Multimedia data generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a multimedia data generation method and device, electronic equipment and a storage medium. The method comprises the steps that first dialogue content input by a user in a dialogue interface is acquired, and the first dialogue content comprises a target multimedia type; processing a target material according to the first dialogue content through an artificial intelligence model to generate target multimedia data matched with the target multimedia type; the target material comprises at least one of a target material uploaded by the user and a target material determined by the artificial intelligence model according to the first dialogue content; and displaying the target multimedia data in the dialogue interface. According to the multimedia data generation method and device, the electronic equipment and the storage medium, intelligent generation of multimedia data of various different multimedia types can be supported, the intelligence is improved, and different requirements of users are met.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of artificial intelligence technology, and specifically to a method, device, electronic device and storage medium for generating multimedia data. Background Art

[0002] With the rapid development of artificial intelligence technology, the application and popularity of artificial intelligence models in various industries are becoming more and more widespread. There are many artificial intelligence models on the market that can help users with multimedia creation or multimedia processing, such as artificial intelligence models that can generate copy, artificial intelligence models that can draw, and artificial intelligence models that can help with photo editing. However, the functions that can be realized by the artificial intelligence models currently launched are relatively simple, with low intelligence, and cannot meet user needs. Summary of the invention

[0003] The embodiments of the present application disclose a method, device, electronic device and storage medium for generating multimedia data, which can support the intelligent generation of multimedia data of multiple different multimedia types, improve intelligence and meet the different needs of users.

[0004] The present application embodiment discloses a method for generating multimedia data, including:

[0005] Acquire a first dialogue content input by a user in a dialogue interface, wherein the first dialogue content includes a target multimedia type;

[0006] Processing the target material according to the first conversation content through the artificial intelligence model to generate target multimedia data matching the target multimedia type; the target material includes at least one of the target material uploaded by the user and the target material determined by the artificial intelligence model according to the first conversation content;

[0007] The target multimedia data is displayed in the dialogue interface.

[0008] The present application embodiment discloses a device for generating multimedia data, the device comprising:

[0009] A dialogue acquisition module, used to acquire a first dialogue content input by a user in a dialogue interface, wherein the first dialogue content includes a target multimedia type;

[0010] a first generating module, configured to process the target material according to the first conversation content through an artificial intelligence model to generate target multimedia data matching the target multimedia type; the target material includes at least one of the target material uploaded by the user and the target material determined by the artificial intelligence model according to the first conversation content;

[0011] A display module is used to display the target multimedia data in the dialogue interface.

[0012] An embodiment of the present application discloses an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method for generating multimedia data as described above.

[0013] An embodiment of the present application discloses a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for generating multimedia data as described above is implemented.

[0014] An embodiment of the present application discloses a computer program product, including a computer program, and when the computer program is executed by a processor, the method for generating multimedia data as described above is implemented.

[0015] The method, device, electronic device and storage medium for generating multimedia data disclosed in the embodiments of the present application obtain a first conversation content input by a user in a conversation interface, the first conversation content includes a target multimedia type, and the target material is processed by an artificial intelligence model according to the first conversation content to generate target multimedia data matching the target multimedia type, and the target multimedia data is displayed in the conversation interface, wherein the target material includes at least one of the target material uploaded by the user and the target material determined by the artificial intelligence model according to the first conversation content. In the embodiments of the present application, the artificial intelligence model can support the intelligent generation of multimedia data of multiple different multimedia types, and the user inputs the target multimedia type to be generated through a conversation, and the target multimedia data matching the target multimedia type can be intelligently generated, which reduces the difficulty of generating the target multimedia data, and the artificial intelligence model supports combining the target material uploaded by the user with the target material generated by the artificial intelligence model to generate the target multimedia data, and the method of generating the target multimedia data is more flexible, improves the intelligence, and meets the different needs of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is an application scenario diagram of a method for generating multimedia data and an auxiliary editing method in one embodiment;

[0018] Figure 2 is a flowchart of a method for generating multimedia data in one embodiment;

[0019] Figure 3A A schematic diagram of the main interface of a target application in one embodiment;

[0020] Figure 3B is a schematic diagram of a dialogue interface in one embodiment;

[0021] Figure 3C is a schematic diagram of a dialogue interface in another embodiment;

[0022] Figure 4 A flowchart of a user uploading a target material in one embodiment;

[0023] Figure 5A is a schematic diagram of a dialogue interface in another embodiment;

[0024] Figure 5B This is a schematic diagram of an interface of a material selection page in an embodiment;

[0025] Figure 5C is a schematic diagram of a dialogue interface in another example;

[0026] Figure 5D is a schematic diagram of a dialogue interface in another example;

[0027] Figure 5E is a schematic diagram of a dialogue interface in another example;

[0028] Fig. 5F is a schematic diagram of a dialogue interface in another example;

[0029] Figure 5G is a schematic diagram of a dialogue interface in another example;

[0030] Figure 6 A flowchart of generating target material by using an AI model in one embodiment;

[0031] Fig. 7A is a schematic diagram of a dialogue interface in another example;

[0032] Figure 7B is a schematic diagram of a dialogue interface in another example;

[0033] Fig. 8A is a schematic diagram of a dialogue interface in another example;

[0034] Figure 8B is a schematic diagram of a dialogue interface in another example;

[0035] Fig. 9 A flowchart of generating target multimedia data according to a recommendation template generated by an AI model in one embodiment;

[0036] Fig. 10A is a schematic diagram of a dialogue interface in another embodiment;

[0037] Fig. 10B is a schematic diagram of a dialogue interface in another embodiment;

[0038] Fig. 10C This is a schematic diagram of a template preview interface in an embodiment;

[0039] Fig. 10D This is a schematic diagram of a template preview interface in another embodiment;

[0040] Fig.10E This is a schematic diagram of an interface of a material selection page in another embodiment;

[0041] Fig.11 is a flowchart of a method for generating multimedia data in another embodiment;

[0042] Fig. 12A is a schematic diagram of a dialogue interface in another embodiment;

[0043] Fig. 12B is a schematic diagram of a dialogue interface in another embodiment;

[0044] Fig.13 This is a schematic diagram of a preview interface of multimedia data in one embodiment;

[0045] Fig.14 A schematic diagram of interface changes for editing and optimizing target multimedia data in one embodiment;

[0046] Fig.15 A schematic diagram of interface changes for editing and optimizing target multimedia data in another embodiment;

[0047] Fig.16 A flowchart of an embodiment in which an AI model supports an editing assistance function on an editing page;

[0048] Fig.17A is a schematic diagram of an interface of an editing page corresponding to target multimedia data in an embodiment;

[0049] Fig. 17B is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment;

[0050] Fig. 17C is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment;

[0051] Fig.17Dis a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment;

[0052] Fig.17E is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment;

[0053] Fig.17F is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment;

[0054] Fig.18 A schematic diagram of interface changes using an AI model search and edit function in one embodiment;

[0055] Fig.19 A schematic diagram of interface changes of a tutorial for using an AI model search and edit function in one embodiment;

[0056] Fig. 20A is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment;

[0057] Fig. 20B is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment;

[0058] Fig.21 A schematic diagram of interface changes when a user uploads a target editing material in one embodiment;

[0059] Fig. 22 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment;

[0060] Fig.23A is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment;

[0061] Fig. 23B is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment;

[0062] Fig.24 A schematic diagram of interface changes for previewing target multimedia data after editing in one embodiment;

[0063] Fig.25 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment;

[0064] Fig.26 A flowchart of entering a call mode in one embodiment;

[0065] Fig.27A is a schematic diagram of a dialogue interface in another embodiment;

[0066] Fig.27B This is a schematic diagram of a call interface in one embodiment;

[0067] Fig.27C is a schematic diagram of a dialogue interface in another embodiment;

[0068] Fig.28 A flowchart of an editing auxiliary method in one embodiment;

[0069] Fig.29 is a block diagram of a device for generating multimedia data in one embodiment;

[0070] Fig.30 A block diagram of an editing auxiliary device in one embodiment;

[0071] Fig.31 FIG. 4 is a structural block diagram of an electronic device in an embodiment. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0073] It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present application and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0074] It is understood that the terms "first", "second", etc. used in this application can be used in this article to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from another element. For example, without departing from the scope of this application, the first guide component can be referred to as the second guide component, and similarly, the second guide component can be referred to as the first guide component. Both the first guide component and the second guide component are guide components, but they are not the same guide component. The term "plurality" used in this application refers to two or more. The term "and / or" used in this application refers to one of the schemes, or any combination of multiple schemes.

[0075] Figure 1 FIG. 1 is an application scenario diagram of a method for generating multimedia data and an auxiliary editing method in one embodiment. Figure 1As shown, the methods provided in each embodiment of the present application can be applied to an electronic device 10, and the electronic device 10 may include but is not limited to mobile phones, wearable devices (such as smart glasses, smart watches, etc.), tablet computers, vehicle-mounted terminals, laptop computers, PCs (Personal Computers), etc.

[0076] An artificial intelligence model may be provided in the electronic device 10, and the artificial intelligence model may support a rich variety of functions related to multimedia data. Optionally, the artificial intelligence model may be a single model or a model composed of multiple sub-models. The embodiment of the present application does not limit the specific model architecture of the artificial intelligence model.

[0077] The electronic device 10 may display a dialogue interface 110, which may include a dialogue window, etc. The dialogue interface 110 may be used to provide an interface for interaction between the artificial intelligence model and the user. The user may input his or her needs in the dialogue interface 110, and the artificial intelligence model may display corresponding feedback content in the dialogue interface 110 based on the content input by the user. Interaction through dialogue may improve interactivity.

[0078] In some embodiments, the artificial intelligence model can support intelligent generation of multimedia data of multiple different multimedia types. When a user needs to generate multimedia data, the user can enter a first dialogue content in the dialogue interface 110, and the first dialogue content includes the target multimedia type required by the user. For example, if the user enters the first dialogue content 112 as "help me generate a recommended food video" in the dialogue interface 110, the target multimedia type required by the user is the video type.

[0079] After the electronic device 10 obtains the first conversation content input by the user in the conversation interface 110, it can perform semantic analysis on the first conversation content through the artificial intelligence model to determine the target multimedia type contained in the first conversation content. Furthermore, the artificial intelligence model can also identify the data generation requirements in the first conversation content. The electronic device 10 can process the target material according to the first conversation content through the artificial intelligence model to generate target multimedia data matching the target multimedia type, and display the target multimedia data in the conversation interface 110. The target material may include at least one of the target material uploaded by the user and the target material determined by the artificial intelligence model according to the first conversation content.

[0080] For example, the artificial intelligence model performs semantic analysis on the first dialogue content 112: "Help me generate a recommended food video", determines that the user needs to generate a video type, and needs to generate a video related to recommended food, then the target material can be processed to generate a recommended food video 114, and the generated recommended food video 114 is displayed in the dialogue interface 110. The target material can be a target material uploaded by the user and / or a target material determined by the artificial intelligence model. For example, the user can upload a food picture as the target material, and the artificial intelligence model can also generate a food picture, a food sound effect and other target materials to generate a recommended food video 114.

[0081] It should be noted that in addition to being deployed in the electronic device 10, the artificial intelligence model can also be deployed in devices such as cloud servers. The electronic device 10 communicates with the cloud server and uses the artificial intelligence model deployed on the cloud server to perform data processing.

[0082] like Figure 2 As shown, in one embodiment, a method for generating multimedia data is provided, which can be applied to the above electronic device. The method may include the following steps:

[0083] Step 210: Acquire a first dialogue content input by the user in the dialogue interface, where the first dialogue content includes a target multimedia type.

[0084] A dialogue interface may refer to an interface that interacts with a user in the form of a dialogue, and the dialogue interface may include but is not limited to a dialogue window, a dialogue page, a dialog box, etc. A user may input functional requirements related to multimedia data in the dialogue interface, and the functional requirements related to multimedia data may include but are not limited to the requirements for generating multimedia data, optimizing multimedia data, and recommending multimedia data, etc. The electronic device may intelligently generate corresponding feedback content based on the functional requirements input by the user in the dialogue interface through an artificial intelligence (AI) model, and send the feedback content to the dialogue interface for the user to view. Through the dialogue interface, the dialogue process between the user and the AI ​​model can be truly simulated, thereby improving the intelligence and interactivity of the AI ​​model.

[0085] In some embodiments, the electronic device may run a target application, which may be an application that provides functions such as generating multimedia data using an AI model and editing multimedia data. When the electronic device starts the target application, the main interface of the target application may be displayed, and the main interface may include an AI guide component, which is used to guide the user to use the provided AI model to process multimedia data, such as generating multimedia data. The user can trigger the AI ​​guide component to use the functions provided by the AI ​​model, and the electronic device can display a dialogue interface in response to the user's triggering operation (such as a click operation, etc.) on the AI ​​guide component.

[0086] For example, Figure 3A FIG. 1 is a schematic diagram of the main interface of a target application in one embodiment. Figure 3A As shown, in the main interface 310 of the target application, an AI guide component 312 can be displayed in the form of a card or the like, and the AI ​​guide component 312 can display preset guide information, such as "Hi, I am your AI smart assistant, how can I help you?" and other preset guide information to guide users to use the functions provided by the AI ​​model. The user can jump from the main interface 310 to the dialogue interface display by clicking on the AI ​​guide component 312. Optionally, in the main interface 310 of the target application, the function information supported by the AI ​​model can also be displayed, such as displaying through the function card 314 that the AI ​​model supports the generation of pictures, supports the generation of videos, supports the generation of texts, and the like. The user can also jump and display the dialogue interface by clicking on any function card 314. It should be noted that the AI ​​guide component 312 and the function information can also be displayed in other forms, not necessarily in the form of cards, such as icons, buttons, etc., which are not limited here. By displaying the AI ​​guidance component on the main interface of the target application and not displaying too many entrances to other functions, it is possible to avoid distracting users by displaying too much information, and to more effectively guide users to use the functions of the AI ​​model. Users can enter the dialogue interface by triggering the AI ​​guidance component on the main interface. The access path is shorter, and the process of entering the dialogue interface is simpler, which improves the convenience of entering the dialogue interface.

[0087] As an optional implementation, the user can also trigger the electronic device to display a dialogue interface by voice triggering. The electronic device can collect the user's voice through an audio collection device (such as a microphone, etc.). If it is detected that the user's voice contains a target trigger instruction, it can respond to the target trigger instruction and display the dialogue interface. Optionally, the target trigger instruction can be set according to actual needs. For example, it can be a model name customized by the user or manufacturer for the AI ​​model, or it can be an instruction for a function supported by the required AI model. For example, if the user says "I want AI to generate pictures", the electronic device can be triggered to display the dialogue interface, which improves the convenience of entering the dialogue interface. It should be noted that the method of triggering the electronic device to display the dialogue interface is not limited to the above-mentioned methods, and other methods can also be used. The embodiments of the present application are not limited to this.

[0088] In some embodiments, when entering the dialogue interface, dialogue guidance information may be displayed in the dialogue interface, and the dialogue guidance information is used to guide the user to input the dialogue content in the dialogue interface. Optionally, the AI ​​model may support the generation of multimedia data of multiple multimedia types, and the multiple multimedia types may include but are not limited to multiple types of image types, video types, audio types, text types, graphic types, etc., then each multimedia type may correspond to one or more dialogue guidance information, and the dialogue guidance information may be used to guide the user to input the dialogue content including the corresponding multimedia type in the dialogue interface. Further, the dialogue guidance information may be used to indicate the content format of the dialogue content, so that the user can more accurately know the multimedia types supported by the AI ​​model and how to trigger the AI ​​to generate multimedia data of various multimedia types.

[0089] For example, Figure 3B FIG. 1 is a schematic diagram of a dialogue interface in an embodiment. Figure 3BAs shown, the electronic device can display a dialogue interface 320, and display a guided dialogue content 322 in the dialogue interface 320. The guided dialogue content 322 may include one or more dialogue guiding information 324. For example, if the AI ​​model supports the generation of multimedia data of video type, text type and image type, three dialogue guiding information 324 may be displayed, corresponding to the video type, text type and image type respectively. The user can learn the multimedia types supported by AI and how to express and describe through the three dialogue guiding information 324, and can trigger multimedia data of various multimedia types. Optionally, the user can input the dialogue content corresponding to the dialogue guiding information 324 in the dialogue interface 320 by triggering (such as clicking, etc.) any dialogue guiding information 324. For example, if the user clicks on the dialogue guiding information: "I want to make a video of a weekend trip", the electronic device can respond to the click operation and input the dialogue content "I want to make a video of a weekend trip" in the dialogue interface 320, helping the user to achieve quick input and simplify user operations. Optionally, the dialogue interface 320 may further include a replacement control 326, which may be triggered (such as by clicking, etc.) by the user. In response to the user's triggering operation on the replacement control 326, the electronic device may replace the displayed dialogue guidance information 324, thereby enriching the display of the dialogue guidance information.

[0090] In some embodiments, when a preset condition is met, the dialogue guidance information may be displayed on the dialogue interface when entering the dialogue interface. The preset condition may include but is not limited to at least one of the following:

[0091] (1) The target application enters the dialog interface for the first time after it is started.

[0092] The dialogue guidance information may be displayed on the dialogue interface when the dialogue interface is displayed for the first time after each start of the target application. Further, each start of the target application may be each cold start of the target application. A cold start may refer to a start mode in which a new process is created and assigned to the target application when the target application is started. In the case of switching the target application from the background to the foreground, the dialogue guidance information is not displayed on the dialogue interface, so as to avoid the situation in which the dialogue guidance information is displayed too frequently and causes trouble to the user.

[0093] (2) The time between the current entry into the dialog interface and the last exit from the dialog interface is greater than or equal to the time threshold.

[0094] The exit time of each electronic device exiting the dialogue interface can be recorded, and each time the dialogue interface is entered, it is determined whether the time between the current time and the last time of exiting the dialogue interface is greater than or equal to the time threshold. If it is greater than or equal to the time threshold, it means that the user has not entered the dialogue interface for a long time. In this case, dialogue guidance information can be displayed on the dialogue interface to help users use the AI ​​model to generate multimedia data more conveniently.

[0095] It should be noted that the duration threshold can be set according to actual needs, such as 12 hours, 24 hours, 2 days, etc., but is not limited thereto.

[0096] (3) The number of times the dialogue guidance information is displayed in the dialogue interface between the current entry into the dialogue interface and the last entry into the dialogue interface is greater than or equal to the number threshold.

[0097] Among them, the number of interface displays may refer to the number of times the electronic device enters and displays the dialogue interface. After displaying the dialogue guidance information in the dialogue interface, the electronic device may record the number of times the interface is re-entered and displayed, and each time the dialogue interface is entered, it is determined whether the number of times the interface is displayed between the last time the dialogue guidance information was displayed in the dialogue interface and the current entry into the dialogue interface is greater than or equal to the number threshold. If the number of times the interface is displayed is greater than or equal to the number threshold, it means that the user has re-entered the dialogue interface for many times, and the dialogue guidance information can be displayed in the dialogue interface to help the user use the AI ​​model to generate multimedia data more conveniently. The recorded number of times the interface is displayed can be reset to zero and recorded again.

[0098] When the preset conditions are met, when entering the dialogue interface, dialogue guidance information is displayed on the dialogue interface, which can help users use the AI ​​model to generate multimedia data more conveniently, and will not display dialogue guidance information too frequently to cause trouble to users, thereby improving the user experience.

[0099] The electronic device can obtain the first conversation content input by the user in the conversation interface, and the first conversation content may be the conversation content input by the user in the current round of conversation. Optionally, the first conversation content may also include the conversation content input by the user in the historical round of conversation, and the historical round of conversation may refer to the conversation before the current round of conversation in the conversation interface displayed this time.

[0100] The first conversation content may include a target multimedia type, which may refer to the multimedia type to which the multimedia data generated by the user's needs belongs. Optionally, the target multimedia type may include but is not limited to any one of an image type, a video type, an audio type, a text type, a graphic type, etc., so as to meet the user's needs for generating different types of multimedia data, and can be applicable to a variety of different creation scenarios, thereby improving intelligence.

[0101] It should be noted that the user may input the conversation content in the conversation interface by touching a virtual keyboard, by handwriting, by voice, or by using an external input device (such as a keyboard, a mouse, etc.), which is not limited here.

[0102] Step 220, processing the target material according to the first conversation content through the artificial intelligence model to generate target multimedia data matching the target multimedia type.

[0103] The electronic device can perform semantic analysis on the first conversation content through the AI ​​model to determine the target multimedia type contained in the first conversation content, and process the target material according to the first conversation content to generate target multimedia data that matches the target multimedia type.

[0104] The target material may refer to the raw material for generating the target multimedia data, and at least part of the content of the target multimedia data is directly or indirectly obtained from the target material. In an embodiment of the present application, the target material may include at least one of the target material uploaded by the user and the target material determined by the artificial intelligence model according to the first conversation content.

[0105] The target material uploaded by the user may refer to the material sent by the user to the AI ​​model through the electronic device. The target material uploaded by the user may be a local material stored in the memory of the electronic device or a material stored in the cloud. The user may select the target material to be uploaded on the electronic device, and the electronic device may send the target material selected by the user to the dialogue interface. The AI ​​model determines the target material uploaded by the user based on the target material input in the dialogue interface.

[0106] The target material determined by the AI ​​model based on the first conversation content may include one or more of the target material generated by the AI ​​model based on the first conversation content, the target material found by the AI ​​model in a database or the Internet based on the first conversation content, and historical multimedia data generated by the AI ​​model. The AI ​​model can determine the target material when the user does not upload the target material, or when the user instructs the AI ​​model to generate or determine the material on its own in the first conversation content. Furthermore, in addition to the target multimedia type, the first conversation content may also include feature information, which can be used to describe the features of the target multimedia data to be generated. For example, if the first conversation content is "Please help me generate a video introducing hot pot", the feature information may include hot pot, introduction, etc. The AI ​​model can determine the target material based on the feature information, thereby ensuring that the generated target multimedia data is more accurate.

[0107] Optionally, the data type corresponding to the target material may be the same as the target multimedia type, or may be different from the target multimedia type. For example, if the target multimedia type is a video type, the data type corresponding to the target material may be a video, or an image, text, audio, etc. If the target multimedia type is a text type, the data type corresponding to the target material may be a text, or a video, image, etc., which is not limited here.

[0108] Optionally, the AI ​​model processes the target material, which may include but is not limited to the AI ​​model performing feature extraction and semantic recognition on the target material, and extracting material content that is compatible with the first conversation content from the target material for processing and handling, or converting the target material into new data according to the first conversation content, or adjusting the content of the target material according to the first conversation content, etc.

[0109] The AI ​​model can process the target material uploaded by the user and / or the target material determined by the artificial intelligence model according to the content of the first conversation, and generate target multimedia data that matches the target multimedia type. When the user uploads the target material, the AI ​​model can process the target material uploaded by the user to generate target multimedia data; when the user does not upload the target material, the AI ​​model can determine the target material according to the content of the first conversation, and process the determined target material to generate target multimedia data. Optionally, when the user uploads the target material, the AI ​​model can also determine the target material according to the content of the first conversation, and simultaneously process the target material uploaded by the user and the target material determined by itself to generate target multimedia data. The target material uploaded by the user and the target material generated by the AI ​​model can be flexibly combined for processing, which improves the intelligence and the accuracy of the generated target multimedia data.

[0110] Optionally, the AI ​​model can also obtain user historical data, learn user personalized information such as user habits and / or user interests based on the user historical data, and process the target material based on the first conversation content and the user personalized information to generate target multimedia data that is more in line with user expectations, thereby improving user satisfaction and usage experience.

[0111] Step 230: Display the target multimedia data in the dialogue interface.

[0112] After the target multimedia data is generated through the AI ​​model, the target multimedia data can be output in the dialogue interface. The dialogue interface can directly display the complete content of the target multimedia data, and can also display the thumbnail content of the target multimedia data. For example, if the target multimedia data is a text, the complete text content can be displayed in the dialogue interface; if the target multimedia data is a picture, a thumbnail of the target multimedia data can be displayed in the dialogue interface; if the target multimedia data is a video, a video cover or video thumbnail of the target multimedia data can be displayed in the dialogue interface. The user can display the complete target multimedia data by clicking on the thumbnail content of the target multimedia data.

[0113] In some embodiments, the artificial intelligence model may generate multiple target multimedia data that match the target multimedia type, and display the multiple target multimedia data in the dialogue interface. The multiple target multimedia data may correspond to different styles or different creative techniques. Among them, the style may refer to the representative appearance presented by the target multimedia data as a whole. For example, multiple pictures of different styles may be generated, and the styles of the pictures may include but are not limited to aesthetic style, realistic style, fresh style, bright style, etc.; multiple texts of different styles may be generated, and the styles of the texts may include but are not limited to concise style, literary style, gorgeous style, humorous style, etc. The creative technique may refer to the creative skills or creative methods used to generate the target multimedia data. Taking the generation of video type target multimedia data as an example, the creative technique may include camera movement, editing method, transition method, etc. Taking the generation of text type target multimedia data as an example, the creative technique may include genre, expression method, rhetoric, etc.; Taking the generation of image type target multimedia data as an example, the creative technique may include image layout, painting order, brushwork, drawing skills, shooting angle, etc., but is not limited to this.

[0114] For example, Figure 3C FIG. 1 is a schematic diagram of a dialogue interface in another embodiment. Figure 3C As shown, the user can enter the first dialogue content 332 in the dialogue interface 320: "Help me generate a recommended food video", and the first dialogue content 332 can be semantically analyzed by the AI ​​model, and 4 recommended food videos 334 corresponding to different styles or different creative techniques can be generated. The target material used to generate the recommended food video 334 can be the target material uploaded by the user or the target material generated by the AI ​​model itself. The generated 4 recommended food videos 334 corresponding to different styles or different creative techniques can be displayed in the dialogue interface 320 for the user to choose, so as to meet the different needs of users and improve the user experience.

[0115] In an embodiment of the present application, the artificial intelligence model can support the intelligent generation of multimedia data of multiple different multimedia types. The user can input the target multimedia type to be generated through dialogue, and the target multimedia data matching the target multimedia type can be intelligently generated, reducing the difficulty of generating the target multimedia data. The artificial intelligence model supports combining the target material uploaded by the user with the target material generated by the artificial intelligence model to generate the target multimedia data. The method of generating the target multimedia data is more flexible, improves intelligence, and meets the different needs of users.

[0116] The target material used by the AI ​​model to generate the target multimedia data can be the target material uploaded by the user. Figure 4 As shown, in one embodiment, before the step of processing the target material according to the first conversation content by the artificial intelligence model, the above method may further include the following steps:

[0117] Step 402: In response to a first trigger operation on a first guide component in a dialog interface, a material selection page is displayed; the material selection page includes one or more pre-stored materials.

[0118] A first guide component may be displayed in the dialogue interface, and the first guide component may be used to guide the user to upload materials. The first guide component may include but is not limited to a guide box, a guide button, a guide information bar, etc. Optionally, after the user inputs the first dialogue content, the first guide component may be displayed in the dialogue interface in response to the input first dialogue content. After obtaining the first dialogue content input by the user in the dialogue interface, the first dialogue content is analyzed by the AI ​​model to determine the user's need to generate multimedia data of the target multimedia type, and then the first guide component may be displayed in the dialogue interface to guide the user to upload the target material for generating the target multimedia data, which can achieve a better guidance effect.

[0119] The user can upload the material by triggering the first guide component. If the electronic device detects the first trigger operation of the user on the first guide component in the dialogue interface, it can respond to the first trigger operation and display the material selection page. The material selection page may include one or more pre-stored materials. Optionally, the material selection page may include one or more materials stored locally on the electronic device and / or one or more materials stored in the cloud. The one or more materials stored in the cloud may be the user's private materials (i.e., materials stored in the cloud by the user through the electronic device) or materials stored in a shared material library (which can be accessed by multiple users at the same time), which is not limited here.

[0120] For example, Figure 5A FIG. 1 is a schematic diagram of a dialogue interface in another embodiment. Figure 5AAs shown, the user enters the first dialogue content 502 in the dialogue interface 500. In response to the first dialogue content 502, a first guidance component 504 may be displayed in the dialogue interface 500. For example, the first guidance component 504 may display guidance content such as "Upload materials and help me directly generate videos", thereby guiding the user to upload target materials. The user may trigger (such as clicking) the first guidance component 504, and then the material selection page may be jumped and displayed, such as jumping to Figure 5B A material selection page 510 is shown.

[0121] For example, Figure 5B FIG. 1 is a schematic diagram of an interface of a material selection page in an embodiment. Figure 5B As shown, the material selection page 510 displayed by the electronic device may include multiple materials 512, which may be locally stored materials or cloud stored materials. If the user clicks "Recent Projects", the locally stored materials may be displayed in the material selection page 510, and if the user clicks "Material Library", the cloud stored materials may be displayed in the material selection page 510. Optionally, the materials may be further classified according to data types, for example, they may be classified into video materials, photo materials, etc. The user may switch between different types of materials for selection in the material selection page 510 according to needs.

[0122] Step 404: In response to a material selection operation on the material selection page, determining at least one selected target material.

[0123] The user may select one or more materials as target materials on the material selection page, and the electronic device may determine at least one target material selected by the user in response to the material selection operation performed by the user on the material selection page.

[0124] For example, Figure 5BAs shown, the user can select the desired target material on the material selection page 510 according to the needs. The material selection page 510 can also mark the selection order corresponding to each target material, such as displaying a number in the upper right corner of the material 512 to indicate the corresponding selection order, so as to facilitate the user to know the selection order of each target material, the number of selected target materials, and which materials are selected and which materials are not selected. Optionally, the material selection page 510 can also include a display sub-area 514, which can be used to display the target material selected by the user. The target materials can be displayed in sequence according to the selection order. The user can also directly cancel the selection of any target material in the display sub-area 514. For example, the user can cancel the selection of the target material by clicking the close button in the upper right corner of the target material, so that the user can adjust the selected target material more conveniently. The material selection page 510 may also include a confirmation control 516. When the user is sure that the selection is complete, the confirmation control 516 can be triggered. In response to the triggering operation of the confirmation control 516, the electronic device can determine the target materials selected by the user, close the material selection page 510, and redisplay the dialogue interface.

[0125] Step 406: Send the selected at least one target material to the dialogue interface.

[0126] After determining at least one target material selected by the user, the selected at least one target material may be sent to the dialogue interface, that is, the target material selected by the user is uploaded. The AI ​​model may process the target material sent to the dialogue interface to generate target multimedia data matching the target multimedia type.

[0127] In some embodiments, the dialogue interface may further include an input box, which may be used to input dialogue content into the dialogue interface. After acquiring at least one target material selected by the user, before sending the at least one target material selected by the user to the dialogue interface, the selected at least one target material may be displayed in the input box, and any target material in the input box may be adjusted in response to an adjustment operation on the target material. Each target material contained in the input box may be sent to the dialogue interface in response to a triggered content sending operation.

[0128] Optionally, when the material selection page is closed and the dialog interface is redisplayed, each target material selected by the user may be displayed in the input box of the dialog interface, and the user may perform an adjustment operation on any target material in the input box, and the adjustment operation may include but is not limited to a position adjustment operation and / or a deletion operation, etc. If an adjustment operation performed by the user on any target material is detected, the target material corresponding to the adjustment operation may be adjusted in response to the adjustment operation.

[0129] As an implementation, the adjustment operation may include a position adjustment operation, and at least one target material selected by the user may be sequentially arranged and displayed in the input box according to the selection order. In response to the position adjustment operation on the first target material in the input box, the first target material may be moved from the first arrangement position to the second arrangement position, and the first target material may be any target material displayed in the input box.

[0130] For example, Figure 5C FIG. 1 is a schematic diagram of a dialogue interface in another example. Figure 5C As shown, the dialogue interface 500 may include an input box 520, and each target material 522 selected by the user may be displayed in the input box 520. Each target material 522 may be sequentially displayed in the input box 520 in the order of selection from first to last. The user may adjust the position of any target material 522. For example, the position of the target material 522 in the input box 520 may be changed by dragging any target material 522. For example, if the third target material 522 is moved to the middle and becomes the second position in the arrangement, the original second target material 522 will automatically move to the third position in the arrangement. The user may freely and flexibly adjust the arrangement position of each target material, thereby flexibly adjusting the position of the target material in the generated target multimedia data (such as the playback order of picture materials or video materials in the generated video data, etc.).

[0131] As an implementation, the adjustment operation may include a deletion operation. In response to the deletion operation on the second target material in the input box, the second target material may be deleted from the input box, where the second target material is any target material displayed in the input box.

[0132] For example, Figure 5C As shown, the user can delete any target material in the input box 520 as needed. For example, the user can click the close button in the upper right corner of the target material 522 to delete the target material 522 from the input box 520, and the deleted target material 522 will no longer be sent to the dialogue interface 500.

[0133] Alternatively, if Figure 5C As shown, the input box 520 may also include a send control 524, and the user may perform a content sending operation by triggering (such as clicking, etc.) the send control 524. The electronic device detects that the send control 524 is triggered and determines that a content sending operation is received. Then, in response to the content sending operation, each target material 522 contained in the input box 520 may be sent to the dialogue interface 500. Further, the current target material 522 in the input box 520 may be sent to the dialogue interface 500 as the dialogue content. If the user performs the above-mentioned adjustment operation, the current target material 522 in the input box 520 may be the adjusted target material 522.

[0134] In some embodiments, each target material displayed in the input box may have a corresponding type label, which can be used to identify the data type corresponding to the target material. The representation of the type label may include but is not limited to one or more of characters, icons, colors, etc. For example, different data types may correspond to different icons, or different data types may correspond to different colors, etc., which can help users quickly distinguish the data types corresponding to each target material and improve interactivity.

[0135] In an embodiment of the present application, the input box of the dialogue interface can display the target materials selected by the user. The user can flexibly adjust the target materials in the input box according to actual needs. The selected target materials can be directly adjusted in the dialogue interface without returning to the material selection interface. The adjustment method is simpler.

[0136] It should be noted that, in addition to triggering the first guide component to display the material selection interface, other methods may also be used to trigger the display of the material selection interface, for example, Figure 5C As shown, the input box 520 may include a material control 526, and the user may trigger the material control 526. In response to the triggering operation of the material control 526, the electronic device may display a material selection interface. The user may reselect a target material, or add a new target material based on the currently selected target material.

[0137] In some embodiments, the user may also input a second conversation content in the input box, and send the second conversation content together with the selected target material to the conversation interface. The electronic device may receive the second conversation content input in the input box, and in response to the triggered content sending operation, send each target material contained in the input box and the second conversation content to the conversation interface. The second conversation content may include but is not limited to text content, voice content, etc.

[0138] The second dialogue content may be a further description or supplementary description of the target multimedia data to be generated. After sending the target materials contained in the input box and the second dialogue content to the dialogue interface, the target materials sent to the dialogue interface may be processed by the artificial intelligence model according to the first dialogue content and the second dialogue content. The artificial intelligence model may perform semantic analysis on the first dialogue content and the second dialogue content, integrate the contextual information of the first dialogue content and the second dialogue content, accurately understand the user's intention, and process the target materials selected by the user to upload to generate the target multimedia data.

[0139] For example, Figure 5D FIG. 1 is a schematic diagram of a dialogue interface in another example. Figure 5DAs shown, the input box 520 may include a content input component 532. By clicking the content input component 532, the user can trigger the electronic device to pull up and display a virtual keyboard 530. The user can input the second dialogue content in the content input component 532 by touching the virtual keyboard 530, such as "help me make a happy video", and then click the send control 524 to send the target materials 522 contained in the input box 520 and the second dialogue content input in the content input component 532 to the dialogue interface 500. The input needs of users in different scenarios can be met, so that the generated target multimedia data is more in line with user expectations.

[0140] For example, Figure 5E FIG. 1 is a schematic diagram of a dialogue interface in another example. Figure 5E As shown, after each target material contained in the input box and the input second conversation content are sent to the conversation interface 500 , each target material 522 selected to be uploaded by the user can be displayed in the conversation interface 500 , and the second conversation content 542 can be displayed.

[0141] In some embodiments, after obtaining at least one target material uploaded by the user, for example, after sending at least one target material selected by the user to the dialogue interface, a material cover corresponding to the at least one target material uploaded by the user can be displayed on the dialogue interface, and the material quantity corresponding to the at least one target material uploaded by the user can be marked on the material cover.

[0142] The material cover may be one of the at least one target material uploaded by the user, and optionally, may be a target material randomly selected from the at least one selected target material as the material cover, or may be the first or last target material of the at least one selected target material as the material cover, but is not limited thereto. The material quantity corresponding to the at least one selected target material may also be marked on the material cover.

[0143] For example, Fig. 5F FIG. 1 is a schematic diagram of a dialogue interface in another example. Fig. 5F As shown, after each target material included in the input box is sent to the dialogue interface 500, a material cover 544 may be displayed in the dialogue interface 500, and the material number of the target materials selected by the user may be marked on the material cover 544. For example, if the user selects 3 target materials, the number 3 may be marked in the upper right corner of the material cover 544. This can avoid the situation where too many selected target materials occupy too much space in the dialogue interface, making the entire dialogue interface more concise, and by marking the number of materials, the user can accurately know the situation of the specific selected target materials, thereby improving the user experience.

[0144] For example, Figure 5GFIG. 1 is a schematic diagram of a dialogue interface in another example. Figure 5G As shown, after the target material selected by the user and the input second dialogue content are sent to the dialogue interface 500, the AI ​​model can process the target material selected by the user according to the first dialogue content and the second dialogue content to generate target multimedia data, such as video data. In the process of generating target multimedia data, the production information 550 can be displayed in the dialogue interface 500, and the cancel production control 552 can be displayed. The user can interrupt the AI ​​model from generating target multimedia data at any time by triggering the cancel production control 552. If it is detected that the cancel production control 552 is triggered, the AI ​​model can cancel the generation of target multimedia data. After the AI ​​model generates the target multimedia data, the generated one or more target multimedia data can be sent to the dialogue interface 500, and the generated one or more target multimedia data can be displayed in the dialogue interface 500.

[0145] In an embodiment of the present application, the user can select the target material on the material selection page according to actual needs. The AI ​​model can intelligently generate target multimedia data that matches the target multimedia type based on the target material uploaded by the user, so that the generated target multimedia data is more in line with user expectations, improves intelligence, and improves the user experience.

[0146] In some embodiments, the target material used by the AI ​​model to generate the target multimedia data may be the target material generated by the AI ​​model based on the first conversation content. Figure 6 As shown, after obtaining the first conversation content input by the user in the conversation interface, the above method may further include the following steps:

[0147] Step 602: Acquire the third dialogue content input by the user in the dialogue interface.

[0148] After the user enters the first dialogue content in the dialogue interface, if there is no target material that can be uploaded, the user can enter the third dialogue content instructing the AI ​​model to generate material in the dialogue interface. Fig. 7A FIG. 1 is a schematic diagram of a dialogue interface in another example. Fig. 7A As shown, the user can enter the third dialogue content 710 in the dialogue interface 500, such as entering "I don't have any materials, can you help me find some materials" to instruct the AI ​​model to generate materials.

[0149] Step 604: If the third conversation content indicates to generate material, the target material is generated according to the first conversation content through the artificial intelligence model.

[0150] After obtaining the third dialogue content input by the user in the dialogue interface, the third dialogue content can be semantically analyzed through the AI ​​model. If it is determined that the third dialogue content indicates the generation of material, the AI ​​model can generate target material based on the first dialogue content. The target material can be matched with the feature information contained in the first dialogue content, so that the target material can be used to generate target multimedia data that meets the user's needs.

[0151] In some embodiments, if the third dialogue content indicates to generate a material, a first inquiry message may be output in the dialogue interface, and the first inquiry message may be used to inquire about the material features corresponding to the required material. The fourth dialogue content input by the user in the dialogue interface is obtained, and the target material features contained in the fourth dialogue content may be identified through the artificial intelligence model, and the target material matching the target material features may be generated according to the first dialogue content.

[0152] In most cases, the feature information in the first dialogue content usually cannot accurately reflect the features of the target material. Therefore, in order to more accurately understand the user's intentions and needs, the first inquiry information can be output in the dialogue interface to ask the user about the material features corresponding to the required material. The user can enter the fourth dialogue content in the dialogue interface, and the fourth dialogue content can be used to describe the features of the target material to be generated. The fourth dialogue content entered by the user in the dialogue interface can be obtained, and the AI ​​model can perform semantic analysis on the fourth dialogue content, identify the target material features contained in the fourth dialogue content, and then generate the target material based on the feature information contained in the first dialogue content and the target material features.

[0153] For example, Figure 7B FIG. 1 is a schematic diagram of a dialogue interface in another example. Figure 7B As shown, after obtaining the third dialogue content input by the user, the first inquiry information 722 may be displayed in the dialogue interface 500, for example, the first inquiry information 722 "OK, what type of material do you need?" is displayed, thereby asking the user about the material features corresponding to the required material. The user may enter the fourth dialogue content 724 in the dialogue interface 500, for example, the dialogue content of "I want video material", and the AI ​​model may obtain the target material feature as video by identifying the fourth dialogue content 724. The AI ​​model may generate the target material according to the first dialogue content and the target material features, for example, it may generate video material related to travel.

[0154] Optionally, after the target material is generated by the AI ​​model, one or more generated target materials can be displayed in the dialogue interface, and the user can choose whether to use the target material generated by the AI ​​model according to actual needs. Figure 7BAs shown, the generated one or more video templates 726 can be displayed in the dialogue interface 500, and the user can choose whether to use any of the video templates 726 to generate video data according to the needs. Further, the dialogue interface 500 may also include a material replacement control 728. If the user is not satisfied with the currently generated target material, the AI ​​model can be triggered (such as clicking) to regenerate the target material by the material replacement control 728. In response to the user's triggering operation on the material replacement control 728, the target material can be regenerated by the AI ​​model, and the newly generated target material can be displayed in the dialogue interface 500. For example, the AI ​​model can regenerate one or more video templates 726, and display the regenerated one or more video templates 726 in the dialogue interface 500.

[0155] In the embodiment of the present application, by displaying the first inquiry information in the dialogue interface, the material characteristics of the target material that the user needs to generate can be further obtained, so that the generated target material better meets the user's needs and improves the degree of intelligence.

[0156] It should be noted that the AI ​​model can also directly generate the target material based on the first conversation content without outputting the first query information. In particular, when the first conversation content includes relatively rich feature information and the first conversation content describes the target multimedia data to be generated in relatively detail, the AI ​​model can directly generate the target material based on the feature information of the first conversation content and process the target material to generate the target multimedia data.

[0157] It should be noted that the target material generated by the AI ​​model mentioned in the above embodiments is not necessarily the target material created by the AI ​​model, but may also be the target material found by the AI ​​model in a database or on the Internet that meets user needs.

[0158] In an embodiment of the present application, the target material can be generated according to the first conversation content through the AI ​​model, thereby improving the flexibility of the method of generating target multimedia data and meeting the different needs of users.

[0159] In some embodiments, the target material used by the AI ​​model to generate the target multimedia data may be historical multimedia data generated by the AI ​​model. The first dialogue content input by the user may also include indication information for indicating the historical multimedia data, and the AI ​​model may determine the historical multimedia data output in the dialogue interface based on the indication information, and process the historical multimedia data to generate target multimedia data matching the target multimedia type.

[0160] The target material used by the AI ​​model to generate the target multimedia data may be the historical multimedia data generated by the AI ​​model after entering the dialogue interface this time, for example, the historical multimedia data generated by the AI ​​model most recently. The user may input indication information for indicating the historical multimedia data to be used, and the indication information may include but is not limited to the multimedia type corresponding to the historical multimedia data, the order in which the historical multimedia data is generated, the expression content of the historical multimedia data, etc.

[0161] The multimedia type corresponding to the historical multimedia data may be the same as the target multimedia type, or the multimedia type corresponding to the historical multimedia data may be different from the target multimedia type. For example, the multimedia type corresponding to the historical multimedia data is a text type, and the target multimedia type is a video type; or the multimedia type corresponding to the historical multimedia data is an image type, and the target multimedia type is a text type; or the multimedia type corresponding to the historical multimedia data and the target multimedia type are both video types, etc., but not limited thereto.

[0162] For example, Fig. 8A FIG. 1 is a schematic diagram of a dialogue interface in another example. Fig. 8A As shown, after entering the dialogue interface 500 this time, before the current round of dialogue, the AI ​​model generates historical multimedia data 812 according to user needs, such as generating a text introducing Xi'an. The user enters the first dialogue content 810 in the dialogue interface 500. The first dialogue content 810 indicates that the target multimedia data is generated according to the historical multimedia data 812, and indicates the target multimedia type corresponding to the target multimedia data. For example, if the first dialogue content 810 is "text into a film", it indicates that the text introducing Xi'an generated by the previous AI model is used to generate the target multimedia data of the video type. The AI ​​model can determine that the target material is the historical multimedia data 812 by performing semantic analysis on the first dialogue content 810, and processes the historical multimedia data 812 to generate corresponding video data.

[0163] In some embodiments, while the AI ​​model uses historical multimedia data as target material, it can also combine the historical multimedia data with the target material generated by the AI ​​model based on the first conversation content and / or the target material uploaded by the user to jointly generate target multimedia data. Figure 8B FIG. 1 is a schematic diagram of a dialogue interface in another example. Figure 8BAs shown, after obtaining the first conversation content including the indication information for indicating the historical multimedia data, the third conversation content input by the user is obtained, such as "I don't have any materials, can you help me find some materials", and the third conversation content indicates the generation of materials. Then, the AI ​​model can be used to generate target materials based on the historical multimedia data and the first conversation content, and then the historical multimedia data and the generated target materials are processed to generate target multimedia data.

[0164] As another optional implementation, the user can also select a material in the material selection page and send the selected one or more target materials to the dialogue interface to upload the material. The AI ​​model can process the historical multimedia data and the target materials uploaded by the user according to the first dialogue content to generate target multimedia data.

[0165] In an embodiment of the present application, the historical multimedia data generated by the AI ​​model can be used as the target material. By processing the historical multimedia data, the target multimedia data required by the user is generated to meet the different needs of the users. This can be applied to different application scenarios and improve intelligence.

[0166] In some embodiments, in order to generate target multimedia data that better meets the user's expectations, the AI ​​model may first input one or more recommended templates for the user to select. Fig. 9 As shown, the step of processing the target material according to the first dialogue content through the artificial intelligence model to generate target multimedia data matching the target multimedia type may include the following steps:

[0167] Step 902: Generate one or more recommendation templates based on the first conversation content through an artificial intelligence model, and display the one or more recommendation templates in the conversation interface.

[0168] Recommendation templates can be used to define the style and / or creation techniques of multimedia data, etc. Different recommendation templates may correspond to different styles and / or creation techniques. After obtaining the first conversation content input by the user, the first conversation content can be semantically analyzed by the AI ​​model to generate one or more recommendation templates. The one or more recommendation templates can meet the characteristic information input by the user in the first conversation content, and can be used to generate target multimedia data of the target multimedia type. If the target multimedia type of the target multimedia data to be generated is different, the type of recommendation template generated by the AI ​​model may be different. For example, if the target multimedia type of the target multimedia data to be generated is a video type, the AI ​​model can generate one or more recommended video templates; if the target multimedia type of the target multimedia data to be generated is a text type, the AI ​​model can generate one or more recommended text templates; if the target multimedia type of the target multimedia data to be generated is an image type, the AI ​​model can generate one or more recommended picture templates, etc., but is not limited to this.

[0169] Furthermore, if the user's needs for target multimedia data are different and the feature information included in the first conversation content is different, the recommended templates generated by the AI ​​model may also be different. For example, if the first conversation content input by the user is "Please help me generate a comic picture", the AI ​​model can generate one or more recommended picture templates, which can be drawn in a comic way, but can correspond to different comic styles, such as aesthetic comic style, Q version cute comic style, action comic style, etc., but not limited to this. By accurately identifying the user's intention through the AI ​​model, the recommended template can be output to the user more accurately, so that the target multimedia data generated subsequently is more in line with the user's expectations.

[0170] After the AI ​​model generates one or more recommendation templates, it can display the one or more recommendation templates in the dialogue interface, and the user can select any recommendation template as the target recommendation template for use according to actual needs. Fig. 10A FIG. 1 is a schematic diagram of a dialogue interface in another embodiment. Fig. 10A As shown, after obtaining the first dialogue content input by the user in the dialogue interface 500, for example, receiving the first dialogue content input by the user "I want you to help me draw a comic avatar", the AI ​​model can generate one or more recommended templates according to the first dialogue content, and display one or more recommended templates 1010 in the dialogue interface 500. Optionally, a template replacement control 1012 can also be displayed. If the user is not satisfied with the recommended template generated by the current AI model, the template replacement control 1012 can be triggered, and the AI ​​model can regenerate one or more recommended templates and display the regenerated recommended templates in the dialogue interface 500.

[0171] In some embodiments, after obtaining the first dialogue content input by the user, the electronic device may display a second guidance component in the dialogue interface in response to the input first dialogue content, and the second guidance component may be used to guide the user to trigger the template generation process. The user may trigger the AI ​​model to generate a recommended template by triggering the second guidance component. The electronic device may input a template generation instruction in the dialogue interface in response to a third trigger operation on the second guidance component, and may generate one or more recommended templates based on the first dialogue content through the artificial intelligence model in response to the template generation instruction.

[0172] The second guide component may include but is not limited to a guide box, a guide button, a guide information bar, etc. Furthermore, the second guide component may display a template generation instruction for triggering the AI ​​model to generate a recommended template. By triggering the second guide component, the user may send a template generation instruction to the dialogue interface. After obtaining the input template generation instruction, the AI ​​model may respond to the template generation instruction and generate one or more recommended templates according to the first dialogue content.

[0173] For example, Fig. 10B FIG. 1 is a schematic diagram of a dialogue interface in another embodiment. Fig. 10B As shown, after obtaining the first dialogue content input by the user in the dialogue interface 500, for example, receiving the first dialogue content input by the user "I want to make a video of a weekend trip", etc., the second guide component 1022 can be displayed in the dialogue interface 500, and the second guide component 1022 can display template generation instructions, such as "recommended templates, I choose and make them myself", etc. The user can trigger the second guide component 1022, and the electronic device can enter the template generation instruction 1024 in the dialogue interface 500. The AI ​​model recognizes the input template generation instruction 1024, and can respond to the template generation instruction 1024, generate one or more recommended templates according to the first dialogue content, and display one or more recommended templates 1010 in the dialogue interface 500. By displaying the second guide component 1022 in the dialogue interface 500, the user can be accurately guided to enter the template generation instruction in the dialogue interface 500, trigger the template generation process, improve the guidance effect, and improve the interactivity.

[0174] It should be noted that the dialogue interface may not display the second guidance component, and the user can enter the template generation instruction in the dialogue interface by himself. After the AI ​​model recognizes the template generation instruction entered by the user, the template generation process can be triggered.

[0175] In some embodiments, the recommended templates displayed in the dialogue interface may be thumbnail contents of the recommended templates, so the user may select any recommendation displayed in the dialogue interface for preview to facilitate obtaining specific template contents. In response to a preview operation of a first recommended template in the dialogue interface, the electronic device may display a template preview interface, which may be used to display the preview contents of the first recommended template, and the first recommended template may be any recommended template. Exemplarily, Fig. 10C FIG. 1 is a schematic diagram of a template preview interface in an embodiment. Fig. 10C As shown, the template preview interface 1030 can display the preview content of the recommended template currently selected by the user in the template preview area 1032. The preview content can be at least part of the template content of the recommended template. For example, if the template is a video template, a partial preview clip of the video template can be displayed in the template preview interface 1030.

[0176] The user can switch the recommended templates displayed in the template preview interface in the template preview interface. In response to the template switching operation triggered in the template preview interface, the electronic device can switch to display the preview content of the second recommended template in the template preview interface. For example, Fig. 10D FIG. 1 is a schematic diagram of a template preview interface in another embodiment. Fig. 10DAs shown, the template switching operation may include a sliding operation. The user may slide left or right on the template preview interface 1030 to switch the recommended templates displaying the preview content in the template preview interface 1030. It should be noted that the template switching operation may also be other operation modes and is not limited to sliding operations. Optionally, the template preview interface 1030 may also display template information corresponding to the current recommended template. For example, the template information 1036 corresponding to the current recommended template displayed on the template preview interface 1030 may include information such as a progress bar, total duration, and number of uses.

[0177] The template preview interface may further include a selection control, and the user may select a recommended template to be used by triggering the selection control. In response to a second trigger operation on the selection control in the template preview interface, the electronic device may use the current recommended template in the template preview interface as a target recommended template and determine a template selection operation for the target recommended template. For example, Fig. 10C As shown, the template preview interface 1030 may include a selection control 1034 , and the user may use the recommended template currently displayed in the template preview interface 1030 by clicking the selection control 1034 .

[0178] In an embodiment of the present application, a user can preview each recommended template through a template preview interface, and can flexibly switch the previewed recommended templates in the template preview interface as needed, thereby facilitating the user's understanding of each recommended template and improving interactivity.

[0179] Step 904, in response to the template selection operation of the target recommendation template, the target material is processed according to the target recommendation template through the artificial intelligence model to generate target multimedia data matching the target multimedia type; the target recommendation template is any recommendation template.

[0180] When the user chooses to use the target recommendation template, the AI ​​model can process the target material according to the target recommendation template to generate target multimedia data that matches the target multimedia type. Furthermore, the AI ​​model can combine the feature information contained in the first conversation content and process the target material according to the target recommendation template, so that the generated target multimedia data is more in line with the user's expectations and the accuracy of the generated target multimedia data is improved.

[0181] The target material can be material uploaded by the user and / or material generated by the AI ​​model.

[0182] In some embodiments, after the user determines to use the target recommendation template to generate the target multimedia data, the user may upload the target material for generating the target multimedia data. In response to the template selection operation on the target recommendation template, a material selection page may be displayed, and in response to the material selection operation on the material selection page, at least one selected target material may be determined. The at least one selected target material may be sent to the dialogue interface, and then the at least one selected target material may be processed by the artificial intelligence model according to the target recommendation template to generate target multimedia data matching the target multimedia type.

[0183] For example, Fig.10E FIG. 1 is a schematic diagram of an interface of a material selection page in another embodiment. Fig.10E As shown, when the user triggers Fig. 10C or Fig. 10D After selecting the control 1034 in the content, the electronic device may jump to and display the material selection page 510, which may include one or more materials to be selected. Furthermore, the material selection page 510 may display the number of materials required for the target recommendation template, such as displaying prompt information such as "Select 2 to 6 materials" on the material selection page 510, so that the user can accurately know the number of target materials that need to be uploaded. Optionally, the target material selected by the user may be a pre-stored material or a temporarily generated material (such as a material temporarily captured by a camera).

[0184] It should be noted that the user performs a material selection operation on the material selection page, and the electronic device responds to the material selection operation on the material selection page, determines at least one selected target material, and sends the selected at least one target material to the dialogue interface. For implementation details, please refer to the above embodiments and the attached Figure 5B ~Attached Fig. 5F The relevant description will not be repeated here.

[0185] After sending each target material selected by the user to the dialogue interface, the AI ​​model can perform semantic recognition on each target material, and process each selected target material according to the target recommendation template based on the first dialogue content to generate target multimedia data. The recommendation template generated by the AI ​​model can be organically combined with the target material uploaded by the user to jointly generate the target multimedia data, rather than simply fitting the target material uploaded by the user into the template, so that the generated target multimedia data can be more in line with user expectations.

[0186] As an implementation mode, after obtaining at least one target material uploaded by the user, it can be determined whether the material quantity corresponding to the at least one target material selected by the user matches the material quantity required by the target recommendation template. If the material quantity corresponding to the at least one target material selected by the user does not match the material quantity required by the target recommendation template, the artificial intelligence model can be used to generate supplementary target materials according to the first conversation content, and the artificial intelligence model can be used to process the at least one target material selected by the user and the supplementary target materials according to the target recommendation template to generate target multimedia data that matches the target multimedia type.

[0187] Each recommendation template generated by the AI ​​model may have a corresponding required number of materials, and the number of materials required for the recommendation template may be a specific number value or a range of numbers. When it is determined that the user needs to use the target recommendation template and the user selects one or more target materials to upload, it can be determined whether the number of materials of the target materials uploaded by the user matches the number of materials required for the target recommendation template. The match may refer to being the same, or being within the number range of materials required for the target recommendation template, etc. If the number of materials of the target materials uploaded by the user does not match the number of materials required for the target recommendation template, the effect of the target multimedia data generated only based on the target materials uploaded by the user may be poor and fail to meet the user's expectations. Therefore, the AI ​​model may generate supplementary target materials based on the first conversation content. The sum of the number of materials of at least one target material selected by the user and the supplementary target material generated by the AI ​​model may match the number of materials required for the target recommendation template, for example, the sum of the number of materials may be equal to the number of materials required for the target recommendation template, or the sum of the number of materials may be within the number range of materials required for the target recommendation template.

[0188] The AI ​​model can process the target materials selected by the user and the supplementary target materials generated by the AI ​​model according to the target recommendation template to generate target multimedia data. This can ensure that the number of target materials used meets the number of materials required by the target recommendation template, thereby ensuring the quality of the generated target multimedia data. By combining the recommendation template generated by the AI ​​model with the target materials uploaded by the user and the materials generated by the AI ​​model, the way of generating target multimedia data is more flexible, with improved intelligence, and meets the different needs of users.

[0189] like Fig.11 As shown, in another embodiment, a method for generating multimedia data is provided, which can be applied to the above electronic device, and the method may include the following steps:

[0190] Step 1102: Acquire first dialogue content input by the user in the dialogue interface, where the first dialogue content includes a target multimedia type.

[0191] Step 1104, processing the target material according to the first conversation content through the artificial intelligence model to generate target multimedia data matching the target multimedia type.

[0192] Step 1106: Display the target multimedia data in the dialogue interface.

[0193] For the description of steps 1102 to 1106 , reference may be made to the relevant description in the above embodiments, which will not be repeated here.

[0194] Step 1108, obtaining the fifth dialogue content input by the user in the dialogue interface.

[0195] After the target multimedia data is displayed in the dialogue interface, the user can let the AI ​​model edit and optimize the target multimedia data. The user can enter the fifth dialogue content in the dialogue interface, and the fifth dialogue content may include editing and optimization instructions, which can be used to indicate the way of editing and processing the target multimedia data to optimize the target multimedia data. The corresponding editing and processing methods of target multimedia data of different multimedia types may be different. For example, for target multimedia data of image type, the corresponding editing and processing may include but is not limited to adjusting the brightness of the image, beautifying the characters in the image, removing part of the image content in the image, etc.; for target multimedia data of video type, the corresponding editing and processing may include but is not limited to adding background music, adding stickers, adjusting the brightness of the screen, etc.; for target multimedia data of text type, the corresponding editing and processing may include but is not limited to expanding a paragraph of text, polishing a paragraph of text, simplifying a paragraph of text, etc.; for target multimedia data of audio type, the corresponding editing and processing may include but is not limited to modifying the timbre, adjusting the pitch, reducing noise, etc., but is not limited to this.

[0196] In some embodiments, after the target multimedia data is generated by the AI ​​model, the target multimedia data may be displayed in the dialogue interface, and a first editing control corresponding to the target multimedia data may be displayed in the dialogue interface. In response to a fourth trigger operation on the first editing control, at least one recommended editing optimization instruction may be displayed in the input box. In response to a selection operation on any recommended editing optimization instruction, any selected recommended editing optimization instruction may be sent to the dialogue interface as the fifth dialogue content.

[0197] While displaying the target multimedia data in the dialogue interface, one or more associated controls corresponding to the target multimedia data may be displayed. The one or more associated controls may be used to provide a variety of functions for further processing the target multimedia data. The one or more associated controls may include but are not limited to a first editing control, a publishing control, a forwarding control, a saving control, etc. The first editing control may be used to provide a function of editing and optimizing the target multimedia data, the publishing control may be used to provide a function of publishing the target multimedia data to a specified application, the forwarding control may be used to provide a function of forwarding the target multimedia data to other devices, the saving control may be used to provide a function of saving the target multimedia data to an electronic device, etc.

[0198] In the case where the user needs to edit and optimize the target multimedia data, the user can trigger the first editing control, and the electronic device can respond to the user's fourth trigger operation on the first editing control, and display at least one recommended editing optimization instruction in the input box. Further, the recommended editing optimization instruction may be related to the editing processing supported by the target multimedia data. The user can select any editing optimization instruction as needed, thereby triggering the AI ​​model to edit the target multimedia data. In response to the user's selection operation on any recommended editing optimization instruction, any selected recommended editing optimization instruction can be sent to the dialogue interface as the fifth dialogue content, and the AI ​​model can edit the target multimedia data according to the input editing optimization instruction.

[0199] For example, Fig. 12A FIG. 1 is a schematic diagram of a dialogue interface in another embodiment. Fig. 12A As shown, one or more target multimedia data generated by the AI ​​model and one or more associated controls corresponding to the target multimedia data, such as the first editing control 1210, the forwarding control, the saving control, etc., can be displayed in the dialogue interface 500. When multiple target multimedia data are displayed, the user can select the target multimedia data to be optimized and click the first editing control 1210 to edit the selected target multimedia data through the AI ​​model. Exemplarily, Fig. 12B FIG. 1 is a schematic diagram of a dialogue interface in another embodiment. Fig. 12B As shown, after the user clicks the first editing control 1210, one or more recommended editing optimization instructions 1212 may be displayed in the input box 520, such as "brighten the entire screen", "replace the entire background music", "add cute stickers", etc. The user may select any recommended editing optimization instruction 1212 according to actual needs and input it into the dialogue interface 500, or may input the fifth dialogue content containing the editing optimization instruction in the input box. By displaying the recommended editing optimization instructions, the user may be more effectively guided to input the editing optimization instructions, which improves interactivity and reduces the difficulty for the user to use the AI ​​function.

[0200] In some embodiments, after the target multimedia data generated by the AI ​​model is displayed in the dialogue interface, the user can perform a preview operation on the target multimedia data, and the electronic device can enter the preview interface of the multimedia data in response to the preview operation of the target multimedia data, and display the preview content of the target multimedia data in the preview interface of the multimedia data. By viewing the preview content of the target multimedia data, the user can further accurately determine whether the target multimedia data needs to be edited and optimized. The preview interface of the multimedia data may include an input box, and one or more recommended editing and optimization instructions may be displayed in the input box of the preview interface of the multimedia data. The user can select any recommended editing and optimization instruction according to actual needs and send it to the dialogue interface.

[0201] In some embodiments, multiple optimization categories may be displayed in the input box, and at least one edit optimization instruction corresponding to the current optimization category may be displayed.

[0202] The method of editing the target multimedia data may correspond to multiple optimization categories, and different optimization categories may include different editing methods. Multiple optimization categories may be displayed in the input box, and the user may select any optimization category according to actual needs, and at least one recommended editing optimization instruction corresponding to the current optimization category may be displayed in the input box according to the current optimization category selected by the user.

[0203] For example, Fig.13 FIG. 1 is a schematic diagram of a preview interface of multimedia data in an embodiment. Fig.13As shown in (b), when detecting that the user selects any target multimedia data for preview operation, the electronic device can display a preview interface 1300 of the multimedia data, and the preview interface 1300 of the multimedia data may include a preview area 1310, and the preview area 1310 can be used to display the preview content of the target multimedia data. In the case where the user needs to edit and optimize the target multimedia data, the user can click on the input box 520 of the preview interface 1300 of the multimedia data, and as shown in (b), the electronic device can pull up the input box 520 and display one or more recommended editing optimization instructions in the input box 520. Further, the user can also click on the pull-up control 1312 in the input box 520, and the electronic device can display multiple optimization categories 1314 in the input box 520, such as the optimization categories such as music category, subtitle category, cover category, material category, etc. shown in (c). The user can select any optimization category 1314 according to actual needs, and the electronic device can display one or more recommended editing optimization instructions corresponding to the optimization category 1314 currently selected by the user in the input box 520. For example, if the currently selected optimization category 1314 is a material category, one or more recommended editing optimization instructions corresponding to the material category can be displayed, such as "brighter overall picture", "3D love stickers", "add a snow effect", "change a transition effect", etc., but not limited to this. Optionally, the user can select any recommended editing optimization instruction, and the recommended editing optimization instruction selected by the user can be input into the content input component. The user can click the send control, and the electronic device can send the recommended editing optimization instruction in the content input component as the dialogue content to the dialogue interface. By classifying the editing processing methods and displaying the recommended editing optimization instructions corresponding to each optimization category, the accuracy of the recommended editing optimization instructions can be improved, the different needs of users can be met, and the user experience can be improved.

[0204] Step 1110, identifying the editing optimization instructions included in the fifth dialogue content through the artificial intelligence model, editing the target multimedia data according to the editing optimization instructions, and displaying the edited target multimedia data in the dialogue interface.

[0205] After obtaining the fifth dialogue content input by the user, the AI ​​model can perform semantic analysis on the fifth dialogue content to extract the editing optimization instructions included in the fifth dialogue content, and edit the target multimedia data according to the editing optimization instructions, and can display the edited target multimedia data in the dialogue interface for the user to view.

[0206] For example, Fig.14 FIG. 1 is a schematic diagram of interface changes for editing and optimizing target multimedia data in one embodiment. Fig.14As shown in (a), multiple target multimedia data generated by the AI ​​model and one or more associated controls can be displayed on the dialogue interface 500. The user can select any target multimedia data and trigger the first editing control to send the fifth dialogue content 1410 with the editing optimization instruction to the dialogue interface 500. Optionally, the target multimedia data selected by the user can also be sent to the dialogue interface 500. As shown in (b) and (c), the AI ​​model can recognize the editing optimization instruction contained in the fifth dialogue content 1410, and edit the target multimedia data selected by the user according to the editing optimization instruction, such as improving the overall picture brightness of the video data selected by the user. After the AI ​​model edits the target multimedia data selected by the user, the edited target multimedia data 1420 can be displayed in the dialogue interface 500. Furthermore, one or more associated controls corresponding to the edited target multimedia data 1420 can also be displayed. Through the associated controls, the user can choose to continue editing and optimizing the edited target multimedia data, or forward the edited target multimedia data to a designated application (such as a social application, video application, question-and-answer application, etc.), or save the edited target multimedia data, etc., which are not limited here.

[0207] For example, Fig.15 FIG. 1 is a schematic diagram of interface changes for editing and optimizing target multimedia data in another embodiment. Fig.15As shown in (a), the AI ​​model can generate target multimedia data of text type, i.e., text 1510, according to the first dialogue content input by the user in the dialogue interface 500. The text 1510 can be displayed in the dialogue interface 500, and the first editing control 1512 can be displayed. Other related controls can also be displayed, such as a regeneration control, a text-to-film control, and a control for entering the teleprompter. The user can click on the first editing control 1512, as shown in (b), to enter the editing page 1520 of the text 1510. In the editing page 1520, multiple main controls 1524 can be displayed, including tool controls, save controls, undo controls, and redo controls. The tool control can be used to provide editing work for editing the text 1510, the save control can be used to save the edited text to the electronic device, the undo control can be used to undo the editing process previously performed, and the redo control can directly restore the text 1510 to the state before the editing process. The user can click on the edit box 1526 in the editing page 1520, as shown in (c), pull up the keyboard, and enter the editing state of the text. The user can also click on any main control 1524 according to actual needs, as shown in (d). If the main control 1524 also includes a sub-control, the sub-control 1528 can be displayed. For example, by clicking on the tool control, the sub-control 1528 that can be displayed may include but is not limited to an expansion control, a polishing control, a simplification control, etc. The user can click on any sub-control 1528 to edit the text. Optionally, the sub-control 1528 can be understood as the optimization category in the above embodiment. After the user clicks on any sub-control 1528, the input box can display the recommended editing optimization instructions corresponding to the sub-control 126 clicked by the user. The user selects any editing optimization instruction and enters it into the editing page, and the AI ​​model can edit the text according to the editing optimization instruction entered by the user. In the process of editing the text, the user can trigger the completion control 1522 in the editing page 1520 at any time to indicate that the editing of the text is completed, and the electronic device can close the editing page 1520, return to the dialogue interface 500, and can also display the edited text in the dialogue interface 500.

[0208] It should be noted that the editing optimization instructions involved in the above embodiments may refer to dialogue content expressed in natural language with editing optimization content, which is used to instruct the AI ​​model to edit and process the target multimedia data, rather than computer operation instruction codes.

[0209] In an embodiment of the present application, after generating the target multimedia data through the AI ​​model, the user can further edit and optimize the target multimedia data according to actual needs. The AI ​​model not only provides the function of generating multimedia data of various multimedia types, but also supports the editing and optimization function of multimedia data. It is rich in functions, can be applied to different application scenarios, meet the different needs of users, and improve intelligence.

[0210] In some embodiments, the above-mentioned method of editing and processing the target multimedia data by inputting editing optimization instructions in the dialogue interface may be a relatively simple editing and processing function. In the embodiment of the present application, the AI ​​model can support the user's more complex editing needs for the target multimedia data and better assist the user in editing and processing the target multimedia data. Fig.16 The above method may further include the following steps:

[0211] Step 1602: Display an editing page corresponding to the target multimedia data.

[0212] The editing page corresponding to the target multimedia data may refer to a page that can provide multiple editing functions for the target multimedia data. The editing page supports complex editing processing of the target multimedia data. The editing page can be understood as a more advanced editing page, or it may be an editor page of the target multimedia type corresponding to the target multimedia data, such as a video editor page, an image editor page, a document editor page, etc., but is not limited to this.

[0213] In some embodiments, a second editing control may be displayed on a dialog interface or a preview interface of multimedia data, and the second editing control may be used to provide an entry to an editing page. A user may trigger the second editing control, and the electronic device may display an editing page corresponding to the target multimedia data in response to the user's triggering operation on the second editing control.

[0214] The editing page may include a preview area and an editing function area. The preview area may be used to display the target multimedia data, and may also be used to display the target multimedia data after editing. The editing function area may support editing of the target multimedia data, and the editing function area may include one or more function controls corresponding to the editing functions. It should be noted that if the target multimedia data corresponds to different target multimedia types, the displayed editing pages are different, and the editing functions supported in the editing pages may also be different. For example, if the target multimedia data is a video type, the editing page may be a video editing page, and the supported editing functions may include but are not limited to clipping, adjusting the ratio, adding special effects, adding audio, adding subtitles, displaying picture-in-picture, etc.; if the target multimedia data is a text type, the editing page may be a document editing page, and the supported editing functions may include but are not limited to adjusting the font, adjusting the font size, adjusting the paragraph, adjusting the layout, inserting a table, inserting a picture, etc.; if the target multimedia data is an image type, the editing page may be a picture type, and the supported editing functions may include but are not limited to adding filters, cutting out, night scene enhancement, making dynamic images, image repair, adding text, etc.

[0215] For example, Fig.17AFIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in an embodiment. Fig.17A As shown, the editing page 1700 may include a preview area 1710 and an editing function area 1720. The preview area 1710 may be used to display the target multimedia data 1712. The editing function area 1720 may include function controls 1722 corresponding to a plurality of editing functions, such as a clipping control, a picture-in-picture control, a special effect control, a subtitle control, an audio control, etc., but not limited thereto. Different function controls 1722 may be used to provide different editing functions for the target multimedia data 1712. The target multimedia data 1712 may be edited in the editing function area 1720, such as adding subtitles, adding audio, setting a cover, etc., but not limited thereto.

[0216] Step 1604, display the dialog component in the editing page.

[0217] In the embodiment of the present application, the AI ​​model can support the editing auxiliary function of multimedia data, and can display a dialogue component in the editing page. The user can communicate with the AI ​​model through the dialogue component to inform the AI ​​model of its own needs. The dialogue component may include but is not limited to a dialogue window, a dialog box, etc. The user can enter functional requirements related to the editing function in the dialogue component, and the AI ​​model can identify the user's needs by performing semantic analysis on the dialogue content entered by the user, and output the content required by the user.

[0218] In some embodiments, the editing page may include an artificial intelligence control, and the user may trigger the artificial intelligence control to open a dialogue component in the editing page to use the editing assistance function of the AI ​​model. The electronic device may display the dialogue component in the editing page in response to the seventh trigger operation on the artificial intelligence control.

[0219] For example, Fig. 17B FIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment. Fig.17A and Fig. 17BAs shown, the edit page 1700 may include an artificial intelligence control 1714. Optionally, when entering the edit page 1700, guidance information may also be displayed near the artificial intelligence control 1714 to guide the user to trigger the artificial intelligence control 1714. For example, guidance information such as "Come and try the AI ​​assistant" may be displayed near the artificial intelligence control 1714. The user may click on the artificial intelligence control 1714, and the electronic device may display a dialogue component 1730 in the edit page 1700. The user may enter the dialogue content in the dialogue component 1730 to inform the AI ​​model of its own needs. The user may close the dialogue component 1730 by clicking on the artificial intelligence control 1714 again, or by clicking on the close button of the dialogue component 1730. Through the artificial intelligence control displayed on the edit page 1700, the user can flexibly choose to turn on / off the dialogue component 1730, thereby improving the convenience of operation.

[0220] Furthermore, since the AI ​​model can provide editing assistance functions to the user, when the user turns on the dialogue component 1730 to use the editing assistance functions of the AI ​​model, the frequency of use of the editing function area 1720 is reduced. Therefore, the dialogue component 1730 can be superimposed and displayed on the editing function area 1720 of the editing page 1700, and the dialogue component 1730 will not block the preview area 1710, and will not hinder the user from viewing the target multimedia data, thereby improving interactivity.

[0221] As an optional implementation, the artificial intelligence control may be displayed in a fixed position on the editing page.

[0222] As another optional implementation, the artificial intelligence control may also support movement on the editing page. In response to a movement operation on the artificial intelligence control, the display position of the artificial intelligence control on the editing page may be moved; if the artificial intelligence control moves to an edge area of ​​the editing page, at least a portion of the artificial intelligence control may be hidden.

[0223] The moving operation may include but is not limited to dragging, sliding, and other operation modes. The user can move the AI ​​control according to actual needs and adjust the display position of the AI ​​control on the editing page. If it is detected that the AI ​​control moves to the edge area of ​​the editing page, at least part of the AI ​​control can be hidden, for example, half of the AI ​​control can be hidden, or 3 / 4 of the AI ​​control can be hidden, or the entire AI control can be hidden, etc.

[0224] For example, Fig. 17C FIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment. Fig. 17CAs shown, the user can move the artificial intelligence control 1714 according to actual needs, thereby adjusting the display position of the artificial intelligence control 1714 on the editing page. Fig.17D FIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment. Fig.17D As shown, if the artificial intelligence control 1714 is moved to the edge area of ​​the editing page, the artificial intelligence control 1714 can be hidden and displayed, which can avoid the artificial intelligence control 1714 from excessively blocking the editing page and affecting the user's editing of the target multimedia data, thereby improving interactivity.

[0225] Step 1606, obtaining the sixth dialogue content input in the dialogue component.

[0226] Step 1608: Output the target content associated with the editing function in the dialogue component based on the sixth dialogue content through the artificial intelligence model.

[0227] After the dialogue component is displayed, the user can enter the dialogue content in the dialogue component, and the sixth dialogue content entered by the user in the dialogue component can be obtained. The sixth dialogue content can be semantically analyzed by the AI ​​model to identify the user's intention, and the target content required by the user and associated with the editing function can be output in the dialogue component.

[0228] In some embodiments, the AI ​​model may support a variety of editing assistance functions, including but not limited to searching for editing functions, searching for usage tutorials, and performing specific editing processing on multimedia data. When the dialogue component is opened and displayed, the third guide component corresponding to each editing assistance function supported by the AI ​​model may be displayed in the dialogue component, and each third guide component may be used to guide the user to use the editing assistance function provided by the AI ​​model. The third guide component may include but is not limited to a guide button, a guide label, a guide frame, etc.

[0229] For example, Fig.17E FIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment. Fig.17E As shown, when the dialogue component 1730 is turned on and displayed, the third guide component 1732 corresponding to each editing auxiliary function supported by the AI ​​model can be displayed in the dialogue component 1730, such as the third guide component 1732 corresponding to the editing auxiliary functions such as finding editing functions, finding usage tutorials, adding effects to videos, and adding music to videos. The user can choose to trigger any third guide component 1732, and the electronic device can respond to the user's triggering operation on any third guide component 1732, and can send the guidance content of any third guide component 1732 as the sixth dialogue content to the dialogue component 1730 to trigger the AI ​​model to display the corresponding target content. Exemplarily, Fig.17FFIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment. Fig.17F As shown, when the user clicks the third guide component 1732 corresponding to the search and edit function, the guide content "find function" corresponding to the third guide component 1732 can be sent to the dialogue component 1730 as the sixth dialogue content 1742. This further improves the efficiency of the user inputting dialogue content in the dialogue component 1730 and improves the convenience of operation.

[0230] Optionally, if the demand indicated by the sixth dialogue content input by the user is too broad and the AI ​​model cannot accurately understand the user's intention, the AI ​​model can output further guidance information in the dialogue interface based on the sixth dialogue content to guide the user to further describe the demand. Fig.17F As shown in the figure, the sixth dialogue content 1742 input by the user: "Find a function" indicates a requirement that is too broad, and the AI ​​model cannot accurately know which function the user needs to find. In this case, guidance information can be displayed in the dialogue interface, such as "You can ask me this: Where is the text function?" to guide the user to enter more detailed requirements. This improves the guidance effect, reduces the learning threshold for users and the difficulty of using AI models, and improves the user experience.

[0231] In some embodiments, the editing assistance functions supported by the AI ​​model include searching for editing functions. The editing function area of ​​the editing page may contain many function controls. When the user needs to find the location of the function control corresponding to a certain editing function in the editing page, the user can enter the sixth dialogue content in the dialogue component. The sixth dialogue content may include the first editing function to be found, and the target content output by the AI ​​model in the dialogue component may include the jump control corresponding to the first editing function. After the AI ​​model identifies the sixth dialogue content and determines the first editing function to be found, the jump control corresponding to the first editing function can be displayed in the dialogue component.

[0232] The jump control corresponding to the first editing function can be used to provide an entry to jump to the function control corresponding to the first editing function. The user can trigger the jump control, and the electronic device can respond to the user's fifth trigger operation on the jump control, close the dialogue component and switch the editing function area to the first sub-page display, and the first sub-page includes the function control corresponding to the first editing function, so that the user can quickly find the function control corresponding to the required first editing function, which is convenient for the user to use.

[0233] It should be noted that the first sub-page can also be the function details page corresponding to the first editing function, and the function details page can be used to provide various editing contents under the first editing function, such as editing parameter adjustment, template use, etc.

[0234] For example, Fig.18This is a schematic diagram of the interface changes of using the AI ​​model to search and edit functions in one embodiment. Fig.18 As shown in (a), the user can input the conversation content 1802 in the conversation component 1730, and the conversation content 1802 includes the first editing function to be found, such as the filter function. The AI ​​model can identify the first editing function to be found indicated by the conversation content 1802 according to the conversation content 1802 input by the user, find the position of the first editing function in the editing function area 1720, and display the loading process in the conversation component 1730. As shown in (b), after the AI ​​model determines the position of the first editing function to be found in the editing function area 1720, the corresponding jump control 1804 can be displayed in the conversation component 1730. Optionally, the specific position of the first editing function to be found in the editing function area 1720 can also be displayed, such as the 6th function position of the filter function in the editing function area 1720. The user can click the jump control 1804, as shown in (c), and the electronic device can close the dialogue component 1730 and switch the editing function area 1720 to a sub-page containing the function control corresponding to the first editing function, such as switching to a sub-page containing the filter control corresponding to the filter function. The user can quickly find the function control corresponding to the required editing function through the AI ​​model, which can solve the problem of high user learning threshold in complex tool-type interfaces or non-tool-type user interaction interfaces.

[0235] In some embodiments, the editing assistance functions supported by the AI ​​model include finding usage tutorials. When the editing page provides a large number of editing functions and the editing functions are relatively complex, the user may not know how to use a certain editing function specifically. In this case, the sixth dialogue content may be input into the dialogue component. The sixth dialogue content may include usage inquiry information corresponding to the second editing function. The target content output by the AI ​​model in the dialogue component may include a usage tutorial link corresponding to the second editing function. After the AI ​​model identifies the sixth dialogue content and determines that the user needs to obtain the usage tutorial corresponding to the second editing function, the usage tutorial link corresponding to the second editing function may be displayed in the dialogue component.

[0236] The tutorial link corresponding to the second editing function can be used to provide an entry to access the tutorial data corresponding to the second editing function. The tutorial link may include but is not limited to being represented by the storage path of the tutorial data, the access path of the tutorial data, the thumbnail content of the tutorial data, etc. The user can trigger the tutorial link, and the electronic device displays the tutorial data corresponding to the second editing function in response to the sixth trigger operation on the tutorial link. The tutorial data may include but is not limited to one or more of a tutorial video, a tutorial picture, and a tutorial document.

[0237] For example, Fig.19This is a schematic diagram of the interface changes of a tutorial for using the AI ​​model search and edit function in one embodiment. Fig.19 As shown in (a), the user can enter the dialogue content 1902 in the dialogue component 1730, and the dialogue content 1902 includes the usage inquiry information corresponding to the second editing function, such as asking how to use the screen framing function. The AI ​​model can identify the dialogue content 1902 indicating the usage of the second editing function according to the dialogue content 1902 input by the user, find the usage tutorial data corresponding to the second editing function, and display the loading process in the dialogue component 1730. As shown in (b), after finding the usage tutorial data corresponding to the second editing function, the AI ​​model can display the usage tutorial link 1904 corresponding to the second editing function in the dialogue component 1730, and the user can click on the usage tutorial link 1904 to play the usage tutorial video. Optionally, the jump control 1906 corresponding to the second editing function can also be displayed in the dialogue component 1730. The user can trigger the jump control 1906 to make the editing function area jump to the sub-page display of the function control containing the second editing function, so as to facilitate the user to use the second editing function. Through the AI ​​model, users can quickly find the usage tutorial for any editing function, which can reduce the learning difficulty of users in complex tool-type interfaces or non-tool-type user interaction interfaces and improve the user experience.

[0238] In some embodiments, the editing assistance function supported by the AI ​​model may also include a specific editing function for multimedia data. When the user needs to edit the target multimedia data, the sixth dialogue content may be input in the dialogue component, and the sixth dialogue content may include an editing instruction. The AI ​​model may edit the target multimedia data according to the editing instruction, and output the edited target multimedia data in the dialogue component.

[0239] Optionally, the editing instructions may include but are not limited to one or more of the following: instructions for adjusting display effects, instructions for adjusting playback audio, instructions for adjusting text content, etc. Among them, the instructions for adjusting display effects may include but are not limited to instructions for adding stickers, instructions for adding filters, instructions for adjusting screen brightness, etc.; instructions for adjusting playback audio may include but are not limited to instructions for adding background music, instructions for adding sound effects, instructions for modifying timbre, instructions for adding dubbing, etc.; instructions for adjusting text content may include but are not limited to instructions for adding subtitles, instructions for adding copywriting, instructions for splitting short sentences, etc. It should be noted that the specific content of the editing instructions can be set according to actual needs and is not limited here. The AI ​​model can provide rich editing and processing functions, thereby reducing the difficulty of users editing multimedia data, improving editing efficiency, and improving intelligence.

[0240] After acquiring the sixth dialogue content input by the user in the dialogue component, the AI ​​model may perform semantic analysis on the sixth dialogue content, identify the editing instructions contained in the sixth dialogue content, and edit the target multimedia data according to the editing instructions. After the target multimedia data is edited, the edited target multimedia data may be displayed in the dialogue component. Optionally, the complete edited target multimedia data may be displayed in the dialogue component, or a thumbnail of the edited target multimedia data may be displayed in the dialogue component.

[0241] In some embodiments, during the process of the AI ​​model editing the target multimedia, editing materials are required, and the editing materials may refer to data content that can provide raw materials, inspiration, etc. for the editing of the target multimedia data. The editing materials may be editing materials generated by the AI ​​model or uploaded editing materials.

[0242] As an implementation method, the target multimedia data is edited and processed, and the editing material used may be an editing material generated by AI. The AI ​​model may obtain one or more recommended editing materials corresponding to the editing instruction according to the editing instruction, and display the one or more recommended editing materials in the dialogue component. The user may select any recommended editing material for use according to actual needs, and the electronic device may respond to the selection operation for the target editing material, and edit the target multimedia data according to the editing instruction and the target editing material through the AI ​​model; the target editing material may be at least one of the one or more recommended editing materials.

[0243] The recommended editing material may match the editing process indicated by the editing instruction contained in the sixth dialogue content. When the user's editing function corresponding to the target multimedia data is different, the AI ​​model may display different recommended editing materials in the dialogue component. For example, if the editing instruction input by the user is an instruction to add background music, the recommended editing material generated by the AI ​​model may be multiple background audio clips; if the editing instruction input by the user is an instruction to add a sticker, the recommended editing material generated by the AI ​​model may be multiple stickers, etc., but is not limited thereto.

[0244] For example, Fig. 20A FIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment. Fig. 20AAs shown in FIG. 1 , one or more recommended editing materials may be displayed in the dialogue component 1730 according to different dialogue contents input by the user in the dialogue component 1730. For example, as shown in (a), if the dialogue content input by the user is “add filter”, multiple recommended filter materials 2010 may be displayed in the dialogue component 1730; as shown in (b), if the dialogue content input by the user is “add sticker”, multiple recommended sticker materials 2020 may be displayed in the dialogue component 1730; as shown in (c), if the dialogue content input by the user is “add text”, multiple recommended sticker materials 2020 may be displayed in the dialogue component 1730. A plurality of recommended text materials 2030 are displayed in the dialogue component 1730; as shown in (d), if the dialogue content input by the user is "add background music", a plurality of recommended music materials 2040 may be displayed in the dialogue component 1730; as shown in (e), if the dialogue content input by the user is "add dubbing", a plurality of recommended sound materials 2050 may be displayed in the dialogue component 1730; as shown in (f), if the dialogue content input by the user is "add sound effects", a plurality of recommended sound effect materials 2060 may be displayed in the dialogue component 1730, but the present invention is not limited thereto. The user may select any recommended editing material as the target editing material for use according to actual needs. If the user is not satisfied with the currently displayed recommended editing materials, the user may also trigger the material change control (such as Fig. 20A The AI ​​model is used to recommend editing materials to users, so that users can choose the materials to be used for editing the target multimedia data, which reduces the difficulty of editing and improves the editing efficiency.

[0245] In some embodiments, after obtaining one or more recommended editing materials corresponding to the editing instructions through an artificial intelligence model according to the editing instructions, the target multimedia data can be preprocessed according to the recommended editing materials, and the preprocessing effects corresponding to the one or more recommended editing materials can be displayed in the dialogue component.

[0246] Optionally, the pre-processing can be a pre-editing process of the target multimedia data based on the recommended editing material. The pre-editing process can be understood as a relatively simple process. For example, the target multimedia data is a target video, and the editing instruction input by the user is an instruction to add background music. The recommended editing material generated by the AI ​​model can be multiple background audios. The pre-editing process can be a process of adding background audio to a video clip captured from the target video. The obtained pre-processing effect can be video clips with different background audios added respectively.

[0247] The user can select any recommended editing material corresponding to any preprocessing effect for use according to actual needs. The electronic device can respond to the selection operation for the target preprocessing effect and edit the target multimedia data according to the editing instruction and the recommended editing material corresponding to the target preprocessing effect through the artificial intelligence model; the target preprocessing effect can be at least one of the preprocessing effects corresponding to one or more recommended editing materials.

[0248] By displaying the preprocessing effect corresponding to each recommended editing material in the dialogue component, users can more intuitively know the editing effect corresponding to each recommended editing material, and the preprocessing method is relatively simple, which can reduce resource consumption.

[0249] In some embodiments, if the user is dissatisfied with the currently displayed recommended editing material, the user may input material description information as the conversation content. The electronic device obtains the conversation content and may analyze the conversation content through the AI ​​model to obtain material description information. The material description information may be used to further describe the material features of the editing material required by the user. The AI ​​model may regenerate the recommended editing material based on the material description information and send the regenerated recommended editing material to the conversation component. Furthermore, the AI ​​model may display one or more material description tags in the conversation component according to the editing instruction. The material description tags may be used to describe the material features of the editing material. The user may select one or more material description tags to form the material description information according to actual needs and send it to the conversation component.

[0250] For example, Fig. 20B FIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment. Fig. 20B As shown, one or more material description tags 2070 can be displayed in the dialogue component 1730 of the editing page 1700. For example, if the editing instruction input by the user is "add sticker", one or more material description tags 2070 corresponding to the editing instruction can be displayed, such as the tag "dreamlike", the tag "cute", the tag "jelly style", etc. The user can select and click on one or more material description tags 2070, and the electronic device can automatically display the content of the one or more material description tags 2070 selected by the user in the content input component, and the user can send it as the dialogue content to the dialogue component 1730, so that the AI ​​model can generate recommended editing materials that are more in line with the user's needs, improve the accuracy of the generated recommended editing materials, and have a better guiding effect. The way for users to input material description information is more convenient, which improves the user's experience.

[0251] Optionally, after obtaining the editing instructions, the AI ​​model may also obtain user historical data, learn user personalized information such as user habits and / or user interests based on the user historical data, and generate one or more recommended editing materials based on the editing instructions and user personalized information, so that the generated recommended editing materials are more in line with the user's actual needs and improve the user retention rate.

[0252] As an implementation method, the target multimedia data is edited and processed, and the editing material used can be the editing material uploaded by the user. The target editing material sent to the dialogue component can be obtained, and the target multimedia data can be edited and processed according to the editing instruction and the target editing material through the AI ​​model.

[0253] Optionally, after obtaining the sixth dialogue content input by the user, the AI ​​model may display guidance information in the dialogue component according to the editing instructions included in the first dialogue content to guide the user to upload the editing material. The user can select the target editing material to be uploaded on the material selection page, and the electronic device can determine one or more target editing materials selected by the user in response to the user's material selection operation, and send the target editing material to the dialogue interface. It should be noted that the way in which the user selects the target editing material can be similar to the way in which the user selects the target material for generating the target multimedia data on the material selection page described in the above embodiments, and will not be repeated here.

[0254] After obtaining the target editing material sent by the user to the dialogue component, the AI ​​model can edit the target multimedia data according to the editing instruction and the target editing material. Further, the AI ​​model can identify the target multimedia data, process the target editing material according to the identification result and the editing instruction, extract the required information from the target editing material, and edit the target multimedia data according to the extracted information.

[0255] For example, Fig.21 FIG. 1 is a schematic diagram of the interface changes when a user uploads a target editing material in an embodiment. Fig.21As shown in (a), the conversation content input by the user is "add background music". The AI ​​model can display guidance information, such as "OK, you can send me a video or music, and I will help you extract it", etc., by analyzing the editing instruction to guide the user to upload the editing material. After the user selects the target editing material 2110, the electronic device can send the target editing material 2110 selected by the user to the dialogue component 1730. The AI ​​model can directly edit the target multimedia data according to the editing instruction and the target editing material 2110, and can also perform secondary processing on the target editing material 2110. As shown in (b), the AI ​​model can perform secondary processing on the target editing material 2110, such as extracting a piece of music from the target editing material 2110, and displaying the processed target editing material 2120 in the dialogue component 1730, and the user can decide whether to use the processed target editing material 2120. In this way, intelligence is improved, the user's need to use his own editing material to edit the target multimedia data is met, and the user experience is improved.

[0256] In some embodiments, the electronic device may also display an editing parameter adjustment component corresponding to the editing instruction in the dialogue component, and may determine the target editing parameter value for adjustment in response to the adjustment operation on the editing parameter adjustment component, and then edit and process the target multimedia data through the AI ​​model according to the editing instruction, target editing material and target editing parameter value.

[0257] Among them, the target editing material can be the editing material generated by the AI ​​model or the editing material uploaded by the user, which is not limited here.

[0258] Different editing instructions may correspond to different editing functions. Different editing functions may correspond to different editing parameters, which may refer to parameters related to the editing process. For example, if the editing function is to add background music, the corresponding editing parameters may include volume parameters, noise reduction parameters, etc.; if the editing function is to add dubbing, the corresponding editing parameters may include speech speed parameters, pitch parameters, etc.; if the editing function is to add subtitles, the corresponding editing parameters may include font parameters, font size parameters, subtitle color parameters, etc., but are not limited thereto.

[0259] An editing parameter adjustment component corresponding to the editing instruction may also be displayed in the dialogue component, and the editing parameter adjustment component may be used to adjust various editing parameters under the editing function corresponding to the editing instruction. The user may adjust the specific parameter value of each editing parameter according to actual needs, and the electronic device may respond to the adjustment operation of the editing parameter adjustment component, determine the adjusted target editing parameter value, and then edit the target multimedia data according to the editing instruction, the target editing material and the target editing parameter value.

[0260] For example, Fig. 22FIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment. Fig. 22 As shown, one or more recommended editing materials are displayed in the dialogue component 1730 of the editing page 1700, and an editing parameter adjustment component corresponding to the editing instruction can also be displayed. As shown in (a), multiple recommended filter materials are displayed in the dialogue component 1730, and an editing parameter adjustment component 2210 related to the filter function can also be displayed, which can be used to adjust editing parameters such as filter strength; as shown in (b), multiple recommended special effect materials are displayed in the dialogue component 1730, and an editing parameter adjustment component 2220 related to the special effect function can also be displayed, which can be used to adjust editing parameters such as transition strength and atmosphere strength; as shown in (c), multiple recommended music materials are displayed in the dialogue component 1730, and an editing parameter adjustment component 2230 related to the music function can also be displayed, which can be used to adjust editing parameters such as volume and noise reduction; as shown in (d), multiple recommended sound materials are displayed in the dialogue component 1730, and an editing parameter adjustment component 2240 related to the dubbing function can also be displayed, which can be used to adjust editing parameters such as speech speed and pitch. Optionally, for the target editing material uploaded by the user, an editing parameter adjustment component may also be displayed in the dialogue component 1730. As shown in (e), the processed target editing material 2120 is displayed in the dialogue component 1730, and an editing parameter adjustment component 2250 related to the music function may also be displayed in the dialogue component 1730, which can be used to adjust editing parameters such as volume and noise reduction. This facilitates users to flexibly adjust editing parameters according to actual conditions, improves the convenience of editing operations, and reduces editing difficulty.

[0261] In some embodiments, there may be multiple editing functions corresponding to the editing instructions contained in the sixth dialogue content input by the user. In order to further clarify the editing function that the user wants to use, the electronic device may display one or more editing guidance information in the dialogue component in response to the editing instruction. The editing guidance information is used to guide the use of the editing function associated with the editing instruction.

[0262] The AI ​​model may perform semantic analysis on the sixth dialogue content, determine the editing instructions contained in the sixth dialogue content, and determine the editing function associated with the editing instruction. If there are multiple editing functions associated with the editing instruction, one or more editing guidance information may be displayed in the dialogue component, and further, multiple editing guidance information corresponding to the multiple associated editing functions may be displayed in the dialogue component, so as to guide the user to determine and use the editing function associated with the editing instruction.

[0263] For example, Fig.23A FIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment. Fig.23AAs shown, the dialogue content input by the user is "add effect", and the editing functions associated with the editing instruction include filter function, special effect function, sticker function, etc., then the editing guidance information 2310 corresponding to each editing function associated with the editing instruction can be displayed in the dialogue component 1730 to guide the user to select any editing function for use.

[0264] In some embodiments, the editing page corresponding to the target multimedia data may also include an input box. During the process of the user using the AI ​​model for editing assistance, the user may also enter the conversation content through the input box to further describe the editing requirements for the target multimedia data. Fig. 23B FIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment. Fig. 23B As shown, when the user clicks on the input box in the editing page 1700, the keyboard can be pulled up for input. Optionally, recommended words 2320 can be displayed in the input box to help the user better describe his or her own editing needs and reduce the difficulty of entering the dialogue content.

[0265] After the AI ​​model edits the target multimedia data, the edited target multimedia data may be displayed in the dialogue component. In some embodiments, the preview area of ​​the edit page may be used to display the edited target multimedia data. The electronic device may display the edited target multimedia data in the preview area in response to a preview operation on the edited target multimedia data.

[0266] For example, Fig.24 FIG. 1 is a schematic diagram of an interface change for previewing target multimedia data after editing in one embodiment. Fig.24 As shown in (a), after the AI ​​model edits the target multimedia data, one or more edited target multimedia data 2410 may be generated, and the one or more edited target multimedia data 2410 may be displayed in the dialogue component 1730 of the editing page 1700. The user may select any target multimedia data 2410 for preview, as shown in (b). For example, if the user selects the first target multimedia data 2410 for preview, the first target multimedia data 2410 may be displayed in the preview area 1710, so as to facilitate the user to view the editing effect of the multimedia data.

[0267] In some embodiments, the user may further edit and optimize the target multimedia data after editing. The user may continue to input editing instructions in the dialogue component, and the AI ​​model may continue to edit the target multimedia data according to the editing instructions re-entered by the user.

[0268] For example, Fig.25FIG. 1 is a schematic diagram of an interface of an editing page corresponding to target multimedia data in another embodiment. Fig.25 As shown in (a), after the AI ​​model edits the target multimedia data, the edited target multimedia data is displayed in the dialogue component 1730 of the editing page 1700. The user enters further editing instructions 2510 in the dialogue component 1730, such as "clearer", and the AI ​​model can further process the edited target multimedia data according to the editing instructions 2510 entered by the user, such as further adjusting the clarity of the picture. As shown in (b), after the AI ​​model adds text to the target multimedia data, the user enters further editing instructions 2520 in the dialogue component 1730, such as "the tone of the text is more enthusiastic", and the AI ​​model can further edit the target multimedia data with the added text according to the editing instructions 2520 entered by the user, such as adjusting the expression method of the text. The AI ​​model can continuously edit the target multimedia data according to the needs of the user, and provides a wealth of editing assistance functions to meet the needs of users in different application scenarios, so that the edited target multimedia data is more in line with user expectations.

[0269] It should be noted that the editing assistance functions and editing processes supported by the AI ​​model are not limited to the types involved in the above embodiments, but can also support more and more complex editing assistance functions. For example, it can also support intelligent editing functions of multiple video clips, etc., but is not limited to this.

[0270] In an embodiment of the present application, the editing page corresponding to the target multimedia data supports the use of an artificial intelligence model for editing assistance. The artificial intelligence model can support the editing assistance function of the multimedia data, and can output the target content associated with the editing function according to the dialogue content input by the user in the dialogue component of the editing page, thereby more intelligently assisting the user to edit the multimedia data, reducing the difficulty of editing and improving editing efficiency.

[0271] In some embodiments, the user can input the conversation content in the conversation interface by voice. Fig.26 As shown, the above method may further include the following steps:

[0272] Step 2602, in response to the eighth trigger operation on the call control, entering the call mode.

[0273] Step 2604, in the call mode, collect user voice data through the audio collection device, and input the conversation content corresponding to the user voice data in the conversation interface.

[0274] The conversation interface may include a call control that can be used to control entry / exit of a call mode. The call mode may refer to a mode in which a user can directly communicate with the AI ​​model by voice.

[0275] The user can trigger the call control in the dialogue interface, and the electronic device can enter the call mode in response to the eighth trigger operation on the call control. In the call mode, the user can input the conversation content by voice, and the electronic device can automatically collect the user's voice data through the audio collection device, and input the conversation content corresponding to the user's voice data in the dialogue interface. The AI ​​model can respond to the user's voice data input by the user in real time, thereby improving the response efficiency.

[0276] For example, Fig.27A FIG. 1 is a schematic diagram of a dialogue interface in another embodiment. Fig.27A As shown, the dialogue interface 500 may include a call control 2710. The user can click on the call control 2710 to choose to enter the call mode. In the call mode, the user only needs to speak the required content, and the electronic device can collect the user's content through an audio collection device such as a microphone and automatically input it into the dialogue interface 500.

[0277] In one embodiment, the electronic device displays the call interface in response to the eighth trigger operation of the call control, and can shrink the call interface in response to the shrink operation of the call interface, and display the shrink component corresponding to the call interface in the dialogue interface. Fig.27B FIG. 1 is a schematic diagram of a call interface in an embodiment. Fig.27B As shown, when the electronic device detects that the user triggers a call control, a call interface 2720 may be displayed. The call interface 2720 may display information such as the name of the AI ​​model, and may also display one or more call control controls, such as a hang-up control 2722, a pause control, a return control, etc.

[0278] The user can choose to shrink the call interface and return to the conversation interface. Fig.27C FIG. 1 is a schematic diagram of a dialogue interface in another embodiment. Fig.27C As shown, if a zoom-out operation of the user to zoom out the call interface 2720 is detected, the call interface 2720 can be zoomed out, and the dialogue interface 500 can be returned to display, and the zoom-out component 2730 can be displayed in the dialogue interface 500, so that the user can accurately know that the current call mode is in progress. Optionally, the zoom-out component 2730 can be displayed in a floating manner on the dialogue interface 500, and the user can return to the call interface 2720 by triggering the zoom-out component 2730. The displayed call interface 2720 can provide the user with a more realistic call experience, thereby improving the intelligence of the AI ​​model.

[0279] In some embodiments, the user can control the electronic device to exit the call mode by triggering the call control in the conversation interface again, or by triggering the hang-up control in the call interface. In the call mode, the electronic device can exit the call mode in response to the ninth trigger operation on the call control or in response to the tenth trigger operation on the hang-up control in the call interface, thereby improving the convenience of user operation and interactivity.

[0280] In an embodiment of the present application, a call mode can be provided. In the call mode, the user can talk directly with the AI ​​model. Compared with the method of long pressing the voice control every time voice input is required, the user does not need to keep pressing the voice control in the call mode, and can also communicate with the AI ​​model through voice, which simplifies user operation, provides a more realistic call experience, and improves the intelligence of the AI ​​model.

[0281] It should be noted that the intelligent functions of the AI ​​model provided in the above embodiments, including but not limited to the function of generating multimedia data, various editing assistance functions, etc., can be aggregated into various applications, such as chat pages of social applications, photo albums, etc., to support use in different scenarios and have a wide range of applications.

[0282] like Fig.28 As shown, in one embodiment, an editing assistance method is provided, which can be applied to the above electronic device, and the method may include the following steps:

[0283] Step 2810: Display an editing page corresponding to the target multimedia data.

[0284] Step 2820, display the dialog component in the edit page.

[0285] Step 2830, obtain the dialogue content entered in the dialogue component.

[0286] Step 2840: Output the target content associated with the editing function in the dialogue component based on the dialogue content through the artificial intelligence model.

[0287] In one embodiment, the editing page includes an editing function area, which is used to display function controls corresponding to one or more editing functions; the dialog content includes a first editing function to be found; the target content includes a jump control corresponding to the first editing function; after step 2840, the method also includes: in response to a triggering operation on the jump control, closing the dialog component and switching the editing function area to a first sub-page display, the first sub-page including a function control corresponding to the first editing function.

[0288] In one embodiment, the conversation content includes usage inquiry information corresponding to the second editing function; the target content includes a usage tutorial link corresponding to the second editing function; after step 2840, the method further includes: in response to a trigger operation on the usage tutorial link, displaying usage tutorial data corresponding to the second editing function, the usage tutorial data including one or more of a usage tutorial video, a usage tutorial picture, and a usage tutorial document.

[0289] In one embodiment, the conversation content includes editing instructions; step 2840 includes: editing the target multimedia data according to the editing instructions through the artificial intelligence model, and outputting the edited target multimedia data in the conversation component.

[0290] In one embodiment, the editing page includes a preview area, which is used to display the target multimedia data; after step 2840, the method also includes: in response to a preview operation on the edited target multimedia data, displaying the edited target multimedia data in the preview area.

[0291] In one embodiment, the step of editing the target multimedia data according to the editing instructions through the artificial intelligence model includes: obtaining one or more recommended editing materials corresponding to the editing instructions through the artificial intelligence model according to the editing instructions, and displaying one or more recommended editing materials in the dialogue component; in response to a selection operation for the target editing material, editing the target multimedia data according to the editing instructions and the target editing material through the artificial intelligence model; the target editing material is at least one of the one or more recommended editing materials.

[0292] In one embodiment, the step of editing the target multimedia data according to the editing instructions through the artificial intelligence model includes: obtaining one or more recommended editing materials corresponding to the editing instructions through the artificial intelligence model according to the editing instructions; preprocessing the target multimedia data according to each recommended editing material, and displaying the preprocessing effects corresponding to one or more recommended editing materials in the dialogue component; in response to a selection operation for a target preprocessing effect, editing the target multimedia data according to the editing instructions and the recommended editing materials corresponding to the target preprocessing effect through the artificial intelligence model; the target preprocessing effect is at least one of the preprocessing effects corresponding to one or more recommended editing materials.

[0293] In one embodiment, the method also includes: displaying an editing parameter adjustment component corresponding to the editing instruction in the dialogue component; determining the target editing parameter value for adjustment in response to the adjustment operation on the editing parameter adjustment component; the step of editing the target multimedia data according to the editing instruction through an artificial intelligence model includes: editing the target multimedia data according to the editing instruction, target editing material and target editing parameter value through an artificial intelligence model; the target editing material is editing material generated by the artificial intelligence model or editing material uploaded by the user.

[0294] In one embodiment, the step of editing the target multimedia data according to the editing instructions through the artificial intelligence model includes: obtaining the target editing material sent to the dialogue component; editing the target multimedia data according to the editing instructions and the target editing material through the artificial intelligence model.

[0295] In one embodiment, the method further comprises: in response to the editing instruction, displaying one or more editing guide information in the dialog component, wherein the editing guide information is used to guide the use of the editing function associated with the editing instruction.

[0296] In one embodiment, the editing instruction includes one or more of the following: an instruction to adjust a display effect, an instruction to adjust audio playback, and an instruction to adjust text content.

[0297] In one embodiment, the method also includes: obtaining a first conversation content input by the user in the conversation interface, the first conversation content including a target multimedia type; processing the target material according to the first conversation content through an artificial intelligence model to generate target multimedia data matching the target multimedia type; the target material includes at least one of the target material uploaded by the user and the target material determined by the artificial intelligence model according to the first conversation content; and displaying the target multimedia data in the conversation interface.

[0298] It should be noted that the description of the editing assistance method provided in the embodiments of the present application can refer to the relevant description of the multimedia data generation method provided in the above embodiments, and will not be repeated here.

[0299] In an embodiment of the present application, the editing page corresponding to the target multimedia data supports the use of an artificial intelligence model for editing assistance. The artificial intelligence model can support the editing assistance function of the multimedia data, and can output the target content associated with the editing function according to the dialogue content input by the user in the dialogue component of the editing page, thereby more intelligently assisting the user to edit the multimedia data, reducing the difficulty of editing and improving editing efficiency.

[0300] like Fig.29As shown, in one embodiment, a multimedia data generation device 2900 is provided, which can be applied to the above-mentioned electronic device. The multimedia data generation device 2900 may include a dialogue acquisition module 2910, a first generation module 2920, and a display module 2930.

[0301] The dialogue acquisition module 2910 is used to acquire the first dialogue content input by the user in the dialogue interface, where the first dialogue content includes the target multimedia type.

[0302] The first generation module 2920 is used to process the target material according to the first conversation content through the artificial intelligence model to generate target multimedia data matching the target multimedia type; the target material includes the target material uploaded by the user, and at least one of the target materials determined by the artificial intelligence model according to the first conversation content.

[0303] The display module 2930 is used to display the target multimedia data in the dialogue interface.

[0304] In one embodiment, the multimedia data generating device 2900 further includes a material determining module and a sending module.

[0305] The display module 2930 is also used to display a material selection page in response to a first trigger operation on a first guide component in the dialogue interface; the first guide component is used to guide the user to upload a material; the material selection page includes one or more pre-stored materials.

[0306] The material determination module is used to determine at least one selected target material in response to a material selection operation on the material selection page.

[0307] The sending module is used to send at least one selected target material to the dialogue interface.

[0308] In one embodiment, the display module 2930 is further configured to display a first guidance component on the dialogue interface in response to the input first dialogue content.

[0309] In one embodiment, the dialogue interface includes an input box, and the input box is used to input dialogue content into the dialogue interface; the multimedia data generation device 2900 also includes an adjustment module.

[0310] The display module 2930 is further used to obtain at least one target material selected by the user and display the at least one selected target material in the input box.

[0311] The adjustment module is used to adjust any target material in response to an adjustment operation on any target material in the input box.

[0312] The sending module is also used to send each target material contained in the input box to the dialogue interface in response to a triggered content sending operation.

[0313] In one embodiment, at least one selected target material is sequentially arranged and displayed in the input box in the order of selection; the adjustment module is further used to move the first target material from the first arrangement position to the second arrangement position in response to a position adjustment operation on the first target material in the input box; the first target material is any target material displayed in the input box; and / or, in response to a deletion of the second target material in the input box,

[0314] In one embodiment, the sending module is further used to receive the second dialogue content input in the input box; in response to the triggered content sending operation, each target material contained in the input box and the second dialogue content are sent to the dialogue interface.

[0315] The first generation module 2920 is also used to process the target material sent to the dialogue interface according to the first dialogue content and the second dialogue content through the artificial intelligence model.

[0316] In one embodiment, the display module 2930 is also used to display a material cover corresponding to at least one target material uploaded by the user on the dialogue interface, where the material cover is one of the at least one target material uploaded by the user; and the material quantity corresponding to the at least one target material uploaded by the user is marked on the material cover.

[0317] In one embodiment, the multimedia data generating device 2900 further includes a question module and a material generating module.

[0318] The dialogue acquisition module 2910 is further used to acquire the third dialogue content input by the user in the dialogue interface.

[0319] The inquiry module is used to output first inquiry information in the dialogue interface if the third dialogue content indicates to generate materials, and the first inquiry information is used to inquire about material features corresponding to the required materials.

[0320] The dialogue acquisition module 2910 is further used to acquire the fourth dialogue content input by the user in the dialogue interface.

[0321] The material generation module is used to identify the target material features contained in the fourth dialogue content through an artificial intelligence model, and generate target material matching the target material features based on the first dialogue content.

[0322] In one embodiment, the first conversation content further includes indication information for indicating historical multimedia data; the target material determined by the artificial intelligence model according to the first conversation content includes: historical multimedia data output in the conversation interface determined by the artificial intelligence model according to the indication information;

[0323] The multimedia type corresponding to the historical multimedia data is the same as the target multimedia type, or the multimedia type corresponding to the historical multimedia data is different from the target multimedia type.

[0324] In one embodiment, the first generating module 2920 includes a template generating unit, a template displaying unit and a processing unit.

[0325] The template generation unit is used to generate one or more recommendation templates according to the first dialogue content through an artificial intelligence model.

[0326] The template display unit is used to display one or more recommended templates in the dialogue interface.

[0327] A processing unit is used to respond to a template selection operation on a target recommendation template, and to process the target material according to the target recommendation template through an artificial intelligence model to generate target multimedia data matching the target multimedia type; the target recommendation template is any recommendation template.

[0328] In one embodiment, the template display unit is also used to display a template preview interface in response to a preview operation on the first recommended template in the dialogue interface, where the template preview interface is used to display the preview content of the first recommended template, where the first recommended template is any recommended template; and in response to a template switching operation triggered in the template preview interface, the preview content of the second recommended template is switched to be displayed in the template preview interface.

[0329] The processing unit is further configured to respond to a second trigger operation on a selection control in the template preview interface, use the current recommended template in the template preview interface as a target recommended template, and determine a template selection operation on the target recommended template.

[0330] In one embodiment, the processing unit is also used to display a material selection page in response to a template selection operation on a target recommendation template; determine at least one selected target material in response to a material selection operation on the material selection page; send at least one selected target material to the dialogue interface; and process at least one selected target material according to the target recommendation template through an artificial intelligence model to generate target multimedia data that matches the target multimedia type.

[0331] In one embodiment, the processing unit is further used to generate supplementary target materials according to the first dialogue content through an artificial intelligence model if the material quantity corresponding to the at least one selected target material does not match the material quantity required by the target recommendation template; the sum of the material quantities of the at least one selected target material and the supplemented target material matches the material quantity required by the target recommendation template; and is also used to process the at least one selected target material and the supplemented target material according to the target recommendation template through an artificial intelligence model to generate target multimedia data that matches the target multimedia type.

[0332] In one embodiment, the display module 2930 is further used to display a second guidance component on the dialogue interface in response to the input of the first dialogue content, and the second guidance component is used to guide the user to trigger the template generation process.

[0333] The sending module is further used to input a template generation instruction in the dialogue interface in response to a third trigger operation on the second guide component.

[0334] The template generation unit is also used to generate one or more recommended templates according to the first dialogue content through an artificial intelligence model in response to the template generation instruction.

[0335] In one embodiment, the multimedia data generating device 2900 further includes an editing module.

[0336] The dialogue acquisition module 2910 is further used to acquire the fifth dialogue content input by the user in the dialogue interface.

[0337] The editing module is used to identify the editing optimization instructions included in the fifth dialogue content through an artificial intelligence model, edit the target multimedia data according to the editing optimization instructions, and display the edited target multimedia data in the dialogue interface.

[0338] In one embodiment, the display module 2930 is further used to display the target multimedia data in the dialogue interface, and to display a first editing control corresponding to the target multimedia data in the dialogue interface.

[0339] The display module 2930 is further configured to display at least one recommended editing optimization instruction in the input box in response to a fourth trigger operation on the first editing control.

[0340] The dialogue acquisition module 2910 is further configured to respond to a selection operation on any recommended editing optimization instruction and send the selected any recommended editing optimization instruction as the fifth dialogue content to the dialogue interface.

[0341] In one embodiment, the display module 2930 is further configured to display multiple optimization categories in the input box, and display at least one recommended editing optimization instruction corresponding to the current optimization category.

[0342] In one embodiment, the target multimedia type includes any one of an image type, a video type, an audio type, a text type, and a graphic type.

[0343] In one embodiment, the multimedia data generating device 2900 further includes an output module.

[0344] The display module 2930 is further used to display an editing page corresponding to the target multimedia data; and to display a dialog component in the editing page.

[0345] The dialogue acquisition module 2910 is further used to acquire the sixth dialogue content input in the dialogue component.

[0346] An output module is used to output target content associated with the editing function in the dialogue component according to the sixth dialogue content through an artificial intelligence model.

[0347] In one embodiment, the editing page includes an editing function area, which is used to display function controls corresponding to one or more editing functions; the sixth dialogue content includes the first editing function to be found; and the target content includes a jump control corresponding to the first editing function.

[0348] The display module 2930 is further used to respond to the fifth trigger operation on the jump control, close the dialogue component and switch the editing function area to the first sub-page display, and the first sub-page includes the function control corresponding to the first editing function.

[0349] In one embodiment, the sixth dialogue content includes usage inquiry information corresponding to the second editing function; the target content includes a usage tutorial link corresponding to the second editing function.

[0350] The display module 2930 is also used to display the usage tutorial data corresponding to the second editing function in response to the sixth trigger operation on the usage tutorial link, and the usage tutorial data includes one or more of the usage tutorial video, usage tutorial picture and usage tutorial document.

[0351] In one embodiment, the sixth dialogue content includes editing instructions; the output module is also used to edit the target multimedia data according to the editing instructions through an artificial intelligence model, and output the edited target multimedia data in the dialogue component.

[0352] In one embodiment, the editing page includes a preview area, and the preview area is used to display the target multimedia data.

[0353] The display module 2930 is further configured to display the edited target multimedia data in the preview area in response to a preview operation on the edited target multimedia data.

[0354] In one embodiment, the output module includes a material recommendation unit, a preprocessing unit and an editing unit.

[0355] A material recommendation unit, configured to obtain one or more recommended editing materials corresponding to the editing instruction according to the editing instruction through an artificial intelligence model;

[0356] A preprocessing unit, used to preprocess the target multimedia data according to each recommended editing material, and display the preprocessing effect corresponding to one or more recommended editing materials in the dialogue component;

[0357] An editing unit is used to respond to a selection operation for a target preprocessing effect, and to edit and process the target multimedia data through an artificial intelligence model according to editing instructions and recommended editing materials corresponding to the target preprocessing effect; the target preprocessing effect is at least one of the preprocessing effects corresponding to one or more recommended editing materials.

[0358] In one embodiment, the output module further includes a parameter adjustment unit.

[0359] The parameter adjustment unit is used to display an editing parameter adjustment component corresponding to the editing instruction in the dialogue component, and determine the target editing parameter value for adjustment in response to the adjustment operation on the editing parameter adjustment component.

[0360] The editing unit is also used to edit and process the target multimedia data through an artificial intelligence model according to editing instructions, target editing materials and target editing parameter values; the target editing materials are editing materials generated by the artificial intelligence model or editing materials uploaded by users.

[0361] In one embodiment, the display module 2930 is further used to display one or more editing guide information in the dialog component in response to the editing instruction, where the editing guide information is used to guide the use of the editing function associated with the editing instruction.

[0362] In one embodiment, the editing instruction includes one or more of the following: an instruction to adjust a display effect, an instruction to adjust audio playback, and an instruction to adjust text content.

[0363] In one embodiment, the editing page includes an artificial intelligence control; the display module 2930 is also used to display a dialog component in the editing page in response to a seventh trigger operation on the artificial intelligence control.

[0364] In one embodiment, the display module 2930 is also used to move the display position of the artificial intelligence control on the editing page in response to a move operation on the artificial intelligence control; if the artificial intelligence control moves to the edge area of ​​the editing page, at least part of the artificial intelligence control is hidden.

[0365] In one embodiment, the dialogue interface includes a call control; the multimedia data generating device 2900 also includes a call module.

[0366] The call module is used to enter the call mode in response to the eighth trigger operation on the call control; in the call mode, the user voice data is collected by the audio collection device, and the conversation content corresponding to the user voice data is input in the conversation interface.

[0367] In one embodiment, the display module 2930 is also used to display the call interface in response to the eighth trigger operation on the call control; in response to the zoom-out operation on the call interface, the call interface is zoomed out and the zoomed-out component corresponding to the call interface is displayed in the dialogue interface.

[0368] In one embodiment, the call module is further used to exit the call mode in response to a ninth trigger operation on the call control or a tenth trigger operation on the hang-up control in the call interface in the call mode.

[0369] In an embodiment of the present application, the artificial intelligence model can support the intelligent generation of multimedia data of multiple different multimedia types. The user can input the target multimedia type to be generated through dialogue, and the target multimedia data matching the target multimedia type can be intelligently generated, reducing the difficulty of generating the target multimedia data. The artificial intelligence model supports combining the target material uploaded by the user with the target material generated by the artificial intelligence model to generate the target multimedia data. The method of generating the target multimedia data is more flexible, improves intelligence, and meets the different needs of users.

[0370] like Fig.30 As shown, in one embodiment, an editing assistance device 3000 is provided, which can be applied to the above-mentioned electronic device. The editing assistance device 3000 may include a display module 3010 , a dialogue acquisition module 3020 and an output module 3030 .

[0371] The display module 3010 is used to display the editing page corresponding to the target multimedia data.

[0372] The display module 3010 is also used to display the dialog component in the editing page.

[0373] The dialogue acquisition module 3020 is used to acquire the dialogue content input in the dialogue component.

[0374] The output module 3030 is used to output the target content associated with the editing function in the dialogue component according to the dialogue content through the artificial intelligence model.

[0375] In one embodiment, the editing page includes an editing function area, which is used to display function controls corresponding to one or more editing functions; the dialog content includes a first editing function to be found; and the target content includes a jump control corresponding to the first editing function.

[0376] The display module 3010 is also used to respond to the triggering operation of the jump control, close the dialogue component and switch the editing function area to the first sub-page display, and the first sub-page includes the function control corresponding to the first editing function.

[0377] In one embodiment, the conversation content includes usage inquiry information corresponding to the second editing function; the target content includes a usage tutorial link corresponding to the second editing function.

[0378] The display module 3010 is also used to display the usage tutorial data corresponding to the second editing function in response to a trigger operation on the usage tutorial link, and the usage tutorial data includes one or more of a usage tutorial video, a usage tutorial picture, and a usage tutorial document.

[0379] In one embodiment, the conversation content includes editing instructions; the output module 3030 is also used to edit the target multimedia data according to the editing instructions through an artificial intelligence model, and output the edited target multimedia data in the conversation component.

[0380] In one embodiment, the editing page includes a preview area, and the preview area is used to display the target multimedia data.

[0381] The display module 3010 is further configured to display the edited target multimedia data in the preview area in response to a preview operation on the edited target multimedia data.

[0382] In one embodiment, the output module 3030 includes a material recommendation unit, a pre-processing unit and an editing unit.

[0383] The material recommendation unit is used to obtain one or more recommended editing materials corresponding to the editing instruction according to the editing instruction through an artificial intelligence model.

[0384] The preprocessing unit is used to preprocess the target multimedia data according to each recommended editing material, and display the preprocessing effect corresponding to one or more recommended editing materials in the dialogue component.

[0385] An editing unit is used to respond to a selection operation for a target preprocessing effect, and to edit and process the target multimedia data through an artificial intelligence model according to editing instructions and recommended editing materials corresponding to the target preprocessing effect; the target preprocessing effect is at least one of the preprocessing effects corresponding to one or more recommended editing materials.

[0386] In one embodiment, the output module 3030 further includes a parameter adjustment unit.

[0387] The parameter adjustment unit is used to display an editing parameter adjustment component corresponding to the editing instruction in the dialogue component; in response to the adjustment operation on the editing parameter adjustment component, determine the target editing parameter value to be adjusted.

[0388] The editing unit is also used to edit and process the target multimedia data through an artificial intelligence model according to editing instructions, target editing materials and target editing parameter values.

[0389] In one embodiment, the output module 3030 is also used to obtain target editing materials sent to the dialogue component; and edit and process the target multimedia data according to the editing instructions and the target editing materials through the artificial intelligence model.

[0390] In one embodiment, the display module 3010 is further used to display one or more editing guide information in the dialog component in response to the editing instruction, and the editing guide information is used to guide the use of the editing function associated with the editing instruction.

[0391] In one embodiment, the editing instruction includes one or more of the following: an instruction to adjust a display effect, an instruction to adjust audio playback, and an instruction to adjust text content.

[0392] In one embodiment, the editing assistance device 3000 further includes a generating module.

[0393] Multimedia type.

[0394] A generation module is used to process the target material according to the first conversation content through an artificial intelligence model to generate target multimedia data that matches the target multimedia type; the target material includes the target material uploaded by the user, and at least one of the target materials determined by the artificial intelligence model according to the first conversation content.

[0395] The display module 3010 is also used to display the target multimedia data in the dialogue interface.

[0396] In an embodiment of the present application, the editing page corresponding to the target multimedia data supports the use of an artificial intelligence model for editing assistance. The artificial intelligence model can support the editing assistance function of the multimedia data, and can output the target content associated with the editing function according to the dialogue content input by the user in the dialogue component of the editing page, thereby more intelligently assisting the user to edit the multimedia data, reducing the difficulty of editing and improving editing efficiency.

[0397] Fig.31 FIG. 1 is a structural block diagram of an electronic device in an embodiment. Fig.31 As shown, the electronic device 3100 may include one or more of the following components: a processor 3110, and a memory 3120 coupled to the processor 3110, wherein the memory 3120 may store one or more computer programs, and the one or more computer programs may be configured to implement the methods described in the above embodiments when executed by one or more processors 3110.

[0398] The processor 3110 may include one or more processing cores. The processor 3110 uses various interfaces and lines to connect the various parts of the entire electronic device 3100, and executes various functions and processes data of the electronic device 3100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 3120, and calling data stored in the memory 3120. Optionally, the processor 3110 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 3110 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 3110, but may be implemented separately through a communication chip.

[0399] The memory 3120 may include a random access memory (RAM) or a read-only memory (ROM). The memory 3120 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 3120 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area may also store data created by the electronic device 3100 during use, etc.

[0400] It can be understood that the electronic device 3100 may include more or fewer structural elements than those in the above structural block diagram, for example, including a display device, a power module, a WiFi (Wireless Fidelity) module, a Bluetooth module, etc., and is not limited here.

[0401] An embodiment of the present application discloses a computer-readable storage medium storing a computer program, wherein the computer program implements the methods described in the above embodiments when executed by a processor.

[0402] The embodiments of the present application disclose a computer program product, including a computer program, and the computer program can be executed by a processor to implement the methods described in the above embodiments.

[0403] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a ROM, etc.

[0404] As used herein, any reference to memory, storage, database, or other medium may include nonvolatile and / or volatile memory. Suitable nonvolatile memory may include ROM, programmable ROM (Programmable ROM, PROM), erasable PROM (Erasable PROM, EPROM), electrically erasable PROM (Electrically Erasable PROM, EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which is used as an external cache memory. By way of illustration and not limitation, RAM may be in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), memory bus direct RAM (RDRAM) and direct memory bus dynamic RAM (DRDRAM).

[0405] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. Those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required for the present application.

[0406] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the above-mentioned processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0407] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0408] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0409] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0410] The above is a detailed introduction to a method, device, electronic device and storage medium for generating multimedia data disclosed in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those of ordinary skill in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for generating multimedia data, It is characterized in that include: Acquire a first dialogue content input by a user in a dialogue interface, wherein the first dialogue content includes a target multimedia type; Processing the target material according to the first conversation content through the artificial intelligence model to generate target multimedia data matching the target multimedia type; the target material includes at least one of the target material uploaded by the user and the target material determined by the artificial intelligence model according to the first conversation content; The target multimedia data is displayed in the dialogue interface.

2. The method according to claim 1, It is characterized in that Before processing the target material according to the first conversation content by the artificial intelligence model to generate target multimedia data matching the target multimedia type, the method further includes: In response to a first trigger operation on a first guide component in the dialogue interface, a material selection page is displayed; the first guide component is used to guide the user to upload a material; the material selection page includes one or more pre-stored materials; In response to a material selection operation on the material selection page, determining at least one selected target material; The selected at least one target material is sent to the dialogue interface.

3. The method according to claim 2, It is characterized in that After obtaining the first dialogue content input by the user in the dialogue interface, the method further includes: In response to the input first dialogue content, a first guidance component is displayed on the dialogue interface.

4. The method according to claim 1, It is characterized in that The dialogue interface includes an input box, and the input box is used to input dialogue content into the dialogue interface; Before processing the target material according to the first conversation content by the artificial intelligence model to generate target multimedia data matching the target multimedia type, the method further includes: Acquire at least one target material selected by a user; Displaying the selected at least one target material in the input box; In response to an adjustment operation on any target material of the input box, adjusting the any target material; In response to the triggered content sending operation, each target material contained in the input box is sent to the dialogue interface.

5. The method according to claim 4, It is characterized in that The at least one selected target material is sequentially displayed in the input box in the order of selection; and in response to an adjustment operation on any target material in the input box, the any target material is adjusted, including: In response to a position adjustment operation on a first target material in the input box, the first target material is moved from a first arrangement position to a second arrangement position; the first target material is any target material displayed in the input box; and / or, In response to a deletion operation on a second target material of the input box, the second target material is deleted from the input box, where the second target material is any target material displayed in the input box.

6. The method according to claim 4, It is characterized in that The step of sending each target material contained in the input box to the dialogue interface in response to the triggered content sending operation includes: Receive the second dialogue content input in the input box; In response to the triggered content sending operation, each target material contained in the input box and the second dialogue content are sent to the dialogue interface; The processing of the target material according to the first conversation content by using the artificial intelligence model includes: The target material sent to the dialogue interface is processed according to the first dialogue content and the second dialogue content through the artificial intelligence model.

7. The method according to any one of claims 1 to 6, It is characterized in that The method further comprises: Displaying, on the dialogue interface, a material cover corresponding to at least one target material uploaded by the user, wherein the material cover is one of the at least one target material uploaded by the user; The material quantity corresponding to the at least one target material uploaded by the user is marked on the material cover.

8. The method according to claim 1, It is characterized in that After obtaining the first dialogue content input by the user in the dialogue interface, the method further includes: Acquiring a third conversation content input by the user in the conversation interface; If the third dialogue content indicates to generate a material, outputting first inquiry information in the dialogue interface, wherein the first inquiry information is used to inquire about material features corresponding to the required material; Acquiring fourth dialogue content input by the user in the dialogue interface; The target material features contained in the fourth dialogue content are identified through an artificial intelligence model, and target material matching the target material features is generated based on the first dialogue content.

9. The method according to claim 1, It is characterized in that The processing of the target material according to the first conversation content by the artificial intelligence model to generate target multimedia data matching the target multimedia type includes: Generate one or more recommendation templates according to the first conversation content through an artificial intelligence model, and display the one or more recommendation templates in the conversation interface; In response to a template selection operation on a target recommendation template, the target material is processed according to the target recommendation template through an artificial intelligence model to generate target multimedia data matching the target multimedia type; the target recommendation template is any recommendation template.

10. The method according to claim 9, It is characterized in that After displaying the one or more recommended templates in the dialogue interface, the method further includes: In response to a preview operation on a first recommended template in the dialogue interface, displaying a template preview interface, wherein the template preview interface is used to display preview content of the first recommended template, where the first recommended template is any recommended template; In response to a template switching operation triggered in the template preview interface, switching to display preview content of a second recommended template in the template preview interface; In response to a second trigger operation on a selection control in the template preview interface, a current recommended template in the template preview interface is used as a target recommended template, and a template selection operation on the target recommended template is determined.

11. The method according to claim 9, It is characterized in that In response to the template selection operation of the target recommendation template, the target material is processed according to the target recommendation template by the artificial intelligence model to generate target multimedia data matching the target multimedia type, including: In response to a template selection operation on a target recommended template, displaying a material selection page; In response to a material selection operation on the material selection page, determining at least one selected target material; Sending the selected at least one target material to the dialogue interface; The selected at least one target material is processed according to the target recommendation template by an artificial intelligence model to generate target multimedia data matching the target multimedia type.

12. The method according to claim 11, It is characterized in that The processing of the selected at least one target material according to the target recommendation template by the artificial intelligence model to generate target multimedia data matching the target multimedia type includes: If the material quantity corresponding to the at least one selected target material does not match the material quantity required by the target recommendation template, generating a supplementary target material according to the first conversation content through an artificial intelligence model; the sum of the material quantities of the at least one selected target material and the supplementary target material matches the material quantity required by the target recommendation template; The selected at least one target material and the supplemented target material are processed according to the target recommendation template by an artificial intelligence model to generate target multimedia data matching the target multimedia type.

13. The method according to any one of claims 9 to 12, It is characterized in that After obtaining the first dialogue content input by the user in the dialogue interface, the method further includes: In response to the input first dialogue content, displaying a second guidance component on the dialogue interface, wherein the second guidance component is used to guide the user to trigger a template generation process; In response to a third trigger operation on the second guide component, inputting a template generation instruction in the dialogue interface; The generating one or more recommendation templates according to the first conversation content by using an artificial intelligence model includes: In response to the template generation instruction, one or more recommended templates are generated according to the first conversation content through an artificial intelligence model.

14. The method according to claim 1, It is characterized in that The method further comprises: Displaying an editing page corresponding to the target multimedia data; displaying a dialog component in the edit page; Obtaining a sixth dialogue content input in the dialogue component; The artificial intelligence model outputs target content associated with the editing function in the dialogue component based on the sixth dialogue content.

15. The method according to claim 14, It is characterized in that The editing page includes an editing function area, and the editing function area is used to display function controls corresponding to one or more editing functions; the sixth dialogue content includes a first editing function to be found; and the target content includes a jump control corresponding to the first editing function; After outputting the target content associated with the editing function in the dialog component, the method further includes: In response to a fifth trigger operation on the jump control, the dialog component is closed and the editing function area is switched to a first sub-page for display, wherein the first sub-page includes a function control corresponding to the first editing function.

16. The method according to claim 14, It is characterized in that The sixth dialogue content includes an editing instruction; and outputting target content associated with an editing function in the dialogue component according to the sixth dialogue content by the artificial intelligence model includes: The target multimedia data is edited and processed by the artificial intelligence model according to the editing instruction, and the edited target multimedia data is output in the dialogue component.

17. The method according to claim 16, It is characterized in that The editing page includes a preview area, and the preview area is used to display the target multimedia data; After the edited target multimedia data is output in the dialogue component, the method further comprises: In response to a preview operation on the edited target multimedia data, the edited target multimedia data is displayed in the preview area.

18. The method according to claim 16, It is characterized in that The editing process of the target multimedia data according to the editing instruction by the artificial intelligence model includes: Acquire, by the artificial intelligence model according to the editing instruction, one or more recommended editing materials corresponding to the editing instruction; Preprocessing the target multimedia data according to each of the recommended editing materials, and displaying the preprocessing effects corresponding to the one or more recommended editing materials in the dialogue component; In response to a selection operation for a target preprocessing effect, the target multimedia data is edited and processed by the artificial intelligence model according to the editing instructions and the recommended editing materials corresponding to the target preprocessing effect; the target preprocessing effect is at least one of the preprocessing effects corresponding to the one or more recommended editing materials.

19. The method according to claim 16, It is characterized in that The method further comprises: Displaying an editing parameter adjustment component corresponding to the editing instruction in the dialogue component; In response to an adjustment operation on the editing parameter adjustment component, determining an adjusted target editing parameter value; The step of editing the target multimedia data according to the editing instruction by the artificial intelligence model and outputting the edited target multimedia data in the dialogue component includes: Through the artificial intelligence model, the target multimedia data is edited and processed according to the editing instructions, target editing materials and the target editing parameter values; the target editing materials are editing materials generated by the artificial intelligence model or editing materials uploaded by users.

20. The method according to any one of claims 1 to 6, 8 to 12, 14 to 19, It is characterized in that The dialogue interface includes a call control; the method further includes: In response to an eighth trigger operation on the call control, entering a call mode; In the conversation mode, user voice data is collected by an audio collection device, and conversation content corresponding to the user voice data is input into the conversation interface.

21. A device for generating multimedia data, It is characterized in that The device comprises: A dialogue acquisition module, used to acquire a first dialogue content input by a user in a dialogue interface, wherein the first dialogue content includes a target multimedia type; a first generating module, configured to process the target material according to the first conversation content through an artificial intelligence model to generate target multimedia data matching the target multimedia type; the target material includes at least one of the target material uploaded by the user and the target material determined by the artificial intelligence model according to the first conversation content; A display module is used to display the target multimedia data in the dialogue interface.

22. An electronic device, It is characterized in that The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method according to any one of claims 1 to 20.

23. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 20 is implemented.

24. A computer program product, It is characterized in that The method comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 20 is implemented.

Images