Theme recommendation method, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a theme recommendation method, electronic equipment and a storage medium, is applied to the technical field of terminals, can quickly recommend a theme of a video expected by a user in an interface of a voice assistant, and improves the interaction efficiency of the user and the voice assistant. The theme recommendation method is applied to the electronic equipment comprising a voice assistant, and comprises the following steps: receiving a first operation of a user; in response to the first operation, displaying a first interface of the voice assistant, the first interface comprising at least one candidate theme; the candidate theme is generated by the voice assistant according to an image recognition result obtained by performing image recognition on an image in an image library of the electronic equipment.

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 topic recommendation method, an electronic device, and a storage medium. Background Art

[0003] With the popularity of electronic devices (such as mobile phones, tablet computers, etc.), users can store a large number of images in the electronic devices, for example, a large number of images can be stored in a gallery. When the electronic device generates a video based on the large number of images stored in the gallery, the electronic device cannot quickly determine the subject of the generated video due to the large number of images in the gallery. Summary of the invention

[0004] The embodiments of the present application provide a topic recommendation method, an electronic device, and a storage medium, which can quickly recommend topics for which users want to generate videos in the interface of a voice assistant, thereby improving the interaction efficiency between users and the voice assistant.

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

[0006] In a first aspect, a topic recommendation method is provided, which is applied to an electronic device including a voice assistant. The method may include:

[0007] Receive a first operation from a user; in response to the first operation, display a first interface of the voice assistant, the first interface including at least one candidate topic; the candidate topic is generated by the voice assistant based on the image recognition results of the image in the gallery of the electronic device.

[0008] It can be understood that when the voice assistant determines that the image library has completed the image recognition process and the voice assistant can recommend at least one candidate theme based on the image recognition results of the image library, in response to the user's first operation, the first interface (i.e., the intelligent interaction interface) displayed includes at least one candidate theme. Thus, the voice assistant can quickly recommend the candidate theme that the user expects to generate a video.

[0009] In a possible case of the first aspect, in response to the first operation, displaying the first interface of the voice assistant may include:

[0010] In response to the first operation, the second interface of the voice assistant is displayed, and the second interface includes a first control, and the first control is used to trigger the gallery to start image recognition processing; in response to the user's operation on the first control, the first prompt information is displayed on the second interface, and the first prompt information is used to prompt that the gallery is performing image recognition; after the gallery completes image recognition, the first interface of the voice assistant is displayed.

[0011] In one scenario, when the gallery has not yet performed image recognition processing, the voice assistant can guide the user to trigger the gallery to perform image recognition processing on the second interface. During the gallery's image recognition process, the second interface of the voice assistant can display information prompting the gallery to recognize images, so as to prompt the user that the gallery is performing image recognition. After the gallery's image recognition is completed, at least one candidate theme generated by the voice assistant based on the gallery's image recognition results is displayed.

[0012] In another possible case of the first aspect, in response to the first operation, displaying the first interface of the voice assistant may include:

[0013] In response to the first operation, the second interface of the voice assistant is displayed, the second interface includes a first control, and the first control is used to trigger the gallery to start image recognition processing; in response to the user's operation on the first control, the third interface of the gallery is displayed, the third interface includes the image recognition progress of the gallery; after the image recognition of the gallery is completed, the first interface of the voice assistant is displayed.

[0014] In another scenario, when the gallery has not yet performed image recognition processing, the voice assistant can guide the user to trigger the gallery to perform image recognition processing on the second interface. During the gallery's image recognition process, the user is redirected to the gallery's image recognition interface. After the gallery's image recognition is completed, at least one candidate theme generated by the voice assistant based on the gallery's image recognition results is displayed.

[0015] In another possible case of the first aspect, the third interface includes an icon of a voice assistant, and in the process of displaying the third interface of the gallery, the above-mentioned theme recommendation method may further include:

[0016] Receive a second operation of the user on the voice assistant icon; in response to the second operation, display a fourth interface of the voice assistant, the fourth interface includes a second prompt message, and the second prompt message is used to prompt the image recognition progress of the gallery.

[0017] It can be understood that, during the process of the gallery image recognition and displaying the gallery image recognition interface, the gallery image recognition interface can respond to the user's trigger operation and return to the fourth interface of the voice assistant (for example, Fig. 9 Intelligent interactive interface 908 shown in (d)).

[0018] In another possible situation of the first aspect, when the image library is in the process of identifying images, the second interface displays a third prompt message, and the third prompt message is used to prompt the image identification time of the image library.

[0019] It can be understood that by displaying the image recognition time of the gallery in the intelligent interactive interface, the user can intuitively determine the image recognition time of the gallery to determine whether to wait for the image recognition to end in this interface. Fig.12 The intelligent interactive interface 1203 shown in (b) displays a prompt message 1205, and the prompt message 1205 is used to prompt the image recognition time of the gallery.

[0020] In another possible case of the first aspect, after the image library recognizes the image, a first interface of the voice assistant is displayed, including:

[0021] After the image recognition in the gallery is completed, if the voice assistant generates at least one candidate theme based on the image recognition results of the gallery, a first interface including at least one candidate theme is displayed.

[0022] For example, in Fig. 9 After the image recognition process shown in (c) is completed, the voice assistant recommends three candidate topics based on the image recognition results of the gallery, showing Fig. 9 The intelligent interactive interface 907 (ie, the first interface) shown in (e).

[0023] In another possible case of the first aspect, the topic recommendation method may further include:

[0024] After the image recognition in the gallery is completed, if the voice assistant has not generated a candidate theme based on the image recognition results of the gallery, the fifth interface of the voice assistant is displayed. The fifth interface includes a fourth prompt message, and the fourth prompt message is used to prompt the voice assistant that no candidate theme has been generated based on the image recognition results of the gallery.

[0025] For example, in Fig. 9 After the image recognition process shown in (c) is completed, the voice assistant does not recommend candidate topics based on the image recognition results of the gallery, and displays Fig. 9 The intelligent interactive interface 910 (ie, the fifth interface) shown in (f) prompts the user that no candidate topics have been generated.

[0026] In another possible case of the first aspect, the topic recommendation method may further include:

[0027] Receive a third operation of the user on a target topic among at least one candidate topic; in response to the third operation, display at least one image corresponding to the target topic in the first interface, and at least one image is an image in the gallery of the electronic device; receive a fourth operation of the user triggering the generation of a video; in response to the fourth operation, display a thumbnail of the target video in the first interface, and the target video is generated based on the at least one image corresponding to the target topic.

[0028] It can be understood that after the voice assistant finds the image corresponding to the target theme from the gallery, it can generate a video corresponding to the target theme based on the image corresponding to the target theme. For example, Fig.10 The video thumbnail 1006 shown in (c) is a video thumbnail generated based on the image corresponding to the candidate subject 1002.

[0029] In another possible case of the first aspect, the topic recommendation method may further include:

[0030] A fifth operation of the user to instruct generation of a video of the first subject is received; the first subject is different from the candidate subject; in response to the fifth operation, fifth prompt information is displayed in the first interface, and the fifth prompt information is used to prompt that the gallery does not include an image corresponding to the first subject.

[0031] It can be understood that the voice assistant receives the user's instruction to generate videos of other topics different from the candidate topics, and the voice assistant is unable to find the image corresponding to the first topic, resulting in the voice assistant being unable to generate the video corresponding to the first topic. The voice assistant can display a prompt message in the intelligent interactive interface to prompt the user to take more images.

[0032] In another possible case of the first aspect, the topic recommendation method may further include:

[0033] In response to the fifth operation, a sixth prompt message is displayed in the first interface, and the sixth prompt message is used to prompt the user to generate videos corresponding to other themes other than the first theme.

[0034] It can be understood that when the voice assistant determines that it cannot generate a video corresponding to the first theme, the voice assistant can recommend other themes for which videos can be generated in the intelligent interactive interface.

[0035] In another possible case of the first aspect, the candidate subject may include a person subject, and the method further includes:

[0036] Receive a sixth operation of the user on a person subject among at least one candidate subject; in response to the sixth operation, display multiple candidate subjects in the first interface; receive a seventh operation of the user on a target person among the multiple candidate subjects. In response to the seventh operation, display at least one portrait corresponding to the target person in the first interface, and the at least one portrait is an image in the gallery of the electronic device; receive an eighth operation of the user triggering the generation of a person video; in response to the eighth operation, display a thumbnail of the person video in the first interface, and the person video is generated according to the at least one portrait corresponding to the target person.

[0037] It can be understood that when the voice assistant determines that there are multiple identical or similar objects corresponding to the candidate topic based on the keywords of the candidate topic, the intelligent interactive interface can display images of multiple objects, and the voice assistant can generate a video of the target object in response to the user's trigger operation. The object is introduced as a person, of course, the object can also be a pet, a building, etc., which is not limited here.

[0038] In another possible case of the first aspect, after receiving the first operation of the user, the method further includes:

[0039] When the voice assistant determines that the image library has not been processed, in response to the first operation, the sixth interface of the voice assistant is displayed, and the sixth interface includes at least one preset theme.

[0040] It can be understood that, when the gallery has not performed image recognition processing on the images in the gallery, the mobile phone receives the user's first operation, and in response to the first operation, displays at least one preset theme in the sixth interface of the voice assistant.

[0041] In another possible case of the first aspect, the topic recommendation method may further include:

[0042] Receive a ninth operation from the user on a second theme among at least one preset theme; in response to the ninth operation, display a seventh prompt message in the sixth interface, the seventh prompt message being used to prompt that the gallery is in the process of recognizing an image; after the gallery completes the image recognition, display the seventh interface; the seventh interface includes at least one image found by the voice assistant based on the image recognition results of the gallery.

[0043] It can be understood that after the voice assistant receives the user's trigger operation on the second theme, it triggers the gallery to perform image recognition processing. Here, when the gallery performs image recognition processing, the gallery can only perform image recognition processing on images related to the second theme, or the gallery can also perform image recognition processing on all images in the gallery.

[0044] For example, assuming that the second topic is "generate a video of last weekend's trip", the gallery can only perform image recognition processing on the images in the gallery with a time stamp of last weekend, so as to improve the efficiency of video generation through targeted image recognition.

[0045] In another possible case of the first aspect, the topic recommendation method may further include:

[0046] After the image recognition in the gallery is completed, an eighth prompt message is displayed in the sixth interface, and the eighth prompt message is used to prompt that the image corresponding to the second theme has not been found. The seventh prompt message is not displayed in the sixth interface.

[0047] For example, the voice assistant determines that the gallery is currently identifying images and displays Fig.15In the smart interaction interface 1503 shown in (c), the seventh prompt message 1505 is displayed in the smart interaction interface 1503, indicating that the library is in the process of recognizing images. After the voice assistant determines that the library has completed the recognition, it is displayed Fig.15 The eighth prompt information 1506 in the intelligent interactive interface shown in (d).

[0048] In another possible case of the first aspect, the topic recommendation method may further include:

[0049] During the image library recognition process, if there is an abnormality in the image recognition, an abnormal prompt message will be displayed on the sixth interface of the electronic device, and the abnormal prompt message is used to prompt that there is an abnormality in the image library recognition.

[0050] That is to say, during the image recognition process of the gallery, there may be insufficient battery power, cloned images, etc., which may cause abnormalities in image recognition.

[0051] In another possible case of the first aspect, the topic recommendation method may further include:

[0052] When the voice assistant determines that there are new images in the gallery that have not been processed by image recognition, the ninth prompt information is displayed in the first interface. The ninth prompt information is used by the user to perform image recognition on the new images in the gallery that have not been processed by image recognition.

[0053] It can be understood that after the voice assistant determines that the gallery has completed the image recognition process, the voice assistant determines that there are new images in the gallery that have not been processed for image recognition. The voice assistant can prompt the user to trigger the gallery to perform image recognition again.

[0054] In another possible case of the first aspect, the first operation is that the user triggers the icon of the voice assistant to trigger the operation of entering the smart film-taking function, or the first operation is that the user triggers the operation of entering the smart film-taking function by triggering the desktop card of the electronic device, and the desktop card includes an entrance to trigger the entry into the smart film-taking function, or the first operation is that the user triggers the entrance of the first interface provided by the gallery to trigger the operation of entering the smart film-taking function.

[0055] In a second aspect, the present application provides an electronic device comprising: one or more processors; a memory; wherein the memory stores one or more computer programs, and the one or more computer programs include instructions, which, when executed by the electronic device, enable the electronic device to perform a topic recommendation method as described in any one of the above-mentioned first aspects.

[0056] 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 topic recommendation method as described in any one of the first aspects.

[0057] 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 topic recommendation method as described in any one of the first aspects.

[0058] 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

[0059] Figure 1 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0060] Figure 2 A software structure diagram of an electronic device provided in an embodiment of the present application;

[0061] Figure 3 Example of user triggering to enter the intelligent interactive interface provided in the embodiment of the present application Figure 1 ;

[0062] Figure 4 Example of user triggering to enter the intelligent interactive interface provided in the embodiment of the present application Figure 2 ;

[0063] Figure 5 Example of user triggering to enter the intelligent interactive interface provided in the embodiment of the present application Figure 3 ;

[0064] Figure 6 Example of user triggering to enter the intelligent interactive interface provided in the embodiment of the present application Figure 4 ;

[0065] Figure 7 Example of user triggering to enter the intelligent interactive interface provided in the embodiment of the present application Figure 5 ;

[0066] Figure 8 Example of user triggering to enter the intelligent interactive interface provided in the embodiment of the present application Figure 6 ;

[0067] Fig. 9 Topic recommendation examples provided for embodiments of this application Figure 1 ;

[0068] Fig.10 Topic recommendation examples provided for embodiments of this application Figure 2 ;

[0069] Fig.11 Topic recommendation examples provided for embodiments of this application Figure 3 ;

[0070] Fig.12 Topic recommendation examples provided for embodiments of this application Figure 4 ;

[0071] Fig.13 Topic recommendation examples provided for embodiments of this application Figure 5 ;

[0072] Fig.14 Topic recommendation examples provided for embodiments of this application Figure 6 ;

[0073] Fig.15 Topic recommendation examples provided for embodiments of this application Figure 7 ;

[0074] Fig.16 Topic recommendation examples provided for embodiments of this application Figure 8 ;

[0075] Fig.17 Topic recommendation examples provided for embodiments of this application Figure 9 . DETAILED DESCRIPTION

[0076] 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.

[0077] 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.

[0078] 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.

[0079] The embodiment of the present application provides a topic recommendation method, which is applied to an electronic device including a voice assistant, wherein the electronic device receives a first operation of a user, and in response to the first operation, displays a first interface (i.e., an intelligent interactive interface) of the voice assistant. The first interface includes at least one candidate topic, and the candidate topic is generated by the voice assistant according to the image recognition result of the image library of the electronic device for the image in the library.

[0080] It can be understood that after the voice assistant determines that the gallery has completed the image recognition process, the voice assistant responds to the user's first operation and displays a first interface including at least one candidate theme.

[0081] Exemplarily, the topic recommendation 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] In some embodiments, the processor 110 may include one or more interfaces. The interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0089] It is understandable that the interface connection relationship between the modules illustrated in the embodiment of the present application is only a schematic illustration and does not constitute a structural limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0090] The charging management module 140 is used to receive charging input from a charger, where the charger can be a wireless charger or a wired charger.

[0091] The power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, and supplies power to the processor 110, the internal memory 121, the external memory, the display screen 194, the camera 193, and the wireless communication module 160. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle number, battery health status (leakage, impedance), etc.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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 status.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] The key 190 includes a power key, a volume key, etc. The key 190 may be a mechanical key or a touch key. The electronic device 100 may receive key input and generate key signal input related to user settings and function control of the electronic device 100.

[0109] Motor 191 can generate vibration prompts. Motor 191 can be used for incoming call vibration prompts, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, audio playback, etc.) can correspond to different vibration feedback effects. For touch operations acting on different areas of the display screen 194, motor 191 can also correspond to different vibration feedback effects. Different application scenarios (for example: time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

[0110] Of course, it is understandable that the above Figure 1 The figure is only an exemplary description when the electronic device is in the form of a mobile phone. If the electronic device is in the form of a tablet computer, a handheld computer, a personal computer, a wearable device (such as a smart watch, a smart bracelet), etc., the structure of the electronic device may include Figure 1 The structure shown in the figure is less than Figure 1 More structures are shown in the figure, which are not limited here.

[0111] It is understandable that the realization of electronic device functions requires software cooperation in addition to hardware support. The software system of the above electronic device can 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 illustrate the software structure of the electronic device.

[0112] Figure 2 A software structure diagram of an electronic device provided in an embodiment of the present application.

[0113] 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.

[0114] The above-mentioned application layer may include a series of application packages.

[0115] 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, memo, and weather.

[0116] 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.

[0117] 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.

[0118] It should be explained that in this application, the use of a voice assistant to generate at least one candidate theme based on the image recognition results of the image library is only an example. In this solution, any application or module that can obtain pictures stored in an electronic device can perform the image recognition process, and there is no limitation here.

[0119] The application package may also include third-party applications, which are applications that users install after downloading the installation package from an application store (or application market), such as map applications, food delivery applications, reading applications (such as e-books), social applications, and travel applications.

[0120] 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.

[0121] like Figure 2As 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.

[0122] 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.

[0123] 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.

[0124] The view system includes visual controls, such as controls for displaying text, controls for displaying images, etc.

[0125] The phone manager is used to provide communication functions for electronic devices, such as the management of call status (including answering, hanging up, etc.).

[0126] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0127] The notification manager enables applications to display notification information in the status bar, which can be used to convey informational messages and disappear automatically after a short stay without user interaction.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] Based on the above hardware architecture and software architecture, the topic recommendation method provided in the embodiment of the present application is introduced below by taking the electronic device as a mobile phone as an example.

[0132] In one possible case of an embodiment of the present application, the mobile phone receives an operation of triggering a user to start a voice assistant, and in response to the user's triggering operation, the mobile phone can start the voice assistant. After starting the voice assistant, the user can use the various functions provided by the voice assistant. For example, after the mobile phone receives an operation (i.e., a first operation) triggered by the user to enter the intelligent interaction interface, the mobile phone displays the intelligent interaction interface in response to the user's operation. The intelligent interaction interface is an interface of the smart film-making function provided by the voice assistant. Using the smart film-making function of the voice assistant, users can create videos. Among them, in some embodiments, the intelligent interaction interface (first interface) can display at least one candidate theme recommended by the voice assistant of the mobile phone based on the image recognition results of the image library in the gallery.

[0133] The gallery may include multiple images. The images in the gallery may be images taken by the user using the camera of the mobile phone; 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.

[0134] It can be understood that the gallery of the mobile phone includes multiple images. After the mobile phone receives the operation triggered by the user to enter the intelligent interaction interface, the voice assistant of the mobile phone can recommend at least one candidate theme based on the multiple images in the gallery, and display the at least one candidate theme in the intelligent interaction interface of the voice assistant for the user to create a video. For example, the gallery includes images of weekend trips and images of children dancing. The voice assistant can recommend two candidate themes based on the images of weekend trips and images of children dancing in the gallery: "Make a video of weekend trips" and "Make a video of children dancing". The voice assistant can display the candidate themes "Make a video of weekend trips" and "Make a video of children dancing" in the intelligent interaction interface for users to create videos.

[0135] For example, the mobile phone receives a trigger operation of the user selecting a target theme from at least one candidate theme. In response to the user's trigger operation, the voice assistant can obtain an image corresponding to the target theme and display at least one image corresponding to the target theme in the intelligent interaction interface. The mobile phone receives a trigger operation of the user generating a video corresponding to the target theme. In response to the user's trigger operation, the voice assistant can generate a video corresponding to the target theme based on at least one image corresponding to the target theme. The voice assistant can also display a thumbnail of the video corresponding to the target theme in the intelligent interaction interface of the voice assistant.

[0136] There are many ways for users to trigger the entry into the intelligent interactive interface.

[0137] In one embodiment, the user can wake up the voice assistant by voice, long pressing the power button, etc. After the voice assistant is woken up, the mobile phone can display the display interface of the voice assistant. The user can trigger the intelligent interaction interface through the display interface of the voice assistant. For example, the mobile phone displays the main interface. After the mobile phone receives the user's voice to wake up the voice assistant, it displays Figure 3 Interface 300 shown in (a) of FIG. 1 . For example, after the mobile phone receives the voice message "Xiao Y Xiao Y" from the user to wake up the voice assistant, it displays Figure 3 Alternatively, after the mobile phone receives the user's long press operation of the power button 301, in response to the user's long press operation, the mobile phone displays Figure 3 Then, after the mobile phone receives the voice information of "generating a video of a child dancing from childhood to adulthood" input by the user, the mobile phone can recognize the voice information input by the user and display the recognized voice information, such as displaying Figure 3 Interface 302 shown in (b) of FIG. 302. After the mobile phone determines that the user's voice information input is completed, it can display Figure 3 Interface 303 shown in (c). Among them, interface 303 includes an entrance to the display interface of each function provided by the voice assistant.

[0138] 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, such as the above-mentioned smart film function. The display interface of different functions of the voice assistant is 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.

[0139] For example, after the user triggers the voice assistant interface through voice instructions, the mobile phone displays the voice assistant dialogue function interface by default, such as the above interface 303. Among them, the interface 303 includes a menu (such as Figure 3 In the area 306 shown in (c), the menu includes functional themes of various functions, such as "dialogue", "recommendation", "smart film", "text creation", etc. After receiving the user's left and right sliding or voice instruction operation, the voice assistant can switch to display the interface of each function.

[0140] In some implementations, when the mobile phone displays the interface 303 of the voice assistant, for example, after the voice assistant of the mobile phone receives the user's operation of sliding the interface 303 to the left, in response to the user's sliding operation, the display Figure 3 Interface 305 shown in (e) of FIG. 305. If the voice assistant of the mobile phone receives the user's trigger operation on the card in interface 305, in response to the user's trigger operation, the display Figure 3For example, after receiving the user's operation of sliding the interface 303 to the left, the voice assistant of the mobile phone directly displays the user's sliding operation. Figure 3 The intelligent interactive interface 304 shown in (d).

[0141] It should be explained that due to the limited size of the display screen, Figure 3 The entrances to the functions in the area 306 shown in (c) are only examples, and the user can display the entrances to other functions by sliding left or right.

[0142] also, Figure 3 The interface displayed on the mobile phone and the interfaces of the voice assistant shown in the figure are only for illustrative description, and the user's triggering operation is also only for example, which is not limited in the embodiments of the present application. Figure 3 In the interface 303 shown in (c), "Smart Photo" is located on the left side of "Dialogue". After the voice assistant of the mobile phone receives the operation of the user sliding the interface 303 to the left, it responds to the user's sliding operation and displays Figure 3 Interface 305 shown in (e).

[0143] 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 the recommendation interface 403 to the left, the mobile phone displays the Figure 4 When the mobile phone receives a user's trigger operation on any card in the interface 404, in response to the user's trigger operation, the mobile phone displays Figure 4 The intelligent interactive interface 405 shown in (d).

[0144] Each card cover displayed in the above interface 404 corresponds to at least one image, and the cover of the card displayed in the interface 404 is any image in the gallery corresponding to the card. The number of cards displayed in the interface 404 can be preset, for example, the number of cards can be set to 20, 24, etc. Due to the limited size of the display screen, not all cards are fully displayed in the interface 404. The voice assistant receives the user's up and down sliding operation on the interface 404, and in response to the user's sliding operation, other cards can be displayed on the display screen.

[0145] In one case, when the image recognition in the gallery is completed, the order of the multiple cards displayed in the interface 404 can be sorted by the voice assistant according to the image recognition results of the gallery. For example, the voice assistant sorts the generated cards according to the number of pictures that can generate cards in the image recognition results. For example, assuming that both card 406 and card 407 are cards generated based on images in the gallery, card 406 corresponds to 10 images, and card 407 corresponds to 6 images, card 406 is placed in front of card 407.

[0146] In another case, when the gallery has not performed image recognition processing on the images in the gallery, the multiple cards displayed in the interface 404 may be randomly sorted, or may be sorted according to a preset rule. For example, the preset rule may be to sort the cards corresponding to portrait images first, and the cards corresponding to landscape images and pet images later, and so on.

[0147] 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 recognition results of the image in the gallery. In other words, the desktop card includes the entrance to the smart photo function. Figure 5 In (a), when the mobile phone displays interface 501, the mobile phone receives a user's trigger operation on desktop card 502 in interface 501, and displays Figure 5 The intelligent interactive interface 503 shown in (b).

[0148] It can be understood that since the desktop card in interface 501 is generated by the voice assistant based on the image recognition result of the image in the gallery, the desktop card includes the candidate theme of "park scenery" and the entrance of "smart film function" (such as the "create video" control in interface 501), the mobile phone can display the intelligent interaction interface in response to the user's triggering operation of the "create video" control in the desktop card 501. Among them, the intelligent interaction interface displays the image found by the voice assistant. Figure 5 The entrance to the "Smart Film-Making Function" in the desktop card is used only as an example to trigger the display of the smart interactive interface.

[0149] When the mobile phone displays the intelligent interactive interface, the voice assistant can also respond to the user's operation to return to the main interface of the mobile phone. For example, when the voice assistant receives the user's trigger operation on the "return" control 504, or receives the user's sliding down the intelligent interactive interface 503, the voice assistant responds to the user's trigger operation, exits the intelligent interactive interface 503, and displays the interface 501. Figure 5 The interface shown in (b) returns to Figure 5 The interface shown in (a).

[0150] like Figure 5 The intelligent interactive interface 503 shown in (b) also provides a function of returning to the recommendation interface (i.e., icon 505). The voice assistant can respond to the user's operation and return to the recommendation interface. Figure 5 The recommendation interface 506 shown in (c) above. When the mobile phone receives a left-right sliding of the recommendation interface 506 by the user, the display interface can be switched.

[0151] In another embodiment, the user can enter the intelligent interactive interface by searching on the negative screen. Figure 6 In (a), the mobile phone responds to the user's input operation, searches for smart photos in the mobile phone, and displays a smart photo card 602 in the interface 601 according to the search results. The mobile phone receives the user's trigger operation on the smart photo card 602, and responds to the user's trigger operation to display Figure 6 The intelligent interaction interface 603 shown in (b) is shown in FIG. Thus, the intelligent interaction interface can be directly displayed by searching for the intelligent film on the negative one screen, so that the intelligent interaction interface can be quickly entered.

[0152] 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 mobile phone, such as the gallery of the mobile phone, receives the user's trigger operation on the "smart photo" control 702, and in response to the user's trigger operation, displays Figure 7 The voice assistant receives the user's trigger operation on the return control 704, or receives the user's sliding operation on the intelligent interaction interface 703, and in response to the user's operation, exits the intelligent interaction interface 703 and returns to the creation interface 701. Figure 7 (b) Return to Figure 7 Middle (a).

[0153] 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 8Similarly, the mobile phone receives a user's trigger operation on the control 804, or receives a user's sliding down the smart interaction interface 803, and in response to the user's trigger 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).

[0154] The above is explained using the example that the gallery has completed image recognition of the images in the gallery and recommended candidate themes. If the voice assistant responds to the user's trigger to enter the intelligent interactive interface, the voice assistant determines that the gallery has not performed image recognition processing, 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 can display the voice assistant's recommendation interface.

[0155] 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 The recommendation interface 805 shown in (c).

[0156] The above-mentioned image recognition processing may be clustering, semantic recognition and other processing of multiple images in the gallery, and the specific processing process will not be elaborated in detail here.

[0157] The following takes the example of a user triggering entry into an intelligent interactive interface through a creation interface in a gallery to introduce in detail the theme recommendation method of an embodiment of the present application.

[0158] In the embodiment of the present application, it is taken as an example that before the mobile phone receives the user's trigger to enter the intelligent interactive interface through the creation interface in the gallery, the gallery does not perform image recognition processing on the image in the gallery.

[0159] In one embodiment, the mobile phone receives a first operation of the user, and in response to the first operation, displays a second interface of the voice assistant. The second interface includes a first control for triggering the start of smart image recognition. The voice assistant receives the user's trigger operation on the first control, and in response to the user's trigger operation, displays a third interface of the gallery. The third interface includes the progress of image recognition in the gallery. After the voice assistant determines that the image recognition in the gallery is completed, the first interface of the voice assistant is displayed.

[0160] For example, refer to Fig. 9In (a), when the mobile phone displays the creation interface 901 of the gallery, if the gallery of the mobile phone receives the user's trigger operation on the "Smart Photo" control 902, in response to the user's trigger operation (first operation), the voice assistant of the mobile phone displays Fig. 9 The intelligent interactive interface 903 (second interface) shown in (b).

[0161] It is understandable that, since the gallery has not previously performed image recognition processing on the images in the gallery, the intelligent interaction interface 903 may display guidance information or guidance controls to guide the user to trigger the gallery to perform image recognition processing. For example, the intelligent interaction interface 903 includes a "Start Smart Image Recognition" control 904 (first control) for triggering the gallery to perform image recognition processing.

[0162] During the image recognition process of the gallery, the mobile phone can display an interface for the user to view the image recognition progress. If the voice assistant of the mobile phone receives the user's trigger operation on the "Start Smart Image Recognition" control 904, in response to the user's trigger operation, the mobile phone can jump to the image recognition interface (third interface) of the gallery to facilitate the user to view the image recognition progress. Fig. 9 In the process of the library processing the image, the library image recognition interface 905 can display the image recognition progress of the library, such as Fig. 9 In (c), an image recognition progress bar 906 is displayed.

[0163] In some embodiments, during the image recognition process of the gallery, the mobile phone can exit the gallery image recognition interface 905 and display other interfaces, or the mobile phone can start other applications. For example, the mobile phone can start a video application to play a video, or it can also start a news application to play news, and so on. Then, the mobile phone receives a trigger operation triggered by the user to enter the gallery image recognition interface, and in response to the user's trigger operation, enters the gallery image recognition interface again. Exemplarily, during the image recognition process of the gallery, the gallery receives a trigger operation triggered by the user to exit the gallery image recognition interface, and in response to the user's operation, exits the gallery image recognition interface 905. The mobile phone receives a trigger operation triggered by the user to enter the gallery image recognition interface again, and in response to the user's trigger operation, displays the gallery image recognition interface again. Fig. 9 The image library recognition interface 905 shown in (c).

[0164] During the image recognition process in the gallery, after the voice assistant receives other operations triggered by the user, in response to the user's triggering operation, the voice assistant can perform the corresponding task. When the voice assistant receives the user's instructions to perform other tasks, for example, the user instructs the voice assistant to set an alarm, query information, etc. through voice commands, the voice assistant can perform the corresponding tasks normally.

[0165] For example, suppose the phone displays Fig. 9In the process of the gallery image recognition interface shown in (c), the voice assistant receives the user's voice instruction to set the alarm clock. In response to the user's trigger operation, the voice assistant sends the alarm setting instruction to the clock application, so that the clock application sets the alarm clock. During the interaction between the voice assistant and the alarm clock application, the gallery continues to perform image recognition processing, so that the voice assistant can perform other tasks without interrupting the gallery image recognition processing operation, thereby improving the interaction performance between the voice assistant and the user.

[0166] In some embodiments, during the process of the gallery performing image recognition processing, the gallery may perform image recognition processing on the images in the gallery in sequence according to the time stamps of the images in the gallery, or the gallery may perform image recognition processing on the images in the gallery randomly, or the gallery may perform image recognition processing on the images in the gallery according to other specific orders, which are not limited here.

[0167] After the gallery image recognition is completed, the phone can jump from the gallery to the voice assistant and redisplay the intelligent interactive interface of the voice assistant, such as Fig. 9 The intelligent interaction interface 907 (first interface) shown in (e) shows three candidate topics generated by the voice assistant based on the image recognition results of the image library.

[0168] In another embodiment, the mobile phone receives a first operation of the user, and in response to the first operation, displays a second interface of the voice assistant. The voice assistant receives a trigger operation of the user on the first control, and in response to the trigger operation of the user, displays a first prompt message in the second interface to prompt that the gallery is in the process of recognizing images. After the voice assistant determines that the gallery has completed recognizing images, it displays the first interface of the voice assistant.

[0169] That is, the voice assistant receives the user's trigger operation on the "Start Smart Image Recognition" control 904. In response to the user's trigger operation, the mobile phone can continue to display the voice assistant interface, such as the smart interactive interface, and can display a prompt message (first prompt message) to prompt the user that the image library is undergoing image recognition processing. Fig. 9 The smart interactive interface 908 shown in (d) includes a prompt message 909 to remind the user that the library is in the process of image recognition. Similarly, after the image recognition is completed, the mobile phone can display Fig. 9 In other words, during the image recognition process in the gallery, the mobile phone does not actively jump to the gallery image recognition interface, but displays prompt information in the intelligent interaction interface to implement image recognition prompts.

[0170] It should be explained that the number of candidate topics displayed in the intelligent interaction interface is a preset number value. For example, it is preset that a maximum of three candidate topics are displayed in the intelligent interaction interface. When the voice assistant determines that the candidate topics generated based on the image recognition results exceed the preset number, the intelligent interaction interface can display a preset number of candidate topics based on the number of images corresponding to each candidate topic.

[0171] The above is explained by the example that before the mobile phone receives the user's trigger to enter the intelligent interactive interface through the creation interface in the gallery, the gallery has not performed image recognition processing on the images in the gallery, and after the image recognition is triggered, candidate themes can be recommended.

[0172] In some other embodiments, after the image recognition in the gallery is completed, if the voice assistant has not generated a candidate topic based on the image recognition results of the gallery, the fifth interface of the voice assistant is displayed, and the fifth interface includes a fourth prompt message, and the fourth prompt message is used to prompt the voice assistant that the candidate topic has not been generated based on the image recognition results of the gallery.

[0173] It can be understood that if the mobile phone receives a user's trigger to enter the smart interaction interface through the creation interface in the gallery, the image in the gallery has not been processed for image recognition, and no candidate theme is recommended after the image recognition is triggered, then the mobile phone displays a prompt message in the smart interaction interface. Fig. 9 After the image recognition process shown in (c) is completed, the voice assistant does not recommend candidate topics based on the image recognition results, and the mobile phone can display Fig. 9 In the intelligent interaction interface 910 shown in (f), a prompt message 911 is displayed in the intelligent interaction interface 910 to prompt that no candidate topic is recommended.

[0174] In some other embodiments, if the gallery has completed the image recognition process and can recommend candidate themes based on the image recognition results before the mobile phone receives a trigger to enter the smart interaction interface, the mobile phone can display the candidate themes recommended by the voice assistant based on the image recognition results of the gallery in the smart interaction interface. Fig. 9 Intelligent interactive interface 907 shown in (e).

[0175] When at least one candidate theme recommended by the voice assistant based on the image recognition results of the gallery is displayed in the intelligent interactive interface, if the voice assistant receives a trigger operation from the user on any candidate theme (the candidate theme selected by the user can be called a target theme), in response to the user's trigger operation (the third operation), the voice assistant searches for image materials corresponding to the target theme from the gallery to generate a corresponding video based on the image materials corresponding to the target theme.

[0176] For example, refer to Fig.10In (a), the mobile phone displays the intelligent interactive interface 1001 of the voice assistant, which includes three candidate topics. In some embodiments, the voice assistant receives the user's trigger operation on the candidate topic 1002 (target topic). In response to the user's trigger operation (third operation), the voice assistant can obtain the image material corresponding to the target topic, and then display Fig.10 The intelligent interaction interface 1003 shown in (b) of FIG. 1003 includes the image material 1004 corresponding to the target theme queried by the voice assistant according to the user's trigger operation on the target theme. The intelligent interaction interface 1003 also displays a "view photo" control, the number of image materials (such as 12), and a "generate video" control.

[0177] It needs to be explained that Fig.10 The image material corresponding to the target theme shown in (b) is only an example. The material corresponding to the target theme found by the voice assistant can be an image material or a video material. The steps here are limited. In addition, the number of image materials corresponding to the target theme is only an example. When the voice assistant finds that the number of image materials corresponding to the target theme is too large, only part of the images can be displayed in the intelligent interaction interface, for example, Fig.10 There are 12 images of image materials corresponding to the target theme shown in (b), but only 9 images are displayed in the intelligent interactive interface 1003.

[0178] After the voice assistant receives the trigger operation of the user clicking the "view more" control, more images can be displayed in the intelligent interactive interface in response to the user's trigger operation.

[0179] The voice assistant receives the user's trigger operation (fourth operation) on the "generate video" control, or receives the trigger operation (fourth operation) of generating a video indicated by the user's voice, and the voice assistant generates a video corresponding to the target theme according to the multiple images included in the image material 1004. You can also display Fig.10 The intelligent interactive interface 1005 shown in (c) is shown in the intelligent interactive interface 1005. The thumbnail 1006 of the target video corresponding to the generated target theme is displayed in the intelligent interactive interface 1005. The voice assistant receives the user's trigger operation on the video thumbnail 1006, and plays the content corresponding to the video in response to the user's trigger operation. The thumbnail of the video can be one of the images in the image material, or it can be a predefined image, which is not limited in the embodiment of the present application.

[0180] In other embodiments, the voice assistant receives a trigger operation from a user indicating to generate another topic (a first topic different from a candidate topic), and in response to the user's trigger operation (fifth operation), the voice assistant does not obtain image material corresponding to the first topic. Fig.10In the intelligent interaction interface 1007 shown in (d), the voice assistant receives the user's trigger operation of "making a video of Nanjing travel". In response to the user's trigger operation, the voice assistant does not find the corresponding image. The intelligent interaction interface 1007 displays a prompt message 1008 (fifth prompt message) to prompt that the image material for generating the video has not been found.

[0181] In some embodiments, when the voice assistant determines that the keyword of the target subject selected by the user corresponds to multiple identical or similar objects (e.g., children, pets, etc.) based on the image recognition results of the image library, the voice assistant can display multiple objects in the intelligent interactive interface for the user to select. After the voice assistant receives the user's selection operation of the target object, in response to the user's selection operation, it searches for the image material corresponding to the target object to generate a video based on the image material corresponding to the queried target object.

[0182] For example, the voice assistant determines that the target subject (character subject) corresponds to a keyword of a child. Fig.10 In (a), during the process of the mobile phone displaying the intelligent interactive interface 1001 of the voice assistant, the voice assistant receives the user's trigger operation on the candidate subject 1002 (character subject). In response to the user's trigger operation (the sixth operation), the voice assistant determines that there are multiple images of children (multiple candidate characters) in the gallery according to the image recognition results of the gallery, and based on this, it can display Fig.11 The intelligent interaction interface 1101 (first interface) shown in (a) of FIG. 1101 displays images 1102 of multiple children (multiple candidate characters) clustered by the voice assistant based on the image recognition results of the image library. The voice assistant receives the user's selection operation of any child (such as child 1, hereinafter referred to as the target child or target character), and in response to the user's trigger operation (the seventh operation), displays the target child or target character. Fig.11 The intelligent interactive interface 1103 shown in (b) of FIG. 1103 displays a prompt message 1104 to prompt the user that the voice assistant is searching for image materials corresponding to the target child.

[0183] After the voice assistant finds the image material corresponding to the target child, it will display Fig.11 In (c) , the intelligent interaction interface 1105 is shown, and multiple images 1106 corresponding to the target child are displayed in the intelligent interaction interface 1105 .

[0184] The voice assistant receives the user's trigger operation on the "generate video" control (the eighth operation), and generates a target video (character video) in response to the user's trigger operation, such as Fig.11 A thumbnail 1108 of the target video is displayed in the intelligent interactive interface 1107 shown in (d).

[0185] When the voice assistant determines that the image library has not been processed, the voice assistant receives a first operation triggered by the user to enter the intelligent interaction interface, and in response to the first operation, displays a sixth interface of the voice assistant. The sixth interface includes at least one preset theme.

[0186] In some embodiments, when the gallery has not performed image recognition on the images in the gallery, the voice assistant receives an operation instructing the user to generate a video corresponding to the second theme. In response to the user's operation, the voice assistant triggers the gallery to perform image recognition. After the gallery completes image recognition, the voice assistant does not find the material corresponding to the second theme based on the gallery's image recognition results. In this case, a prompt message (the eighth prompt message) is displayed in the intelligent interaction interface of the voice assistant to prompt that the material corresponding to the target theme has not been found and more images can be taken. Exemplarily, during the process of displaying the intelligent interaction interface of the voice assistant on the mobile phone, the voice assistant receives an operation instructing the user to "generate a video of a child's success". In response to the user's operation, the voice assistant finds multiple children, such as Fig.12 In (a), there are images of three children in the interface 1201. The voice assistant receives the user's selection operation for the first child. In response to the user's trigger operation, the voice assistant does not find the image of the child, and displays a prompt message 1202 to prompt the user that the image of the child has not been found and to take more images.

[0187] It can be understood that after the voice assistant receives the user's instruction to generate the target video, the gallery has not completed the image recognition, or the gallery has deleted the image of the first child after the image recognition is completed, resulting in the voice assistant not finding the image of the child. In another example, when the voice assistant determines that there is no image material of the object corresponding to the keyword of the target theme in the gallery based on the image recognition results of the gallery, and the voice assistant determines that there are newly added images in the gallery that have not been processed by image recognition, the voice assistant can prompt the user to perform image recognition on the newly added images by displaying a prompt message (the ninth prompt message) in the intelligent interactive interface, and the user can trigger the gallery to perform image recognition on the newly added images. As a result, after the gallery performs image recognition on the newly added images, it can recommend candidate themes that better meet the user's expectations in the intelligent interactive interface.

[0188] For example, Fig.12The prompt information 1204 displayed in the smart interaction interface 1203 shown in (b) is used to prompt the user to perform smart image recognition on the newly added images. The voice assistant receives the user's trigger operation of "Start Smart Image Recognition". In response to the user's trigger operation, the gallery can perform image recognition. The smart interaction interface 1203 can display prompt information 1205 to prompt the user that the gallery is performing image recognition on the newly added images in the gallery, as well as the image recognition time. After the voice assistant determines that the gallery has completed the image recognition of the newly added images, the voice assistant has not recommended a candidate topic based on the gallery's image recognition results, and displays Fig.12 The prompt message 1207 in the intelligent interactive interface 1206 shown in (c) indicates that the gallery has completed the recognition of the newly added image and has not recommended any theme.

[0189] During the process of the gallery recognizing the image, the mobile phone provides a function of checking the progress of the gallery recognition, that is, during the process of the gallery recognizing the image, the user can check the progress of the gallery recognition.

[0190] In some embodiments, during the image recognition process of the image library, a prompt message can be displayed in the intelligent interaction interface of the voice assistant to prompt the image recognition time of the image library, so that the user can determine whether to wait for the image recognition to end in the intelligent interaction interface based on the image recognition time displayed in the prompt message.

[0191] Optionally, when the voice assistant determines that the image recognition time of the gallery is longer than the preset time, a prompt message can be displayed in the intelligent interaction interface to prompt the image recognition time of the entire image recognition process. Among them, the preset time is a pre-set time, for example, the preset time can be 10s, 15s, and so on. When the voice assistant determines that the image recognition time of the gallery for the images in the gallery is less than the preset time, the image recognition time may not be prompted in the intelligent interaction interface. For example, when the mobile phone determines that the entire image recognition time of the gallery is 8s, the prompt message that can be displayed in the intelligent interaction interface is "Smart image recognition is in progress, please wait."

[0192] Exemplarily, a prompt message 1205 is displayed in the intelligent interactive interface 1203 as shown in (b) of FIG12 , and the prompt message 1205 displays the image recognition time.

[0193] The above embodiments are described by using the example of prompting the image recognition progress in the gallery or through the voice assistant for the user to view. In other embodiments, during the image recognition process of the gallery, a notification control can also be displayed through the control center interface of the mobile phone to prompt the image recognition progress of the gallery. For example, Fig.13 As shown in (a), the control center interface of the mobile phone displays a notification control 1301 for prompting the image recognition progress of the image library, which is used to prompt the image recognition progress of the image library. The mobile phone receives the user's trigger operation on the notification control 1301, and in response to the user's trigger operation, the mobile phone displays Fig. 9 Similarly, when the gallery stops processing the images in the gallery, a prompt message indicating that the image recognition has stopped may also be displayed in the control center interface of the mobile phone. Fig.13 The control center interface shown in (b) shows a notification control 1302 indicating the progress of the image library recognition. The notification control 1302 indicates that the image recognition is stopped. The mobile phone receives a user's trigger operation on the notification control 1302, and in response to the user's trigger operation, the mobile phone displays Fig. 9 The image library recognition interface 906 shown in (c).

[0194] When the library completes the image recognition of the image in the library, the control center interface may also display a prompt message indicating that the image recognition is completed. Fig.13 The control center interface shown in (c) shows a notification control 1305, which displays a prompt message "Smart image recognition has been completed". The mobile phone receives the user's trigger operation on the notification control 1305, and in response to the user's trigger operation, displays Fig.13 The intelligent interaction interface 1306 shown in (d) is shown in the interface 1306. A message control 1307 indicating that the image recognition is completed is displayed. During the image recognition process of the gallery, the mobile phone receives an operation from the user to trigger the display of the intelligent interaction interface again. In response to the user's operation, the intelligent interaction interface of the voice assistant is displayed again. The intelligent interaction interface can display a prompt message indicating that the gallery is recognizing the image.

[0195] In some embodiments, the third interface of the gallery may include an icon of a voice assistant. When the mobile phone displays the third interface of the gallery in which the gallery is identifying images, the mobile phone receives a second operation of the user on the icon of the voice assistant in the third interface of the gallery, and displays a fourth interface of the voice assistant in response to the second operation. The fourth interface includes a second prompt message to prompt the progress of the gallery's identification.

[0196] For example, refer to Fig.14 In (a), when the mobile phone displays the gallery image recognition interface 1401 (the third interface), the gallery receives a user's trigger operation on the voice assistant icon 1402 in the gallery image recognition interface 1401, and in response to the user's trigger operation (the second operation), switches to Fig.14 The intelligent interactive interface 1403 (the fourth interface) shown in (b) above is a diagram showing a prompt message 1404 (the second prompt message) displayed in the intelligent interactive interface 1403 to prompt the user that the library is performing image recognition and the image recognition progress of the library.

[0197] It should be explained that, when the voice assistant icon 1402 is displayed in any interface of the mobile phone, the mobile phone receives a trigger operation of the voice assistant icon 1402 by the user, and in response to the trigger operation of the user, it can switch to the intelligent interaction interface. In other words, no matter which interface of the mobile phone displays the voice assistant icon, the mobile phone receives a trigger operation of the icon by the user, and can start a conversation with the voice assistant, or resume a conversation with the voice assistant.

[0198] The above method in which the user triggers the voice assistant icon in the gallery image recognition interface and then triggers the display of the voice assistant's intelligent interaction interface is only an example. The user can also trigger the entry into the voice assistant's intelligent interaction interface in other ways, which is not limited here.

[0199] In the embodiment of the present application, in the scenario where the gallery does not perform image recognition processing on the images in the gallery, after the mobile phone receives the user's trigger to enter the intelligent interaction interface through the creation interface in the gallery, the pre-set theme can be displayed in the intelligent interaction interface. After the mobile phone receives the user's instruction to generate a certain target theme video, it triggers the gallery to perform image recognition processing on the images in the gallery to determine whether to generate a video corresponding to the target theme based on the image recognition results. In other words, in this scenario, the voice assistant triggers the gallery to perform real-time image recognition processing only after receiving the operation to generate a video.

[0200] For example, refer to Fig.15 In (a), when the mobile phone displays the creation interface 1501 of the gallery, the mobile phone detects the user's triggering operation on the smart film control and displays Fig.15 The intelligent interactive interface 1502 shown in (b) of FIG. 3 is displayed in the intelligent interactive interface 1502. Since the gallery has not yet performed image recognition processing on the images in the gallery, the themes displayed in the intelligent interactive interface 1502 are pre-set themes.

[0201] Display on mobile phone Fig.15 During the process of the intelligent interactive interface 1502 in (b), the mobile phone receives the user's operation on the "Generate Today's Vlog Video" control, or the mobile phone receives the user's voice instruction "Generate Today's Vlog Video" operation, and the voice assistant determines that the time for the gallery to recognize the image in the gallery is less than the preset time, and in response to the user's operation, displays Fig.15 The intelligent interactive interface 1503 shown in (c) is shown in FIG. Fig.15 In the intelligent interactive interface 1503 shown in (c), a dialogue message 1504 and a prompt message 1505 are displayed. The prompt message 1505 indicates "Intelligent image recognition is in progress, please wait...".

[0202] In one case, the phone displays Fig.15In the process of the intelligent interactive interface 1503 shown in (c), when the gallery performs image recognition processing on the images in the gallery, it only performs image recognition processing on the images in the gallery that correspond to the semantics in the dialogue message 1504. For example, the gallery only performs image recognition processing on the images in the gallery whose time mark is today. For another example, the voice assistant receives the user's instruction to "generate a video of tourism in city A". In response to the user's operation, the voice assistant triggers the gallery to perform image recognition processing only on the images of city A in the gallery. Here, the gallery specifically recognizes the images in the gallery, rather than all the images in the gallery, which is conducive to improving the efficiency of obtaining materials corresponding to the theme, so as to improve the efficiency of generating videos.

[0203] In another case, the phone displays Fig.15 During the process of the intelligent interactive interface 1503 shown in (c), the gallery can perform image recognition processing on all images in the gallery, so that in the subsequent process of generating a video, there is no need to trigger the gallery for image recognition.

[0204] When the library determines that there is no image corresponding to the subject in the library based on the image recognition results, the phone displays Fig.15 The prompt information 1506 shown in (d) is used to prompt the user that no image corresponding to the theme has been found.

[0205] When the library determines that the subject corresponds to at least one image based on the image recognition results, the phone displays Fig.15 The control 1507 shown in (e) displays multiple images corresponding to the target theme. Fig.15 The number of images displayed in the control 1507 in (e) is only an example. After the mobile phone detects that the user clicks the trigger operation of the "view photos" control, more images can be displayed in the control 1507.

[0206] In the embodiment of the present application, when the image library determines multiple images corresponding to the target theme based on the image recognition results, the mobile phone can perform similarity detection and / or aesthetic scoring on the multiple images to filter out images with a similarity between any two images less than a similarity threshold and / or an aesthetic score greater than a scoring threshold. As a result, the display effect of the video generated by the mobile phone based on the filtered images is better.

[0207] The voice assistant receives a trigger operation of the user on the "generate video" control, or receives a trigger operation of generating a video indicated by the user's voice. In response to the user's trigger operation, the voice assistant generates a video corresponding to the theme based on multiple images corresponding to the theme in the control 1507, and then displays the video. Fig.15 Video 1508 shown in (f).

[0208] Depend on Fig.15It can be seen that during the entire process of the voice assistant generating the corresponding video in response to the trigger operation instructed by the user, the mobile phone has been displaying the intelligent interactive interface and has not jumped to other interfaces. The user can intuitively see the entire video generation process.

[0209] In another scenario, the voice assistant receives a user trigger operation on the "Generate Today's Vlog Video" control in the smart interaction interface 1502, or receives a user voice instruction to "Generate Today's Vlog Video". The voice assistant determines that the time for the library to recognize images in the library is longer than the preset time. The mobile phone can display a prompt message in the smart interaction interface to remind the user of the time for the library to recognize images. For example, the mobile phone displays Fig.16 The prompt information 1601 shown in (a) is used to prompt the image library to execute the image recognition process.

[0210] It is understandable that when the time it takes for the gallery to recognize images in the gallery is longer than the preset time, a prompt message indicating the recognition time will be displayed in the smart interactive interface of the mobile phone, and the user can determine whether to wait for the recognition results in this interface based on the prompt message.

[0211] In the embodiment of the present application, after the voice assistant receives the user's instruction to generate a video of the target subject, the voice assistant determines that the gallery has not performed image recognition processing on the images in the gallery. Thereafter, during the image recognition processing of the gallery, image recognition abnormalities may occur. The voice assistant may display a prompt message to indicate the cause of the abnormality. For example, Fig.16 The intelligent interactive interface shown in (a) displays a prompt message 1601 to indicate that the image library is in the process of image recognition. Fig.16 During (a), the image recognition process was interrupted due to low battery of the mobile phone, and the display Fig.16 The prompt message 1602 shown in (b) indicates that an abnormality has occurred in the image library recognition.

[0212] Another example Fig.16 As shown in (c), the image recognition process is interrupted because the image library is cloning the image, and the intelligent interactive interface displays a prompt message 1603. Fig.16 As shown in (d), due to an exception in the image library recognition process, the image recognition process is interrupted and the intelligent interactive interface displays a prompt message 1604.

[0213] It should be noted that the above Fig.16The reasons for the abnormal image recognition in the image library shown in (b) to (d) are only examples. During the image recognition process, the image recognition may be interrupted due to other reasons. For example, during the image recognition process of the image library, the mobile phone detects that the device temperature is too high, resulting in the interruption of the image recognition process. In this case, the prompt message "Image recognition is not completed, the device temperature is too high, please cool the device, and it will automatically continue after the temperature drops" can be displayed in the smart interaction interface. For another example, during the image recognition process of the image library, the mobile phone detects that the user has ended the process, resulting in the interruption of the image recognition process. In this case, when the mobile phone displays the smart interaction interface again, the prompt message "Image recognition is not completed, image recognition is interrupted, please continue image recognition" can be displayed in the smart interaction interface.

[0214] In the embodiment of the present application, after the user wakes up the voice assistant by voice, long pressing the power button, etc., he can also interact with the voice assistant by voice to generate a video corresponding to the target theme in the dialogue interface of the voice assistant. Fig.17 The voice assistant's dialogue interface 1701 (i.e., intelligent interactive interface) shown in (a) of FIG. 17 is a diagram of a mobile phone. When the mobile phone displays the voice assistant's dialogue interface 1701, it receives a user's voice instruction "generate a video of a child dancing". In response to the user's voice instruction, the voice assistant determines that the gallery has not yet performed image recognition on the images in the gallery. In this case, the "Start Intelligent Image Recognition" control is displayed in the dialogue interface 1701. After the voice assistant receives the user's voice instruction to start intelligent image recognition, the mobile phone displays the "Start Intelligent Image Recognition" control in response to the user's trigger operation. Fig.17 The image library recognition interface 1702 shown in (b).

[0215] In another case, during the image recognition process of the gallery, the dialog interface of the voice assistant does not jump to the gallery image recognition interface, but a prompt message is displayed in the dialog interface, such as Fig.17 The dialogue interface 1701 shown in (d) displays a prompt message 1703 to remind the user that the gallery is identifying images.

[0216] After the gallery is finished recognizing the image, the phone will display Fig.17 The prompt information 1704 shown in (c) in the figure prompts the user to select the child to be generated from the multiple children recommended according to the image recognition results. For example, when the voice assistant receives the user's selection operation for the first child, in response to the user's selection operation, the voice assistant determines that the image of the child in the image library is not sufficient to generate a video according to the image recognition results of the image library, and displays Fig.17The prompt message 1705 shown in (e) in the figure is displayed to remind the user that there are not enough images available in the gallery. For another example, the voice assistant receives the user's selection operation for the first child. In response to the user's selection operation, the voice assistant determines the image of the child in the gallery based on the image recognition result of the gallery, and the mobile phone displays Fig.17 The prompt information 1706 shown in (f) prompts the user that the voice assistant is searching for the image corresponding to the child.

[0217] In another case, after the gallery has finished recognizing the images in the gallery, when the gallery recommends a child based on the recognition results, the dialogue interface displays the image of the child. The voice assistant receives a trigger operation of the user selecting the child, and in response to the user's operation, directly recommends an image corresponding to the child.

[0218] In the embodiment of the present application, after the image corresponding to the target theme is displayed in the intelligent interactive interface of the voice assistant, the voice assistant receives the user's voice instruction to generate a video, or receives the user's trigger operation on the "generate video" control. In response to the user's operation, the voice assistant generates the corresponding video based on the image corresponding to the target theme, and then displays the generated video cover in the intelligent interactive interface. Thus, the user can quickly generate a video of the user's desired theme through the intelligent interactive interface of the voice assistant.

[0219] It should be noted that the above Figures 3 to 17 The interface and content in the interface shown in the figure are only used as an example, and this application does not limit this. For example, the icon of the voice assistant can be any icon different from the existing application. The figure is only used as an example and is not limited here.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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 topic recommendation method in the above-mentioned embodiment.

[0224] An embodiment of the present application also 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 topic recommendation method in the above-mentioned embodiment.

[0225] 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 topic recommendation method in the above-mentioned embodiment.

[0226] 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 execution instructions, and when the device is running, the processor may execute the computer execution instructions stored in the memory so that the device executes the topic recommendation method performed by the electronic device in the above-mentioned method embodiments.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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 topic recommendation method, characterized in that: Applied to an electronic device including a voice assistant, the method comprises: Receiving a first operation from a user; In response to the first operation, a first interface of the voice assistant is displayed, the first interface including at least one candidate topic; the candidate topic is generated by the voice assistant based on the image recognition results of the image in the gallery of the electronic device.

2. The method according to claim 1, characterized in that: In response to the first operation, displaying a first interface of the voice assistant includes: In response to the first operation, displaying a second interface of the voice assistant, wherein the second interface includes a first control, and the first control is used to trigger the image library to start image recognition processing; In response to the user's operation on the first control, displaying first prompt information on the second interface, wherein the first prompt information is used to prompt that the image library is performing image recognition; After the image library is finished recognizing the image, the first interface of the voice assistant is displayed.

3. The method according to claim 1, characterized in that: In response to the first operation, displaying a first interface of the voice assistant includes: In response to the first operation, displaying a second interface of the voice assistant, wherein the second interface includes a first control, and the first control is used to trigger the image library to start image recognition processing; In response to the user's operation on the first control, displaying a third interface of the gallery, wherein the third interface includes the image recognition progress of the gallery; After the image library is finished recognizing the image, the first interface of the voice assistant is displayed.

4. The method according to claim 3, characterized in that The third interface includes an icon of the voice assistant, and in the process of displaying the third interface of the gallery, the method further includes: receiving a second operation of the user on the icon of the voice assistant; In response to the second operation, a fourth interface of the voice assistant is displayed, wherein the fourth interface includes second prompt information, and the second prompt information is used to prompt the image recognition progress of the gallery.

5. The method according to claim 3 or 4, characterized in that: When the image library is in the process of identifying images, the second interface displays third prompt information, and the third prompt information is used to prompt the image identification time of the image library.

6. The method according to claim 2 or 3, characterized in that: After the image library is finished recognizing the image, the first interface of the voice assistant is displayed, including: After the image recognition in the gallery is completed, if the voice assistant generates at least one candidate theme based on the image recognition results of the gallery, a first interface including the at least one candidate theme is displayed.

7. The method according to claim 2 or 3, characterized in that: The method further comprises: After the image recognition in the image library is completed, if the voice assistant fails to generate the candidate theme based on the image recognition results of the image library, the fifth interface of the voice assistant is displayed, and the fifth interface includes fourth prompt information, and the fourth prompt information is used to prompt the voice assistant that the candidate theme has not been generated based on the image recognition results of the image library.

8. The method according to any one of claims 1 to 7, characterized in that The method further comprises: receiving a third operation of the user on a target topic among the at least one candidate topic; In response to the third operation, displaying at least one image corresponding to the target theme in the first interface, wherein the at least one image is an image in a gallery of the electronic device; Receiving a fourth operation of the user triggering generation of a video; In response to the fourth operation, a thumbnail of a target video is displayed in the first interface, where the target video is generated based on at least one image corresponding to the target subject.

9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: receiving a fifth operation of the user on the video instructing to generate a first theme, the first theme being different from the candidate theme; In response to the fifth operation, fifth prompt information is displayed in the first interface, and the fifth prompt information is used to prompt that the gallery does not include images corresponding to the first theme.

10. The method according to claim 9, characterized in that The method further comprises: In response to the fifth operation, a sixth prompt message is displayed in the first interface, and the sixth prompt message is used to prompt the user to generate videos corresponding to other themes other than the first theme.

11. The method according to any one of claims 1 to 10, characterized in that The candidate topics include a person topic, and the method further includes: receiving a sixth operation of the user on a person theme in the at least one candidate theme; In response to the sixth operation, displaying a plurality of candidate characters in the first interface; receiving a seventh operation performed by the user on a target person among the plurality of candidate persons; In response to the seventh operation, displaying at least one portrait corresponding to the target person in the first interface, wherein the at least one portrait is an image in a gallery of the electronic device; Receiving an eighth operation triggered by a user to generate a character video; In response to the eighth operation, a thumbnail of the character video is displayed in the first interface, and the character video is generated based on at least one portrait corresponding to the target person.

12. The method according to any one of claims 1 to 11, characterized in that: After receiving the first operation of the user, the method further includes: When the voice assistant determines that the gallery has not been processed for image recognition, in response to the first operation, the sixth interface of the voice assistant is displayed, and the sixth interface includes at least one preset theme.

13. The method according to claim 12, characterized in that The method further comprises: receiving a ninth operation of the user on a second theme among the at least one preset theme; In response to the ninth operation, displaying a seventh prompt message in the sixth interface, the seventh prompt message being used to prompt that the image library is in the process of identifying images; After the image recognition in the gallery is completed, the seventh interface is displayed; the seventh interface includes at least one image found by the voice assistant based on the image recognition results of the gallery.

14. The method according to claim 13, characterized in that The method further comprises: After the image recognition in the image library is completed, an eighth prompt message is displayed in the sixth interface, and the eighth prompt message is used to prompt that the image corresponding to the second theme has not been found. The seventh prompt message is not displayed in the sixth interface.

15. The method according to any one of claims 2 to 14, characterized in that: The method further comprises: During the process of image recognition in the image library, if there is an abnormality in the image recognition, an abnormality prompt information is displayed on the sixth interface of the electronic device, and the abnormality prompt information is used to prompt that there is an abnormality in the image recognition in the image library.

16. The method according to any one of claims 1 to 15, characterized in that: The method further comprises: When the voice assistant determines that there are newly added images in the gallery that have not been processed by image recognition, a ninth prompt message is displayed in the first interface, and the ninth prompt message is used by the user to perform image recognition on the newly added images in the gallery that have not been processed by image recognition.

17. The method according to any one of claims 1 to 16, characterized in that: The first operation is that the user triggers the icon of the voice assistant to trigger the operation of entering the smart film-making function, or the first operation is that the user triggers the desktop card of the electronic device to trigger the operation of entering the smart film-making function, and the desktop card includes an entrance to trigger the entry into the smart film-making function, or the first operation is that the user triggers the entrance of the first interface provided by the gallery to trigger the operation of entering the smart film-making function.

18. An electronic device, characterized in that: include: one or more processors; Memory; Wherein, 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 topic recommendation method as described in any one of claims 1-17.

19. A computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, characterized in that: When the instruction is executed on an electronic device, the electronic device executes the topic recommendation method as described in any one of claims 1 to 17.

Images