Statement recommendation method and electronic equipment

Abstract

The invention discloses a statement recommendation method and electronic equipment. The method is applied to the electronic equipment and comprises the steps that a first interface is displayed, and the first interface comprises a first control; in response to a trigger operation on the first control, a second interface is displayed, K recommendation cards and K recommendation statements included in the second interface are in one-to-one correspondence, each recommendation card displays a corresponding recommendation statement, and the K recommendation statements are determined according to portrait data of the user and photo data of the user; each recommendation card is used for triggering the electronic equipment to slice the photo data according to the recommendation statement corresponding to each recommendation card so as to obtain a video associated with the recommendation statement corresponding to each recommendation card, and K is a positive integer. Based on the statement recommendation method provided by the invention, the video generation efficiency can be improved, and the user experience can be improved.

Description

Technical Field

[0001] This application relates to the technical field of terminals, and more particularly, to a sentence recommendation method and an electronic device. Background Art

[0002] After the terminal device interacts with the user, the terminal device can process the photo data stored in the terminal device to generate a video, so as to meet the user's usage requirements.

[0003] In the prior art, in the scenario where the terminal device interacts with the user, after the terminal device recognizes the user's input instruction (such as voice or text), it will process the photo data stored in the terminal device to generate a video based on the recommended sentences of a fixed template. However, this method has the problem that the recommended sentences based on the fixed template cannot generate a video for the photo data stored in the terminal device, or the generated video cannot meet the user's requirements, resulting in a poor user experience. In addition, in the above implementation process, frequent conversations are required between the terminal device and the user, resulting in low video generation efficiency.

[0004] Therefore, how to improve the efficiency of video generation and enhance the user experience has become an urgent problem to be solved at present. Summary of the Invention

[0005] This application provides a sentence recommendation method and an electronic device, which can improve the efficiency of video generation and enhance the user experience.

[0006] In a first aspect, this application provides a sentence recommendation method, which is applied to an electronic device. The method includes: displaying a first interface, where the first interface includes a first control; in response to a trigger operation on the first control, displaying a second interface, where the K recommended cards included in the second interface correspond one-to-one to K recommended sentences, each recommended card displays the corresponding recommended sentence, the K recommended sentences are determined according to the user's portrait data and the user's photo data, and each recommended card is used to trigger the electronic device to process the photo data into a video according to the recommended sentence corresponding to each recommended card, so as to obtain the video associated with the recommended sentence corresponding to each recommended card, and K is a positive integer.

[0007] Each recommended card displays the corresponding recommended sentence, and the content of the recommended sentence displayed on each recommended card is not specifically limited. For example, the recommended sentence displayed on a recommended card may include time, place, person, and event. For example, the recommended sentence displayed on a recommended card may include time, person, and event. Optionally, each recommended card may further include a cover image corresponding to each recommended card.

[0008] The portrait data of the user includes feature data representing the user of the electronic device. For example, the portrait data of the user may include one or more of the following data: age, gender, interests, hobbies, birthday, graduation date, marriage date, hometown, residential address, relationships (for example, the relationships can be but are not limited to parent-child relationship, spouse relationship, parent-child relationship, or friendship, etc.).

[0009] In the above technical solution, after the electronic device receives a trigger operation on the first control of the first interface, the electronic device can directly display a second interface including K recommended cards, where each recommended card is used to generate a video based on the photos in the photo data associated with the recommended statement corresponding to each recommended card. This method avoids the problem of low video generation efficiency in the videos generated by frequent conversations between the user and the electronic device, that is, this method can improve the efficiency of video generation. Since the recommended statements displayed on each recommended card are determined based on the user's portrait data and photo data, it is ensured as much as possible that the recommended statements displayed on each recommended card are content that the user is interested in, so that the videos generated based on each recommended card can better meet the user's needs. This method avoids the problem that videos cannot be generated by processing photo data with fixed-template recommended statements and the generated videos cannot meet the user's needs, that is, this method can improve the user's experience. In summary, this method can improve the efficiency of video generation and enhance the user's experience.

[0010] In a possible implementation manner, in response to a trigger operation on the first control, displaying the second interface includes: in response to a trigger operation on the first control, displaying a third interface, where the third interface includes a plurality of cards corresponding to a plurality of preset categories; in response to a trigger operation on one of the plurality of cards, displaying the second interface.

[0011] The multiple different preset categories are not specifically limited and can be set according to user needs. For example, each preset category can be but is not limited to any of the following categories: my daily video record (video blog, Vlog), family photos, daily gatherings, growth theme, travel Vlog, food collection, my portraits, interests and hobbies, or urban architecture, etc.

[0012] In the above technical solution, after the user triggers the first control on the first interface, the electronic device displays multiple cards including multiple preset categories for the user. The user can trigger a card of one preset category among the multiple cards of multiple preset categories according to their own needs. After that, the electronic device displays a second interface including K recommended cards belonging to the one preset category, so that the videos generated based on each recommended card can better meet the user's needs, thereby improving the user experience. In the above implementation process, only two trigger operations by the user are required for the electronic device to display the second interface, and this method is also beneficial to improving the efficiency of video generation.

[0013] In another possible implementation, after displaying the second interface in response to the trigger operation on the first control, the method further includes: in response to the trigger operation on the first recommended card among the K recommended cards, displaying a fourth interface, where the fourth interface includes a thumbnail of the first video, and the first video is a video associated with the first recommended statement generated by the electronic device after processing the photo data according to the first recommended statement.

[0014] In the above technical solution, after the electronic device receives the trigger operation on the first control of the first interface, the electronic device can directly display the second interface including K recommended cards. After that, after the electronic device receives the trigger operation on the first recommended card, the electronic device displays the fourth interface including the thumbnail of the first video, and the first video is video data generated from the photos in the photo data associated with the first recommended statement corresponding to the first recommended card. This method can improve the convenience and efficiency of video generation. Since the first recommended statement is determined based on the user's portrait data and photo data, it is possible to ensure that the first recommended statement is the content that the user is interested in, so that the video generated by the electronic device based on the first recommended statement displayed on the first recommended card can better meet the user's needs, that is, this method can also improve the user experience.

[0015] In another possible implementation, in response to the trigger operation on the first control, displaying the third interface includes: in response to the trigger operation on the first control, displaying an interface including the second control and the thumbnail corresponding to the photo data; in response to the trigger operation on the second control, displaying the third interface.

[0016] The thumbnail corresponding to the photo data can be the thumbnail corresponding to all the photos of the photo data, or the thumbnail corresponding to some of the photos of the photo data, and no specific limitation is made in this regard.

[0017] In another possible implementation, the method further includes: classifying the photo data to obtain K photo sets corresponding to K different event types, where the K photo sets and K recommended statements are in one-to-one correspondence, and each recommended statement is determined according to the corresponding photo set and the user's portrait data; analyzing and processing each photo set to obtain the memory information of each photo set, where the memory information includes the information recorded by the photos in each photo set; determining the recommended statement corresponding to each photo set according to the memory information and portrait data of each photo set, so as to obtain K recommended statements.

[0018] The memory information of each photo set includes the information recorded by the photos in each photo set, and the information recorded by the photos in each photo set is not specifically limited. For example, the memory information of each photo set includes the time, location, people, and events recorded by the photos in each photo set. For example, the memory information of each photo set includes the time, people, and events recorded by the photos in each photo set.

[0019] In the above technical solution, the electronic device can classify the user's photo data according to the event type. After that, for the user's portrait data and the photo data set of each event type, a recommended statement corresponding to each event type is generated, and the implementation process of the method is relatively simple. Since the recommended statement displayed on each recommendation card is determined based on the user's portrait data and photo data, it can be ensured as much as possible that the recommended statement displayed on each recommendation card is the content that the user is interested in, so that the video generated based on each recommendation card can better meet the user's needs, that is, the method can improve the user's usage experience.

[0020] In another possible implementation, the memory information of each photo set specifically includes the time, location, people, and events recorded by the photos in each photo set, the event is one of the K different event types, and, determining the recommended statement corresponding to each photo set according to the memory information and portrait data of each photo set, so as to obtain K recommended statements, includes: determining the personal information of the person according to the portrait data and the people recorded by the photos in the memory information of each photo set; generating the recommended statement corresponding to each photo set according to the personal information of the person and the memory information of each photo set, so as to obtain K recommended statements.

[0021] The personal information of the person may include the person, the person's relationship, the role of the person (such as child, daughter, son, father, or mother, etc.).

[0022] In the above technical solution, when the memory information of each photo set specifically includes time, location, people, and events, the electronic device can generate a recommendation statement including time, location, people, and events based on the user portrait and the memory information of each photo set.

[0023] In another possible implementation, the photo data is classified to obtain K photo sets corresponding to K different event types, including: screening the photo data according to at least one preset time range to obtain at least one photo set that meets the at least one preset time range; classifying the at least one photo set that meets the at least one preset time range according to the event type to obtain K photo sets.

[0024] In another possible implementation, the electronic device includes a first application, a second application, and a media processing module. The first interface is the interface of the first application, and in response to a trigger operation on the first control, a second interface is displayed, including: in response to the trigger operation on the first control, the first application sends a start instruction to the second application, where the start instruction carries the identifier of the first interface and the identifier of the first control; after the second application receives the start instruction, the second application sends a recommendation statement loading instruction to the media processing module, where the recommendation statement loading instruction is used to request to obtain a recommendation card for generating a video according to the photo data; after the media processing module obtains the recommendation statement loading instruction, the media processing module generates K card information corresponding to the K recommendation cards according to the portrait data and the photo data; the media processing module sends the K card information to the second application; after the second application loads the card information, the second application displays the second interface.

[0025] The K card information corresponds to the K recommendation cards one by one, and each card information is used to generate the corresponding recommendation card, where each card information may include the recommendation statement in the corresponding recommendation card of each card information. Optionally, each card information may further include other information, and the other information may include, but is not limited to, the cover image of the card and the URL of the card, where the URL of the card is used to indicate the address of the resource (such as parameters, etc.) corresponding to each recommendation card, and the resource corresponding to each recommendation card is used to generate the structure (such as an oval or square structure card) of each recommendation card. In this way, the electronic device can obtain the resource corresponding to each recommendation card according to the address indicated by the URL of the card included in each recommendation card.

[0026] In the above technical solution, in the first application of the electronic device, an intelligent video creation entry (i.e., the first control) is added. The user triggers this entry to launch the second application of the electronic device. In the second interface of the second application, multiple recommendation cards including a plurality of recommendation statements generated based on the user's real photo data and portrait data are displayed. The recommendation statements displayed on each recommendation card can be used as prompts for intelligent video creation, thereby effectively improving the convenience and efficiency of the user in creating videos.

[0027] In another possible implementation, the electronic device further includes a media learning module. And after the second application receives a start instruction, the method further includes: the media processing module sends a query instruction to the media learning module; the media learning module sends a query result including portrait data and photo data to the media processing module, so that the media processing module can obtain the portrait data and photo data.

[0028] In the above technical solution, the media processing middleware can obtain the portrait data and photo data stored in the media learning module by interacting with the media learning module. After that, the media processing middleware can determine the K recommendation statements corresponding to the K recommendation cards included in the second interface based on the obtained portrait data and photo data.

[0029] In another possible implementation, the first application is a gallery, the photo data includes the photos stored in the gallery, and the second application is a voice assistant.

[0030] In the above technical solution, in the gallery application of the electronic device, an intelligent video creation entry (i.e., the first control) is added. The user triggers this entry to launch the voice assistant of the electronic device. In the second interface of the voice assistant, multiple recommendation cards including a plurality of recommendation statements generated based on the user's real photo data and portrait data are displayed. The recommendation statements displayed on each recommendation card can be used as prompts for intelligent video creation, thereby effectively improving the convenience and efficiency of the user in creating videos.

[0031] In another possible implementation, the first interface is the desktop of the electronic device, where the desktop of the electronic device includes icons of one or more applications, or the first interface is the interface of an application of the electronic device.

[0032] In the above technical solution, the user can enter the first interface through multiple different ways provided by the electronic device, and this method can flexibly trigger the electronic device to display the first interface.

[0033] In another possible implementation, K is a preset value.

[0034] K is a preset value, and this preset value is a value with an upper limit. The value of K can be predefined or dynamically adjusted. There is no specific limitation on the value of K, and it can be set according to the actual scenario. For example, K can be set equal to 1, 2, 3, etc. according to the user's usage requirements. Another example, K can be set equal to 2, 4, etc. according to the performance of the electronic device.

[0035] In the above technical solution, when K is a preset value, that is, the second interface displayed by the electronic device includes a preset K recommended cards, it can save the resources consumed by the electronic device to generate the recommended cards.

[0036] In a second aspect, the present application provides a statement recommendation device, which is applied to an electronic device. The device includes a processing unit. Wherein, the processing unit is configured to: display a first interface, where the first interface includes a first control; in response to a trigger operation on the first control, display a second interface, where the K recommended cards included in the second interface correspond one-to-one with K recommended statements, and each recommended card displays a corresponding recommended statement. The K recommended statements are determined according to the user's portrait data and the user's photo data. Each recommended card is used to trigger the electronic device to edit the photo data according to the recommended statement corresponding to each recommended card to obtain a video associated with the recommended statement corresponding to each recommended card, and K is a positive integer.

[0037] In a possible implementation manner, the processing unit is further configured to: in response to a trigger operation on the first control, display a third interface, where the third interface includes multiple cards corresponding to multiple preset categories; in response to a trigger operation on one of the multiple cards, display the second interface.

[0038] In another possible implementation manner, the processing unit is further configured to: in response to a trigger operation on the first control, display an interface including a second control and a thumbnail corresponding to the photo data; in response to a trigger operation on the second control, display the third interface.

[0039] In another possible implementation manner, the processing unit is further configured to: after displaying the second interface in response to a trigger operation on the first control, perform the following operations: in response to a trigger operation on the first recommended card among the K recommended cards, display a fourth interface, where the fourth interface includes a thumbnail of a first video, and the first video is a video associated with the first recommended statement generated by the electronic device after editing the photo data according to the first recommended statement.

[0040] In another possible implementation manner, the processing unit is further configured to: classify the photo data to obtain K photo sets corresponding to K different event types, where the K photo sets and the K recommended statements correspond one by one, and each recommended statement is determined according to the corresponding photo set and the portrait data of the user; analyze each photo set to obtain the memory information of each photo set, where the memory information includes the information recorded by the photos in each photo set; determine the recommended statement corresponding to each photo set according to the memory information of each photo set and the portrait data, so as to obtain the K recommended statements.

[0041] In another possible implementation manner, the memory information of each photo set specifically includes the time, location, people, and event recorded by the photos in each photo set, the event is one of the K different event types, and the processing unit is further configured to: determine the personal information of the person according to the portrait data and the people recorded by the photos in the memory information of each photo set; generate the recommended statement corresponding to each photo set according to the personal information of the person and the memory information of each photo set, so as to obtain the K recommended statements.

[0042] In another possible implementation manner, the processing unit is further configured to: screen the photo data according to at least one preset time range to obtain at least one photo set that meets the at least one preset time range; classify and process the at least one photo set that meets the at least one preset time range according to the event type to obtain the K photo sets.

[0043] In another possible implementation manner, the first interface is the desktop of the electronic device, where the desktop of the electronic device includes icons of one or more applications, or the first interface is the interface of an application of the electronic device.

[0044] In another possible implementation manner, K is a preset value.

[0045] In a third aspect, an electronic device is provided, including a unit for executing any one of the statement recommendation methods in the first aspect. This device can be a terminal device or a chip inside the terminal device. This device can include an input unit and a processing unit.

[0046] When the device is a terminal device, the processing unit can be a processor, and the input unit can be a communication interface; the terminal device can further include a memory for storing computer program code. When the processor executes the computer program code stored in the memory, the terminal device executes any one of the statement recommendation methods in the first aspect.

[0047] When the device is a chip in a terminal device, the processing unit may be a processing unit inside the chip, and the input unit may be an output interface, a pin, a circuit, etc.; the chip may further include a memory, and the memory may be a memory inside the chip (for example, a register, a cache, etc.), or may be a memory located outside the chip (for example, a read-only memory, a random-access memory, etc.); the memory is used to store computer program code, and when the processor executes the computer program code stored in the memory, the chip is caused to execute any one of the statement recommendation methods in the first aspect.

[0048] In a possible implementation, the memory is used to store computer program code; a processor, the processor executes the computer program code stored in the memory, and when the computer program code stored in the memory is executed, the processor is used to execute any one of the statement recommendation methods in the first aspect.

[0049] In a fourth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores computer program code, and when the computer program code is run by a statement recommendation device, the statement recommendation device is caused to execute any one of the statement recommendation methods in the first aspect.

[0050] In a fifth aspect, a computer program product is provided, and the computer program product includes: computer program code, and when the computer program code is run by a statement recommendation device, the statement recommendation device is caused to execute any one of the statement recommendation methods in the first aspect.

[0051] It can be understood that the beneficial effects of the above second aspect to the fifth aspect can be referred to the relevant descriptions in the above first aspect, and will not be elaborated here.

[0052] It should be understood that the description of technical features, technical solutions, beneficial effects or similar languages in this application does not imply that all features and advantages can be realized in any single embodiment. On the contrary, it can be understood that the description of features or beneficial effects means that at least one embodiment includes specific technical features, technical solutions or beneficial effects. Therefore, the descriptions of technical features, technical solutions or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and beneficial effects described in this embodiment can be combined in any appropriate manner. Those skilled in the art will understand that an embodiment can be implemented without one or more specific technical features, technical solutions or beneficial effects of a specific embodiment. In other embodiments, additional technical features and beneficial effects can also be identified in specific embodiments that do not embody all embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of the hardware system of the electronic device 100 provided by an embodiment of the present application.

[0054] Figure 2 It is a schematic diagram of the software system of the electronic device 100 provided by an embodiment of the present application.

[0055] Figure 3 It is a schematic diagram of the system architecture applicable to the statement recommendation method provided by an embodiment of the present application.

[0056] Figure 4 It is a schematic diagram of a process for obtaining portrait data and memory nodes provided by an embodiment of the present application.

[0057] Figure 5 It is a schematic diagram of an entrance interface of an electronic device provided by an embodiment of the present application.

[0058] Figure 6 It is a schematic diagram of an intelligent video editing interface of an electronic device provided by an embodiment of the present application.

[0059] Figure 7 It is a schematic diagram of an intelligent video editing interface of an electronic device provided by an embodiment of the present application.

[0060] Figure 8A It is a schematic diagram of an intelligent video editing interface of an electronic device provided by an embodiment of the present application.

[0061] Figure 8B It is a schematic diagram of an intelligent video editing interface of an electronic device provided by an embodiment of the present application.

[0062] Figure 9A It is a schematic diagram of an intelligent video editing interface of an electronic device provided by an embodiment of the present application.

[0063] Figure 9B It is a schematic diagram of an intelligent video editing interface of an electronic device provided by an embodiment of the present application.

[0064] Figure 10 It is a schematic diagram of an intelligent video editing interface of an electronic device provided by an embodiment of the present application.

[0065] Figure 11 It is a schematic diagram of an entrance interface of an electronic device provided by an embodiment of the present application.

[0066] Figure 12 It is a schematic diagram of an entrance interface of an electronic device provided by an embodiment of the present application.

[0067] Figure 13 It is a schematic diagram of an entrance interface of an electronic device provided by an embodiment of the present application.

[0068] Figure 14 It is a schematic diagram of a sentence recommendation method provided by an embodiment of the present application.

[0069] Figure 15 It is the above Figure 14 Schematic diagram of the specific implementation process of S1412 in the provided sentence recommendation method.

[0070] Figure 16 It is a schematic diagram of a sentence recommendation method provided by an embodiment of the present application.

[0071] Figure 17 It is a schematic diagram of a sentence recommendation device provided by an embodiment of the present application. Detailed implementation manners

[0072] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0073] In the embodiments of the present application, any two of the three description methods of "picture", "image", and "photo" can be interchanged, that is, the meanings represented by any two of these three description methods are the same.

[0074] The camera hardware test method provided by the embodiments of the present application can be applied to an electronic device. For example, the electronic device can be but is not limited to a mobile phone, a smart screen, a tablet computer, a wearable electronic device, a vehicle-mounted electronic device, an augmented reality (AR) device, a virtual reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a projector, a vehicle-mounted device, etc. That is, the specific type of the electronic device is not limited in the embodiments of the present application.

[0075] Next, the hardware structure and software structure of the electronic device will be introduced in detail in conjunction with the accompanying drawings.

[0076] Figure 1 It is a schematic diagram of the hardware system of the electronic device 100 provided by the embodiments of the present application.

[0077] The type of the electronic device 100 is not specifically limited and can be selected according to the actual scenario. Exemplarily, the electronic device 100 can be a mobile phone, a smart screen, a tablet computer, a wearable electronic device, a vehicle-mounted electronic device, an augmented reality (AR) device, a virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a projector, a vehicle-mounted device, and so on. The embodiments of the present application do not impose any restrictions on the specific type of the electronic device 100.

[0078] 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, a headphone 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, a barometric 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.

[0079] It should be noted that Figure 1 the structure shown does not specifically limit the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than Figure 1 the components shown, or the electronic device 100 may include Figure 1 a combination of certain components among the components shown, or the electronic device 100 may include Figure 1 sub-components of certain components among the components shown. Figure 1 The components shown may be implemented in hardware, software, or a combination of software and hardware.

[0080] The processor 110 may include one or more processing units. For example, the processor 110 may include at least one of the following processing units: an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and a neural-network processing unit (NPU). Among them, different processing units may be independent devices or integrated devices.

[0081] The controller may generate operation control signals according to the instruction operation code and timing signals to complete the control of fetching and executing instructions.

[0082] A memory may also be provided in the processor 110 for storing instructions and data. For example, the processor 110 may store instructions for executing the camera hardware test method provided in the embodiments of the present application. For example, the processor 110 may store data obtained by executing the camera hardware test method provided in the embodiments of the present application. In some embodiments, the memory in the processor 110 is a cache memory. This memory may save the instructions or data that the processor 110 has just used or recycled. If the processor 110 needs to use the instruction or data again, it can directly call it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system. In some embodiments, the processor 110 may include one or more interfaces. For example, the processor 110 may include at least one of the following interfaces: an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM interface, and a USB interface.

[0083] Figure 1The connection relationships between the modules shown are only illustrative and do not constitute a limitation on the connection relationships between the modules of the electronic device 100. Optionally, the modules of the electronic device 100 may also adopt a combination of various connection methods in the above embodiments.

[0084] The electronic device 100 can implement a display function through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, connected to 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, which execute program instructions to generate or change display information.

[0085] The display screen 194 can be used to display images or videos. For example, the display screen 194 can display images or videos captured by the camera application of the electronic device, etc. The display screen 194 includes a display panel. The display panel can adopt a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a mini light-emitting diode (Mini LED), a micro light-emitting diode (Micro LED), a micro OLED (Micro OLED), or a quantum dot light-emitting diode (QLED). In some embodiments, the electronic device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1.

[0086] The electronic device 100 can implement a shooting function through an ISP, a camera 193, a video codec, a GPU, a display screen 194, and an application processor, etc.

[0087] The ISP is used to process the data fed back by the camera 193. For example, when taking a photo, the shutter is opened, and light passes through the lens and is transmitted to the camera photosensitive element. The optical signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing and converts it into an image visible to the naked eye. The ISP can perform algorithm optimization on the noise, brightness, and color of the image. The ISP can also optimize parameters such as the exposure and color temperature of the shooting scene. In some embodiments, the ISP may be provided in the camera 193.

[0088] The camera 193 is used to capture images (e.g., still images) or videos. For example, the images or videos captured by the camera 193 can be stored in the database 342 included in the gallery database 340 shown below Figure 3 The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in standard red green blue (RGB), YUV and other formats. In some embodiments, the electronic device 100 may include one or N cameras 193, where N is a positive integer greater than 1.

[0089] The external memory interface 120 can be used to connect an external memory card, such as a secure digital (SD) card, to implement the storage capacity expansion of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement the data storage function.

[0090] The internal memory 121 can be used to store computer-executable program code, and the executable program code includes instructions. For example, the instructions for executing the camera hardware test method provided by the embodiments of the present application can be 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 can store the operating system and application programs required for at least one function (e.g., the sound playback function and the image playback function). The data storage area can store the data created during the use of the electronic device 100 (e.g., audio data and phone book). In addition, the internal memory 121 may include high-speed random access memory, and may also include non-volatile memory, such as: at least one disk storage device, a flash memory device, and a universal flash storage (UFS), etc. The processor 110 executes various processing methods of the electronic device 100 by running the instructions stored in the internal memory 121 and / or the instructions stored in the memory provided in the processor.

[0091] The gyroscope sensor 180B can be used to determine the motion posture of the electronic device 100. In some embodiments, the angular velocity of the electronic device 100 about three axes (i.e., the x-axis, y-axis, and z-axis) can be determined by the gyroscope sensor 180B. The gyroscope sensor 180B can be used for anti-shake shooting. For example, when the shutter is pressed, the gyroscope sensor 180B detects the angle of jitter of the electronic device 100, calculates the distance that the lens module needs to compensate according to the angle, and enables the lens to offset the jitter of the electronic device 100 through reverse movement to achieve anti-shake. The gyroscope sensor 180B can also be used in scenarios such as navigation and motion-sensing games.

[0092] The distance sensor 180F is used to measure distance. The electronic device 100 can measure distance through infrared or laser. In some embodiments, for example, in a shooting scenario, the electronic device 100 can use the distance sensor 180F to measure distance to achieve rapid focusing. For example, the distance sensor 180F can be but is not limited to a TOF sensor.

[0093] The touch sensor 180K, also known as a touch control device. The touch sensor 180K can be disposed on the display screen 194. The touch sensor 180K and the display screen 194 form a touch screen, and the touch screen is also called a touch control screen. The touch sensor 180K is used to detect touch operations acting on or near it. For example, the touch sensor 180K is used to detect the touch operation of the user triggering the creation video control 510 shown below. Figure 5 Another example is that the touch sensor 180K is used to detect the touch operation of the user triggering the control 600 shown below. Figure 6 The touch sensor 180K can transmit the detected touch operation to the application processor to determine the type of touch event. The touch sensor 180K can provide a visual output related to the touch operation through the display screen 194. In some other embodiments, the touch sensor 180K can also be disposed on the surface of the electronic device 100 and at a different position from the display screen 194.

[0094] The motor 191 can generate vibrations. In some implementations, the motor 191 can be an automatic focus (AF) motor for a camera. The camera AF is used to adjust the focus of the lens to make the photographed object clear and sharp. It can drive the lens assembly to move forward and backward according to the user's manual operation or the instructions of the automatic focusing system. The camera AF is usually driven by the electronic control system or motor inside the camera, and precisely controls the movement of each lens assembly according to the user's operation or the instructions of the automatic control algorithm to achieve the shooting requirements and the desired shooting effect. In some other implementations, the motor 191 can be used for incoming call reminders and can also be used for touch feedback. The motor 191 can produce different vibration feedback effects for touch operations on different applications. For touch operations on different areas of the display screen 194, the motor 191 can also produce different vibration feedback effects. Different application scenarios (such as time reminders, receiving messages, alarms, and games) can correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

[0095] The hardware system of the electronic device 100 has been described in detail above. Now, the software system of the electronic device 100 will be introduced. The software system can adopt a layered architecture, an event-driven architecture, a microkernel architecture, a microservices architecture, or a cloud architecture. In the embodiments of this application, the layered architecture is taken as an example to exemplarily describe the software system of the electronic device 100.

[0096] Exemplarily, Figure 2 The schematic diagram of the software system of the electronic device 100 provided by the embodiments of this application. Refer to Figure 2 In this case, the software system adopts a layered architecture. The layered architecture divides the software into several layers, and each layer has a clear role and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into five layers, from top to bottom, namely the application layer 210, the application framework layer 220, the Android Runtime and core library layer 230, the hardware abstract layer (HAL) 240, and the kernel layer 250.

[0097] The application layer 210 can include a series of application packages. For example, the application packages can include applications such as a voice assistant (such as the YOYO intelligent assistant), a camera, a gallery, video editing, chat, call, map, navigation, calendar, Bluetooth, music, and video.

[0098] Each of the above applications may include more specific functional modules, and the functions and numbers of the functional modules included in each application are not specifically limited. For example, the language assistant may include a dialogue module, a language model, a statement recommendation module, and a creation card loading module. For example, video editing may include an editing module, a playback module, and service modules (such as a computer vision analysis module and a transition recognition module, etc.). For example, the gallery may include a business module and a notification module. For example, the camera may include a photographing module.

[0099] Each of the above applications can be used to generate application data. For example, the language assistant is used to answer questions input by users. For example, in response to a user triggering the language assistant, the language assistant presents at least one recommended card to the user, where the at least one recommended card includes recommended statements, and the at least one recommended card is associated with one or more photos corresponding to the recommended statements.

[0100] For example, the gallery is used to generate photos. For example, video editing is used to perform editing processing on a video (such as adding special effects and / or deleting video content, etc.) to obtain an edited video.

[0101] The application framework layer 220 provides application programming interfaces (APIs) and programming frameworks for the applications in the application layer. The application framework layer 220 includes some predefined functions.

[0102] As Figure 2 shown, the application framework layer 220 may include a window manager, a notification manager, an activity manager, an input manager, a view system, a content provider, a resource manager, etc.

[0103] The window manager provides a window manager service (WMS), and the WMS can be used for window management, window animation management, surface management, and as a transfer station for the input system.

[0104] The content provider is used to store and obtain data, and make this data accessible to applications. The data may include videos, images, audio, dialed and answered calls, browsing history and bookmarks, phone books, etc.

[0105] The view system includes visual controls, such as controls for displaying text, controls for displaying pictures, etc. The view system can be used to build applications.

[0106] The display interface can be composed of one or more views. For example, a display interface including a text message notification icon may include a view for displaying text and a view for displaying pictures. For example, the display interface may but is not limited to be the one in the following text from 5 toFigure 13 The page shown in

[0107] The resource manager provides various resources for the application, such as localized strings, icons, pictures, layout files, video files, and so on.

[0108] The notification manager enables the application to display notification information in the status bar. It can be used to convey notification-type messages, which can disappear automatically after a short stay without user interaction. For example, the notification manager is used to inform that the download is complete, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as the notification of a background-running application, or a notification that appears in the form of a dialogue window on the screen. For example, it prompts text information in the status bar, emits a prompt sound, the electronic device vibrates, the indicator light flashes, etc.

[0109] The activity manager can provide the activity manager service (AMS). AMS can be used for the startup, switching, scheduling of system components (such as activities, services, content providers, broadcast receivers), and the management and scheduling of application processes.

[0110] The input manager can provide the input manager service (IMS). IMS can be used to manage the input of the system, such as touch screen input, key input, sensor input, etc. IMS retrieves events from the input device node and distributes the events to the appropriate window through interaction with the WMS.

[0111] Android Runtime includes the core libraries and the virtual machine. Android Runtime is responsible for the scheduling and management of the Android system.

[0112] The core libraries include two parts: one part is the functional functions that need to be called by programming languages (such as the Java language), and the other part is the core libraries of Android.

[0113] The application layer 210 and the application framework layer 220 run in the virtual machine. The virtual machine executes the programming files (such as Java files) of the application layer 210 and the application framework layer 220 as binary files. The virtual machine is used to perform functions such as object lifecycle management, stack management, thread management, security and exception management, and garbage collection.

[0114] The core library layer 230 can include multiple functional modules. For example: surface manager, media framework, libc, SQLite, OpenGL ES, Webkit, etc.

[0115] The Surface Manager is used to manage the display subsystem and provides the fusion of 2-Dimensional (2D) and 3-Dimensional (3D) layers for multiple applications.

[0116] The media framework supports the playback and recording of a variety of common audio and video formats, as well as static image files, etc.

[0117] The libc (C library) is the standard library of the C language. Libc is one of the most fundamental libraries in the system and is implemented through Linux system calls. For example, libc can be used to connect to or disconnect from the camera service, set the camera's shooting parameters, start and stop previewing, take pictures, etc.

[0118] The Hardware Abstraction Layer (HAL) 240 is an interface layer located between the operating system kernel and the upper-layer software, and its purpose is to abstract the hardware. The hardware abstraction layer is an abstract interface for the device kernel driver and is used to implement an application programming interface for accessing the underlying device to a higher-level Java API framework. HAL contains multiple library modules, such as the camera HAL (such as aperture, TOF sensor, lens, or focus motor, etc.), the Vendor repository, the display screen, Bluetooth, audio, etc. Each of these library modules implements an interface for a specific type of hardware component. It can be understood that the camera HAL can provide an interface for the camera FWK to access hardware components such as the camera. The Vendor repository can provide an interface for the media FWK to access hardware components such as the encoder. When the system framework layer API requests access to the hardware of the portable device, the Android operating system will load the library module for this hardware component.

[0119] The kernel layer 250 is the foundation of the Android operating system, and all the final functions of the Android operating system are completed through the kernel layer. The kernel layer can include display drivers, camera drivers, audio drivers, and sensor drivers.

[0120] It should be noted that the Figure 2 schematic diagram of the software structure of the electronic device shown is only an example and does not limit the specific module division in different layers of the Android operating system. Specifically, reference can be made to the introduction of the software structure of the Android operating system in conventional technologies. In addition, the shooting method provided in this application can also be implemented based on other operating systems (such as IOS or HarmonyOS, etc.), and this application will not list them one by one.

[0121] Figure 3 is a schematic diagram of the system architecture applicable to the statement recommendation method provided in the embodiments of this application. As Figure 3As shown, the system architecture includes an entrance 300, a voice assistant 310, a media processing middle platform 320, a media learning middle platform 330, a gallery database 340, and a video editing module 350. It can be understood that Figure 3 Each of the modules shown is a module in the terminal device.

[0122] The entrance 300 includes multiple entrance methods, namely a desktop entrance 300a, a gallery application entrance 300b, and a system entrance 300c. Among them, each entrance method is used to call the dialogue module 311 in the voice assistant 310, that is, through each entrance, the dialogue module 311 in the voice assistant 310 can be entered, so that the electronic device displays the interface corresponding to the dialogue module 311.

[0123] Exemplarily, the desktop entrance 300a may include any of the following entrance methods: a desktop quick entrance, a global search entrance, a YOYO desktop card entrance, or a gallery desktop card entrance. For example, Figure 5 As shown in the desktop S5 of the mobile phone, the desktop S5 includes a desktop quick entrance 500. In response to the user triggering the video creation control 510 in the desktop quick entrance 500, the mobile phone can display the interface corresponding to the dialogue module 311 in the voice assistant 310.

[0124] Exemplarily, the gallery application entrance 300b may include any of the following entrance methods: the creation page of the gallery or the floating ball of the voice assistant 310 on the picture page. For example, Figure 13 As shown in the floating ball 1300 displayed on the photo page S13 provided by the mobile phone, in response to the user triggering the floating ball 1300, the mobile phone can display the interface corresponding to the dialogue module 311 in the voice assistant 310.

[0125] Exemplarily, the system entrance 300c may include any of the following entrance methods: voice or the power button. For example, taking the power button as an example, when the electronic device displays a desktop including at least one application icon, the user presses the power button of the electronic device and holds it for about 0.5 to 1 second. Then, in response to the vibration of the electronic device, the user releases the finger, and the interface of the dialogue module 311 in the voice assistant 310 can be seen on the screen of the electronic device, indicating that the dialogue module 311 has been successfully entered. For example, taking voice as an example, in the voice wake-up interface, the user says "Hello YOYO", and the voice assistant 310 can be successfully woken up. Then, after the user wakes up the voice assistant 310, the user says "Please open the dialogue module 311 of the voice assistant 310", and then the interface of the dialogue module 311 in the voice assistant 310 is displayed on the screen of the electronic device, indicating that the dialogue module 311 has been successfully entered.

[0126] The voice assistant 310 is used to obtain the input instructions of the user through the interactive interface of the voice conversation and / or text conversation provided to the user, and send a data loading instruction associated with the input instructions of the user to the creation card management module 321 in the media processing middle platform 320. The data loading instruction carries an entry identifier (for example, a desktop shortcut entry identifier) and a smart video creation identifier. The entry identifier is used to identify the entry, and the smart video creation identifier is used to identify the smart video creation. The smart video creation of the terminal device (also known as the smart video creation button or control) is used to launch the YOYO smart assistant of the terminal device, and display the recommended statements (also known as prompt words) for generating smart video creation based on the user's portrait data and the user's photo data in the skill interface of the launched YOYO smart assistant.

[0127] In one example, the voice assistant 310 may include Figure 3The shown dialogue module 311, language model 312, creation card loading module 313, statement recommendation module 314, text creation module 315, and knowledge Q&A module 316. Specifically, the dialogue module 311 is used to obtain the input instructions of the user. For example, the input instructions of the user can be text or voice. The language model 312 is used to identify the input instructions of the user obtained by the dialogue module 311, and send the recognition result corresponding to the input instructions of the user to the creation card loading module 313. For example, the language model 312 can be, but is not limited to, a large language model (LLM). The creation card loading module 313 is used to generate a data loading instruction associated with the input instructions of the user according to the recognition result corresponding to the input instructions of the user obtained from the language model 312, and send the data loading instruction to the creation card management module 321 included in the media processing middle platform 320, so that the creation card management module 321 returns the recommendation information associated with the input instructions of the user based on the data loading instruction to the creation card loading module 313. The creation card loading module 313 can also obtain the edited video from the editing module 351 of the video clip 350. In one example, the recommendation information can include recommended statements. In another example, the recommendation information can include recommended statements, the uniform resource locator (URL) of the card encapsulating the recommended statements, and the cover image of the card encapsulating the recommended statements. In one example, the target recommended statement can be a statement containing the four elements of time, place, person, and event. For example, the target recommended statement can be "Xiaoming played with his classmates at the school gate yesterday", and "played" is the event. In another example, the target recommended statement can be a statement containing the four elements of time, place, person, and interest. For example, the target recommended statement can be "Xiaoming took pictures in the park yesterday", and "took pictures" is the interest. The statement recommendation module 314 is used to display the recommendation information obtained by the creation card loading module 313 to the user. For example, the statement recommendation module 314 can, but is not limited to, display the recommendation information to the user in the form of a recommendation card. The text creation module 315 is used to perform text editing processing on pictures and / or videos, such as adding text, etc. The knowledge Q&A module 316 is used to answer the questions input by the user.

[0128] There is no specific limitation on the name of the voice assistant 310. For example, the name of the voice assistant 310 can be, but is not limited to, YOYO Smart Assistant or YOYO Smart Assistant.

[0129] The media processing middleware 320 is used to obtain a data loading instruction associated with the user's input instruction from the voice assistant 310, and process the portrait data and memory nodes obtained from the media learning middleware 330 according to the data loading instruction to obtain the recommended information described above. Then, the recommended information is returned to the voice assistant 310 so that the voice assistant 310 can display the recommended information to the user after loading the recommended information.

[0130] The portrait data includes data for representing the user characteristics of the terminal device, and the content included in the portrait data is not specifically limited. For example, the portrait data may include, but is not limited to, one or more of the following data: the age, gender, interests, hobbies, birthday, graduation date, graduation school, marriage date, account, hometown, residential address, work experience of the user of the terminal device, and the personal relationships of the user of the terminal device (for example, parents, spouse, children, friends, teachers and students, and colleagues).

[0131] The memory nodes include the time range corresponding to the photos stored in the terminal device, the location corresponding to the photos stored in the terminal device, the events corresponding to the photos stored in the terminal device, and the people associated with the photos stored in the terminal device. Neither the time range nor the events are specifically limited. For example, the time range may be, but is not limited to, at least one of the following ranges: yesterday, this week, last week, this month, last month. For example, the events may be, but are not limited to, at least one of the following events: having a birthday, family gathering, wedding, graduation ceremony, travel, play, food, sports, scenery, with a cat, with a dog. The people associated with the photos include the people involved in the photos. For example, if photo A includes Xiaoming and Zhang, then the people associated with photo A include Xiaoming and Zhang.

[0132] In one example, the media processing middleware 320 may include Figure 3 the shown creation card management module 321, recall material processing module 322, and finished video module 323. Specifically, the creation card management module 321 obtains the data loading instruction from the creation card loading module 313 and sends the data loading instruction to the recall material processing module 322. The recall material processing module 322 obtains the portrait data and memory nodes described above from the media learning middleware 330, and processes the portrait data and memory nodes according to the data loading instruction to obtain the recommended information described above. The creation card management module 321 obtains the recommended information from the recall material processing module 322 and obtains the data associated with the recommended information. Next, the creation card management module 321 Figure 3 obtains the material corresponding to the recommended information through the shown search material module, and then, through Figure 3The shown screening material module screens the materials obtained from the search material module. Thereafter, the selected material module selects the materials obtained from the screening material module. Then, the theme title generation module is used to generate title information for the materials obtained from the screening material module. Finally, the video production module 323 processes the title information and materials obtained from the theme title generation module to obtain the video associated with the recommended statement in the recommended information. The video production module 323 can send the obtained video to the creation card loading module 313, so that the video is displayed to the user through the interface of the voice assistant 310. The video production module 323 can send the obtained video to the video editing 350, so that the video editing 350 can edit and process the video data obtained in the foregoing steps (for example, adding special effects, adding text, adding audio, etc.).

[0133] The media learning middle platform 330 is used to learn the pictures obtained from the database 342 in the picture library database 340, and store the learned portrait data and memory nodes. In one example, the media learning middle platform 330 may include Figure 3 The shown portrait learning module 331, portrait storage module 332, memory learning module 333, and memory storage module 334. Specifically, the portrait learning module 331 is used to learn the user portrait in the pictures obtained from the database 342, and send the obtained portrait data of the user to the portrait storage module 332, so that the portrait storage module 332 stores the obtained portrait data. The memory learning module 333 is used to learn the time, place, and people in the pictures obtained from the database 342 to obtain memory nodes, and send the obtained memory nodes to the memory storage module 334, so that the memory storage module 334 stores the obtained memory nodes. Thereafter, when the media processing middle platform 320 needs to obtain portrait data and memory nodes, the media processing middle platform 320 can obtain portrait data from the portrait storage module 332 and obtain memory nodes from the memory storage module 334.

[0134] The picture library database 340 is used to store photos and extract information from the photos. In one example, the picture library database 340 may include Figure 3 The shown computer vision (CV) analysis module 341 and database 342. Specifically, the computer vision analysis module 341 is used to obtain information from pictures. For example, if a picture is a picture of a child playing in the park, information such as the child playing in the park can be obtained based on the processing of this picture by the computer vision analysis module 341. The database 342 is used to store pictures and the information extracted from the pictures by the computer vision analysis module 341. For example, the pictures stored in the database 342 can be pictures taken by the camera of an electronic device, or pictures obtained by the electronic device through a chat application, etc.

[0135] The video clip module 350 is used to process the video obtained from the creation card loading module 313. The processing performed by the video clip module 350 on the obtained video is not specifically limited and can be set according to actual needs. In one example, the video clip 350 may include Figure 3 shown as an editing module 351, a playback module 352, and a highlight service module 353. Among them, the highlight service module 353 includes a computer vision analysis module, a transition recognition module, an original sound recognition module, and a highlight segment analysis module. Specifically, the computer vision analysis module is used to analyze the video and obtain corresponding analysis results. The transition recognition module is used to identify the transitions or conversions between adjacent frame pictures in the video. The original sound recognition module is used to identify the audio in the video. The highlight segment analysis module is used to extract important or highlight segments in the video.

[0136] It should be understood that the above Figure 3 shown system architecture is only illustrative and does not impose any limitation on the system architecture applicable to the statement recommendation method provided in the embodiments of the present application. For example, Figure 3 shown in the voice assistant 310 may not include the text creation module 315. For example, Figure 3 shown in the media learning middle platform 330, the portrait learning module 331 and the portrait storage module 332 can be combined into one module.

[0137] Next, in combination with the Figure 4 shown architecture, the specific processes of obtaining portrait data and memory nodes involved in the statement recommendation method provided in the embodiments of the present application will be introduced.

[0138] Figure 4 is a schematic diagram of a process for obtaining portrait data and memory nodes provided in the embodiments of the present application. As Figure 4 shown, this architecture includes a media service 410, a capability platform 420, and a voice assistant 430. It can be understood that Figure 4 each module shown is a module in the terminal device, Figure 4 each module shown and Figure 3 each module shown can be modules in the same terminal device.

[0139] The media service 410 includes a media data center 411, a camera application 412, a gallery application 413, and a video editor 414. The media data center 411 includes gallery behaviors, video editing behaviors, camera tags, and picture tags. The camera application 412 includes filter recommendations and mode recommendations (such as portrait mode, etc.). The gallery application 413 includes highlight moments and mode recommendations. The video editor 414 includes template recommendations, music recommendations, material recommendations, and special effect recommendations.

[0140] The capability platform 420 includes a decision-making center 421, a media learning middle platform 422, and a perception middle platform 423. The decision-making center 421 includes material recommendation, food recommendation, and travel recommendation. The media learning middle platform 422 learns the user's media data obtained from the media data center 411 through interface 1 to learn the user's preferences (also known as interests or hobbies). For example, the preferences can be but are not limited to Figure 4 the food preferences, travel preferences, photography preferences, video editing preferences, and travel preferences shown in. The perception middle platform 423 is used to perceive information, which can be but is not limited to one or more of the following information: the stop location of the electronic device, the WiFi at the stop point of the electronic device, the in-vehicle WiFi connected to the electronic device, and the APP used by the user for the electronic device.

[0141] The decision-making center 421 queries the user's preferences from the media learning middle platform 422 through interface 2 and sends the queried user's preferences to the voice assistant 430 through interface 4 so that the voice assistant 430 can obtain the user's preferences. At the same time, the decision-making center 421 can also send the queried user's preferences to the video editing 414 through interface 3.

[0142] It should be noted that Figure 4 the voice assistant 430 in Figure 3 corresponds to the voice assistant 310 in Figure 4 the media learning middle platform 422 in Figure 3 corresponds to the media learning middle platform 330 in Figure 4 the video editing 414 in Figure 3 corresponds to the video editing 350 in

[0143] It should be understood that the above Figure 4 shown process of obtaining portrait data and memory nodes is only for illustration and does not limit the process of obtaining portrait data and memory nodes involved in the sentence recommendation method provided by the embodiments of the present application.

[0144] To better understand the sentence recommendation method provided in the embodiments of the present application, before introducing a sentence recommendation method provided in the embodiments of the present application, the user interface (UI) of the electronic device involved in the sentence recommendation method provided in the embodiments of the present application will be introduced first. It should be noted that the UI is a media interface for interaction and information exchange between an application or an operating system and a user, and it realizes the conversion between the internal form of information and the form acceptable to the user. The user interface is the source code written in specific computer languages such as Java and Extensible Markup Language (XML). The interface source code is parsed and rendered on the electronic device and finally presented as content recognizable by the user, such as controls like pictures, text, and buttons. A control is also called a widget and is the basic element of the user interface. Typical controls include a toolbar, a menubar, a textbox, a button, a scrollbar, pictures, and text. The attributes and content of the controls in the interface are defined through tags or nodes. For example, XML through, <textview> 、 <imgview> 、 <videoview>Nodes such as these are used to define the controls included in the interface. One node corresponds to one control or property in the interface. After being parsed and rendered, the nodes are presented as content visible to the user. A commonly used form of the user interface is the graphical user interface (GUI), which refers to the user interface related to computer operations presented in a graphical manner. It can be interface elements such as an icon, window, control, etc. displayed on the display screen of an electronic device. Among them, the controls can include visible interface elements such as icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, Widgets, etc.

[0145] In one example, taking the path for the user to enter the intelligent video editing through the desktop card provided by the electronic device as an example, the user interface of the electronic device involved in the embodiments of the present application is introduced. Please refer to Figure 5 , when the user triggers the video creation control 510 in the desktop card 500 displayed on the desktop S5 of the mobile phone, the mobile phone displays the intelligent video editing interface S6, as Figure 6 shown. The intelligent video editing interface S6 is provided with a control 600 and a text box 610 including thumbnails of photos. After the user triggers the control 600, the mobile phone displays the intelligent video editing interface S7 as Figure 7 shown. Among them, the intelligent video editing interface S7 includes a plurality of preset categories, and the plurality of categories can but are not limited to including categories such as daily Vlog, my photo, family contract, growth theme, travel Vlog, and food collection shown in the intelligent video editing interface S7. In response to a trigger operation on a certain category in the intelligent video editing interface S7, the mobile phone displays the aforementioned recommended information included in the certain category. Exemplarily, taking the user triggering the family photo category in the intelligent video editing interface S7 as an example, the mobile phone displays the intelligent video editing interface S8A as Figure 8A shown. Among them, three recommended cards (i.e., recommended card 801a, recommended card 802b, and recommended card 803c) are displayed in the dialog box 800A in the intelligent video editing interface S8A, and each recommended card includes the cover image of the card and the recommended statement. Among them, the recommended statement displayed on the recommended card 801 is "Make a video of the child playing with the father yesterday", and the cover image of the card is 8010. The recommended statement displayed on the recommended card 802 is "Generate a warm video of the child and the mother last month", and the cover image of the card is 8020. The recommended statement displayed on the recommended card 803 is "Generate a growth video of the child from last year to this year", and the cover image of the card is 8030. Exemplarily, taking the user triggering the daily Vlog category in the intelligent video editing interface S7 as an example, the mobile phone displays the intelligent video editing interface as Figure 8B The shown intelligent video compilation interface S8B, in which three recommended cards are displayed in the dialog box 800B in the intelligent video compilation interface S8B. Each recommended card includes a recommended statement and a cover image of the card. The three recommended statements corresponding to the three recommended cards are "Create a video of the baby dancing", "Create a video of traveling in Nanjing", and "Generate a video of playing badminton yesterday" respectively. Then, in response to the user triggering Figure 8A the operation of the first recommended card in the shown dialog box 800A, when there are multiple pictures of the child playing with the father yesterday stored in the phone's gallery, the phone displays as Figure 9A the shown intelligent video compilation dialog interface S9A, that is, the text 900 (i.e., the user's input instruction) of "Create a video of the child playing with the father yesterday" is displayed in the dialog interface S9A, and the text 910 of "The gallery is performing image recognition. You can view the progress in the gallery" is also displayed. In response to the phone generating a video of the child playing with the father yesterday, the phone displays as Figure 9B the shown intelligent video compilation dialog interface S9B. The text 920 of "A video of the child playing with the father yesterday has been generated for you. Come and take a look~" and the generated video 930 are displayed in the dialog interface S9B. When the user needs to view the video 930, the user triggers the open video control 940 in the video 930, and then can view the content of the video 930.

[0146] Optionally, in response to the user triggering the operation of the first recommended card in the dialog box 800A, when there are no pictures of the child playing with the father yesterday stored in the phone's gallery, the phone displays as Figure 10 the shown intelligent video compilation dialog interface S10, that is, the text 1000 (i.e., the user's input instruction) of "Create a video of the child playing with the father yesterday" is displayed in the dialog interface S10, and the text 1010 of "There are no available photos in the gallery for this theme. You can try clicking the following theme to create a video: Generate a video of the child holding hands with the mother last month" is also displayed.

[0147] It should be noted that in the above text, taking the case where the user triggers the video creation control 510 displayed on the phone's desktop S5 and the phone displays the intelligent video compilation interface S6 as an example, the three recommended cards corresponding to the three recommended statements displayed in the dialog box 800A in the intelligent video compilation interface S8A provided by the embodiments of the present application are introduced through the desktop card of the phone. In another example, after the user triggers the video creation control 510 on the phone's desktop S5, the phone can directly display as Figure 8A the shown intelligent video compilation interface S8A. In yet another example, after the user triggers the video creation control 510 on the phone's desktop S5, the phone displays as Figure 8A the shown intelligent video compilation interface S8A. In yet another example, after the user triggers the video creation control 510 on the phone's desktop S5, the phone displays as Figure 7 The shown intelligent video compilation interface S7. After that, in response to a trigger operation in the family photo category in the intelligent video compilation interface S7, the mobile phone displays as shown in Figure 8A the shown intelligent video compilation interface S8A.

[0148] In another example, taking the path for the user to enter intelligent video compilation through the global search provided by the electronic device as an example, the user interface of the electronic device involved in the embodiments of the present application is introduced. For example, the user can enter the global search page by pulling down the home screen of the mobile phone. Please refer to Figure 11 the shown user interface S11. A global search control 1100 is displayed at the bottom of the user interface S11. After the user enters the keyword "intelligent" in the global search control 1100, an intelligent video compilation control 1110 is displayed on the user interface S11. In response to a trigger operation on the intelligent video compilation control 1110, the mobile phone displays as shown in Figure 7 the shown intelligent video compilation interface S7. After that, in response to a trigger operation in the family photo category in the intelligent video compilation interface S7, the mobile phone displays as shown in Figure 8A the shown intelligent video compilation interface S8A. Or, in response to a trigger operation on the intelligent video compilation control 1110, the mobile phone can directly display as shown in Figure 8A the shown intelligent video compilation interface S8A.

[0149] In yet another example, taking the path for the user to enter intelligent video compilation through the creation page in the gallery provided by the electronic device as an example, the user interface of the electronic device involved in the embodiments of the present application is introduced. The user triggers the gallery to display the creation page. Please refer to Figure 12 the shown creation page S12. An intelligent video compilation control 1200 is displayed in the creation page S12. In response to a trigger operation on the intelligent video compilation control 1200, the mobile phone displays as shown in Figure 7 the shown intelligent video compilation interface S7. After that, in response to a trigger operation on the family photo in the intelligent video compilation interface S7, the mobile phone displays as shown in Figure 8A the shown intelligent video compilation interface S8A. Or, in response to a trigger operation on the intelligent video compilation control 1200, the mobile phone directly displays as shown in Figure 8A the shown intelligent video compilation interface S8A.

[0150] In yet another example, taking the path for the user to enter intelligent video compilation through the floating ball in the gallery provided by the electronic device as an example, the user interface of the electronic device involved in the embodiments of the present application is introduced. After the user enters the photo album in the gallery, the mobile phone displays as shown in Figure 13 the shown photo page S13. An intelligent video compilation floating ball 1300 is displayed in the photo page S13. After that, in response to a trigger operation on the floating ball 1300, the mobile phone displays as shown in Figure 7 the shown intelligent video compilation interface S7. After that, in response to a trigger operation on the family photo in the intelligent video compilation interface S7, the mobile phone displays as shown in Figure 8A The shown intelligent video compilation interface S8A. Alternatively, in response to a trigger operation on the floating ball 1300, the mobile phone directly displays as Figure 8A the shown intelligent video compilation interface S8A.

[0151] It should be noted that the above user interfaces are only exemplary and do not impose any limitation on the user interfaces applicable to the sentence recommendation method provided in the embodiments of the present application.

[0152] Next, in combination with Figures 14 to 16 a detailed introduction to the sentence recommendation method provided in the embodiments of the present application will be given.

[0153] Below, taking the Figure 3 shown system architecture as an example, in combination with Figure 14 a sentence recommendation method provided in the embodiments of the present application will be introduced. Figure 14 is a schematic flowchart of a sentence recommendation method provided in the embodiments of the present application. It can be understood that Figure 14 the shown method can be executed by a terminal device. For example, the terminal device can be the electronic device described above Figure 1 shown. As Figure 14 shown, the sentence recommendation method includes S1401 to S1421, and a detailed introduction to S1401 to S1421 will be given below.

[0154] S1401, the user sends a trigger instruction to view the creation page of the gallery in the gallery of the terminal device.

[0155] The trigger instruction to view the creation page of the gallery is used to trigger the gallery of the terminal device to display the creation page, where the creation page includes an intelligent video compilation control. In the embodiments of the present application, the intelligent video compilation control of the terminal device is used to pull up the YOYO intelligent assistant of the terminal device, and display recommended sentences (also called prompt words) for generating intelligent videos based on the user's portrait data and the user's photo data in the skill interface of the pulled-up YOYO intelligent assistant.

[0156] The trigger instruction to view the creation page of the gallery is not specifically limited and can be set according to the actual application scenario. For example, the trigger instruction to view the creation page of the gallery can be, but is not limited to, an operation of clicking the production control in the gallery or a double-click operation on the production control in the gallery, etc.

[0157] S1402, in response to the trigger instruction to view the creation page of the gallery, the gallery of the terminal device displays the creation page including the intelligent video compilation control.

[0158] In one example, after the user triggers the gallery identifier (e.g., icon) on the desktop display of the terminal device, the terminal device displays the main page of the gallery. After that, in response to the user triggering the production control in the main page of the gallery, the terminal device displays the creation page of the gallery, such as Figure 12 the creation page S12 shown Figure 12 which also shows the intelligent video production control 1200

[0159] S1403, the user sends a trigger instruction for the intelligent video production control to the creation page of the gallery of the terminal device.

[0160] In one example, the user's finger triggers (e.g., single - click operation or double - click operation) Figure 12 the intelligent video production control 1200 shown, so as to achieve the purpose of triggering the intelligent video production control in the creation page of the gallery.

[0161] Optionally, after the terminal device displays the creation page of the gallery, if the user does not currently need to obtain the video generated by intelligent video production, the user can, but is not limited to, exit the creation page of the gallery through a downward - sliding gesture operation. After that, the terminal device displays the desktop including one or more application identifiers (e.g., icons).

[0162] For example, the user can perform a downward - sliding gesture operation on Figure 12 the creation page S12 shown. After that, the interface displayed by the terminal device is as Figure 5 shown

[0163] S1404, in response to the user triggering the intelligent video production control in the creation page of the gallery, the gallery sends a start YOYO intelligent assistant instruction (carrying the creation page identifier of the gallery and the intelligent video production identifier) to the YOYO intelligent assistant.

[0164] After the user triggers the intelligent video production control in the creation page of the gallery, the gallery will send an instruction to start the YOYO intelligent assistant, and the instruction to start the YOYO intelligent assistant carries the creation page identifier of the gallery and the intelligent video production identifier. So that after the YOYO intelligent assistant obtains the instruction to start the YOYO intelligent assistant, it generates a recommended statement loading instruction according to this instruction. Optionally, the instruction to start the YOYO intelligent assistant can also carry other information, and no specific limitation is imposed on other information. For example, other information can be, but is not limited to, the start time, etc.

[0165] The creation page identifier of the gallery is used to identify the creation page of the gallery, and no specific limitation is imposed on the form of the creation page identifier of the gallery. For example, the creation page identifier of the gallery can be the number of this creation page.

[0166] The intelligent video clip identifier is used to identify the intelligent video clip control. The intelligent video clip of the terminal device can recommend a recommended statement for generating a video clip to the user based on the user portrait data and the user memory nodes described above. The form of the intelligent video clip identifier is not specifically limited. For example, the intelligent video clip identifier can be the icon of a preset intelligent video clip control or the symbol of a preset intelligent video clip control.

[0167] S1405, the YOYO intelligent assistant sends a binding instruction to the media processing middle platform. Correspondingly, the media processing middle platform receives the binding instruction sent by the YOYO intelligent assistant.

[0168] The binding instruction is used to request binding the YOYO intelligent assistant and the media processing middle platform. Among them, the binding instruction can carry the address information of the media processing middle platform. For example, the binding instruction can be the onBindAppClip instruction.

[0169] S1406, the media processing middle platform sends a binding success message to the YOYO intelligent assistant. Correspondingly, the YOYO intelligent assistant receives the binding success message sent by the media processing middle platform.

[0170] For example, the binding success message can be SmartVideoCreationClip.

[0171] In this way, after the terminal device executes the above S1405 and S1406, that is, the YOYO intelligent assistant of the terminal device and the media processing middle platform of the terminal device are successfully bound. After that, data interaction can be carried out between the YOYO intelligent assistant and the media processing middle platform.

[0172] Optionally, in the case where the YOYO intelligent assistant and the media processing middle platform do not need to carry out data interaction, the binding relationship between the YOYO intelligent assistant and the media processing middle platform can also be deleted, so as to save network resources.

[0173] S1407, the YOYO intelligent assistant sends a recommended statement loading instruction to the media processing middle platform. Correspondingly, the media processing middle platform receives the recommended statement loading instruction sent by the YOYO intelligent assistant.

[0174] The recommended statement loading instruction is used to request to obtain the recommended information for generating a video clip (i.e., a video). Among them, the recommended information can include the URL of the recommended card, the recommended statement, and the cover photo of the recommended card.

[0175] S1408, the media processing middle platform generates a query instruction (for querying the user portrait data and the user memory nodes of the terminal device) according to the recommended statement loading instruction.

[0176] The query instruction is used to query the user portrait data and the user memory nodes of the terminal device.

[0177] The portrait data of the user includes feature data representing the user of the terminal device, and the content included in the portrait data of the user is not specifically limited. For example, the portrait data of the user may include, but is not limited to, one or more of the following data: the age, gender, interests, hobbies, birthday, graduation date, graduation school, marriage date, account number, hometown, residential address, work experience of the user of the terminal device, and the personal relationships of the user of the terminal device (for example, the personal relationships may be, but are not limited to, parent-child relationship, spouse relationship, parent-child relationship, friend relationship, teacher-student relationship, or colleague relationship, etc.).

[0178] The memory nodes of the user include the time range corresponding to the photos stored in the terminal device, the location corresponding to the photos stored in the terminal device, the events corresponding to the photos stored in the terminal device, and the people associated with the photos stored in the terminal device. Neither the time range nor the events are specifically limited. For example, the time range may be, but is not limited to, at least one of the following ranges: yesterday, this week, last week, this month, last month. For example, the events may be, but are not limited to, at least one of the following events: having a birthday, family gathering, wedding, graduation ceremony, travel, play, food, sports, scenery, with a cat, with a dog. The people associated with the photo refer to the people involved in the photo. For example, if photo A includes Xiaoming and Zhang, then the people associated with photo A include Xiaoming and Zhang. Exemplarily, taking all the photos stored in the photo gallery of the terminal device including photo A and photo B as an example to describe the memory nodes of the user. In one example, photo A records the event that Xiaoming and Xiaoli flew a kite in the park on January 1, 2024. Photo B records the event that Xiaoming read a book in the library on January 4, 2024. Based on this, the memory nodes of the user may include: the time range from January 1, 2024 to January 4, 2024, the locations including the park and the library, the events including flying a kite and reading a book, the people including Xiaoming, and the existence of Xiaoming and Xiaoli.

[0179] Exemplarily, taking the portrait data of the user including the user's birthday as an example, the user's birthday can be represented by the following code:

[0180]

[0181] Exemplarily, a memory node of a user applicable to the embodiments of the present application can be represented by the following code:

[0182]

[0183]

[0184] It should be noted that the examples of the portrait data of the user and the examples of the memory nodes of the user described above do not constitute any limitation on the portrait data of the user and the memory nodes applicable to the embodiments of the present application.

[0185] In this way, after the media processing middleware obtains the recommendation statement loading instruction, the media processing middleware can generate a query instruction for querying the portrait data of the user of the terminal device and the memory nodes of the user. After that, the media processing middleware sends the query instruction to the media learning middleware, so that the media learning middleware returns the query result obtained to the media processing middleware. S1409, the media processing middleware sends a query instruction to the media learning middleware. Correspondingly, the media learning middleware receives the query instruction sent by the media processing middleware.

[0186] S1410, the media learning middleware performs a query according to the query instruction to obtain a query result (carrying the portrait data of the user and the memory nodes of the user).

[0187] The query result carries the portrait data of the user and the memory nodes of the user, and the number of memory nodes of the user included in the query result is not specifically limited. For example, the query result may include one or more memory nodes of the user.

[0188] In one example, after a preset duration after the terminal device is charged and the screen is turned off, the portrait learning module included in the media learning middleware can start the portrait learning function for the application data generated by the application in the terminal device to obtain the portrait data of the user described above. For example, the application may be, but is not limited to, a gallery, a video, an album, a memo, a contact list, etc. At the same time, the memory learning module included in the media learning middleware can start the memory learning function for the pictures and / or videos in the terminal device to obtain the memory nodes of the user described above. For example, the pictures and / or videos in the terminal device may be, but are not limited to, the data stored in a gallery, a video, an album. Thereafter, the portrait storage module included in the media learning middleware can store the portrait data of the user obtained from the portrait learning module, and the memory storage module included in the media learning middleware can store the memory nodes of the user obtained from the memory learning module.

[0189] The preset duration is not specifically limited. For example, it can be set according to the operating performance of the terminal device. Exemplarily, when the operating performance of the terminal device is high, the preset duration can be shorter, such as 15 seconds or 30 seconds, etc. When the operating performance of the terminal device is low, the preset duration can be longer, such as 60 seconds or 100 seconds, etc.

[0190] In practical applications, in order to reduce the power consumption of the terminal device, in the embodiments of the present application, within a preset time range, when the terminal device performs multiple charging and screen-off operations, the media learning middleware only performs the portrait learning function and the memory learning function as described above after a preset duration after a certain charging and screen-off operation among the multiple charging and screen-off operations. The certain charging and screen-off operation among the multiple charging and screen-off operations is not specifically limited. For example, the certain charging and screen-off operation can be, but is not limited to, the first screen-off operation or the second screen-off operation among the multiple charging and screen-off operations, etc. The preset time range is not specifically limited. For example, the preset time range can be, but is not limited to, 12 hours or 24 hours.

[0191] S1411, the media learning middleware sends the query result (carrying the user's portrait data and the user's memory nodes) to the media processing middleware. Correspondingly, the media processing middleware receives the query result sent by the media learning middleware.

[0192] S1412, the media processing middleware processes the query result to generate a recommendation result (carrying K card information, each card information including the URL of each card, the recommended statement in each card, and the cover photo of each card, where K is a positive integer).

[0193] As described above, after the media processing middleware receives the recommended statement loading instruction sent by the YOYO intelligent assistant, the media processing middleware first obtains the user data (i.e., the user's portrait data and the user's memory nodes) for generating the recommended statement for the finished video from the media learning middleware. Then, the media processing middleware processes the user data to obtain the data requested by the recommended statement loading instruction (i.e., the recommendation result). In one example, the recommendation result carries K card information, where each card information includes the URL of each card, the recommended statement in each card, and the cover photo of each card. The cover photo of each card is not specifically limited. For example, the cover photo of each card is a photo associated with the recommended statement in each card. For example, when the recommended statement included in a card information is "Produce a video of the child playing with the father yesterday", the cover photo included in the card information can be one of the photos of the child playing with the father yesterday. Optionally, each card information can also carry other information, which is not specifically limited. For example, the other information can be, but is not limited to, the device model of the terminal device.

[0194] K is a preset positive integer, and the value of K is not specifically limited. For example, K can be equal to 1, 2, 3, or 5, etc.

[0195] As an example of the present application, for the specific implementation process of the media processing middleware processing the query result to generate a recommendation result, please refer to Figure 15 Shown as S1412-0 to S1412-15. In one example, the memory material processing module included in the media processing middle platform executes S1412. Taking the memory material processing module executing S1412 as an example, the following Figure 15 will introduce the shown S1412-0 to S1412-15 in detail.

[0196] S1412-0, the memory material processing module obtains the i-th time range, where i is a positive integer.

[0197] The i-th time range can correspond to a moment or a time range, and no specific limitation is made thereto. For example, the i-th time range can be 3 pm yesterday, yesterday, this week (excluding yesterday), last week, this month (excluding this week and last week), or last month, etc.

[0198] No specific limitation is made to the manner in which the memory material processing module obtains the i-th time range. For example, the i-th time range defined in advance is stored in the memory material processing module.

[0199] In one example, when the memory material processing module executes S1412-1 for the first time after executing S1411, i can be equal to 1. After that, when the memory material processing module executes S1412-1 for the second time after executing S1411, i is equal to 2, and so on. When the memory material processing module executes S1412-1 for the W-th time after executing S1411, i is equal to W, where W is an integer greater than 2.

[0200] For example, taking W equal to 2 as an example, the first time range can be yesterday, and the second time range can be this week (excluding yesterday). For example, taking W equal to 5 as an example, the first time range can be yesterday, the second time range can be this week (excluding yesterday), the third time range can be last week, the fourth time range can be this month (excluding this week and last week), and the fifth time range can be last month (excluding yesterday).

[0201] S1412-1, the memory material processing module queries the query result according to the i-th time range to obtain the memory nodes of the user corresponding to the i-th time range.

[0202] As described above, a memory node includes a time range corresponding to a photo stored in a terminal device, a location corresponding to the photo stored in the terminal device, an event corresponding to the photo stored in the terminal device, and a person associated with the photo stored in the terminal device. That is to say, the time range corresponding to each memory node is the time range included in each memory node. In one example, a query result includes multiple memory nodes of a user, and the multiple memory nodes may correspond to different time ranges. Thus, the recollection material processing module may query the multiple memory nodes according to the i-th time range, so as to obtain the memory nodes of the user corresponding to the i-th time range. Thereafter, the recollection material processing module processes the memory nodes of the user corresponding to each time range (i.e., the i-th time range), so that the data processing efficiency can be improved.

[0203] S1412-2. The recollection material processing module clusters the memory nodes of the user corresponding to the i-th time range according to a preset event, so as to obtain at least one event class corresponding to the i-th time range.

[0204] That at least one event class corresponding to the i-th time range means that the i-th time range corresponds to one event class, or the i-th time range corresponds to multiple event classes, where the multiple event classes correspond to multiple different events in a preset event type. For example, taking the memory nodes of the user corresponding to the i-th time range including the user's memory node 1, the user's memory node 2, and the user's memory node 3 as an example, clustering the memory nodes of the user corresponding to the i-th time range according to a preset event may obtain event class 1 including the user's memory node 1, and event class 2 including the user's memory node 2 and the user's memory node 3, and the events corresponding to event class 1 and the events corresponding to event class 2 are different.

[0205] The preset event is not specifically limited and can be set according to actual situations. In one example, the preset event includes one or more of the following events: birthday, family gathering, wedding, graduation ceremony, travel, play, food, sports, scenery, pet companionship (such as with a cat or with a dog).

[0206] It should be noted that after the recollection material processing module clusters the memory nodes of the user corresponding to the same time range (i.e., the i-th time range), the principle of the subsequent processing flow executed by the recollection material processing module for the memory nodes of the user corresponding to each class is the same.

[0207] S1412-3. The recollection material processing module aggregates the photos or videos of the events associated with at least one event class corresponding to the i-th time range, so as to obtain an aggregation result of at least one event class corresponding to the i-th time range.

[0208] In one example, when the i-th time range corresponds to multiple event classes, the multiple event classes correspond to multiple aggregation results, where each aggregation result is the aggregation result of the corresponding event class.

[0209] S1412-4, the recollection material processing module determines whether the photos or videos included in the aggregation result corresponding to the at least one event class corresponding to the i-th time range include people.

[0210] In one example, when the i-th time range corresponds to multiple event classes and the multiple event classes correspond to multiple aggregation results, accordingly, the recollection material processing module needs to determine whether the photos or videos included in the aggregation result of each event class corresponding to the i-th time range include people.

[0211] As an example of the present application, the recollection material processing module may determine whether the photos or videos included in the aggregation result corresponding to each event class include people according to the fields in the memory nodes of the users corresponding to each event class, where the memory nodes of the users corresponding to the i-th time range include the memory nodes of the users corresponding to each event class. Specifically, in one example, when the memory nodes of the users corresponding to each event class include a person field, the recollection material processing module may determine that the photos or videos included in the aggregation result corresponding to each event class include people according to the person field. At the same time, the recollection material processing module may know the person corresponding to the identifier of the people included in the photos or videos included in the aggregation result corresponding to each event class according to the field value of the person field, where the identifier of the person represents the person having a mapping relationship with the identifier of the person. For example, if there is a mapping relationship 1 between the identifier of the person 1 and the person 1, the recollection material processing module may determine the person 1 according to the mapping relationship 1 and the identifier of the person 1. In another example, when the memory nodes of the users corresponding to each event class do not include a person field, the recollection material processing module may determine that the photos or videos included in the aggregation result corresponding to each event class do not include people.

[0212] As another example of the present application, the recollection material processing module may also perform person recognition on the photos or videos included in the aggregation result corresponding to each event class to identify whether the photos or videos included in the aggregation result corresponding to each event class include people. The specific implementation of the person recognition is not limited. For example, the recollection material processing module may but is not limited to execute the person recognition process based on a neural network model.

[0213] In this way, after the recollection material processing module determines that the photos or videos included in the aggregation result corresponding to each event class in the i-th time range include people, the recollection material processing module executes S1412-5 to obtain the person information in the photos or videos included in the aggregation result corresponding to each event class in the i-th time range. After the recollection material processing module determines that the photos or videos included in the aggregation result corresponding to each event class do not include people, the recollection material processing module executes S1412-6, that is, further determines whether the photos or videos included in the aggregation result corresponding to each event class include locations.

[0214] S1412-5. The recollection material processing module obtains the person information i in the photo or video data included in the aggregation result corresponding to at least one event class in the i-th time range according to the portrait data of the user in the query result and the people in the photos or videos included in the aggregation result corresponding to at least one event class in the i-th time range.

[0215] The person information i may include people and their relationships. There is no specific limitation on the relationships between people. For example, the relationships between people include but are not limited to father-son, mother-daughter, teacher-student, colleague, friend, etc.). Exemplarily, taking a photo included in the aggregation result corresponding to at least one event class in the i-th time range as an example, which includes person A and person B, the person information i includes the following information: person A is a child, and person B is person A's father.

[0216] In one example, the recollection material processing module executes the above S1412-5, that is, the recollection material processing module finds the portrait data of the people in the photos or videos included in the aggregation result corresponding to at least one event class in the i-th time range from the portrait data of the user in the query result. After that, the recollection material processing module determines the relationships between people in the person information i according to the portrait data found in the previous step. In this way, the recollection material processing module obtains the people and their relationships in the person information i.

[0217] S1412-6. The recollection material processing module determines whether the photo or video data included in the aggregation result corresponding to at least one event class in the i-th time range includes a location.

[0218] In one example, when there are multiple event classes corresponding to the i-th time range and there are multiple aggregation results corresponding to these multiple event classes, accordingly, the recollection material processing module needs to determine whether the photo or video data included in the aggregation result corresponding to each event class in the i-th time range includes a location.

[0219] As an example of the present application, the recollection material processing module can determine whether the photos or videos included in the aggregation result corresponding to each event class include a location according to the fields in the memory nodes of the users corresponding to each event class. Among them, the memory nodes of the users corresponding to the i-th time range include the memory nodes of the users corresponding to each event class. Specifically, when the memory nodes of the users corresponding to each event class include a location field, the recollection material processing module can determine that the photos or videos included in the aggregation result corresponding to each event class include a location. When the memory nodes of the users corresponding to each event class do not include a location field, the recollection material processing module can determine that the photos or videos included in the aggregation result corresponding to each event class do not include a location.

[0220] In this way, after the recollection material processing module determines that the photos or videos included in the aggregation result of each event class corresponding to the i-th time range include a location, it executes S1412-7 to obtain the location in the photos or videos included in the aggregation result of each event class corresponding to the i-th time range. After the recollection material processing module determines that the photos or videos included in the aggregation result of each event class corresponding to the i-th time range do not include a location, it executes S1412-8.

[0221] S1412-7, the recollection material processing module obtains the location i in the photos or videos included in the aggregation result of at least one event class corresponding to the i-th time range.

[0222] In one example, the recollection material processing module can obtain the location in the photos or videos included in the aggregation result of at least one event class corresponding to the i-th time range in the following way: when the photos or videos included in the aggregation result of at least one event class corresponding to the i-th time range include a person, the recollection material processing module obtains the location from the field value of the location field in the memory nodes of the users corresponding to the aggregation result of at least one event class corresponding to the i-th time range, where the field value of the location field represents the location.

[0223] For example, the location field in the user's memory node can be the city field. Based on this, the location field and the corresponding field value in the memory node of the user corresponding to the i-th time range can be expressed as: "city": "Changsha".

[0224] S1412-8, the recollection material processing module counts the number of photos or videos included in the aggregation result of at least one event class corresponding to the i-th time range as number A.

[0225] In this way, the recollection material processing module can count the number of photos or videos included in the aggregation result of each event class in all event classes corresponding to the i-th time range as number A.

[0226] S1412-9, the recollection material processing module determines whether the number A meets the preset quantity 1.

[0227] The preset quantity 1 is not specifically limited and can be set according to user requirements. In one example, the preset quantity 1 is a fixed value. For example, the preset quantity 1 can be, but is not limited to, 5, 7, 8, or 10, etc. In another example, the preset quantity 1 is a data range. For example, the data range corresponding to the preset quantity 1 is [5, 10].

[0228] In this way, after the recollection material processing module determines that the number A meets the preset quantity 1, it executes S1412-10 to generate a recommended statement for at least one event category corresponding to the ith time range. After the recollection material processing module determines that the number A does not meet the preset quantity 1, it updates i to i + 1 and then executes the aforementioned S1412-0 again, that is, the recollection material processing module re-executes the process similar to S1412-0 to S1412-9 for a new time range to obtain the recommended statement determined based on the memory nodes of the user corresponding to the new time range. It should be understood that the specific value corresponding to the time range corresponding to the recollection material processing module each time it executes S1412-0 is different.

[0229] S1412-10, the recollection material processing module generates a recommended statement for at least one event category corresponding to the ith time range according to the preset statement format, based on the person information i, the ith time range, the location i, and at least one event category corresponding to the ith time range.

[0230] The preset statement format includes person, time, location, and event. For example, the preset statement format can be the following statement: "Generate the [video] of [person] [time] [location] [event]", where, [] can be called slot information. For example, [person] can be called person slot information. Another example is that the preset statement format can be the following statement: "Generate the [warm video] of [person] [time] [location] [event]". Another example is that the preset statement format can be the following statement: "Generate the [recollection video] of [person] [time] [location] [event]".

[0231] The recommended statement for at least one event category corresponding to the ith time range includes the person information i, the ith time range, the location i, and at least one event category corresponding to the ith time range.

[0232] In one example, the recollection material processing module generates a recommended statement corresponding to at least one event class for the ith time range according to the preset statement format, based on the person information i, the ith time range, the location i, and at least one event class corresponding to the ith time range. Exemplarily, the following steps may be included: The recollection material processing module updates the person slot information in the preset statement format to the person information i, updates the time slot information in the preset statement format to the ith time range, updates the location slot information in the preset statement format to the location i, and updates the event slot information in the preset statement format to at least one event class corresponding to the ith time range, so as to generate a recommended statement corresponding to at least one event class for the ith time range.

[0233] For example, taking the preset statement format as the following statement: "Generate the [video] of [person] [time] [location] [event]", the recommended statement corresponding to at least one event class for the ith time range can be expressed as: "Generate the [video] of [person information i] [the ith time range] [location i] [at least one event class corresponding to the ith time range]".

[0234] Thus, after the recollection material processing module executes S14121-10 to obtain the recommended statements for each event class corresponding to the ith time range, the recollection material processing module can continue to execute S1412-11, that is, determine the number of currently generated recommended statements associated with events.

[0235] In S1412-11, the recollection material processing module counts the number of currently generated recommended statements associated with events as the number B.

[0236] In the embodiments of the present application, when the number of currently generated recommended statements associated with events is multiple, the multiple recommended statements may correspond to the same or different time ranges. In one example, after the recollection material processing module first executes S1412-9, and the recollection material processing module sequentially executes S1412-10, S1412-11, S1412-12, and S1412-14, when the number of currently generated recommended statements associated with events is multiple, the multiple recommended statements correspond to the same time range. In another example, after the recollection material processing module first executes S1412-9, and the recollection material processing module executes S1412-0 again, when the number of currently generated recommended statements associated with events is multiple, the multiple recommended statements correspond to different time ranges.

[0237] In S1412-12, the recollection material processing module determines whether the quantity B meets the preset quantity 2.

[0238] The preset quantity 2 is not specifically limited and can be set according to user needs. In one example, the preset quantity 2 is a fixed value. For example, the preset quantity 2 can be, but is not limited to, 1, 2, 3, 5, etc. In another example, the preset quantity 2 is a data range. For example, the data range corresponding to the preset quantity 2 is [2, 5].

[0239] In this way, after the recall material processing module determines that the number of recommended statements associated with the event satisfies the preset quantity 2, it executes S1412-14 to determine the B recommended statements associated with the event generated currently as the K recommended statements corresponding to the K card information carried in the recommendation result. After the recall material processing module determines that the number of recommended statements associated with the event does not satisfy the preset quantity 2, it executes S1412-13, that is, the recall material processing module can also process the query result according to the i-th time range to generate at least one recommended statement for the i-th time range corresponding to the interest category.

[0240] In the embodiment of the present application, the principle of the recall material processing module processing the query result according to the i-th time range to generate the recommended statement associated with the interest is the same as the principle of the recall material processing module processing the query result according to the i-th time range to generate the recommended statement associated with the event described in S1412-0 to S1412-10 above. The difference is that the events in S1412-0 to S1412-10 above are all replaced by interests, and the preset statement format in S1412-10 should be replaced by a statement including person, time, place, and interest. For example, in this case, the preset statement format can be, but is not limited to, the following statement: "Generate [Video, Wonderful Video or Memory Video] of [Person] [Time] [Place] [Interest]". In addition, in this implementation manner, the recall material processing module can determine the interest of the person according to the portrait data of the user in the query result and the person in the photo or video included in the aggregation result corresponding to at least one event category in the i-th time range. The interest is not specifically limited. For example, the interest can be, but is not limited to, one or more of the following interests: playing games, singing, dancing, reading, practicing calligraphy, playing basketball. For example, the specific implementation of the recall material processing module processing the query result according to the i-th time range to generate the recommended statement associated with the interest is not elaborated in detail here. Optionally, the interest of the above person can also be replaced by the hobby of the person, and this is not specifically limited.

[0241] S1412-14, the recall material processing module determines the B recommended statements associated with the event generated currently as the K recommended statements corresponding to the K card information carried in the recommendation result.

[0242] In the embodiments of the present application, the arrangement order of the K recommended statements corresponding to the K card information can be determined according to the time range corresponding to each recommended statement. In one example, the recommended statements corresponding to the time ranges can be arranged in the order of the time ranges. For example, taking 3 (i.e., K equals 2) recommended statements corresponding to 3 time ranges (i.e., time range A, time range B, and time range C) as an example, if time range A is yesterday, time range B is this week (excluding yesterday), and time range C is last week, then the recommended statement corresponding to time range C is the 1st recommended statement, the recommended statement corresponding to time range B is the 2nd recommended statement, and the recommended statement corresponding to time range A is the 3rd recommended statement. In another example, the recommended statements corresponding to the time ranges can be arranged according to the length of the time ranges. For example, the recommended statement corresponding to the time range with the smallest time length can be used as the 1st recommended statement among the K recommended statements, the recommended statement corresponding to the time range with the second smallest time length can be used as the 2nd recommended statement among the K recommended statements, and so on. The recommended statement corresponding to the time range with the largest time length can be used as the last recommended statement among the K recommended statements.

[0243] S1412-15. When the sum of the number of currently generated recommended statements associated with events and the number of recommended statements associated with interests satisfies the preset number 2, the recollection material processing module determines the currently generated recommended statements associated with events and the recommended statements associated with interests as the K recommended statements corresponding to the K card information carried in the recommendation result.

[0244] The above describes in detail the specific principle of the recollection material processing module provided in the embodiments of the present application for executing S1412 in combination with S1412-0 to S1412-15. The following gives examples to describe the recommended statements generated based on the above principle.

[0245] Exemplarily, taking the case where the recollection material processing module processes the query results according to each of 5 (i.e., the values of i described above are 1, 2, 3, 4, and 5 respectively) time ranges as an example for description. Among them, the 5 time ranges are in sequence: yesterday as the 1st time range (i.e., the 1st time range), this week (excluding yesterday) as the 2nd time range, last week as the 3rd time range, this month (excluding this week and last week) as the 4th time range, and last month as the 5th time range. First, when the recollection material processing module processes the query results according to "yesterday", and the number of photos or videos associated with the event corresponding to "yesterday" is greater than 8 (i.e., the preset number), the format of the recommended statement associated with the event generated by the recollection material processing module can be as follows: "Generate the [recollection video] of [person] yesterday at [location] [event]". Second, when the recollection material processing module processes the query results according to "this week (excluding yesterday)", and the number of photos or videos associated with the event corresponding to "this week (excluding yesterday)" is greater than 8 (i.e., the preset number), the format of the recommended statement associated with the event generated by the recollection material processing module can be as follows: "Generate the [video] of [person] this week at [location] [event]". Then, when the recollection material processing module processes the query results according to "last week", and the number of photos or videos associated with the event corresponding to "last week" is greater than 8 (i.e., the preset number), the format of the recommended statement generated by the recollection material processing module can be as follows: "Generate the [recollection video] of [person] last week at [location] [event]". After that, when the recollection material processing module processes the query results according to "this month (excluding this week and last week)", and the number of photos or videos associated with the event corresponding to "this month (excluding this week and last week)" is greater than 8 (i.e., the preset number), the format of the recommended statement generated by the recollection material processing module can be as follows: "Generate the [wonderful video] of [person] this month at [location] [event]". Finally, when the recollection material processing module processes the query results according to "last month", and the number of photos or videos associated with the event corresponding to "last month" is greater than 8 (i.e., the preset number), the format of the recommended statement generated by the recollection material processing module can be as follows: "Generate the [video] of [person] last month at [location] [event]".

[0246] In an example, the preset quantity 2 is equal to 5. After performing the foregoing multiple steps, the recollection material processing module can know that the number of recommended statements associated with the currently obtained events is 5, which meets the preset quantity 2. Then the recollection material processing module can determine the 5 recommended statements obtained in the foregoing steps as the 5 recommended statements corresponding to the K card information carried in the recommendation result.

[0247] In another example, the preset quantity 2 is equal to 8. After performing the foregoing multiple steps, the recollection material processing module can learn that the number of recommended statements associated with the currently obtained event (i.e., 5) does not meet the preset quantity 2 (i.e., 8). Then, the recollection material processing module can process the query results according to the above 5 time ranges respectively to generate 3 recommended statements associated with interests. Thereafter, when the number of recommended statements associated with the event and the recommended statements associated with interests obtained by the recollection material processing module meets the preset quantity, the currently generated recommended statements associated with the event and the recommended statements associated with interests are determined as the K recommended statements corresponding to the K card information carried in the recommendation result.

[0248] So far, after the media processing middleware executes the above S1412-0 to S1412-15, a recommendation result carrying K card information is obtained, where each card information includes the URL of each card, the recommended statement in each card, and the cover photo of each card, and K is a positive integer).

[0249] S1413, the media processing middleware sends the recommendation result to the YOYO intelligent assistant. Correspondingly, the YOYO intelligent assistant receives the recommendation result sent by the media processing middleware.

[0250] S1414, in response to the YOYO intelligent assistant loading the recommendation result, the YOYO intelligent assistant displays a recommendation interface including K recommended cards corresponding to the K card information.

[0251] The YOYO intelligent assistant loading the recommendation result includes the YOYO intelligent assistant loading the K card resources according to the URLs of the K cards corresponding to the K recommended cards.

[0252] The YOYO intelligent assistant displays a recommendation interface including K recommended cards corresponding to the K card information, and the presentation form of each recommended card in the recommendation interface is not specifically limited. For example, taking K equal to 3 as an example, these 3 recommended cards can be but are not limited to Figure 8A the form shown in the text 800 in the intelligent video composition interface S8A shown, and the time range corresponding to the first recommended card in the text 800 (for example, the day before yesterday) is earlier than the time range corresponding to the second recommended card (for example, yesterday), and the time range corresponding to the second recommended card is earlier than the time range corresponding to the third recommended card (for example, today).

[0253] It should be noted that the above S1401 to S1414 are described by taking the path of entering the intelligent card through the gallery creation page as an example. Optionally, it is also possible to enter the intelligent card through other paths. For example, other paths can be the desktop card, global search, or floating ball in the gallery described above.

[0254] So far, after performing the above S1401 to S1414, the statement recommendation method provided by this application can be implemented. In some implementation manners, after performing the above S1401 to S1414, S1415 to S1421 shown by the dashed line in Figure 14 can also be executed. Next, S1415 to S1421 will be introduced.

[0255] S1415, the user sends a trigger operation for one of the K recommended cards in the recommendation interface to the YOYO intelligent assistant.

[0256] S1416, in response to the user's trigger operation for one of the K recommended cards in the recommendation interface, the YOYO intelligent assistant generates a video instruction for generating an intelligent video corresponding to the one recommended card.

[0257] In the above S1416 step, the video instruction for generating an intelligent video corresponding to the one recommended card is used to indicate generating a video corresponding to the recommended statement in the one recommended card. For example, if the recommended statement in one of the K recommended cards triggered by the user is "Make a video of the child playing with the father yesterday", then the video instruction for generating an intelligent video corresponding to the one recommended card is used to indicate making a video of the child playing with the father yesterday.

[0258] S1417, the YOYO intelligent assistant sends the video instruction for generating an intelligent video to the media processing middle platform. Correspondingly, the media processing middle platform receives the video instruction for generating an intelligent video sent by the YOYO intelligent assistant.

[0259] S1418, the media processing middle platform generates a video according to the video instruction for generating an intelligent video.

[0260] The media processing middle platform searches for photos or videos in the terminal device's picture library corresponding to the video instruction for generating an intelligent video according to the video instruction for generating an intelligent video. After that, the searched photos or videos corresponding to the video instruction for generating an intelligent video are subjected to screening processing and selection processing to obtain the target photos or videos corresponding to the photos or videos corresponding to the video instruction for generating an intelligent video. Finally, a video is generated according to the target photos or videos corresponding to the photos or videos corresponding to the video instruction for generating an intelligent video. Neither the screening processing nor the selection processing is specifically limited and can be predefined according to user requirements. For example, the above screening processing can be but is not limited to at least one of the following processes: removing duplicate photos, removing blurred photos, and removing photos with relatively dark light. For example, the above selection processing can be but is not limited to at least one of the following processes: selecting a frontal photo or video of a person, selecting a photo or video of a person at a happy moment, and selecting a photo or video including multiple people.

[0261] Exemplarily, in the above S1418, the video generated by the media processing middleware can be the video 930 shown in the intelligent video editing dialogue interface S9B as Figure 9B shown. The length of the video 930 is 20 seconds.

[0262] S1419, the media processing middleware sends the video to the video editing service. Correspondingly, the video editing service receives the video sent by the media processing middleware.

[0263] In this way, after executing S1419, the video editing service can receive the video sent by the media processing middleware. After that, in the video editing service, the video can be edited according to the user's editing needs. For example, the editing process can be but is not limited to one or more of the following processes: rendering process, transition process, special effect process, adding text, adding audio, adding filters, etc.

[0264] S1420, the media processing middleware sends the video to the YOYO intelligent assistant. Correspondingly, the YOYO intelligent assistant receives the video sent by the media processing middleware.

[0265] S1421, the YOYO intelligent assistant displays a recommendation interface including the video.

[0266] In this way, after receiving the video, the YOYO intelligent assistant can display a recommendation interface including the video. Optionally, the recommendation interface including the video in the above S1421 step further includes the K recommendation cards in the above S1414, and the information of one recommendation card among the K recommendation cards selected by the user in the above S1416 step.

[0267] Exemplarily, the YOYO intelligent assistant displaying a recommendation interface including the video in the above S1412 can be as Figure 9B shown in the intelligent video editing dialogue interface S9B. The text 920 of "A video of your child playing with your father yesterday has been generated for you. Come and take a look~" and the generated video 930 are displayed in the dialogue interface S9B. When the user needs to view the video 930, the user triggers the open video control 940 in the video 930, and then the content of the video 930 can be viewed.

[0268] It should be understood that the above Figure 14 shown statement recommendation method is only for illustration and does not constitute any limitation to the statement recommendation method provided by this application. For example, in another example, the recommendation card can only include the recommended statement. In this case, the recommendation card does not include the cover image of the card. For example, in another example, the recommended statement displayed on the recommendation card can be a statement including time, person, and event. For example, in another example, the recommended statement displayed on the recommendation card can be a statement including time, place, person, and interest (also known as hobby or preference).

[0269] In an embodiment of the present application, in the gallery application of a terminal device, an intelligent video creation entry (i.e., an intelligent video creation control) is added. After a user performs a triggering operation on the intelligent video creation entry, the YOYO intelligent assistant on the terminal device side is launched, and K recommended statements included in K recommended cards generated based on the user's memory nodes and portrait data determined from the user's real photo data are displayed on the skill page of the YOYO intelligent assistant. Since each recommended card is used to generate a video based on the photos in the photo data associated with the recommended statement corresponding to each recommended card, this method avoids the problem of low video generation efficiency in the videos generated by frequent conversations between the user and the electronic device, that is, this method can improve the efficiency of video generation. Since the recommended statements displayed on each recommended card are determined based on the user's portrait data and photo data, it is ensured as much as possible that the recommended statements displayed on each recommended card are content that the user is interested in, so that the videos generated based on each recommended card can better meet the user's needs. This method avoids the problem that videos cannot be generated for the photo data processed by the recommended statements based on a fixed template, and the generated videos cannot meet the user's needs, that is, this method can enhance the user's experience. In summary, this method can improve the efficiency of video generation and enhance the user's experience.

[0270] Next, Figure 16 Another statement recommendation method provided by an embodiment of the present application is introduced. Figure 16 The described statement recommendation method is only illustrative and does not impose any limitation on the statement recommendation method provided by the present application.

[0271] Figure 16 It is a schematic diagram of another statement recommendation method provided by an embodiment of the present application. The resource allocation method provided by an embodiment of the present application can be executed by Figure 1 the electronic device 100 shown in the figure. Among them, the electronic device 100 can be, but is not limited to, a mobile phone. It can be understood that the electronic device 100 can be implemented as software, or a combination of software and hardware. Exemplarily, as Figure 16 shown, the statement recommendation method includes S1610 and S1620. Next, S1610 and S1620 are introduced in detail.

[0272] S1610, the electronic device displays a first interface, where the first interface includes a first control.

[0273] The first interface includes a first control, where the first control is used to trigger the electronic device to display a second interface. That is to say, the first control provided on the first interface is an entry control for entering the second interface.

[0274] In the embodiments of the present application, the first interface is not specifically limited. It should be understood that the first interface described below is only for illustration and does not constitute any limitation on the first interface applicable to the embodiments of the present application.

[0275] In one example, the first interface is the desktop of an electronic device. Among them, the desktop of the electronic device includes icons of one or more applications. For example, the first interface may be the desktop of an electronic device including at least one application icon, such as Figure 5 the desktop S5 of the shown mobile phone. The first control may be Figure 5 the video creation control 510 in the shown desktop quick access entry 500.

[0276] In another example, the first interface is the interface of an application of an electronic device. For example, the first interface may be the interface of the gallery application of an electronic device, such as Figure 12 the creation page S12 of the gallery in the shown mobile phone. The first control may be Figure 12 the intelligent video creation control 1200 displayed in the shown creation page S12. For example, the first interface may be the album interface of an electronic device, such as Figure 13 the photo page S13 of the shown mobile phone, and an intelligent video creation floating ball 1300 is displayed in the photo page S13.

[0277] In yet another example, the first interface is the global search interface of an electronic device. For example, the first interface may be Figure 11 the user interface S11 shown. The first control may be Figure 11 the intelligent video creation control 1110 in the shown user interface S11.

[0278] The way the electronic device displays the first interface is not specifically limited either. For example, taking the first interface being the desktop of the electronic device as an example, in response to the user's unlocking operation on the electronic device, the electronic device displays the first interface. In one example, the first interface is the interface of an application of the first electronic device. For example, taking the first interface being the interface of the gallery application of the electronic device as an example, in response to the user's triggering operation on the icon of the gallery application of the electronic device, the electronic device displays the first interface. For example, taking the first interface being the interface of the gallery application of the electronic device as an example, in response to the user's voice wake-up operation on the gallery application, the electronic device displays the first interface.

[0279] S1620, in response to a triggering operation on a first control, display a second interface, where the K recommended cards included in the second interface correspond one-to-one with K recommended statements, each recommended card displays the corresponding recommended statement, the K recommended statements are determined according to the user's portrait data and the user's photo data, and each recommended card is used to trigger the electronic device to create a video from the photo data according to the recommended statement corresponding to each recommended card, so as to obtain a video associated with the recommended statement corresponding to each recommended card, and K is a positive integer.

[0280] K is a preset value, and this preset value is a value with an upper limit. The value of K can be predefined or dynamically adjusted. There is no specific limitation on the value of K, and it can be set according to the actual scenario. For example, K can be set to 1, 2, or 3, etc. according to the user's usage requirements. Another example is that K can be set to 2 or 4, etc. according to the performance of the electronic device.

[0281] The K recommended statements are determined according to the user's portrait data and the user's photo data, that is, each recommended statement is determined according to the user's portrait data and the user's photo data, where the user's photo data is the photos stored in the electronic device. For example, the user's photo data can be, but is not limited to, the photos stored in the gallery of the electronic device.

[0282] In one example, before the electronic device displays the second interface, the electronic device can also obtain the K recommended statements by performing the following steps: The electronic device classifies the photo data to obtain K photo sets corresponding to K different event types, where the K photo sets and the K recommended statements correspond one-to-one, and each recommended statement is determined according to the corresponding photo set and the user's portrait data; the electronic device analyzes each photo set to obtain the memory information of each photo set, where the memory information includes the information recorded by the photos in each photo set; the electronic device determines the recommended statement corresponding to each photo set according to the memory information and portrait data of each photo set, so as to obtain K recommended statements.

[0283] Optionally, the memory information of each photo set in the above implementation manner may specifically include the time, location, people, and events recorded by the photos in each photo set, the event is one of the K different event types, and, determining the recommended statement corresponding to each photo set according to the memory information and portrait data of each photo set, so as to obtain K recommended statements, includes: The electronic device determines the personal information of the person according to the portrait data and the people recorded by the photos in the memory information of each photo set; the electronic device generates the recommended statement corresponding to each photo set according to the personal information of the person and the memory information of each photo set, so as to obtain K recommended statements.

[0284] The character information of a character may include the character, the character relationship of the character, the role of the character (for example, a child, a daughter, a son, a father or a mother, etc.), etc., without specific limitation.

[0285] There is no specific limitation on the method for the electronic device to generate a recommendation sentence corresponding to each photo set based on the character information of the character and the memory information of each photo set. In one example, the electronic device can generate a recommendation sentence corresponding to each photo set according to the character information of the character and the memory information of each photo set in accordance with a preset sentence format, wherein the preset sentence format includes a character, a place, a time, and an event. For a detailed description of the electronic device generating a recommendation sentence corresponding to each photo set according to the character information of the character and the memory information of each photo set in accordance with a preset sentence format, please refer to the relevant description in step S1412-10 above and no further details will be given here.

[0286] Optionally, in the above implementation, the electronic device classifies the photo data to obtain K photo sets corresponding to K different event types, including: the electronic device filters the photo data according to at least one preset time range to obtain at least one photo set that satisfies at least one preset time range; the electronic device classifies at least one photo set that satisfies at least one preset time range according to event type to obtain K photo sets.

[0287] Exemplarily, the character information of the character in the above example can be the above Figure 15 The person information i in the provided method, the memory information of each photo set may include the above Figure 15 The i-th time range, location i and i-th time range in the provided method correspond to at least one event class, and the i-th time range corresponds to at least one event class; at least one preset time range in the above example can be the above Figure 15 In the i-th time range of the method provided, at least one set of photos in at least one preset time range in the above example can be the above Figure 15 The i-th time range in the provided method corresponds to the aggregation result of at least one event class.

[0288] The second interface includes K recommendation cards and K recommendation sentences corresponding to each other, and each recommendation card displays a corresponding recommendation sentence. The content of the recommendation sentence displayed on each recommendation card is not specifically limited. For example, the recommendation sentence displayed on a recommendation card may include time, place, person, and event. For example, the recommendation sentence displayed on a recommendation card may include time, person, and event. Optionally, each recommendation card may also include a cover image of the card.

[0289] For example, the second interface can be Figure 8A The shown intelligent video compilation interface S8A, in which, in the dialog box 800A in the intelligent video compilation interface S8A, three recommended cards (i.e., an example of the previous K recommended cards) are displayed. Each recommended card includes a recommended statement and a picture associated with the recommended statement. The three recommended statements corresponding to the three recommended cards are "Create a video of the child playing with the father yesterday", "Generate a warm video of the child and the mother last month", and "Generate a growth video of the child from last year to this year". For another example, the second interface may be Figure 8B The shown intelligent video compilation interface S8B, in which, in the dialog box 800B in the intelligent video compilation interface S8B, three recommended cards (i.e., an example of the previous K recommended cards) are displayed. Each recommended card includes a recommended statement and a picture associated with the recommended statement. The three recommended statements corresponding to the three recommended cards are "Create a video of the baby dancing", "Create a video of traveling in Nanjing", and "Generate a video of playing badminton yesterday".

[0290] In the embodiment of the present application, in response to a trigger operation on the first control, the electronic device displays the second interface. After the user triggers the first control of the first interface, the specific implementation process of the electronic device displaying the second interface is not limited.

[0291] In one implementation manner, in response to a trigger operation on the first control, the electronic device directly displays the second interface. It can be understood that in this implementation manner, during the process of the electronic device switching from the first interface to the second interface, there is no switching operation involving other interfaces.

[0292] For example, taking the first interface as Figure 5 the shown desktop S5 of the mobile phone, the first control may be Figure 5 the video creation control 510 in the shown desktop S5. After the user triggers Figure 5 the video creation control 510 in it, the mobile phone may display Figure 8A the shown intelligent video compilation interface S8A or Figure 8B the shown intelligent video compilation interface S8B.

[0293] In another implementation manner, in response to a trigger operation on the first control, the electronic device first displays other interfaces. Thereafter, after a trigger operation on the control of the other interface, the electronic device then displays the second interface.

[0294] In an example, in response to a trigger operation on the first control, the electronic device displays the second interface. Exemplarily, it may include the following steps: In response to a trigger operation on the first control, the electronic device displays the third interface, where the third interface includes multiple cards corresponding to multiple preset categories; in response to a trigger operation on one of the multiple cards, the electronic device displays the second interface.

[0295] The multiple different preset categories are not specifically limited and can be set according to user needs. For example, each preset category can be but is not limited to any of the following categories: My Daily Vlog, Family Photos, Daily Gatherings, Growth Theme, Travel Vlog, Food Compilation, My Photo Shoot, Hobbies, or City Architecture, etc.

[0296] For example, the third interface can be the intelligent video editing interface S7 of the mobile phone as shown in Figure 7 which includes multiple preset categories. The multiple categories can be but are not limited to including the Daily Vlog, My Photo Shoot, Family Contract, Growth Theme, Travel Vlog, and Food Compilation shown in the intelligent video editing interface S7. In response to a trigger operation on a certain category in the intelligent video editing interface S7, the mobile phone displays the second interface described above.

[0297] In the above implementation manner, after the electronic device displays the first interface, after the user's trigger operation on the first control of the first interface, the electronic device first displays the third interface. Then, after the user's trigger operation on a card of a preset category displayed on the third interface, the first electronic device displays the second interface.

[0298] In another example, in response to a trigger operation on the first control, the electronic device displays the second interface, including: in response to a trigger operation on the first control, displaying an interface including the second control and the thumbnail corresponding to the photo data; in response to a trigger operation on the second control, displaying the third interface, where the third interface includes multiple cards corresponding to multiple preset categories; in response to a trigger operation on one of the multiple cards, the electronic device displays the second interface.

[0299] The thumbnail corresponding to the photo data can be the thumbnail corresponding to all the photos of the photo data, or the thumbnail corresponding to some of the photos of the photo data, and no specific limitation is made thereto.

[0300] For example, the above interface including the second control and the thumbnail corresponding to the photo data can be the intelligent video editing interface S6 of the mobile phone as shown in Figure 6 where the second control can be control 600, and the thumbnail corresponding to the photo data can be the photo content displayed in text box 610.

[0301] The third interface and the multiple cards of the multiple preset categories can be referred to the description above, and will not be elaborated here in detail.

[0302] In the above implementation manner, after the electronic device displays the first interface, and after the user performs a trigger operation on the first control of the first interface, the electronic device first displays an interface including a second control and a thumbnail corresponding to the photo data. Next, when the user performs a trigger operation on the second control, the electronic device displays a third interface. After that, after the user performs a trigger operation on a preset type of card displayed on the third interface, the first electronic device displays the second interface.

[0303] As an example of the present application, the electronic device includes a first application, a second application, and a media processing module. The first interface is the interface of the first application. And the electronic device executes the above S1620, that is, in response to a trigger operation on the first control, the electronic device displays the second interface, including: in response to a trigger operation on the first control, the first application sends a start instruction to the second application, where the start instruction carries the identifier of the first interface and the identifier of the first control; after the second application receives the start instruction, the second application sends a recommended statement loading instruction to the media processing module, where the recommended statement loading instruction is used to request to obtain recommended cards for generating a video according to the photo data; after the media processing module obtains the recommended statement loading instruction, the media processing module generates K card information corresponding to K recommended cards according to the portrait data and the photo data; the media processing module sends the K card information to the second application; after the second application loads the K card information, it displays the second interface.

[0304] Optionally, the media processing module of the electronic device may further include a recall material processing module. In one example, after the media processing module obtains the recommended statement loading instruction, the media processing module generates K card information corresponding to K recommended cards according to the portrait data and the photo data, including: after the recall material processing module obtains the recommended statement loading instruction, the recall material processing module generates K card information corresponding to K recommended cards according to the portrait data and the photo data.

[0305] The K card information corresponds to the K recommended cards one by one. Each card information is used to generate the corresponding recommended card. Among them, each card information may include the recommended statement in the corresponding recommended card of each card information. Optionally, each card information may further include the cover image of the card and the URL of the card, where the URL of the card is used to indicate the address of the resource (such as parameters, etc.) corresponding to each recommended card, and the resource corresponding to each recommended card is used to generate the structure of each recommended card (such as an oval or square structured card). In this way, the electronic device can obtain the resource corresponding to each recommended card according to the address indicated by the URL of the card included in each recommended card.

[0306] For example, one of the K recommended cards may be Figure 8A The recommended cards 801, 802, or 803 shown in the intelligent video compilation interface S8A.

[0307] Optionally, the electronic device further includes a media learning module, and after the second application receives the start instruction, the method further includes: the media processing module sends a query instruction to the media learning module; the media learning module sends a query result including portrait data and photo data to the media processing module, so that the media processing module can obtain the portrait data and photo data.

[0308] Optionally, the first application is a gallery, the photo data includes the photos stored in the gallery, and the second application is a voice assistant.

[0309] Exemplarily, the first application may be Figure 14 The gallery shown, and the second application may be Figure 14 The YOYO intelligent assistant shown. The first interface in the above example may be the Figure 14 Creation page of the gallery shown above, and the first control may be the intelligent video compilation control included in the creation page. The identifier of the first application in the above example may be the creation page identifier of the gallery in the method provided above, and the identifier of the first control may be the intelligent video compilation identifier in the method provided above. Figure 14 The creation page identifier of the gallery in the method provided above, and the identifier of the first control may be the intelligent video compilation identifier in the method provided above. Figure 14 The second interface in the above example may be the Figure 14 Recommendation interface of the K recommended cards shown above. The K card information in the above example may be the Figure 15 Recommendation information shown above.

[0310] Optionally, after the electronic device executes the above S1620, the electronic device may further perform the following operations: in response to a trigger operation on the first recommended card among the K recommended cards, the electronic device displays a fourth interface, where the fourth interface includes a thumbnail of a first video, and the first video is a video associated with the first recommended statement generated by the electronic device after performing video compilation processing on the photo data according to the first recommended statement. After that, in response to a trigger operation on the thumbnail of the first video, the electronic device displays a browsing interface of the first video. The electronic device displays the browsing interface of the first video, and at this time, the first video is in a playing state.

[0311] The fourth interface includes a thumbnail of the first video, and there is no specific limitation on whether the fourth interface includes other information. For example, the fourth interface may further include the first recommended card corresponding to the first recommended statement, and the first recommended statement displayed after the user triggers the first recommended card.

[0312] For example, the fourth interface may be Figure 9B The dialogue interface S9B of the intelligent video compilation of the shown mobile phone, in which the text 920 "A video of your child playing with your father yesterday has been generated for you. Come and take a look~" and the generated video 930 are displayed. When the user needs to view the video 930, the user triggers the open video control 940 in the video 930, and then can view the content of the video 930.

[0313] It should be understood that the above Figure 16 shown statement recommendation method is only illustrative and does not impose any limitation on the statement recommendation method provided by this application.

[0314] In the embodiments of this application, after the electronic device receives a trigger operation on the first control of the first interface, the electronic device can directly display a second interface including K recommended cards. Each recommended card is used to generate video data based on the photos in the photo data associated with the recommended statement corresponding to each recommended card. This method avoids the problem of low video generation efficiency in the videos generated by frequent conversations between the user and the electronic device, that is, this method can improve the convenience of video generation and the efficiency of video generation. Since the recommended statements displayed on each recommended card are determined based on the user's portrait data and photo data, it is possible to ensure that the recommended statements displayed on each recommended card are content that the user is interested in, so that the videos generated based on each recommended card can better meet the user's needs. This method avoids the problems that videos cannot be generated by processing photo data with fixed-template recommended statements and that the generated videos cannot meet the user's needs, that is, this method can improve the user's experience. In summary, this method can improve the efficiency of video generation and enhance the user's experience.

[0315] As described above in combination with Figures 1 to 16 , the electronic device, software architecture, system architecture, and statement recommendation method applicable to the statement recommendation method of the embodiments of this application have been described in detail. Next, the device embodiments of this application will be described in combination with Figure 17 It should be understood that the statement recommendation device in the embodiments of this application can execute various statement recommendation methods of the foregoing embodiments of this application. That is, for the specific working processes of the following various products, reference can be made to the corresponding processes in the foregoing method embodiments.

[0316] Figure 17 is a schematic diagram of the statement recommendation device provided by the embodiments of this application. Exemplarily, Figure 17 the shown statement recommendation device 1700 is applied to an electronic device. The statement recommendation device 1700 includes a processing unit 1710. Next, the functions of the processing unit 1710 will be introduced.

[0317] The processing unit 1710 is configured to: display a first interface, where the first interface includes a first control; in response to a trigger operation on the first control, display a second interface, where the K recommended cards included in the second interface correspond one-to-one to K recommended statements, each recommended card displays a corresponding recommended statement, the K recommended statements are determined according to the user's portrait data and the user's photo data, and each recommended card is used to trigger the electronic device to generate a video associated with the recommended statement corresponding to each recommended card by making a finished video from the photo data according to the recommended statement corresponding to each recommended card, and K is a positive integer.

[0318] In a possible implementation manner, the processing unit 1710 is further configured to: in response to a trigger operation on the first control, display a third interface, where the third interface includes a plurality of cards corresponding to a plurality of preset categories; in response to a trigger operation on one of the plurality of cards, display the second interface.

[0319] In another possible implementation manner, the processing unit 1710 is further configured to: in response to a trigger operation on the first control, display an interface including a second control and a thumbnail corresponding to the photo data; in response to a trigger operation on the second control, display the third interface.

[0320] In another possible implementation manner, the processing unit 1710 is further configured to: after displaying the second interface in response to a trigger operation on the first control, perform the following operations: in response to a trigger operation on a first recommended card among the K recommended cards, display a fourth interface, where the fourth interface includes a thumbnail of a first video, and the first video is a video associated with the first recommended statement generated by the electronic device after making a finished video from the photo data according to the first recommended statement.

[0321] In another possible implementation manner, the processing unit 1710 is further configured to: perform a classification process on the photo data to obtain K photo sets corresponding to K different event types, where the K photo sets correspond one-to-one to the K recommended statements, and each recommended statement is determined according to the corresponding photo set and the user's portrait data; perform an analysis process on each photo set to obtain memory information of each photo set, where the memory information includes information recorded by the photos in each photo set; determine the recommended statement corresponding to each photo set according to the memory information of each photo set and the portrait data, so as to obtain the K recommended statements.

[0322] In another possible implementation manner, the memory information of each photo set specifically includes the time, location, people, and events recorded in the photos in each photo set, the event being one of the K different event types, and the processing unit 1710 is further configured to: determine the personal information of the person according to the portrait data and the memory information of each photo set including the people recorded in the photos in each photo set; generate a recommended statement corresponding to each photo set according to the personal information of the person and the memory information of each photo set, so as to obtain the K recommended statements.

[0323] In another possible implementation manner, the processing unit 1710 is further configured to: screen the photo data according to at least one preset time range to obtain at least one photo set that meets the at least one preset time range; classify and process the at least one photo set that meets the at least one preset time range according to the event type to obtain the K photo sets.

[0324] In another possible implementation manner, the first interface is the desktop of the electronic device, where the desktop of the electronic device includes icons of one or more applications, or the first interface is the interface of an application of the electronic device.

[0325] In another possible implementation manner, K is a preset value.

[0326] It should be noted that the above statement recommendation device 1700 is embodied in the form of a functional unit. The term "unit" here can be implemented in software and / or hardware forms, and no specific limitation is made thereto.

[0327] For example, the "unit" can be a software program, a hardware circuit, or a combination of the two that implements the above functions. The hardware circuit may include an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor, or a group of processors, etc.) for executing one or more software or firmware programs, and a memory, a merged logic circuit, and / or other suitable components that support the described functions.

[0328] Therefore, the units in the examples described in the embodiments of the present application can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician 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 present application.

[0329] The present application also provides a computer program product which, when executed by a processor, implements the statement recommendation method described in any of the method embodiments of the present application.

[0330] This computer program product can be stored in a memory, for example, it is a program which, after processes such as preprocessing, compilation, assembly and linking, is finally converted into an executable target file that can be executed by a processor.

[0331] The present application also provides a chip which includes a processor. When the processor executes instructions, the processor implements the statement recommendation method described in any of the method embodiments of the present application when it executes.

[0332] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a computer, it implements the statement recommendation method described in any of the method embodiments of the present application. This computer program can be a high-level language program or an executable target program.

[0333] In the present application, "at least one" means one or more, and "a plurality" means two or more. "At least one (item)" or a similar expression thereof refers to any combination of these items, including any combination of single item(s) or plural item(s). For example, at least one (item) of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, c can be single or multiple.

[0334] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution is prior or posterior. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0335] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians 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 present application.

[0336] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0337] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in electrical, mechanical or other forms.

[0338] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0339] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0340] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.< / videoview> < / imgview> < / textview>

Claims

1. A statement recommendation method, characterized in that, Applied to an electronic device, the method includes: Displaying a first interface, wherein the first interface includes a first control; In response to a trigger operation on the first control, displaying a second interface, wherein the K recommended cards included in the second interface correspond one-to-one with K recommended statements, each recommended card displays the corresponding recommended statement, the K recommended statements are determined according to the user's portrait data and the user's photo data, and each recommended card is used to trigger the electronic device to process the photo data into a video according to the recommended statement corresponding to each recommended card, so as to obtain a video associated with the recommended statement corresponding to each recommended card, where K is a positive integer.

2. The method according to claim 1, wherein The step of, in response to a trigger operation on the first control, displaying a second interface includes: In response to a trigger operation on the first control, displaying a third interface, wherein the third interface includes a plurality of cards corresponding to a plurality of preset categories; In response to a trigger operation on one of the plurality of cards, displaying the second interface.

3. The method according to claim 1 or 2, characterized in that, After the step of, in response to a trigger operation on the first control, displaying a second interface, the method further includes: In response to a trigger operation on the first recommended card among the K recommended cards, displaying a fourth interface, wherein the fourth interface includes a thumbnail of a first video, and the first video is a video associated with the first recommended statement generated after the electronic device processes the photo data according to the first recommended statement.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: Classifying the photo data to obtain K photo sets corresponding to K different event types, wherein the K photo sets correspond one-to-one with the K recommended statements, and each recommended statement is determined according to the corresponding photo set and the portrait data; Analyzing each photo set to obtain memory information of each photo set, wherein the memory information includes information recorded by the photos in each photo set; Determining the recommended statement corresponding to each photo set according to the memory information of each photo set and the portrait data, so as to obtain the K recommended statements.

5. The method according to claim 4, wherein The memory information of each photo set specifically includes the time, location, people, and events recorded by the photos in each photo set, the event is one of the K different event types, and the step of determining the recommended statement corresponding to each photo set according to the memory information of each photo set and the portrait data, so as to obtain the K recommended statements includes: Determining the personal information of the person according to the portrait data and the people recorded by the photos in the memory information of each photo set; Generating the recommended statement corresponding to each photo set according to the personal information of the person and the memory information of each photo set, so as to obtain the K recommended statements.

6. The method according to claim 4 or 5, characterized in that The step of classifying the photo data to obtain K photo sets corresponding to K different event types includes: Filter the photo data according to at least one preset time range to obtain at least one photo set that meets the at least one preset time range; Classify at least one photo set that meets the at least one preset time range according to the event type to obtain the K photo sets.

7. The method according to any one of claims 1 to 6, characterized in that The electronic device includes a first application, a second application, and a media processing module. The first interface is the interface of the first application, and, in response to a trigger operation on the first control, displaying a second interface, including: In response to a trigger operation on the first control, the first application sends a start instruction to the second application, where the start instruction carries the identifier of the first interface and the identifier of the first control; After the second application receives the start instruction, the second application sends a recommendation statement loading instruction to the media processing module, where the recommendation statement loading instruction is used to request to obtain a recommendation card for generating a video based on the photo data; After the media processing module obtains the recommendation statement loading instruction, the media processing module generates K card information corresponding to the K recommendation cards according to the portrait data and the photo data; The media processing module sends the K card information to the second application; After the second application loads the K card information, it displays the second interface.

8. The method according to claim 7, wherein The electronic device further includes a media learning module, and, after the second application receives the start instruction, the method further includes: The media processing module sends a query instruction to the media learning module; The media learning module sends a query result including the portrait data and the photo data to the media processing module so that the media processing module obtains the portrait data and the photo data.

9. The method according to claim 7 or 8, characterized in that, The first application is a gallery, the photo data includes the photos stored in the gallery, and the second application is a voice assistant.

10. The method according to any one of claims 1 to 9, characterized in that, The first interface is the desktop of the electronic device, where the desktop of the electronic device includes icons of one or more applications, or the first interface is the interface of an application of the electronic device.

11. The method according to any one of claims 1 to 10, characterized in that, K is a preset value.

12. An electronic device, characterized in that, The electronic device includes: one or more processors, and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the electronic device to execute the statement recommendation method as described in any one of claims 1 to 11.

13. A chip system, characterized in that, The chip system is applied to an electronic device, the chip system includes one or more processors, and the one or more processors are used to call computer instructions to cause the electronic device to execute the statement recommendation method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes instructions, and when the instructions run on an electronic device, the electronic device is caused to execute the statement recommendation method as described in any one of claims 1 to 11.

Images