Interaction method, apparatus, electronic device, storage medium, and computer program product

Abstract

The present disclosure relates to the technical field of computers, and particularly relates to an interaction method and device, electronic equipment, computer readable storage medium and computer program product. The interaction method comprises: receiving a first operation, wherein the first operation is used for selecting first media content in a conversation message, and the conversation message belongs to a conversation message of user interaction with an intelligent system; displaying first visual information of the first media content and input first information; and displaying second media content, wherein the second media content is associated with the first information and the first media content. Based on the interaction method, the second media content can be more conveniently and accurately generated in combination with the first information, the user can more accurately select the media content in the conversation message in the conversation process, and the efficiency and accuracy of the user interaction with the intelligent system are improved.

Description

Technical Field

[0001] This article relates to the field of computer technology, and in particular to an interactive method, apparatus, electronic device, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of AI (Artificial Intelligence) technology, users can interact with intelligent systems through various electronic devices to meet their creative needs. When interacting with intelligent systems, users can send not only text messages but also media content such as images and videos. Summary of the Invention

[0003] Based on some scenarios described herein, an interaction method is provided, comprising: receiving a first operation, wherein the first operation is used to select first media content in a session message, the session message being a session message for interaction between a user and an intelligent system; displaying first visual information of the first media content and input first information; and displaying second media content, wherein the second media content is associated with the first information and the first media content.

[0004] Based on certain scenarios described herein, an interactive device is provided, comprising: a first receiving module, a first display module, and a second display module. The first receiving module is configured to receive a first operation, wherein the first operation is used to select first media content in a session message, the session message being a session message for user-intelligent system interaction. The first display module is configured to display first visual information of the first media content and first input information. The second display module is configured to display second media content, wherein the second media content is associated with the first information and the first media content.

[0005] According to some embodiments herein, an electronic device is provided, comprising: at least one memory; and at least one processor coupled to the at least one memory. The at least one processor is configured to execute an interaction method as described in any embodiment herein, based on instructions stored in the at least one memory.

[0006] According to some of the scenarios described herein, a computer-readable storage medium is provided having computer instructions stored thereon that, when executed by a processor, implement an interactive method as described in any of the scenarios herein.

[0007] Based on some of the scenarios described herein, a computer program product is provided that, when run on a computer, enables the computer to implement an interactive method as described in any of the scenarios herein.

[0008] Other features, aspects, and advantages of this document will become clear from the following detailed description of exemplary scenarios with reference to the accompanying drawings. Attached Figure Description

[0009] The following description refers to the accompanying drawings. It should be understood that the drawings described below only relate to certain situations described herein and are not intended to limit the scope of this document. In the drawings: Figure 1 This is a schematic diagram illustrating the system architecture according to some scenarios described in this article; Figure 2 This is a flowchart illustrating the interaction methods according to some scenarios described in this article; Figure 3 This is a schematic diagram illustrating the interactive interface according to other scenarios described herein; Figure 4 This is a schematic diagram illustrating the interactive interface according to some other scenarios described in this article; Figure 5 This is a schematic diagram illustrating the interactive interface in some scenarios according to this article; Figure 6 This is a schematic diagram illustrating the interactive interface according to some other scenarios described in this article; Figure 7 This is a schematic diagram illustrating the interactive interface in some scenarios according to this article; Figure 8 This is a schematic diagram illustrating the interactive interface according to some other scenarios described in this article; Figure 9 This is a schematic diagram illustrating the interactive interface in some scenarios according to this article; Figure 10 This is a schematic diagram illustrating the interactive interface according to some scenarios described in this article; Figure 11 A block diagram of an interactive device is shown for some scenarios described herein; Figure 12 Block diagrams of electronic devices according to some scenarios described herein are shown; Figure 13 A block diagram of an electronic device according to some scenarios described herein is shown.

[0010] It should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not necessarily drawn to actual scale. The same or similar reference numerals are used in the various drawings to denote the same or similar parts. Therefore, once an item is defined in one drawing, it may not be discussed further in subsequent drawings. Detailed Implementation

[0011] The technical solution described herein will be clearly and completely described below with reference to the accompanying drawings. It should be understood that this document can be implemented in various forms and should not be construed as being limited to the situation described herein.

[0012] It should be understood that the steps described in the method embodiments herein may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this document is not limited in this respect. Unless otherwise specifically stated, the relative arrangement of components and steps set forth in these embodiments should be interpreted as merely exemplary and does not limit the scope of this document.

[0013] As used herein, the term "comprising" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". The term "based on" means "at least partially based on".

[0014] It should be noted that the concepts of "first," "second," etc., mentioned in this article are used only to distinguish different devices, modules, or units, and are not used to define the order of functions performed by these devices, modules, or units or their interdependencies. Unless otherwise specified, the concepts of "first," "second," etc., are not intended to imply that the objects described in this way must be in a given order in time, space, ranking, or any other way.

[0015] It should be noted that the terms "one" and "more" used in this document are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0016] The names of messages or information exchanged between multiple devices in this document are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0017] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this article are information and data authorized by the user or fully authorized by all parties. The collection, use and processing of related data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0018] The following detailed description, in conjunction with the accompanying drawings, is provided, but the document is not limited to these specific scenarios. These specific scenarios may be combined with each other, and identical or similar concepts or processes may not be elaborated upon in certain situations. Furthermore, in some cases, specific features, structures, or characteristics may be combined in any suitable manner by those skilled in the art.

[0019] It should be understood that this article does not impose any restrictions on how the image to be applied / processed is obtained. In some cases, it can be obtained from storage devices, such as internal or external memory. In other cases, it can be captured by using a camera. It should be noted that the acquired image can be a single captured image or a frame from a captured video, and is not particularly limited to these.

[0020] In the context of this document, "image" can refer to any of a variety of images, such as color images, grayscale images, etc. It should be noted that the type of image is not specifically limited in the context of this specification. Furthermore, an image can be any suitable image, such as a raw image obtained by a camera device, or an image from which specific processing has been performed, such as preliminary filtering, dealiasing, color adjustment, contrast adjustment, normalization, etc. It should be noted that preprocessing operations may also include other types of preprocessing operations known in the art, which will not be described in detail here.

[0021] In related technologies, when users interact with intelligent systems, they can send text messages as well as multimedia content such as images and videos. During user-intelligent system interactions, the currently sent conversation message may be related to the content of historical conversation messages. To make the intelligent system understand the currently sent conversation message more clearly and explicitly, historical conversation messages can usually be selected (referenced) while sending the current conversation message to indicate which historical conversation message the current message is related to or is used to reply to. However, related technologies can only select the entire conversation message. When the conversation message includes one or more media contents, the user cannot directly select the media content and finds it difficult to clearly describe the specific media content they want to select. The intelligent system may have difficulty determining which media content the user's conversation message is specifically targeting, affecting the efficiency and accuracy of the conversation. For example, during a user-intelligent system conversation, the user cannot select images or videos for further creation or editing. During the editing of prompts, the user's description of the image may be vague or misleading, resulting in low creation efficiency and even affecting the generated result.

[0022] Improving the efficiency and accuracy of user interaction with intelligent systems is a problem that needs to be solved. Based on this, this paper provides an interaction method that receives a first operation, which selects first media content from the conversation message between the user and the intelligent system; displays first visual information of the first media content and the input first information; and then displays second media content associated with the first information and the first media content. Based on the interaction method presented in this paper, the first media content in the conversation message can be specifically selected, and the selected first media content can be intuitively displayed to the user through the first visual information. This allows for more convenient and accurate generation of second media content by combining the first information, enabling users to select media content in the conversation message more accurately during the conversation, thus improving the efficiency and accuracy of user interaction with the intelligent system.

[0023] Figure 1 This is a schematic diagram illustrating the system architecture according to some scenarios described in this article.

[0024] Figure 1 The system architecture 100 shown includes one or more client devices 102 connected to network 101, one or more servers 103, and external services 104 for implementing the interaction methods described herein.

[0025] Network 101 can be a public network, such as the Internet, or a private network, such as a local area network (LAN) or a wide area network (WAN), or a combination thereof.

[0026] Client device 102 can be a personal computer, laptop computer, mobile phone, tablet computer (Tablet PC), personal digital assistant (PDA), portable media player (PMP), set-top box, television, video game console, digital assistant, wearable device, desktop computer, or any other computing device. Client device 102 can run an operating system that manages the hardware and software of client device 102.

[0027] Server 103 can be a rack server, router, computer, personal computer, portable digital assistant, mobile phone, laptop computer, tablet computer, camera, camcorder, netbook, desktop computer, media center, or any combination thereof.

[0028] Client device 102 can provide client-side functionality, including user-oriented input and output processing, such as displaying various media content, receiving and responding to user operations, and communication with server 103. Server 103 includes various interfaces to client device 102, processing modules, data and models, and interfaces with external service 104. Server 103 communicates with external service 104 via network 101 for task completion or information retrieval.

[0029] Figure 2 This is a flowchart illustrating the interaction methods for some scenarios described in this article. For example... Figure 2 As shown, the interaction method includes steps S202 to S206.

[0030] In step S202, a first operation is received, wherein the first operation is used to select the first media content in the session message, and the session message belongs to the session message of the user interacting with the intelligent system.

[0031] The first action triggers the selection of the first media content to be referenced, which then becomes the referenced media content. For example, the first action could be clicking the first media content in a conversation message, long-pressing the first media content in a conversation message, selecting the first media content from a list of media content, or triggering the selection of the first media content through an interactive control associated with it, etc., and is not limited to the examples given. Conversation messages are conversational messages between the user and the intelligent system, and can include text information as well as media content such as images or videos. For example, if a conversation message includes multiple images, the user can select one image as the first media content. Intelligent systems include intelligent agents, bots, applications, intelligent assistants, and other intelligent or AI-based software / hardware devices. The first media content includes images; for example, the first media content is a picture or video.

[0032] In step S204, the first visual information of the first media content and the first input information are displayed.

[0033] The first visual information is used to display the selected first media content to the user, allowing the user to confirm the selected media content and input instructions based on it. For example, the first visual information could be a thumbnail of the first media content, an icon representing the first media content, or the name of the first media content. The first information could be user-input instructions, which can be associated with the first media content to instruct the intelligent system to generate a response message based on the first information and the first media content. For example, in a conversation between the user and the intelligent system, the first information could be a prompt from the user requesting the intelligent system to regenerate the media content based on the first media content.

[0034] In step S206, second media content is displayed, wherein the second media content is associated with the first information and the first media content.

[0035] The second media content is media content generated by the intelligent system based on the first information and the first media content. For example, the second media content can be an image or a video. The second media content can be media content obtained by modifying the first media content based on the first information, or it can be media content regenerated based on the first information while referencing the first media content.

[0036] Through the interaction method described above, the first media content in the conversation message can be specifically selected, and the selected first media content can be intuitively displayed to the user through the first visual information. This makes it easier and more accurate to combine the first information to generate the second media content, enabling the user to select the media content in the conversation message more accurately during the conversation, thereby improving the efficiency and accuracy of the user's interaction with the intelligent system.

[0037] The interaction method presented in this paper can be applied not only to interactions between users and intelligent systems, but also, for example, to interactions between users in communication.

[0038] In some cases, receiving the first operation includes: displaying third media content, wherein the third media content includes at least one of media content generated in the session and media content received by the intelligent system, the third media content including the first media content; and receiving a first selection operation on the first media content, wherein the first operation includes a first selection operation.

[0039] For example, the conversation messages and third-party media content within them can be displayed on the user's interface with the intelligent system, or the third-party media content can be displayed in a separate creation interface. The third-party media content can be either media content generated by the intelligent system or media content sent by the user and received by the intelligent system. The user can select first-party media content from the third-party media content through a first selection operation. For example, third-party media content includes images, such as pictures or videos.

[0040] The above method allows users to quickly and accurately select primary media content from secondary media content. The secondary media content can be media content generated by the intelligent system or media content sent by the receiving user, making it convenient for users to select primary media content and improving the interaction efficiency between users and the intelligent system.

[0041] The following describes some methods for displaying third-media content.

[0042] In some cases, displaying third media content includes: displaying third media content in response to a second operation, wherein the second operation includes triggering a first control or inputting a first symbol.

[0043] For example, the first control can be displayed in different interfaces, such as the session interface and the authoring interface. For instance, the first control could be an add control used to add media content as the first media content. The first symbol could be a specific symbol entered by the user in the input area, such as "@", "#", etc. Symbols such as "".

[0044] Using the method described above, users can trigger the display of third media content through a second operation, making it convenient for users to select first media content from the third media content.

[0045] Third-party media content can be displayed on different interfaces.

[0046] In some cases, displaying third media content includes: displaying a first interface, wherein the first interface includes the third media content; and sliding to display the third media content in response to a third operation.

[0047] For example, the first interface can be a creation interface where users can upload media content and input instructions to create new media content. At least one third-party media content can be displayed on the first interface in various formats, such as lists, grids, or cards; this document does not limit this. If the first interface cannot display all third-party media content, a third operation can be used to switch to a different third-party media content. For example, the second operation could be a swipe, a scroll, or a trigger operation on an interactive control.

[0048] Using the methods described above, third-party media content that users can select can be displayed on the first interface, and more third-party media content can be switched and displayed based on the third operation, making it convenient for users to select the first-party media content.

[0049] In some cases, displaying third-media content includes: displaying a second interface, wherein the second interface includes session messages, and the session messages include third-media content.

[0050] For example, the second interface can be a conversation interface between the user and the intelligent system. This conversation interface includes at least one conversation message, and this message includes third-party media content. For example, the conversation message can be displayed in a message unit style, such as a message unit with a rounded rectangle border. For example, the message unit can be displayed in a message bubble style, etc., and is not limited to the examples given. The at least one conversation message can be sent by the user to the intelligent system, or it can be sent by the intelligent system to the user. For conversation messages that include third-party media content, at least one piece of third-party media content can be displayed in the message unit.

[0051] Using the methods described above, third-party media content can be displayed in the user's interactive interface with the intelligent system, from which the user can select first-party media content.

[0052] The following describes how to display the first visual information of the first media content and the first input information in different interfaces.

[0053] In some cases, the first interface includes a first display area and a first input area. The first display area includes third media content. Displaying first visual information of the first media content and first input information includes: displaying the first visual information in the first input area; and displaying the first visual information and the first information in the first input area in response to inputting the first information in the first input area.

[0054] A third media content can be displayed in the first display area so that the user can select the first media content from it. First visual information of the first media content can be displayed in the first input area. When the user enters first information in the first input area, both the first visual information and the user-entered first information can be displayed simultaneously in the first input area. The first information can be received first through the first input area, and in response to a first operation, both the first visual information and the first information can be displayed simultaneously in the first input area. The order of the first operation and the input of the first information is not restricted.

[0055] The method described above enables the display of a first display area and a first input area on the first interface, facilitating the user's selection of first media content. After selection, the first visual information and the user's input information are simultaneously displayed to the user, improving the interaction efficiency and experience between the user and the intelligent system.

[0056] In some cases, the first interface also includes at least one candidate instruction control. In response to an operation on any candidate instruction control, a prompt message corresponding to the operated candidate instruction control is displayed in the first input area. This prompt message can be part of the first information. Users can quickly select the desired processing or other function for the first media content without needing a specific description in the first information. For example, at least one candidate instruction control may include functions such as template selection, scaling, resolution adjustment, image removal, and image enhancement.

[0057] When interacting with the intelligent system, users can express their needs for content generation by inputting information, or they can choose pre-set templates to more conveniently and quickly create the media content they need using the intelligent system.

[0058] In some cases, the first interface also includes at least one candidate template. In response to triggering the first template among the at least one candidate template, the first template is displayed as selected. The second media content is associated with the first information, the first template, and the first media content. There can be one or more candidate templates, and they can be displayed to the user in different formats, such as grids, lists, or cards. The user can select the desired template from the at least one candidate template to achieve different functions; for example, candidate templates can be different content templates, different style templates, different video story templates, different processing templates, etc. The intelligent system can generate second media content that meets the user's needs based on the first information, the first media content, and the first template.

[0059] Using the methods described above, users can quickly generate second media content that meets their needs through command controls and candidate templates, improving the efficiency of user interaction with the intelligent system.

[0060] In some cases, displaying first visual information of first media content and first input information includes: displaying a first interface in response to a first selection operation on a second interface, wherein the first interface includes a first input area; displaying first visual information in the first input area; and displaying first visual information and first information in the first input area in response to inputting first information in the first input area.

[0061] For example, the second interface could be a conversation interface between the user and the intelligent system, while the first interface could be the user's creation interface. If the user selects one of the media contents from the third media content of the conversation message on the second interface as the first media content, the user can switch from the second interface to the first interface, and the first visual information of the first media content will be displayed in the first display area of ​​the first interface. If the user enters first information in the first input area of ​​the first interface, both the first visual information and the first information will be displayed simultaneously in the first input area.

[0062] Using the method described above, users can switch from the second interface to the first interface after selecting the first media content, making subsequent operations more convenient for them.

[0063] After selecting the first media content through the first operation, the user can choose not to switch to the first interface, but instead directly display the first visual information and first information related to the first media content on the second interface.

[0064] For example, such as Figure 3 As shown, the first interface 302 is the user's creation interface. The first interface 302 includes a first display area 304 and a first input area 306. The first display area 304 displays at least one third media content, which includes at least one media content generated during the session and media content received by the intelligent system. After the user selects the first media content 308 from the at least one media content, the first visual information 310 and the input first information 312 are displayed in the first input area 306 of the first interface 302.

[0065] In some cases, the second interface includes a second display area and a second input area. The second display area is used to display session messages. Displaying first visual information of the first media content and first input information includes: in response to a first selection operation in the second display area, displaying the first visual information in the second input area; in response to inputting the first information in the second input area, displaying the first visual information and the first information in the second input area.

[0066] For example, the second interface could be a conversation interface between the user and the intelligent system, and the second display area could display conversation messages. For instance, if the user selects one of the third media contents in the conversation message as the first media content in the second display area, the first visual information of the first media content can be displayed in the second input area. The user can also input first information in the second input area, and both the first visual information and the first information can be displayed simultaneously in the second input area.

[0067] For example, such as Figure 4As shown, the second interface 402 is the conversation interface between the user and the intelligent system, including multiple conversation messages. The second interface includes a second display area 404 and a second input area 406. The conversation information 408 is the intelligent system's historical replies to the user, including text content and multiple media content, where the multiple media content includes a first media content 410. The user can select the first media content 410 in the conversation message 408 through a first operation. For example, the user can long-press the first media content 410 to display multiple options and click the select (reference) option to select the first media content 410. Alternatively, a selection (reference) control can be displayed for each media content, responding to the user triggering the selection (reference) control to select the first media content 410.

[0068] Using the method described above, after a user selects the first media content on the second interface, the first visual information associated with the first media content can be directly displayed in the second input area of ​​the second interface. The user can also directly input the first information in the second input area, which improves the efficiency and experience of the user's interaction with the intelligent system.

[0069] In some situations, media content can be of different types. Type can indicate how the media content is acquired; for example, media content generated by an intelligent system is type one, while media content received by the intelligent system is type two. In some cases, the initial operation on different types of media content may differ.

[0070] In some cases, in response to the first media content belonging to a first type, a selection (reference) control is displayed in the second interface in association with the first media content, and a first trigger operation is received on the selection control as the first operation. In response to the first media content belonging to a second type, a second trigger operation is received, a selection (reference) option is displayed, and a third trigger operation is received. The first operation includes both the second and third trigger operations; the second trigger operation acts on the first media content, and the third trigger operation is used to trigger the reference option. Of course, the same first operation can be used for different types of media content.

[0071] Figure 5 and Figure 6 These are two different display styles for the second interface.

[0072] like Figure 5 As shown, the second interface 502 includes a first type of media content 504 and a second type of media content 506.

[0073] For example, such as Figure 5As shown, for media content 504, a selection (reference) control 508 can be displayed in association with media content 504 in the second interface 402, and a first trigger operation on the selection control 508 is received as the first operation. For media content 506, a second trigger operation is received to display the selection (reference) option 510, and a third trigger operation is received. The first operation includes both the second and third trigger operations. The second trigger operation acts on the first media content, and the third trigger operation is used to trigger the control 510. For example, the second trigger operation could be a long press, a click, a double click, etc.

[0074] like Figure 6 As shown, in the second interface 402, multiple options can be displayed in response to a second trigger operation on the first media content 604. For example, these options may include "Save," "Quote," "Share," "Feedback," and "Delete." The user can click the "Quote" option 604 to select the first media content 602, and a first visual information 608 of the first media content 602 will be displayed in the second input area 606. The first visual information 608 is a thumbnail of the first media content 602. First information 610 can be displayed in the second input area 606. The first information 610 is the user-input instruction information, including the user's requirements for the media content generated by the intelligent system and other instructions related to the first media content 602, used to instruct the intelligent system to generate media content that meets the user's requirements based on the first media content 602 and the first information 610.

[0075] The following describes how to input the first piece of information.

[0076] In some cases, displaying first visual information of the first media content and input first information includes: displaying the first visual information; receiving a fourth operation, wherein the fourth operation is used to select the first media content; displaying first identification information of the first media content; and in response to inputting second information, displaying the first identification information and the second information as the first information.

[0077] For example, the first identification information of the first media content can be index information, instruction information, etc., and can be displayed in the form of text, text hyperlinks, etc. The first identification information forms a mapping relationship with the first media content. For example, the first identification information can include any one or more of the following: the type, order, filename, and content theme of the first media content. The second information is user-inputted instruction information, which can be associated with the first media content. For example, the second information can be a prompt indicating that the user requests the intelligent system to regenerate the media content based on the first media content. When the user inputs the second information, the first identification information and the second information are displayed, and the first identification information and the second information are used as the first information.

[0078] By using the method described above, the first media content can be selected through the fourth operation, and the first identification information of the first media content can be displayed. The first information input by the user may include the first identification information and the second information, making the expression of the first information more accurate. The intelligent system can respond more accurately to the first media content selected by the user, thereby improving the efficiency and accuracy of the interaction between the user and the intelligent system.

[0079] Users can select multiple first media content. In some cases, the first media content includes multiple first media content, and the first identification information includes multiple first identification information. In response to inputting second information, displaying the first identification information and the second information includes: in response to inputting second information for each first media content, displaying the first identification information of each first media content and the second information corresponding to each first media content as the first information.

[0080] For example, a user can select multiple media contents from the same session message as the first media content, or multiple media contents from different session messages as the first media content. Each first media content has corresponding first identification information. When entering a message, the user can describe the first media content using the first identification information of different first media content. In this case, the first information includes the first identification information of each first media content and second information describing each first media content.

[0081] By using the method described above, the first identification information and the second information of multiple first media content can be used as the first information, enabling users to input the second information more conveniently and accurately for different first media content. This facilitates the intelligent system in matching the first identification information with the first media content described by the user, thereby improving the efficiency and accuracy of user interaction with the intelligent system.

[0082] In some cases, receiving a fourth operation includes: in response to a fifth operation, displaying fourth media content, wherein the fourth media content includes the first media content; and receiving a second selection operation, wherein the second selection operation is used to select the first media content from the fourth media content, and the fourth operation includes the fifth operation and the second selection operation.

[0083] For example, the fifth operation could be a trigger operation on the second control, or it could be the user entering a second symbol or special command in the input area. For example, the second symbol could be "@", "#", etc. Symbols such as "".

[0084] For example, the fourth media content may include at least one first media content, from which the user can select the first media content they wish to reference. For example, the fourth media content may include multiple selected (referenced) first media contents. For example, the fourth media content may also include media content other than the first media content in the session message, and at least one media content from the stored media content.

[0085] In response to selecting media content other than the first media content from the fourth media content, the selected media content is designated as the first media content, and its visual and identifier information is displayed as the first visual and identifier information. Users can then input second information. This allows users to more conveniently and efficiently reference media content and input second information.

[0086] Using the method described above, users can display the fourth media content through the fifth operation and select the first media content from it, thus improving the convenience and efficiency of the operation.

[0087] For example, the fourth operation could also be an operation on the first visual information of the first media content, to select the first media content. For example, the fourth operation could be an operation such as long-pressing the first visual information or clicking on the first visual information.

[0088] For example, such as Figure 7 As shown, the user can input the character "@" in the second input area 702 of the second interface 402. In response to the user's input of the character "@", multiple pieces of fourth-media content and corresponding identification information are displayed. For example... Figure 7 As shown, the identification information is used to indicate the type and order of each fourth media content. Visual information corresponding to each fourth media content can also be displayed, such as thumbnails. Users can select media content as the first media content from the fourth media content; for example, the user selects media content 704 as the first media content. When the user selects media content 704, the identification information 706 of media content 704 can be displayed in the second input area 702. For example, if the user selects video, image 1, and image 2 in sequence, and enters the second information after each selection, the final first information obtained will be "The main character in the video is changed to the image of image 1, and there is a cat from image 2 next to him."

[0089] In some cases, the first identification information is displayed in the input area, which includes a first input area of ​​a first interface or a second input area of ​​a second interface. In response to the input of second information, displaying the first identification information and the second information includes: in response to the input of the second information in the input area, displaying the second information after the first identification information.

[0090] For example, the first interface could be the user's creation interface, and the second interface could be the user's dialogue interface with the intelligent system. After the user selects the first media content through the fourth operation, the first identification information of the first media content can be displayed in the input area, and if the user enters the second information, the second information can be displayed after the first identification information in the order of input.

[0091] By using the method described above, the first identification information and the second information of the first media content can be displayed in the display area, making it easier for users to identify the different first media content they have selected and their corresponding descriptions, thereby improving the interactive experience.

[0092] When interacting with the intelligent system, users can not only select the first media content in the conversation message, but also upload stored media content, enabling the intelligent system to combine different media content to generate new media content.

[0093] In some cases, in response to the sixth operation, the fifth media content is displayed, wherein the fifth media content includes at least one of the media content in the session message and the stored media content; a seventh operation is received, wherein the seventh operation is used to select the sixth media content from the fifth media content; and second visual information of the sixth media content is displayed.

[0094] For example, the sixth operation could be a click, long press, or other action on the first visual information, or it could be a trigger action on a control. The fifth media content includes media content from conversation messages as well as stored media content. Stored media content can include local media content stored on the user's electronic device, or cloud media content stored in the cloud. If the user selects the sixth media content from the fifth media content via the seventh operation, the second visual information of the sixth media content is displayed; for example, the second visual information could be a thumbnail of the sixth media content or an icon representing the sixth media content.

[0095] Using the methods described above, users can not only reference media content in conversation messages, but also upload media content beyond that in conversation messages, so that the intelligent system can generate media content that meets the user's needs, thereby improving the efficiency and experience of user interaction with the intelligent system.

[0096] In some cases, the seventh operation is used to select and add sixth media content, and the second visualization information of the sixth media content includes: the first visualization information of the first media content, the second visualization information of the sixth media content, and the input third information; and the seventh media content is displayed, wherein the seventh media content is associated with the third information, the first media content, and the sixth media content.

[0097] For example, after the user selects the sixth media content through the seventh operation, visual information of the first media content and visual information of the second media content can be displayed simultaneously in the display area of ​​the first or second interface. The third information is the user-input instruction, which can be associated with the first and sixth media content. For example, the third information could be a prompt indicating that the intelligent system is requesting a regeneration of media content based on the first and sixth media content. The seventh media content can be the media content generated by the intelligent system based on the third information, the first media content, and the sixth media content.

[0098] By using the method described above, a sixth media content can be added after the first media content has been selected, and a new seventh media content can be generated based on the first media content, the sixth media content, and the corresponding third information. This improves the efficiency and convenience of user interaction with the intelligent system and enhances the interactive experience.

[0099] For example, such as Figure 6 As shown, an add control 612 is displayed in the first input area 606. The user can trigger the add control 612 to display at least one fifth media content, and select a sixth media content from at least one fifth media content through a seventh operation.

[0100] For example, such as Figure 3 As shown, in the first interface 302, the user can also continue to add a sixth media content they want to select. For example, they can select the first media content from the third media content, or by triggering the add control 314, the fifth media content can be displayed, and the sixth media content can be selected from the fifth media content to add. If there are too many fifth media contents and it is impossible to display all media content at the same time, the user can display different media content by sliding or triggering relevant controls.

[0101] like Figure 8 As shown, in response to a triggering operation of the add control 314 on the first interface 302 or the control 614 on the second interface 402, at least one fifth media content is displayed. The fifth media content can be an image or a video. The user can select a sixth media content 802 from the fifth media content. After the user selects the sixth media content 802, second visual information of the sixth media content 802 can be displayed in the first input area 306 or the second input area 608. For example, as Figure 3 As shown, the second visualization information 316 of the sixth media content 802 can be displayed in the first input area 306.

[0102] In some cases, the seventh operation is used to select the sixth media content and replace the first media content with the sixth media content. The second visualization information of the sixth media content includes: displaying the second visualization information of the sixth media content and the first information; displaying the eighth media content, wherein the eighth media content is associated with the first information and the sixth media content.

[0103] For example, after a user selects the sixth media content through the seventh operation, instead of adding a reference to the sixth media content, the first media content is replaced with the sixth media content. In this case, after selecting the sixth media content, the first visual information of the first media content will also be replaced with the second visual information of the sixth media content. The eighth media content can be media content generated by the intelligent system based on the first information and the sixth media content.

[0104] Using the methods described above, users can replace media content more conveniently and quickly, improving the efficiency and experience of user interaction with the intelligent system.

[0105] When the first media content is replaced with the sixth media content, the first identification information and the sixth media content form a mapping relationship so that the intelligent system can accurately generate the eighth media content.

[0106] For example, by triggering a replacement operation on the first media content 308, the following can be displayed: Figure 8 The fifth media content is shown, and a sixth media content is selected from it to replace it. For example, as shown... Figure 9 As shown, a user can long-press the first visual information to display the first media content and a replacement control 902. The user can trigger the replacement control 902 to initiate a replacement operation on the first media content. For example, in response to triggering the replacement control 902, a fifth media content is displayed, including at least one media content from the media content in the session message and stored media content. In response to selecting a sixth media content from the fifth media content, the second visual information of the sixth media content 802 is displayed to replace the first visual information.

[0107] In some cases, the identification information of each first media content is used to indicate the type and order of each first media content. The interaction method further includes: receiving a ninth operation, wherein the ninth operation includes a deletion operation on any first media content among a plurality of first media content; updating first information, wherein the updated first information deletes the identification information of the deleted first media content and updates the identification information of the remaining first media content.

[0108] For example, the identification information can indicate whether the first media content is an image or a video, and also indicate the order in which the first media content is referenced within that type. The ninth operation can be a click, long press, or other operation on the first visual information, or it can be a trigger operation on a certain control. For example, the ninth operation can be clicking the delete control displayed associated with the first visual information to delete the corresponding first media content. If the user has referenced multiple media content, after deleting the first media content, the identification information related to the first media content in the first information will be deleted, and the identification information of the remaining media content in the first information will be updated, such as updating the sequence number of the remaining media content.

[0109] like Figure 3 As shown, the first media content 308 can be deleted by triggering the delete control 318 displayed in the first visual information 310. When the user deletes the first media content 308, the content of the first information 312 will be updated, deleting the identification information associated with the first media content 308 and updating the identification information of other media content. Through this method, the first information can be automatically updated when the user deletes the first media content, improving the efficiency and accuracy of user interaction with the intelligent system and enhancing the user experience.

[0110] In some cases, displaying second media content includes: receiving an eighth operation, wherein the eighth operation is used to send first media content and first information; displaying a first session message, wherein the first session message includes first visual information and first information of the first media content; and displaying a second session message, wherein the second session message includes second media content, the second media content being generated based on the first media content and the first information.

[0111] For example, the eighth operation could be a trigger operation on a certain control. The user can send the first media content and the first information to the intelligent system through the eighth operation. The first session message can be a session message sent by the user to the intelligent system, including the first visual information and the first information of the first media content. The second session message can be the intelligent system's response to the first session message, including second media content generated based on the first media content and the first information.

[0112] For example, such as Figure 10As shown, the user can trigger the send control 1002 to perform the eighth operation, sending the first media content and the first information to the intelligent system. The second interface 402 displays the first session message 1004, which includes the first visual information and the first information of multiple first media contents; the second interface 402 also displays the second session message 1006, which includes the second media content, generated based on the first media content and the first information. The first media content and the first information can be displayed in one session unit or in multiple session units. The generation and display of the seventh and eighth media contents are similar to the methods described above and will not be repeated here.

[0113] Using the methods described above, users can send the referenced media content and related instruction information to the intelligent system to more accurately generate new media content that meets their requirements.

[0114] Figure 11 A block diagram of an interactive device is shown for some scenarios described herein.

[0115] like Figure 11 As shown, the interactive device 11 includes a first receiving module 111, a first display module 112, and a second display module 113. The first receiving module 111 is configured to receive a first operation, wherein the first operation is used to select first media content in a session message, the session message being a session message for user-intelligent system interaction. The first display module 112 is configured to display first visual information of the first media content and the input first information. The second display module 113 is configured to display second media content, wherein the second media content is associated with the first information and the first media content.

[0116] The interactive device described above receives a first operation, which selects first media content from the conversation message between the user and the intelligent system; displays first visual information of the first media content and the input first information; and then displays second media content associated with the first information and the first media content. Based on this interactive device, the user can specifically select the first media content from the conversation message and intuitively display the selected first media content to the user through the first visual information. This allows for more convenient and accurate generation of second media content by combining the first information, enabling the user to more accurately select media content from the conversation message during the conversation, thus improving the efficiency and accuracy of the user's interaction with the intelligent system.

[0117] In some cases, the first receiving module 111 is configured to display third media content, wherein the third media content includes at least one of media content generated in the session and media content received by the intelligent system, and the third media content includes the first media content; and to receive a first selection operation on the first media content, wherein the first operation includes a first selection operation.

[0118] In some cases, the first receiving module 111 is configured to display third media content in response to a second operation, wherein the second operation includes triggering a first control or inputting a first symbol.

[0119] In some cases, the first receiving module 111 is configured to display a first interface, wherein the first interface includes third media content; in response to a third operation, the third media content is displayed by sliding.

[0120] In some cases, the first interface includes a first display area and a first input area, the first display area includes third media content, and the first display module 112 is configured to display first visual information in the first input area; in response to inputting first information in the first input area, the first visual information and the first information are displayed in the first input area.

[0121] In some cases, the first receiving module 111 is configured to display a second interface, wherein the second interface includes session messages, and the session messages include third media content.

[0122] In some cases, the first display module 112 is configured to display a first interface in response to a first selection operation on a second interface, wherein the first interface includes a first input area; displays first visual information in the first input area; and displays the first visual information and the first information in the first input area in response to inputting first information in the first input area.

[0123] In some cases, the second interface includes a second display area and a second input area. The second display area is used to display session messages. The first display module 112 is configured to display first visual information in the second input area in response to a first selection operation of first media content in the second display area; and to display the first visual information and the first information in the second input area in response to inputting first information in the second input area.

[0124] In some cases, the first display module 112 is configured to display first visual information; receive a fourth operation, wherein the fourth operation is used to select first media content; display first identification information of the first media content; and in response to inputting second information, display the first identification information and the second information as the first information.

[0125] In some cases, the first media content includes multiple first media content items, the first identification information includes multiple first identification information items, and the first display module 112 is configured to display the first identification information of each first media content item and the second information corresponding to each first media content item as the first information item in response to inputting second information for each first media content item.

[0126] In some cases, the first display module 112 is configured to display fourth media content in response to a fifth operation, wherein the fourth media content includes the first media content; and to receive a second selection operation, wherein the second selection operation is used to select the first media content from the fourth media content, the fourth operation including the fifth operation and the second selection operation.

[0127] In some cases, the first identification information is displayed in the input area, which includes the first input area of ​​the first interface or the second input area of ​​the second interface. The first display module 112 is configured to display the second information after the first identification information in response to the input of the second information in the input area.

[0128] In some cases, the interactive device 11 further includes a third display module 114, a second receiving module 115, and a fourth display module 116. The third display module 114 is configured to display fifth media content in response to a sixth operation, wherein the fifth media content includes at least one of the media content in the session message and stored media content. The second receiving module 115 is configured to receive a seventh operation, wherein the seventh operation is used to select a sixth media content from the fifth media content. The fourth display module 116 is configured to display second visual information of the sixth media content.

[0129] In some cases, the seventh operation is used to select and add sixth media content, and the fourth display module 116 is configured to display first visual information of the first media content, second visual information of the sixth media content, and input third information; and to display seventh media content, wherein the seventh media content is associated with the third information, the first media content, and the sixth media content.

[0130] In some cases, the seventh operation is used to select the sixth media content and replace the first media content with the sixth media content. The fourth display module 116 displays the second visual information and the first information of the sixth media content; and displays the eighth media content, wherein the eighth media content is associated with the first information and the sixth media content.

[0131] In some cases, the second display module 113 is configured to receive an eighth operation, wherein the eighth operation is used to send first media content and first information; display a first session message, wherein the first session message includes first visual information and first information of the first media content; and display a second session message, wherein the second session message includes second media content, the second media content being generated based on the first media content and the first information.

[0132] Figure 12 A block diagram of an electronic device according to some scenarios described herein is shown.

[0133] like Figure 12 As shown, the electronic device 12 includes: at least one memory 121; and at least one processor 122 coupled to the at least one memory 121, the at least one processor 122 being configured to perform an interaction method as described above based on instructions stored in the at least one memory 121.

[0134] Memory 121 is used to store one or more computer-readable instructions. Memory 121 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory, dynamic random access memory, static random access memory, read-only memory, and flash memory. Memory 121 may, for example, store operating systems, application programs, boot loaders, databases, and other programs, as well as various application programs and various data.

[0135] Processor 122 is used to execute computer-readable instructions to implement the interactive method in any of the aforementioned scenarios. The specific implementation of each step of the method can be found in the scenarios described above, and repeated details will not be repeated here.

[0136] The processor 122 can be various processing devices, such as a central processing unit (CPU), a network processor, etc.; it can also be a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The CPU can be based on x86 or ARM architectures, etc.

[0137] The processor 122 and the memory 121 can communicate with each other directly or indirectly. For example, the processor 122 and the memory 121 can communicate via a network. The network can include a wireless network, a wired network, and / or any combination of wireless and wired networks. The processor 122 and the memory 121 can also communicate with each other via a system bus, which is not limited herein.

[0138] It should be noted that Figure 12The components of the interactive device 12 shown are merely exemplary and not limiting. The interactive device 12 may have other components depending on the specific application requirements. The processor 122 can control other components in the interactive device 12 to perform desired functions.

[0139] The interactive device 12 can be implemented by software, firmware and / or hardware, and can be integrated into a device with the relevant application installed.

[0140] The electronic device described above receives a first operation, which is used to select first media content in a conversation message between the user and the intelligent system; displays first visual information of the first media content and the input first information; and then displays second media content associated with the first information and the first media content. The electronic device described above can specifically select the first media content in the conversation message and intuitively display the selected first media content to the user through the first visual information. It can also more conveniently and accurately combine the first information to generate the second media content, enabling the user to more accurately select media content in the conversation message during the conversation, thus improving the efficiency and accuracy of the user's interaction with the intelligent system.

[0141] Figure 13 A block diagram of an electronic device according to some scenarios described herein is shown.

[0142] Figure 13 The electronic device 13 shown can be a computer system with a dedicated hardware structure, which can perform corresponding functions when the relevant application is installed.

[0143] Electronic devices include, but are not limited to, various mobile terminals and fixed terminals such as digital televisions and desktop computers.

[0144] like Figure 13 As shown, the Central Processing Unit (CPU) 131 performs various processes based on programs stored in Read-Only Memory (ROM) 132 or programs loaded from storage section 138 into Random Access Memory (RAM) 133. In RAM 133, data required when the CPU 131 performs various processes is stored as needed. The CPU is merely exemplary; it can also be other types of processors, such as the various processors described above. ROM 132, RAM 133, and storage section 138 can be various forms of computer-readable storage media. It should be noted that although... Figure 13The diagram shows ROM 132, RAM 133 and storage section 138, but one or more of them may be combined or located in the same or different memory or storage modules.

[0145] CPU 131, ROM 132 and RAM 133 are interconnected via bus 134. Input / output interface 135 is also connected to bus 134.

[0146] The following components are connected to the input / output interface 135: input section 136, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 137, including displays such as cathode ray tubes, liquid crystal displays, speakers, vibrators, etc.; storage section 138, including hard disks, magnetic tapes, etc.; and communication section 139, including network interface cards such as LAN cards, modems, etc. Communication section 139 allows communication processing via a network such as the Internet. It is easy to understand that, although... Figure 13 The portion of the electronic device 13 shown communicates via bus 134, but it may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of wireless and wired networks.

[0147] As needed, drive 1310 is also connected to input / output interface 135. Removable media 1311, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 1310 as needed, so that computer programs read from them can be installed into storage section 138 as needed.

[0148] When the above series of processes are implemented through software, the program constituting the software can be installed from a network such as the Internet or a storage medium such as a removable medium 1311.

[0149] According to this document, the processes described in the above-referenced flowchart can be implemented as computer software programs. For example, some scenarios described herein include a computer program product that, when run on a computer, causes the computer to implement the interactive methods of any of the aforementioned scenarios. The computer program product includes computer instructions carried on a computer-readable medium, containing program code for performing the methods shown in the flowchart. In such a scenario, the computer instructions can be downloaded and installed from a network via communication section 139, or installed from storage section 138, or installed from ROM 132. When the computer program is executed by CPU 131, the interactive methods described herein are performed.

[0150] The computer program product described above can receive a first operation, which is used to select first media content in a conversation message between the user and the intelligent system; display first visual information of the first media content and the input first information; and then display second media content associated with the first information and the first media content. The computer program product described above can specifically select the first media content in the conversation message and intuitively display the selected first media content to the user through the first visual information. It can also more conveniently and accurately combine the first information to generate the second media content, enabling the user to more accurately select media content in the conversation message during the conversation, thereby improving the efficiency and accuracy of the user's interaction with the intelligent system.

[0151] It should be noted that, in the context of this document, a computer-readable medium can be a tangible medium that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0152] A computer-readable medium may be a computer-readable storage medium, a computer-readable signal medium, or any combination thereof.

[0153] Computer-readable storage media include, but are not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0154] This document also provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement an interactive method for any of the aforementioned scenarios.

[0155] The computer-readable storage medium described above can receive a first operation, which is used to select first media content in a session message of interaction between a user and an intelligent system; display first visual information of the first media content and first input information; and then display second media content associated with the first information and the first media content. The computer-readable storage medium described above can specifically reference the first media content in the session message, and intuitively display the referenced content to the user through the first visual information. It can also more conveniently combine the first information to generate second media content, making it easier for the user to reference the media content in the session message during interaction with the intelligent system, thereby improving the efficiency of user interaction with the intelligent system.

[0156] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, radio frequency, etc., or any suitable combination thereof.

[0157] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0158] In one scenario, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform any of the aforementioned scenarios. For example, the instructions may be embodied in computer program code.

[0159] In this document, computer program code for performing the operations described herein may be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer may be connected to the user's computer via any type of network, or it may be connected to an external computer.

[0160] The flowcharts and block diagrams in the accompanying figures illustrate the architecture, functionality, and operation of possible implementations of the systems, methods, and computer program products according to the various scenarios described herein. In this respect, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the figures. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0161] The functions described above can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), systems-on-a-chip (SoCs), complex programmable logic devices, and so on.

[0162] While certain specific situations described herein have been illustrated in detail by way of examples, those skilled in the art should understand that these examples are for illustrative purposes only and not intended to limit the scope of this document. Those skilled in the art should understand that modifications can be made to these situations without departing from the scope and spirit of this document. The scope of this document is defined by the appended claims.

Claims

1. An interaction method, comprising: Receive a first operation, wherein the first operation is used to select a first media content in a session message, the session message being a session message of interaction between the user and the intelligent system; Displaying first visual information of the first media content and the first input information; Display second media content, wherein the second media content is associated with the first information and the first media content.

2. The interaction method according to claim 1, wherein, The receiving first operation includes: Displaying third media content, wherein the third media content includes at least one of the media content generated in the session and the media content received by the intelligent system, and the third media content includes the first media content; Receive a first selection operation on the first media content, wherein the first operation includes the first selection operation.

3. The interaction method according to claim 2, wherein, The content displayed as third-party media includes: In response to a second operation, the third media content is displayed, wherein the second operation includes triggering a first control or inputting a first symbol.

4. The interaction method according to claim 2, wherein, The content displayed as third-party media includes: Display a first interface, wherein the first interface includes the third media content; In response to the third operation, the third media content is displayed by sliding.

5. The interaction method according to claim 4, wherein, The first interface includes a first display area and a first input area. The first display area includes the third media content. The first visual information for displaying the first media content and the first input information include: Display the first visual information in the first input area; In response to inputting the first information in the first input area, the first visual information and the first information are displayed in the first input area.

6. The interaction method according to claim 2, wherein, The content displayed as third-party media includes: The second interface is displayed, wherein the second interface includes the session messages, and the session messages include the third media content.

7. The interaction method according to claim 6, wherein, The first visual information for displaying the first media content and the first input information include: In response to the first selection operation on the second interface, a first interface is displayed, wherein the first interface includes a first input area; Display the first visual information in the first input area; In response to inputting the first information in the first input area, the first visual information and the first information are displayed in the first input area.

8. The interaction method according to claim 6, wherein, The second interface includes a second display area and a second input area. The second display area is used to display the session message. The first visual information displaying the first media content and the first input information include: In response to the first selection operation in the second display area, the first visual information is displayed in the second input area; In response to inputting the first information in the second input area, the first visual information and the first information are displayed in the second input area.

9. The interaction method according to claim 1, wherein, The first visual information for displaying the first media content and the first input information include: Display the first visual information; Receive a fourth operation, wherein the fourth operation is used to select the first media content; Display the first identification information of the first media content; In response to the input of second information, the first identification information and the second information are displayed as the first information.

10. The interaction method according to claim 9, wherein, The first media content includes multiple first media content items, the first identification information includes multiple first identification information items, and the step of displaying the first identification information and the second information in response to inputting second information includes: In response to inputting second information for each first media content, the system displays first identification information for each first media content and second information corresponding to each first media content as the first information.

11. The interaction method according to claim 9, wherein, The fourth receiving operation includes: In response to the fifth operation, fourth media content is displayed, wherein the fourth media content includes the first media content; A second selection operation is received, wherein the second selection operation is used to select the first media content from the fourth media content, and the fourth operation includes the fifth operation and the second selection operation.

12. The interaction method according to claim 11, wherein, The first identification information is displayed in an input area, which includes a first input area of ​​a first interface or a second input area of ​​a second interface. The step of displaying the first identification information and the second information in response to inputting second information includes: In response to the input of the second information in the input area, the second information is displayed after the first identification information.

13. The interaction method according to claim 1, further comprising: In response to the sixth operation, the fifth media content is displayed, wherein the fifth media content includes at least one of the media content in the session message and the stored media content; Receive a seventh operation, wherein the seventh operation is used to select a sixth media content from the fifth media content; The second visual information displays the sixth media content.

14. The interaction method according to claim 13, wherein, The seventh operation is used to select and add the sixth media content, and the second visual information for displaying the sixth media content includes: Displaying first visual information of the first media content, second visual information of the sixth media content, and third input information; Displays a seventh media content, wherein the seventh media content is associated with the third information, the first media content, and the sixth media content.

15. The interaction method according to claim 13, wherein, The seventh operation is used to select the sixth media content and replace the first media content with the sixth media content, wherein the second visual information for displaying the sixth media content includes: Displaying the second visual information and the first information of the sixth media content; Display eighth media content, wherein the eighth media content is associated with the first information and the sixth media content.

16. The interaction method according to any one of claims 1-15, wherein, The content displayed on the second media includes: Receive an eighth operation, wherein the eighth operation is used to send the first media content and the first information; Display a first session message, wherein the first session message includes first visual information of the first media content and the first information; The second session message is displayed, wherein the second session message includes the second media content, which is generated based on the first media content and the first information.

17. An interactive device, comprising: The first receiving module is configured to receive a first operation, wherein the first operation is used to select a first media content in a session message, the session message being a session message of interaction between the user and the intelligent system; The first display module is configured to display first visual information of the first media content and first input information; The second display module is configured to display second media content, wherein the second media content is associated with the first information and the first media content.

18. An electronic device comprising: At least one memory; as well as At least one processor coupled to the at least one memory, the at least one processor being configured to execute the interaction method as described in any one of claims 1 to 16 based on instructions stored in the at least one memory.

19. A computer-readable storage medium having stored thereon computer instructions that, when executed by a processor, implement the interactive method as described in any one of claims 1 to 16.

20. A computer program product, when run on a computer, causes the computer to implement the interactive method as described in any one of claims 1 to 16.

Images