can enter the intelligent interactive interface by triggering a desktop card. The desktop card can be generated by the voice assistant based on the image in the gallery. Figure 5 In (a), when the mobile phone displays the interface 501, the mobile phone receives a user's trigger operation on the desktop card 502 in the interface 501. If the mobile phone determines that the image library has been processed, it responds to the user's trigger operation and displays Figure 5 The voice assistant receives the user's sliding down the intelligent interactive interface 503, responds to the user's triggering operation, exits the intelligent interactive interface 503, and displays the interface 501, that is, Figure 5 The interface shown in (b) returns to Figure 5 The interface shown in (a) in the figure. When the voice assistant receives the user's trigger operation on the control 504 or the control 505, the intelligent interactive interface can be displayed.

[0137] If the mobile phone determines that the desktop card 502 is triggered for the first time, or the gallery does not include materials, or the gallery has not been image-recognized, or after the gallery has processed the images, the voice assistant has not recommended candidate themes based on the gallery's image recognition results, the mobile phone can display the voice assistant's recommendation interface, i.e., display Figure 5 Interface 506 shown in (c). The voice assistant receives the user's operation of sliding the interface 506 to the right, and displays the intelligent interactive interface of the voice assistant in response to the user's sliding operation.

[0138] In another embodiment, the user can enter the intelligent interactive interface by searching on the negative first screen. Figure 6 In (a), the mobile phone searches for smart photos in the interface 601 in response to the user's input operation, and the interface 601 displays a smart photo card 602. The mobile phone receives the user's trigger operation on the smart photo card 602. In some embodiments, after the image library is processed for image recognition, the smart interaction interface displayed by the mobile phone can display at least one candidate theme generated according to the image recognition result of the image library, such as Figure 6 As shown in (b), three candidate topics are displayed in the intelligent interaction interface 603.

[0139] In other embodiments, if the mobile phone determines that it is the first time to search for smart films on the negative one screen, or the gallery does not include the material, or the gallery has not been processed for image recognition, or after the gallery has processed the image, the voice assistant has not recommended a candidate theme based on the gallery's image recognition results, then the mobile phone can display the voice assistant's recommendation interface, that is, display Figure 6 Interface 604 shown in (c). The voice assistant receives the user's operation of sliding the interface 604 to the right, and displays the intelligent interactive interface of the voice assistant in response to the user's sliding operation.

[0140] In another embodiment, the user can trigger the intelligent interaction interface through the creation interface in the gallery. Figure 7 In (a), when the mobile phone displays the creation interface 701 of the gallery, the gallery receives the user's trigger operation on the "Smart Film" control 702.

[0141] In some embodiments, if the mobile phone determines that the creation interface is triggered for the first time, or the gallery does not include materials, or the gallery has not been image-recognized, or after the gallery has processed the images, the voice assistant has not recommended candidate themes based on the gallery's image recognition results, then the mobile phone may display the voice assistant's recommendation interface, that is, display Figure 7 Interface 703 shown in (b). The voice assistant receives the user's operation of sliding the interface 703 to the right, and displays the intelligent interactive interface of the voice assistant in response to the user's sliding operation.

[0142] In other embodiments, if the mobile phone determines that the image library has been processed, it displays Figure 7 In the interface 704 shown in (c), the voice assistant receives the user's trigger operation on the control 705 and displays the intelligent interactive interface of the voice assistant.

[0143] In another embodiment, the user can enter the intelligent interactive interface by triggering the gallery creation card displayed in the main interface. Since the gallery integrates the intelligent filming function entrance of the voice assistant, the gallery creation card displayed in the main interface can also include the intelligent filming function entrance. Figure 8 In (a), the gallery creation card 802 displayed in the interface 801 includes an entry for the smart photo creation function. When the mobile phone displays the interface 801, the mobile phone receives a user's trigger operation on the "smart photo creation" control in the gallery creation card 802. In response to the user's trigger operation, the mobile phone displays Figure 8 Similarly, the mobile phone receives the user's sliding down the smart interaction interface 803, responds to the user's triggering operation, exits the smart interaction interface 803, and returns to the main interface 801, that is, Figure 8 (b) Return to Figure 8 Middle (a).

[0144] If the voice assistant responds to the user's trigger to enter the intelligent interactive interface, and the voice assistant determines that the gallery has not performed image recognition processing, or, after the gallery has processed the image, the voice assistant has not recommended a candidate theme based on the gallery's image recognition results, the mobile phone can display the voice assistant's recommendation interface.

[0145] It can be understood that after the gallery performs image recognition processing on multiple images in the gallery, the smart interactive interface displayed by the mobile phone can display at least one candidate theme recommended by the voice assistant based on the image recognition results of the gallery, such as Figure 8 As shown in (b), three candidate topics are displayed in the intelligent interaction interface 803. However, when the voice assistant does not recommend a candidate topic based on the image recognition results of the image library, or the voice assistant determines that the image library has not performed image recognition processing on the image, the mobile phone displays Figure 8 Interface 805 shown in (c).

[0146] The following takes the example of a user waking up the voice assistant through voice instructions and triggering entry into the intelligent interactive interface as an example to introduce in detail the video generation process of an embodiment of the present application.

[0147] For example, when the mobile phone displays any interface, after the mobile phone receives the user's long press of the power button, it starts the voice assistant in response to the user's operation. After the mobile phone receives the user's voice instruction to generate a target video corresponding to the target theme (for example, the target theme is "generate a video of a child dancing from childhood to adulthood"), it displays Fig. 9 Interface 901 shown in (a). The target theme may correspond to one or more objects, and the object corresponding to the target theme is generated by the voice assistant according to the clustering result of the image library in the image library.

[0148] After the mobile phone receives the first voice message indicated by the user's voice, the mobile phone can perform semantic analysis on the first voice message to determine the target subject according to the result of the semantic analysis. In one case, when the mobile phone fails to recognize the semantics corresponding to the first voice message, a prompt message is displayed in the interface of the voice assistant to prompt the user that the target subject is not recognized, and the user can re-instruct. For example, the prompt message can be "I'm sorry, I don't know what video to generate, please say it again."

[0149] In one case, when multiple objects clustered in the gallery are not labeled, and the target subject corresponds to only one object, the voice assistant responds to the user's operation and displays Fig. 9 The intelligent interaction interface 902 shown in (b) shows an object corresponding to the target theme and other objects obtained by clustering the gallery.

[0150] The voice assistant receives the user's voice instruction to confirm the operation of the child's portrait (target object), and in response to the user's operation (first operation), displays Fig. 9 The intelligent interaction interface 903 shown in (c) includes the material corresponding to the target theme found by the voice assistant. Here, the material corresponding to the target theme found by the voice assistant can be an image material or a video material, depending on the material actually found, and is not limited here.

[0151] In another case, when multiple objects clustered in the gallery are marked, when the target subject corresponds to only one object, the voice assistant responds to the user's operation and directly displays Fig. 9 Intelligent interactive interface 903 shown in (c). That is, the voice assistant responds to the user's operation and directly finds the material corresponding to the object marked as "second daughter".

[0152] When the voice assistant is searching for materials corresponding to the target theme, a prompt message can be displayed in the intelligent interactive interface to prompt that the materials corresponding to the target theme are being searched. This avoids the problem that the voice assistant interface does not change during the material search process, causing the user to think that the voice assistant is stuck.

[0153] It should be explained that due to the limited size of the display screen, when the voice assistant finds a lot of materials, only part of the materials may be displayed in the intelligent interactive interface. Fig. 9 The voice assistant shown in (c) has found 30 materials corresponding to the target theme, and 9 materials are displayed in the intelligent interaction interface 903. The voice assistant receives the user's trigger operation on the "view all" control, and in response to the user's trigger operation, all materials can be displayed in the intelligent interaction interface.

[0154] like Fig. 9 The sorting of multiple materials corresponding to the target theme displayed in the intelligent interaction interface 903 shown in (c) can be sorted according to the time mark of the material, or it can be random, which is not limited here. Among them, the time mark of the material can be used to indicate the time when the mobile phone took the material, and it can also be used to indicate the last time the mobile phone saved the material, which is not limited here. In addition, the number of materials displayed in the intelligent interaction interface of the voice assistant can be pre-set, for example, 9 materials can be set to display. In addition, the total amount threshold of the material that the voice assistant can find can also be pre-set, for example, the total amount threshold of the material can be set to 50. Thereby, it is avoided that in the scenario where the voice assistant finds more materials, the voice assistant obtains more materials from the gallery, causing the voice assistant to freeze.

[0155] In one case, when the voice assistant receives a user voice instruction to "generate a video" (the third operation), in response to the user's operation, the voice assistant generates a target video based on the material corresponding to the target theme (the first material), and displays a thumbnail of the target video in the intelligent interactive interface, such as Fig. 9 The smart interactive interface 904 shown in (d) shows a thumbnail 905 of the target video. The voice assistant receives the user's instruction to play the video, and in response to the user's operation, displays Fig. 9The voice assistant receives the user's operation on the "return" control 908, and in response to the user's operation, returns Fig. 9 The intelligent interactive interface 904 shown in (d).

[0156] In another case, when the voice assistant receives the user's voice instruction to "generate a video", in response to the user's operation, the voice assistant determines that all materials corresponding to the target theme have been deleted from the gallery. In this case, the voice assistant cannot generate the target video corresponding to the target theme, but displays a prompt message in the intelligent interaction interface to prompt the user that the materials corresponding to the target theme are no longer stored locally and the video cannot be generated.

[0157] When there are multiple objects corresponding to the target topic, all of the objects have been labeled, for example, all of the objects have been named, and the voice assistant responds to the user's operation and displays Fig.10 The intelligent interactive interface 1001 shown in (a) of FIG. 1001 displays multiple objects corresponding to the target subject. The voice assistant receives the user's voice instruction to select the second daughter portrait (target object), and in response to the user's operation (second operation), displays Fig.10 The intelligent interactive interface 1002 shown in (b) of FIG. 1 includes the material (first material) corresponding to the target object found by the voice assistant. Thereafter, the implementation process of the voice assistant generating the target video according to the material corresponding to the found target object can be referred to the above description. Fig. 9 The introduction process will not be repeated here.

[0158] In some embodiments, after the voice assistant receives the user's voice instruction to select the target object, it performs semantic recognition on the user's voice information. If the target object is not recognized, the voice assistant interface may display a prompt message (third prompt message) to prompt the user to re-instruct. In another embodiment, the voice assistant receives the user's second operation. In response to the second operation, if the material of the target corresponding object is not found, the voice assistant interface may display a prompt message to prompt the user to select another object.

[0159] Suppose the voice assistant determines that the object includes other children, such as the eldest daughter and the son, based on the portrait clustering results of the gallery. For example, the voice assistant determines that the object includes 5 children based on the portrait clustering results of the gallery. Fig.10 In (a), portrait cards of three children can be displayed. The voice assistant receives the user's trigger operation on the "View All" control and, in response to the user's operation, can display Fig.11The interface 1101 shown in (a) shows the portrait cards of all children. The voice assistant receives the user's selection operation on the portrait card in the interface 1101, and in response to the user's operation, displays the portrait card selected by the user in the intelligent interactive interface.

[0160] In addition, the voice assistant can also edit the name of the portrait card in response to the user's operation (the sixth operation), wherein the editing process includes adding a name, modifying a name, or deleting a name. Fig.10 The trigger operation of the text "Second Daughter" shown in (a) above responds to the user's operation and displays Fig.11 Interface 1102 shown in (b). The voice assistant can modify the name of the portrait card in interface 1102 in response to the user's operation.

[0161] It can be understood that when multiple objects have different names, the voice assistant can accurately find the materials of objects with different names based on the objects corresponding to the target subject indicated by the user, so as to improve the efficiency of video generation.

[0162] In addition, multiple portrait cards can be assigned different sequence numbers, so that the user can generate a video corresponding to a certain sequence number through voice instructions. Fig.10 In the process of the intelligent interactive interface 1001 shown in (a), after the voice assistant receives the user's voice instruction "the second child", in response to the user's operation, the voice assistant searches for the material corresponding to the second child (i.e., the eldest daughter).

[0163] After the voice assistant receives the user's voice instruction of "second child" (second voice information), it performs semantic analysis on the second voice information. If the semantics corresponding to the second voice information is not recognized, a prompt message is displayed in the intelligent interaction interface to prompt the user to re-instruct.

[0164] In the embodiment of the present application, after the voice assistant finds the material corresponding to the target theme (the first material), the voice assistant can respond to the user's trigger operation (the fourth operation) to add, replace, change the order, delete, etc. of the material corresponding to the target theme. As a result, the video generated based on the material processed by the voice assistant better meets the user's requirements.

[0165] It should be pointed out that when the voice assistant receives a voice message from the user indicating the number of material processing for the first material, the material processing is performed according to the indicated number. If the voice assistant receives a message from the user that does not indicate the number of material processing for the first material, the preset number is used to process the first material. Among them, the preset number is less than the quantity threshold; when the voice or text semantics corresponding to the message indicated by the user does not indicate the number of material processing for the first material, the preset number is the number of gears corresponding to the voice or text semantics, and different gears correspond to different numbers. For example, the user's voice message is "add a lot of materials for children dancing", the preset number can be 50% of the first material, and the user's voice message is "add a small amount of materials for children dancing", the preset number can be 30% of the first material.

[0166] In some embodiments, the voice assistant can respond to the user's voice instruction operation and add materials based on the materials corresponding to the target theme to generate a target video with richer content. Fig.12 The intelligent interactive interface 1201 shown in (a) shows the material 1 of the second daughter dancing (the first material). The voice assistant receives the user's voice instruction "help me add the material of the second daughter smiling", and in response to the user's operation (the fourth operation), the voice assistant displays the following Fig.12 The intelligent interactive interface 1202 shown in (b) wherein the intelligent interactive interface 1202 displays a prompt message to prompt the user that the voice assistant is searching for materials of the second daughter's smile.

[0167] In one embodiment, the voice assistant does not find the material of the second daughter smiling (the second material). Fig.12 The intelligent interactive interface shown in (e) displays a prompt message to indicate that no video of the second daughter smiling has been found.

[0168] In another embodiment, after the voice assistant finds the material of the second daughter's smile (the second material), the material 2 (the total material) after adding the material of the second daughter's smile is displayed in the intelligent interactive interface, such as Fig.12 The intelligent interactive interface 1203 is shown in (c).

[0169] Compared to Fig.12 (b) shows the number of materials, such as Fig.12The number of materials in the intelligent interaction interface 1203 displayed in (c) has increased by 5. That is to say, the voice assistant has found 5 materials of the second daughter's smile and added the materials to the materials corresponding to the target theme. In addition, the order of the materials displayed in the intelligent interaction interface 1203 can be sorted according to the time stamp of each material, or the newly added material can be sorted in front, or the newly added material can be sorted in the back, or the newly added material can be randomly sorted together with the original material. The order of the materials displayed in the intelligent interaction interface is not limited here.

[0170] In display Fig.12 In the process of the intelligent interactive interface 1203 shown in (c), the voice assistant receives the user's voice instruction "generate video" operation. In response to the user's operation, the voice assistant generates a target video based on the added material 2 and displays a thumbnail of the target video in the intelligent interactive interface, such as Fig.12 The smart interactive interface 1204 shown in (d) displays a thumbnail 1205 of the target video.

[0171] In some embodiments, the voice assistant receives the user's voice instruction of "help me add the materials of the second daughter and the father", and in response to the user's operation (the fourth operation), the voice assistant displays the following Fig.12 The intelligent interactive interface 1207 shown in (f) of FIG. The intelligent interactive interface 1207 shows two portraits. The voice assistant receives the user's selection operation on the first portrait. In response to the user's operation, the voice assistant searches for materials of the second daughter and the father.

[0172] It should be noted that, in the process of displaying the material corresponding to the target theme on the intelligent interactive interface, the voice assistant can receive the user's voice instructions to add materials multiple times, and add the corresponding material in response to each voice instruction operation of the user.

[0173] For example, Fig.13 The intelligent interactive interface 1301 shown in (a) shows a prompt message to prompt the voice assistant to search for the material of the second daughter's smile normally. After the voice assistant finds the material of the second daughter's smile, it directly adds the material of the second daughter's smile to the original material, such as Fig.13 The intelligent interactive interface 1302 shown in (b) shows the material 3 after adding the material of the second daughter's smile. Fig.13 The 30 materials shown in (a) are increased to Fig.13 The 40 materials shown in (b) above. In other words, the voice assistant found 10 materials of the second daughter smiling.

[0174] After that, the voice assistant receives the user's voice instruction to add the material again, and in response to the user's operation, the voice assistant searches for the corresponding material. Fig.13 After the intelligent interactive interface 1302 shown in (b) is shown, the voice assistant receives the user's voice instruction "help me add more ingredients for my second daughter's meal", and in response to the user's voice instruction operation, the voice assistant finds the corresponding ingredients and displays Fig.13 The intelligent interaction interface 1303 shown in (c) shows the material after adding the material of the second daughter eating in the intelligent interaction interface 1303, and the material about the second daughter found by the voice assistant has reached the total amount threshold. That is, the total amount of material found by the voice assistant is 50.

[0175] After that, the voice assistant receives the user's voice instruction "Help me add more materials for my second daughter's painting" again. In response to the user's instruction, the voice assistant's intelligent interaction interface 1303 displays a prompt message 1304 (the first prompt message) to remind the user that the number of materials has reached the upper limit and that some materials can be added only after deleting some materials. For example, the voice assistant receives the user's trigger operation on the "View All" control in the intelligent interaction interface 1303, and in response to the user's trigger operation, displays Fig.13 The voice assistant receives the user's selection operation on the material in the interface 1305, and in response to the user's operation, selects the corresponding material. The material not selected in the interface 1305 is the material to be replaced. The voice assistant receives the user's trigger operation on the "add" control in the interface 1305, and in response to the user's trigger operation, displays Fig.13 The voice assistant receives the user's selection operation on the drawing material in the interface 1306, and selects the corresponding material in response to the user's operation. The voice assistant receives the user's trigger operation on the "add" control in the interface 1306, and replaces the unselected material in the interface 1305 with the drawing material selected in the interface 1306 in response to the user's operation.

[0176] That is to say, when the voice assistant determines that the total amount of materials has reached the total amount threshold, after the voice assistant receives the user-triggered instruction operation to add materials, in response to the user's trigger operation, a prompt message can be displayed in the voice assistant's intelligent interactive interface, prompting the user to use the newly found materials to replace the original materials in the interface.

[0177] In some embodiments, after the voice assistant receives the user's voice instruction to add materials, the voice assistant can determine the number of materials to be added according to the semantics corresponding to the user's voice message. In some embodiments, when the voice assistant receives the user's voice instruction to clearly indicate the number of materials to be added, the voice assistant adds the materials according to the indicated number. For example, the voice message indicated by the user's voice is "add 5 materials for eating", and the voice assistant determines that the number of materials added this time is 5. In other embodiments, when the number of materials to be added is not indicated in the user's voice message received by the voice assistant, a preset number of materials is added. For example, the voice assistant receives the user's voice instruction to add a voice message of "add a small amount / a small part / a little material", and the voice assistant determines that the upper limit of the added material is the material number 1 (for example, the material number 1 is 9, 10, etc.). For another example, the voice assistant receives the user's voice instruction to add a voice message of "add a large amount / most of / a lot of materials", and the voice assistant determines that the upper limit of the added material is the material number 2 (for example, the material number 2 is 15, etc.).

[0178] It should be explained that when the voice assistant adds materials multiple times in response to the user's instructions, the number of materials added by the voice assistant each time is less than the preset number, so that the number of materials added is not greater than the total threshold. The way the voice assistant adds materials in the above example is only an example. In actual application, the voice assistant can determine the number of times to add materials based on the number of times the user actually instructs to add materials, and determine the number of materials to add based on the number of materials actually found.

[0179] In other embodiments, the voice assistant receives a user voice instruction to replace the material corresponding to the target theme, and in response to the user's voice instruction operation, replaces part of the material corresponding to the target theme with other materials to generate a target video based on the replaced material (sixth material). In the case where the voice assistant receives a voice message from the user indicating the replacement of the material and does not explicitly indicate the number of replacement materials, the voice assistant can determine the number of replacement materials based on the semantics corresponding to the voice message. For example, the voice assistant receives a voice message of "replace a small amount / a small part / a little material", and the voice assistant determines that the upper limit of the replacement material is the number of materials 3 (for example, the number of materials 3 is 30% of the original number of materials). For another example, the voice assistant receives a voice message of "replace a large amount / most of / a lot of material" from the user indicating the replacement of the material, and the voice assistant determines that the upper limit of the replacement material is the number of materials 4 (for example, the number of materials 4 is 50% of the original number of materials).

[0180] For example, when the voice assistant receives the user's voice instruction to "replace a small amount of dancing material with smiling material", the display Fig.14The intelligent interactive interface 1401 shown in (a) in the figure. The intelligent interactive interface 1401 displays a prompt message to indicate that the voice assistant is searching for the material of the second daughter's smile. After the voice assistant finds the material of the second daughter's smile (the fifth material), it directly replaces 30% (i.e., 20*30% is 6 materials) of the dancing material in the original material with the smiling material. During the replacement process, the voice assistant displays Fig.14 The prompt message 1403 shown in (b) in the figure is displayed to remind the user that the voice assistant is replacing the material. Fig.14 The prompt information 1404 shown in (c) is used to prompt the user that the material has been replaced. It can be seen that the user can intuitively determine the entire process of material replacement through the intelligent interactive interface.

[0181] For example, if the voice assistant receives a voice message from the user instructing to replace the materials, and the message clearly indicates the number of materials to be replaced, the voice assistant can directly determine the number of materials to be replaced. For example, if the voice assistant receives a voice message from the user instructing to replace the first three materials with the materials for the second daughter's painting, the voice assistant determines that the number of materials to be replaced is 3. Fig.14 The prompt information 1405 displayed in the intelligent interactive interface shown in (d) clearly indicates the number of replacement materials.

[0182] In some cases, the voice assistant receives a user voice instruction to replace the material, and in response to the user's operation, displays Fig.14 The prompt message 1406 shown in (e) in the figure reminds the user that the voice assistant is searching for materials. When the voice assistant finds the photo of the second daughter's painting, the voice assistant performs the process of replacing the materials. After the voice assistant finishes replacing the materials, it displays Fig.14 The material 1407 shown in (f) in the figure. When the voice assistant fails to find the photo of the second daughter's painting, a prompt message may be displayed in the intelligent interactive interface to prompt the user that the material has not been found.

[0183] In other embodiments, the voice assistant can respond to the user's voice instruction operation to delete some materials based on the materials corresponding to the target theme to generate a target video based on the remaining materials, so that the materials in the generated target video are all the materials expected by the user.

[0184] For example, when the voice assistant finds the material of the second daughter dancing and displays it on the intelligent interactive interface, the voice assistant receives the user's voice instruction to delete the photo, and in response to the user's operation, displays Fig.15In the figure (a), the intelligent interactive interface 1501 is shown, wherein prompt information is displayed in the intelligent interactive interface 1501 to prompt the content for voice instruction. Here, the user voice instructs "help me delete most of the photos", and the voice assistant determines to delete 20 photos based on the number of materials corresponding to the original target theme, and displays Fig.15 The intelligent interactive interface 1502 shown in (b) can be understood as follows: the voice assistant receives a voice message from the user instructing to delete the material as "replace a large amount / most / many materials", and the voice assistant determines that the upper limit of the deleted material is 5 materials (for example, 5 materials is 50% of the original material quantity).

[0185] The deletion instruction received by the voice assistant clearly indicates the number or type of materials to be deleted, and the voice assistant can directly delete the corresponding number or type of materials. Fig.15 After the intelligent interactive interface 1502 shown in (b) is displayed, the voice assistant continues to receive the user's voice instruction "help me delete ten more photos". In response to the user's operation, the voice assistant deletes the ten photos in the material and displays Fig.15 The intelligent interactive interface 1503 shown in (c) is shown in FIG. Thereafter, assuming that the voice assistant displays Fig.15 After the intelligent interactive interface 1503 shown in (c) is shown, the voice assistant receives the user's voice instruction "help me delete all photos" and displays the following in response to the user's operation: Fig.15 The prompt information 1504 shown in (d) in the figure prompts the user that at least one material is needed to generate a video. That is, the voice assistant does not perform the operation of deleting all materials. For example, Fig.15 In the intelligent interactive interface 1505 shown in (e), the voice assistant receives the user's voice instruction "Help me delete the photos of people wearing hats". In response to the user's operation, the voice assistant deletes the photos of people wearing hats and displays the deleted materials.

[0186] exist Fig.15 After the intelligent interactive interface 1505 shown in (e) is displayed, the voice assistant receives the user's voice instruction "help me delete the third and fifth materials", and the voice assistant deletes the corresponding materials, and displays the remaining materials after deleting the materials in the intelligent interactive interface, such as Fig.15 Intelligent interactive interface 1506 shown in (f).

[0187] It can be understood that after the voice assistant receives the user's instruction to delete the material, the voice assistant can randomly select material from the material corresponding to the target theme for deletion, or the voice assistant can determine the material to be deleted based on the time stamp of the material. For example, the voice assistant can determine specially designated material as the material to be deleted, etc. The specific material to be deleted by the voice assistant is not limited in the embodiment of the present application.

[0188] In other embodiments, the voice assistant can adjust the order of the materials in response to the user's voice instruction operation, so that the order of playing the materials in the target video generated according to the materials after the order adjustment can meet the user's needs.

[0189] For example, Fig.16 In the intelligent interactive interface 1601 shown in (a), the voice assistant receives the user's voice instruction "help me move the last photo to the front", and in response to the user's operation, displays Fig.16 The intelligent interactive interface 1602 shown in (b) in FIG. 1602 displays prompt information to prompt the user of the information indicated by the voice. After the voice assistant completes the order change, it displays Fig.16 The intelligent interactive interface 1603 shown in (c) of FIG. 1603 shows the material after the order is adjusted (the seventh material). The materials included in the seventh material are the same as those in the first material, and the order of the materials in the seventh material is different from that in the first material.

[0190] It needs to be explained that the above Figures 12 to 16 The description of the voice assistant adding, replacing, deleting, and reordering the materials corresponding to the target theme is only used as an example. After the voice assistant finds the materials corresponding to the target theme, the voice assistant can respond to the user's instructions and perform at least one of the following processing operations: adding, replacing, reordering, and deleting the materials corresponding to the target theme. For example, after the voice assistant receives the user's voice instruction "delete the materials of drawing and add the materials of children running", in response to the user's operation, the voice assistant executes the process of deleting and adding materials.

[0191] In the embodiment of the present application, after the voice assistant generates the target video according to the material corresponding to the target theme, the voice assistant can respond to the user's trigger operation to share, download, delete, etc. the target video. In other words, the user does not need to download the target video to the local mobile phone for storage to realize the operation of the target video. Fig. 9The intelligent interaction interface 904 shown in (d) also displays an area 906, which includes controls for operating the target video, for example, area 906 includes controls such as "Like", "Dislike", "Share", "Download" and "Delete". The voice assistant receives the user's trigger operation on the controls in area 906, and executes the corresponding function in response to the user's trigger operation. For example, the voice assistant receives the user's trigger operation on the "Download" control, and in response to the user's trigger operation, the voice assistant downloads the target video displayed in the intelligent interaction interface 904 to the local storage of the mobile phone. After the voice assistant downloads the target video to the local storage of the mobile phone, the voice assistant can prompt the user through voice that the video has been saved. For example, the voice assistant issues a prompt message "The video has been saved". Alternatively, a prompt message is displayed in the intelligent interaction interface 904 to prompt the user that the video has been saved.

[0192] For example, the voice assistant receives a user's trigger operation on the "Share" control, and in response to the user's trigger operation, displays Fig.17 The share card 1701 shown in (a) of FIG. 1701. It can be seen that the user can share the target video without downloading the target video to the gallery for storage, which improves the user experience. For another example, the voice assistant receives the user's trigger operation on the "delete" control in area 906, and in response to the user's trigger operation, displays Fig.17 The voice assistant receives the user's trigger operation on the "delete" control in the delete card 1702. In response to the user's operation, the voice assistant deletes the target video and displays Fig.17 Interface 1703 shown in (c).

[0193] In addition, the voice assistant can also edit the target video in response to the user's operation, such as adjusting the length, changing the background music, etc. Fig. 9 The intelligent interactive interface 904 shown in (d) also includes controls such as "smart text", "change template", "change music", and "adjust duration". The voice assistant receives the user's trigger operation on any control, and executes the corresponding function in response to the user's operation. For example, the voice assistant receives the user's trigger operation on the "change music" control, and in response to the user's operation, the voice assistant executes the process of changing the background music of the target video.

[0194] In some embodiments, after the voice assistant receives the user's instruction to generate a video, the voice assistant determines that the material corresponding to the target theme in the gallery has been deleted. In this case, the voice assistant cannot generate a video. Fig.18In the intelligent interactive interface 1801 shown in (a), a prompt message 1802 is displayed in the intelligent interactive interface 1801 to prompt that the voice assistant is creating a video. If the voice assistant determines that some of the materials corresponding to the target theme have been deleted locally, it will display Fig.18 In the intelligent interactive interface 1803 shown in (b), a prompt message 1804 is displayed in the intelligent interactive interface 1803 to prompt that some materials have been deleted locally, please reconfirm the materials.

[0195] If the voice assistant determines that all the materials corresponding to the target topic have been deleted locally, it will display Fig.18 In the intelligent interactive interface 1805 shown in (c), a prompt message 1806 is displayed in the intelligent interactive interface 1805 to prompt that the material has been deleted locally and the video cannot be generated.

[0196] In some embodiments, the voice assistant may receive an operation triggered by a user to change the template of a target video, and in response to the user's operation, the voice assistant performs a corresponding function. Fig.19 After the target video 1902 is displayed in the intelligent interactive interface 1901 shown in (a), the voice assistant receives the user's instruction to "change to a happier template". In response to the user's operation, the voice assistant changes the template of the target video and displays the changed target video 1903. Fig.19 In the intelligent interaction interface 1904 shown in (b), the voice assistant receives the user's instruction to change the template again. In response to the user's instruction, the voice assistant fails to find the corresponding template. The intelligent interaction interface 1904 displays a prompt message 1905 to prompt that the corresponding template is not found and other templates can be tried. Among them, area 1906 displays recommended templates.

[0197] In some embodiments, the voice assistant may receive an operation triggered by a user to adjust the duration of a target video, and in response to the user's operation, the voice assistant adjusts the duration of the target video. Fig. 20 After the target video 202 is displayed in the intelligent interactive interface 2001 shown in (a), the voice assistant receives the user's instruction to "add a little time", and in response to the user's operation, displays a prompt message 203 to indicate that the time is being extended. After the voice assistant completes the operation of extending the time of the target video, it displays Fig. 20 In the intelligent interactive interface 2004 shown in (b), the adjusted video 2005 is displayed in the intelligent interactive interface 2004.

[0198] When the user does not explicitly instruct to adjust the length of the video, the voice assistant lengthens or shortens the preset length, for example, the preset length is 5s or 10s.

[0199] When the user explicitly indicates the length of the video to be adjusted, the voice assistant lengthens or shortens the target video according to the length indicated by the user. Fig. 20 After the target video is displayed in the intelligent interactive interface 2006 shown in (c), the voice assistant receives the user's instruction "shorten by 2 seconds", and in response to the user's operation, displays the target video 2007 after the adjusted length. For another example, the voice assistant receives the user's instruction "help me adjust it to 20 seconds", and in response to the user's operation, displays Fig. 20 In the smart interaction interface 2008 shown in (d), the adjusted video 2009 is displayed in the smart interaction interface 2008. The duration of the video 2009 is 20 seconds. The voice assistant receives the user's instruction "please adjust it to 2 seconds", and the smart interaction interface 2008 displays a prompt message and the adjusted video 2010, and the prompt message indicates the minimum duration of the video. Similarly, the voice assistant receives the user's instruction "please adjust it to 1 hour", and displays the prompt message in the smart interaction interface 2008. Fig. 20 The intelligent interactive interface 2011 shown in (e) displays a prompt message and an adjusted video 2012, and the prompt message indicates the maximum duration of the video. In other words, for the effect of the video, the duration of the video adjusted by the voice assistant cannot exceed the maximum duration, nor be less than the minimum duration.

[0200] In some embodiments, the voice assistant can adjust the material in the target video to generate a new video based on the adjusted material. Fig.21 As shown, the voice assistant receives the "adjust material" operation instructed by the user, and in response to the user's operation, the material of the target video is displayed in the intelligent interactive interface 2101. The voice assistant responds to the user's operation of deleting the material of the target video, or adding the material, to obtain the adjusted material, and the voice assistant generates a new video based on the adjusted material.

[0201] The above embodiment is an exemplary introduction to the process of video generation using multiple portraits as the object corresponding to the target theme. Of course, the object type in this solution can be a portrait, or a pet, different geographical locations, etc. For example, after the voice assistant receives the user's instruction to "generate a video of pets playing", the voice assistant determines that there are materials corresponding to three pets in the gallery based on the clustering results of the gallery, and the images of the three pets can be displayed in the intelligent interactive interface. For another example, the voice assistant receives the user's instruction to "generate a video of holiday travel", and the voice assistant determines that there are travel materials of multiple locations in the gallery based on the clustering results of the gallery. For example, the voice assistant determines that there are travel materials of city A, city B, and city C, and the images of city A, city B, and city C can be displayed in the intelligent interactive interface for the user to select and determine the target city.

[0202] It should be noted that the above is the image recognition processing of the images in the gallery that has been completed before the voice assistant receives the user's instruction to generate the target video corresponding to the target theme. The image recognition processing can be the gallery performing clustering, semantic recognition and other processing on the images in the gallery. The specific image recognition processing process is not elaborated in detail here.

[0203] However, in one possible case, before the voice assistant receives the user's instruction to generate a target video corresponding to the target theme, the voice assistant determines that the gallery has not performed image recognition processing on the images in the gallery, and the voice assistant can guide the user to instruct the gallery to perform image recognition operations through voice or text. After the voice assistant determines that the gallery has completed image recognition, it searches for the material corresponding to the target theme based on the image recognition results, so as to generate the target video based on the material corresponding to the target theme.

[0204] It is understandable that, in order to realize the above functions, the above-mentioned electronic devices, etc. include hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of the present invention.

[0205] The embodiment of the present application can divide the functional modules of the above-mentioned electronic device etc. according to the above-mentioned method example. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0206] In the case of dividing each functional module according to each function, a possible composition diagram of the electronic device involved in the above embodiment, the electronic device may include: a display unit, a transmission unit and a processing unit, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here.

[0207] The embodiment of the present application also provides an electronic device, including one or more processors and one or more memories. The one or more memories are coupled to the one or more processors, and the one or more memories are used to store computer program codes, and the computer program codes include computer instructions. When the one or more processors execute the computer instructions, the electronic device executes the above-mentioned related method steps to implement the video generation method in the above-mentioned embodiment.

[0208] An embodiment of the present application further provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on an electronic device, the electronic device executes the above-mentioned related method steps to implement the video generation method in the above-mentioned embodiment.

[0209] An embodiment of the present application further provides a computer program product, which includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the above-mentioned related method steps to implement the video generation method in the above-mentioned embodiment.

[0210] In addition, an embodiment of the present application also provides a device, which may specifically be a chip, component or module, and the device may include a connected processor and memory; wherein the memory is used to store computer-executable instructions, and when the device is running, the processor may execute the computer-executable instructions stored in the memory so that the device executes the video generation method performed by the electronic device in the above-mentioned method embodiments.

[0211] Among them, the electronic device, computer-readable storage medium, computer program product or device provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0212] Through the description of the above implementation methods, technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0213] Each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0214] 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 computer-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, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform 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 flash memory, mobile hard disk, read-only memory, random access memory, disk or optical disk.

[0215] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A video generation method, characterized in that: Applied to an electronic device including a voice assistant, the method comprises: Receive a first operation triggered by a user to generate a target video corresponding to a target theme; In response to the first operation, displaying an interface of the voice assistant, wherein the interface of the voice assistant includes at least one candidate object corresponding to a keyword of the target topic; receiving a second operation of the user on a target object among the at least one candidate object; In response to the second operation, displaying a first material corresponding to the target object in the interface of the voice assistant, where the first material is an image or video found by the voice assistant from a gallery of the electronic device; Receiving a third operation triggered by a user to generate the target video; In response to the third operation, a thumbnail of the target video is displayed in the interface of the voice assistant, and the target video is generated based on the first material corresponding to the target object.

2. The method according to claim 1, characterized in that: In the process of displaying the first material corresponding to the target object in the first interface, the method further includes: receiving a fourth operation of the user; In response to the fourth operation, the target material after material processing of the first material corresponding to the target object is displayed in the interface of the voice assistant, and the material processing includes at least one of adding material, replacing material, deleting material or changing the order of materials.

3. The method according to claim 2, characterized in that The method comprises: If the fourth operation of the user indicates the amount of material processing to be performed on the first material, performing material processing according to the indicated amount; If the user's fourth operation does not indicate the number of material processings to be performed on the first material, a preset number is used to process the first material, and the preset number is less than a quantity threshold; wherein, when the voice or text semantics corresponding to the fourth operation does not indicate the number of material processings to be performed on the first material, the preset number is the number of gears corresponding to the voice or text semantics, and different gears correspond to different numbers.

4. The method according to claim 2 or 3, characterized in that: The material processing is adding material, and the target material displayed in the interface of the voice assistant includes the total material after adding the second material to the target object, and the total material includes the first material and the second material.

5. The method according to any one of claims 2 to 4, characterized in that: The material processing is adding material, and the method further includes: In response to the fourth operation, a first prompt message is displayed in the interface of the voice assistant, and the first prompt message is used to prompt that the total number of materials corresponding to the target object has reached an upper limit.

6. The method according to claim 5, characterized in that The method further comprises: receiving a fifth operation of the user; In response to the fifth operation, a third material is displayed in the interface of the voice assistant, where the third material includes the material obtained by deleting part of the total material and then adding the fourth material.

7. The method according to claim 2 or 3, characterized in that: The material processing is replacement material, and the target material displayed in the interface of the voice assistant includes a sixth material obtained by replacing part of the material in the target object with the fifth material, and the sixth material includes the fifth material and part of the first material.

8. The method according to claim 2 or 3, characterized in that: The material processing is to delete the material, and the target material displayed in the interface of the voice assistant includes part of the first material after the material is deleted.

9. The method according to claim 2 or 3, characterized in that: The material processing is to change the order of materials. The target material displayed in the interface of the voice assistant includes a seventh material. The materials included in the seventh material are the same as those in the first material, and the order of the materials in the seventh material is different from the order of the materials in the first material.

10. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: receiving a sixth operation by the user; In response to the sixth operation, the object name of the at least one candidate object displayed in the interface of the voice assistant is edited, and the editing includes adding a name, modifying a name, or deleting a name.

11. The method according to any one of claims 1 to 10, characterized in that: The method further comprises: receiving a seventh operation of the user; In response to the seventh operation, displaying a target interface, the target interface including the at least one candidate object and other candidate objects; The receiving a second operation of the user on the target object among the at least one candidate object comprises: A second operation of the user on a target object among the candidate objects on the target interface is received.

12. The method according to any one of claims 1 to 11, characterized in that: The method further comprises: If a deletion operation of the target video by the user is received, in response to the deletion operation, the thumbnail of the target video is not displayed in the interface of the voice assistant; If a sharing operation of the target video by the user is received, in response to the sharing operation, a sharing interface is displayed in the interface of the voice assistant; If a template changing operation of the target video by the user is received, in response to the template changing operation, the video after the template changing is displayed in the interface of the voice assistant; If a duration adjustment operation of the user on the target video is received, the video after the duration adjustment is displayed in the interface of the voice assistant in response to the duration adjustment operation.

13. The method according to any one of claims 1 to 12, characterized in that: The first operation is a voice instruction operation. After receiving the first operation of a user triggering the generation of a target video corresponding to the target theme, the method further includes: Performing semantic analysis on the first voice information of the first operation instruction; If the semantics corresponding to the first voice information is identified, determining the keywords corresponding to the target topic according to the identified semantics; If the semantics corresponding to the first voice information is not recognized, or if a candidate object matching the keyword is not recognized from the gallery, a second prompt message is displayed in the interface of the voice assistant, and the second prompt message is used to prompt the adjustment of the voice indication operation.

14. The method according to any one of claims 1 to 13, characterized in that: After receiving the second operation of the user on the target object among the at least one candidate object, the method further includes: performing semantic analysis on the second voice information of the second operation instruction; If the semantics corresponding to the second voice information is not recognized, or a target object matching the semantics corresponding to the second voice information is not recognized from the at least one candidate object, a third prompt message is displayed in the interface of the voice assistant, and the third prompt message is used to prompt the user to select other candidate objects.

15. The method according to any one of claims 1 to 14, characterized in that: The candidate object is a person, and what is displayed on the interface of the voice assistant is an image of the candidate object, wherein the image of the candidate object includes a portrait; and the target subject includes keywords related to the person.

16. An electronic device, characterized in that: include: one or more processors; Memory; One or more computer programs are stored in the memory, and the one or more computer programs include instructions. When the instructions are executed by the electronic device, the electronic device executes the video generation method as described in any one of claims 1-15.

17. A computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, characterized in that: When the instructions are executed on an electronic device, the electronic device is enabled to execute the video generating method according to any one of claims 1 to 15.

Images