Interaction method and apparatus in communication scenario, and computer device, storage medium and computer program product

Abstract

The present application relates to an interaction method and apparatus in a communication scenario, and a computer device, a storage medium and a computer program product. The method may be applied to the technical fields of instant messaging, etc., and comprises: in a conversation page of an application program, displaying a first conversation message sent by a first object (S202); when the first conversation message includes key information, and prompt information with respect to a second object, displaying an interaction picture corresponding to the key information (S204); and when the first conversation message includes a virtual prop, displaying the virtual prop in the interaction picture; or when the first conversation message includes a virtual expression, displaying that at least one virtual image in the interaction picture presents an expression corresponding to the virtual expression, such that the virtual image presents the expression corresponding to the virtual expression (S206).

Description

Interactive methods, devices, computer equipment, storage media, and computer program products in communication scenarios

[0001] This application claims priority to Chinese Patent Application No. 2024104910122, filed on April 22, 2024, entitled "Interactive Method, Apparatus, Computer Equipment and Storage Medium in Communication Scenarios", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of instant messaging technology, and in particular to an interactive method, apparatus, computer device, storage medium and computer program product in a communication scenario. Background Technology

[0003] In instant messaging applications, users typically communicate with others through one-on-one chats or group chats. During special occasions (such as holidays), they might send appropriate emoticons to increase engagement. However, this form of interaction is relatively limited and cannot effectively enhance the overall interaction experience. Summary of the Invention

[0004] According to various embodiments of this application, an interaction method, apparatus, computer device, computer-readable storage medium, and computer program product in a communication scenario are provided.

[0005] This application provides an interaction method in a communication scenario, executed by a computer device, the method comprising:

[0006] Display the first session message sent by the first object in the application's session page;

[0007] When the first session message contains key information and prompts for the second object, an interactive screen corresponding to the key information is displayed. The interactive screen includes the virtual image of the first object and the virtual image of the second object.

[0008] If the first conversation message contains a virtual item, the virtual item is displayed in the interactive screen; or, if the first conversation message contains a virtual emoticon, at least one virtual character in the interactive screen displays an emoticon corresponding to the virtual emoticon.

[0009] This application also provides an interactive device in a communication scenario, the device comprising:

[0010] The first display module is used to display the first session message sent by the first object in the session page of the application;

[0011] The second display module is used to display an interactive screen corresponding to the key information when the first session message contains key information and prompt information for the second object. The interactive screen includes a virtual image of the first object and a virtual image of the second object.

[0012] The third display module displays the virtual prop in the interactive screen when the first conversation message contains a virtual prop; or, when the first conversation message contains a virtual emoticon, displays at least one virtual character in the interactive screen displaying an emoticon corresponding to the virtual emoticon.

[0013] This application also provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the interaction method in the communication scenario.

[0014] This application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the interaction method in the communication scenario.

[0015] This application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the interaction method in the communication scenario.

[0016] Details of one or more embodiments of this application are set forth in the following drawings and description. Other features and advantages of this application will become apparent from the specification, drawings, and claims. Attached Figure Description

[0017] Figure 1 is an application environment diagram of the interaction method in a communication scenario in one embodiment;

[0018] Figure 2 is a flowchart illustrating an interaction method in a communication scenario in one embodiment;

[0019] Figure 3A is a schematic diagram of an interactive screen in one embodiment;

[0020] Figure 3B is a schematic diagram of the interactive screen in another embodiment;

[0021] Figure 3C is a schematic diagram of the interactive screen in another embodiment;

[0022] Figure 4 is a flowchart illustrating the interaction method in a communication scenario in another embodiment;

[0023] Figure 5 is a schematic diagram of a page in one embodiment where virtual images of other objects are added to the interactive screen;

[0024] Figure 6 is a schematic diagram of a page in another embodiment where virtual images of other objects are added to the interactive screen;

[0025] Figure 7 is a flowchart illustrating the display of an interactive screen in one embodiment;

[0026] Figure 8 is a schematic diagram of a page for taking a group photo of virtual characters in an interactive screen in one embodiment;

[0027] Figure 9 is a schematic diagram of a page that displays a prompt after saving a group photo image or video in one embodiment;

[0028] Figure 10 is a flowchart illustrating the interaction method in a communication scenario in another embodiment;

[0029] Figure 11 is a structural block diagram of an interactive device in a communication scenario in one embodiment;

[0030] Figure 12 is a structural block diagram of an interactive device in a communication scenario in another embodiment;

[0031] Figure 13 is an internal structure diagram of a computer device in one embodiment. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0033] It should be noted that in the following description, the terms "first, second, and third" are used only to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, and third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0034] The interactive method in the communication scenario provided in this application embodiment can be applied to the application environment shown in Figure 1. Terminal 102 communicates with server 104 and second terminal 106 via a network. The data storage system can store the data that server 104 needs to process. The data storage system can be integrated on server 104 or placed on the cloud or other network servers.

[0035] The first terminal 102 displays a first conversation message sent by a first object in the application's conversation page. When the first conversation message contains key information and prompts for a second object, an interactive screen corresponding to the key information is displayed. The interactive screen includes virtual avatars of the first and second objects. If the first conversation message contains virtual items, the virtual items are displayed in the interactive screen. Alternatively, if the first conversation message contains virtual emoticons, at least one virtual avatar in the interactive screen displays an emoticon corresponding to the virtual emoticon. After displaying the interactive screen, the first terminal 102 can also send object information of each object and identification information of the group photo template in the interactive screen to the server 104. The server 104 can send the virtual avatar and identification information corresponding to the object information to the second terminal 106, so that the second terminal 106 can display the interactive screen based on the identification information.

[0036] The first terminal 102 and the second terminal 106 can be smartphones, tablets, laptops, desktop computers, IoT devices, and portable wearable devices, respectively. IoT devices can be smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices, etc. Portable wearable devices can be smartwatches, smart bracelets, and head-mounted devices, etc.

[0037] Server 104 can be a standalone physical server or a service node in a blockchain system. These service nodes form a peer-to-peer (P2P) network, where the P2P protocol is an application-layer protocol running on top of the Transmission Control Protocol (TCP). Furthermore, server 104 can also be a server cluster composed of multiple physical servers, and can be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0038] In one embodiment, as shown in Figure 2, an interaction method in a communication scenario is provided. This method can be executed by a computer device, such as the server or terminal in Figure 1, or by the server and terminal working together. Taking the execution of this method by the terminal in Figure 1 as an example, it includes the following steps:

[0039] S202, Display the first session message sent by the first object in the application's session page.

[0040] This application can be an instant messaging application, including personal instant messaging applications (hereinafter referred to as personal communication applications) and enterprise instant messaging applications (hereinafter referred to as enterprise communication applications). The personal communication application can be a communication application with personal social attributes, while the enterprise communication application can be a communication application with both work and instant messaging attributes. That is, the enterprise communication application can be used for both instant messaging and performing work tasks, such as clocking in / out, handling leave / attendance, booking office space, and initiating meetings. Furthermore, the application can also be other applications with instant messaging functionality, such as video applications, shopping applications, food delivery applications, sharing applications, live streaming applications, and game applications with instant messaging capabilities.

[0041] The conversation page can be an interactive page for one-to-one interaction (such as chat) between the first and second parties, or it can be an interactive page for a communication group to which the first and second parties belong. This communication group can be an interactive group or discussion group composed of various users of the application, or it can be an interactive group composed of users of the application and users of other applications, such as a customer group composed of users of personal communication applications and users of enterprise communication applications; that is, the members of this customer group include users of both personal and enterprise communication applications.

[0042] The first object can be the user who sends the first conversation message, such as the first user to send "@Xiaoming Happy Birthday", as shown in Figure 3A(a); in addition, the first object can also be the system assistant that sends the first conversation message, such as the intelligent assistant of a social application used for human-computer interaction.

[0043] The first conversation message can be a dialogue message between different parties, and it can be a text, image-text, audio, or video message. This first conversation message can be in the local language or another regional language. The proposed solution can perform information detection on various voice conversation messages, such as precise and fuzzy keyword matching in different languages, and detection of prompts in different languages, to detect whether the first conversation message contains key information and prompts for the second party. Furthermore, the first conversation message can be a group conversation message sent by the first party through a communication group, such as a group conversation message sent by a user or system assistant in a communication group; additionally, the first conversation message can also be a conversation message sent via one-on-one chat (e.g., sent to the second party in a one-on-one chat), such as a conversation message sent by a user or system assistant in a one-on-one chat.

[0044] It should be noted that the first conversation message of the image and text type can be a single message or a message composed of two messages, such as a text conversation message and an image conversation message. The text conversation message can contain prompts for the second object (such as "@Xiaoming"), and the image conversation message can contain key information or information corresponding to key information (such as displaying an emoticon image with "Happy Birthday" or displaying an emoticon image with "cake").

[0045] In one embodiment, the terminal may first receive a first session message sent by a first object. When the first session message is a text or image / text type session message, the first session message is displayed on the session page of the application. When the first session message is an audio or video type session message, a media identifier used to represent the first session message is displayed on the session page.

[0046] The terminal can be a device held by a first object, a device held by a second object, or a device held by other objects (such as other members in a communication group). In subsequent embodiments, unless otherwise specified, the terminal will be described as a device held by the first object.

[0047] A media identifier can be a session identifier used to represent the first session message of an audio or video type.

[0048] The display method can vary depending on the type of the first conversation message. For example, when the first conversation message is a text or image message, it can be displayed directly, as shown in Figure 3A(a); while when the first conversation message is an audio or video message, the corresponding media identifier is displayed on the conversation page. For example, when the first conversation message is an audio message, the media identifier can be a conversation identifier that represents the audio type, as shown in Figure 3A(b).

[0049] S204, when the first session message contains key information and prompts for the second object, display the interactive screen corresponding to the key information.

[0050] The key information can be pre-set keywords or key phrases that can trigger interaction, such as "Happy Birthday" in "@Xiaoming Happy Birthday" sent on a birthday, or "Welcome to the Penguin Family" in "Welcome to the Penguin Family" sent when welcoming new members; in addition, the key information can also be other text information or image information corresponding to the pre-set keywords or key phrases.

[0051] The hint information can be the name of the second object, or a combination of the name of the second object and a symbol used for object hints. In some practical applications, this symbol can be the @ symbol.

[0052] Interactive screens can be screens used for interaction between different objects or between virtual avatars of different objects, and corresponding to key information. These interactive screens can also be called group photos. If applied in a communication group, they can be called group photo screens, including the virtual avatars of the first and second objects. The virtual avatars can be cartoon-style virtual characters or animals. Each object selects a corresponding virtual avatar from the application's model library based on their interests. When needed in certain application scenarios, the virtual avatar is retrieved and displayed. It should be noted that when the first object is a system assistant, the virtual avatar of the first object can be the virtual avatar of the system assistant, which can be a preset cartoon avatar of the system assistant. The virtual avatar of this system assistant can correspond to the corporate logo (logo) of the developer of the application (such as a social application).

[0053] It should be noted that the correspondence between the interactive screen and the key information can be that the first virtual object in the interactive screen presents a posture corresponding to the key information, or expresses words corresponding to the key information. These words can be displayed in the form of special effects text.

[0054] For example, suppose Xiao Li (the user sending the first message) sends the message "@Happy Birthday Xiao Ming" to Xiao Ming. The interactive screen could be a photo of Xiao Ming's virtual avatar and Xiao Li's virtual avatar together. Furthermore, in this interactive screen, Xiao Li's virtual avatar might make a gesture wishing Xiao Ming a happy birthday, or say "Happy Birthday Xiao Ming." As another example, suppose it's Xiao Ming's birthday, and the smart assistant sends him the first message "@Happy Birthday Xiao Ming." The interactive screen could be a photo of Xiao Ming's virtual avatar and the smart assistant's virtual avatar together.

[0055] Furthermore, the interactive screen can also include a group photo template corresponding to key information. For example, if the first conversation message is "@Xiaoming Happy Birthday," then the group photo template can include at least one of the following: a background image with a birthday atmosphere or birthday elements, lighting effects, dynamic effects, or static effects. This group photo template can be determined by the terminal based on the key information, or it can be determined by the terminal in response to a selection operation by the first object. The selection operation of the first object can be based on the key information.

[0056] In one embodiment, when the first session message is an audio or video session message, the terminal can perform speech recognition on the first session message to obtain speech-recognized text; then, it can detect whether the speech-recognized text contains key information and prompts for the second object. When the first session message is an audio or video session message, the terminal can directly detect whether the first session message contains key information and prompts for the second object.

[0057] In one embodiment, when the first session message contains key information and a prompt message for the second object, the terminal can automatically activate the function for displaying virtual avatars for group photo interaction, and then display the virtual avatars of the first object and the second object. The avatar of the first object can present a posture corresponding to the key information, or express words corresponding to the key information. Alternatively, when the first session message contains key information and a prompt message for the second object, the terminal can automatically activate the function for displaying virtual avatars for group photo interaction, and then display a group photo template corresponding to the key information, the virtual avatar of the first object, and the virtual avatar of the second object. It should be noted that during the display process, the virtual avatars of the first and second objects can change dynamically, such as changing postures according to the key information. In specific application scenarios, the virtual avatars can perform a birthday dance or sing a birthday song, etc.

[0058] In one embodiment, when displaying virtual objects, the account name of each object can be displayed at a corresponding location (such as above the head, below the feet, or other unobstructed locations). This account name can be the object's registered name, such as a nickname used by a user on an instant messaging application. If the instant messaging application is an enterprise communication application, the account name can also be the user's real name to facilitate better understanding among internal personnel.

[0059] Before displaying the interactive screen, the terminal can first display a group photo interface, and render a group photo module (such as a group photo area) in the group photo interface, and then display the interactive screen in the group photo module.

[0060] S206, if the first session message contains a virtual prop, display the virtual prop in the interactive screen; or, if the first session message contains a virtual emoticon, display at least one virtual character in the interactive screen displaying an emoticon corresponding to the virtual emoticon.

[0061] Virtual props can refer to prop-like emoticons, which allow the first recipient to express their current psychological or emotional state, or to convey blessings to the other party. For example, a virtual prop could be a virtual cake or virtual fireworks to express birthday wishes to a second recipient. In some specific application scenarios, virtual props can include atmosphere-related virtual props, such as virtual fireworks, which can be displayed in a corresponding position on the interactive screen (such as a corner). Alternatively, virtual props can include personal items or objects placed near the recipient, which can be displayed on a part of the virtual avatar or nearby. It should be noted that the virtual props can be displayed in the positions described above, or they can be customized by the first recipient, the second recipient, or other recipients.

[0062] It should be noted that the virtual props displayed in the interactive screen can be virtual props from the first session message, or virtual props generated based on the virtual props from the first session message and having corresponding special effects, such as dynamic effects. In addition, the image resolution can be higher.

[0063] Virtual emoticons can be facial expressions or similar emoji packs. The first user can use these virtual emoticons to express their current psychological or emotional state. For example, if the virtual emoticon is a smiling face, it can convey the first user's joy, causing their virtual avatar to display a smiling expression in the interactive scene. It should be noted that the virtual avatar of a second user can also display a corresponding expression.

[0064] In one embodiment, the first session message is a text-type or image-type session message; the method further includes: if the first session message contains target interaction information, the terminal retrieves a target virtual item corresponding to the target interaction information from an emoji library and displays the retrieved target virtual item on the interaction screen; or, it generates a corresponding target virtual item based on the target interaction information and displays the generated target virtual item on the interaction screen. Furthermore, if the number of virtual items corresponding to the target interaction information retrieved from the emoji library is large, these tag elements can be displayed for selection by the first object, or a predetermined number of virtual items can be displayed.

[0065] The target interactive information can be specific words that correspond to the target virtual item, such as "cake," "muah," or "I love you." When the first conversation message is a text or image-text type conversation message, the target interactive information can be input by the first object. When the first conversation message is an audio or video type conversation message, the target interactive information can be issued by the first object in the form of voice.

[0066] For example, if the first conversation message contains target interaction information, the target virtual prop corresponding to the target interaction information can be retrieved from an emoji library (such as the first object's local emoji library or online emoji library), and then displayed in the corresponding position on the interaction screen. For instance, a virtual cake could be displayed in the first object's hand on the interaction screen, or a graphical heart could be displayed in front of the first object's virtual avatar (opposite to the second object's virtual avatar). The first object's virtual avatar could make a pouting gesture, while the second object's virtual avatar could make a happy or shy expression. Furthermore, besides retrieving the target virtual prop corresponding to the target interaction information from the emoji library, the terminal can also input the target interaction information into a generative model. This generative model generates a target virtual prop with corresponding effects based on the target interaction information, and then displays the target virtual prop on the interaction screen.

[0067] The generative model can be a generative adversarial network model, a variational autoencoder, a diffusion model, or other Transformer-based models.

[0068] In another embodiment, the first session message is a text-type or image-type session message; the method further includes: when the first session message contains target interaction information, the terminal determines the target virtual expression corresponding to the target interaction information, generates a virtual image with an expression corresponding to the virtual expression based on the target interaction information and the virtual image, so that the virtual image in the interactive screen presents an expression corresponding to the virtual expression.

[0069] In generating virtual avatars with expressions corresponding to virtual emoticons, generative models can be used.

[0070] In one embodiment, the terminal can detect whether the first session message contains an emoticon or whether it contains target interaction information. If the first session message contains an emoticon, and the emoticon is a prop-type emoticon (i.e., a virtual prop), then the virtual prop is displayed in the interaction screen. If the emoticon is a facial expression-type emoticon (i.e., a virtual expression), then at least one virtual character in the interaction screen is controlled to display an expression corresponding to the virtual expression. For example, if the virtual expression is a smiley face, then the virtual character displays a smiling expression.

[0071] For example, when the first conversation message is a text or image / text type conversation message, the terminal can detect whether the first conversation message contains emoticons. If it contains virtual fireworks, the virtual fireworks will be displayed in the corresponding position of the interactive screen (such as the corner of the interactive screen). If it contains a virtual cake, the virtual cake will be displayed in the hands of the first object in the interactive screen (the first object's hands are in the posture of holding a cake).

[0072] In one embodiment, if the first conversation message contains an emoticon, and if the emoticon is a virtual item, the terminal can also use a generative model to combine the virtual item with preset descriptive information to generate a target virtual item with corresponding effects, and then display the target virtual item in the interactive screen. Alternatively, if the emoticon is a virtual emoticon, the terminal can also use a generative model to combine the virtual emoticon and virtual avatar to generate a virtual avatar with an expression corresponding to the virtual emoticon, so that the virtual avatar in the interactive screen displays an expression corresponding to the virtual emoticon.

[0073] For example, if the emoticon is a virtual emoticon of a happy laugh, the terminal can also use a generative model to combine the virtual emoticon of a happy laugh with the virtual image to generate a virtual image of a happy laugh, so that the virtual image in the interactive screen presents the expression of a happy laugh, as shown in Figure 3B.

[0074] In another embodiment, if the first session message contains an emoticon, and the emoticon includes a virtual prop and a virtual emoticon, the terminal can control the virtual avatar to display an expression corresponding to the virtual emoticon. For example, if the virtual emoticon is a smiley face, the virtual avatar will display a smiling expression. In addition, the virtual prop will be directly displayed in the interactive screen, or a target virtual prop with corresponding special effects will be displayed in the interactive screen. The target virtual prop can be generated based on the virtual prop.

[0075] For example, if the emoticon pack includes virtual fireworks and a virtual laughing expression, the terminal can control the virtual avatar to display a laughing expression. In addition, the virtual fireworks can be directly displayed in the interactive screen, or virtual fireworks with dynamic effects can be displayed in the interactive screen, as shown in Figure 3C.

[0076] In one embodiment, when the first session message is an audio or video session message, the terminal first performs speech recognition on the first session message to obtain speech recognition text; if the speech recognition text contains target interactive information, the target virtual prop corresponding to the target interactive information is displayed in the interactive screen.

[0077] For example, when the first conversation message is an audio or video message, the terminal can perform speech recognition on the audio message or the speech in the video message to obtain the speech-recognized text. If the speech-recognized text contains target interaction information, the terminal retrieves the target virtual prop corresponding to the target interaction information from the emoji library and displays the target virtual prop at the corresponding position on the interaction screen. For example, if the target interaction information is "kiss," a graphic heart is displayed on the interaction screen in front of the virtual image of the first object (opposite to the virtual image of the second object). The virtual image of the first object can make a pouting gesture, while the virtual image of the second object can make a happy or shy expression.

[0078] Furthermore, for displaying interactive images on other users' terminals, the terminal of the first user can send target information containing identification information of the group photo template, object information of the first user, and object information of the second user to the server. This allows the server to send the identification information and the corresponding virtual images to the terminals of other users, thereby displaying the interactive image on their terminals. Alternatively, the server can proactively push the identification information and the corresponding virtual images to the terminals of other users.

[0079] In one embodiment, the terminal may also display virtual props on the virtual image of the second object to indicate that the second object is the main character.

[0080] The virtual prop used to represent the second object as the protagonist can be a virtual item with protagonist characteristics, such as a virtual crown or birthday hat, or other animated images or emoticons. It should be noted that this virtual prop can change according to the posture and angle of the second virtual object to match it.

[0081] In one embodiment, the terminal can obtain virtual props with protagonist characteristics from the server based on key information, or generate virtual props with protagonist characteristics based on key information. For example, the terminal can call a large model (such as a Wensheng video model) to generate virtual props with protagonist characteristics, and then display the virtual props with protagonist characteristics on a second object in the interactive screen.

[0082] To better understand the group photo interaction method in this application, the following explanation is provided with reference to Figure 4:

[0083] S1, User 1 sends a session message;

[0084] S2, If the conversation message is a voice message, the instant messaging application will convert the conversation message into a text message;

[0085] S3, determine whether the text message is in the local language;

[0086] S4-1, If ​​it is the local language, perform matching of the specified keywords to obtain matching result a;

[0087] S5, determine whether the text message contains the keyword that triggers the group photo function based on the matching result 'a'. If it contains the keyword, proceed to S6; otherwise, proceed to S12.

[0088] S6, enable group photo function;

[0089] S7, obtain the communication accounts of user 1 and the user 2 who was mentioned;

[0090] S8, retrieve the virtual characters of User 1 and User 2 based on their communication accounts;

[0091] S9, load the virtual characters of User 1 and User 2;

[0092] S10, render the virtual characters of User 1 and User 2 to the group photo interface;

[0093] S11, send the group photo template ID and the user's communication account to the server.

[0094] S12, perform fuzzy matching to obtain matching result b;

[0095] S13, Based on the matching result b, determine whether the text message contains words corresponding to the keywords that trigger the group photo function. If it does, execute S6 to S11; if it does not, execute S15.

[0096] S4-2, If it is a non-local language, perform multilingual keyword matching to obtain matching result c;

[0097] S14. Based on the matching result c, determine whether the text message contains the keyword that triggers the group photo function. If it does, execute S6 to S11; if it does not, execute S15.

[0098] S15, group photo function not enabled.

[0099] In addition, after rendering the virtual characters of User 1 and User 2 onto the group photo interface, it can continue to receive conversation messages sent by other users, and when the conversation message meets the corresponding conditions, render the virtual characters of other users onto the group photo interface.

[0100] In the above embodiments, a first conversation message sent by a first object is displayed on the application's conversation page. When the first conversation message contains key information and prompts for a second object, an interactive screen corresponding to the key information and including the virtual avatars of the first and second objects will be displayed. This not only enables interaction at the message level but also links the virtual avatars of the participating objects, allowing them to interact with each other, which is beneficial for improving the interaction effect. In addition, if the first conversation message contains virtual props, the virtual props are displayed in the interactive screen; or, if the first conversation message contains virtual emoticons, at least one virtual avatar in the interactive screen displays an emoticon corresponding to the virtual emoticon, thereby increasing the interactive atmosphere and encouraging more objects to participate in the interaction, effectively improving the interaction rate.

[0101] In one embodiment, when the first session message is a session message sent by the first object in a communication group, that is, the first object and the second object are members in the communication group, after S204, the terminal can display the second session message sent by other objects in the communication group on the session page; when the second session message contains key information or information corresponding to the key information, the virtual image of other objects is displayed on the interactive screen.

[0102] Other objects can be group members in the communication group other than the first and second objects, and can be one or more. It should be noted that "multiple" can be two or more. The information corresponding to the key information can be information that is not pre-set but expresses the same or similar semantics as the key information. For example, if the key information is "Happy Birthday," then the corresponding information could be "Happy birthday," "Happy Birthday," or "+1." It should be noted that "+1" could indicate that the user is also sending the same content as the previous conversation message, but "+1" is used for simplicity.

[0103] After receiving the second session message, the terminal can also detect whether the second session message contains virtual props or virtual emoticons. If it contains virtual props or virtual emoticons, it can display the virtual image of other objects in the interactive screen, and also display the virtual prop, or control the virtual image of other objects to present an expression corresponding to the virtual emoticon.

[0104] For example, after the first object sends a birthday message to Xiaoming in the communication group, if other objects in the communication group also send birthday messages, the virtual image of the other object will be added to the interactive screen for display. In addition, if the message also contains virtual props, the virtual props will be displayed in the corresponding position on the interactive screen. For example, if the virtual prop is a virtual cake, the virtual cake will be displayed in the hand of the other object's virtual image, thus presenting the image of the other object's virtual image holding a cake, as shown in Figures (a) and (b) of Figure 5.

[0105] In one embodiment, before displaying the virtual image of another object, the terminal can also perform a time determination to decide whether to display it on the interactive screen. Specifically, when the terminal receives a second session message sent by another object in the communication group, it obtains the reception time of the second session message; when the second session message contains key information or information corresponding to the key information, and the reception time meets a preset time condition, the virtual image of the other object is displayed on the interactive screen.

[0106] The preset time condition can be a pre-defined time interval for displaying the virtual avatar, such as 0 to 2 minutes after the start of displaying the interactive screen; or the preset time condition can be a pre-defined time value for displaying the virtual avatar, which counts down after the start of displaying the interactive screen, with the initial value being this time value.

[0107] Furthermore, when the second conversation message contains key information or information corresponding to the key information, and the reception time meets the preset time condition, the terminal can also determine whether the number of virtual objects in the interactive screen meets the preset quantity condition, such as whether the number of virtual objects is greater than or equal to the quantity threshold. If it meets the condition, the virtual image of other objects is displayed in the interactive screen. In addition, if the second conversation message sent by the other object contains virtual props, virtual expressions, or interactive information with the target, it is displayed in accordance with the above embodiment.

[0108] In one embodiment, to allow each participant to more intuitively understand the time and quantity requirements for taking a group photo, the terminal can display a countdown, the specified maximum number of photos, and the number of virtual avatars currently displayed on the interactive screen.

[0109] For example, when other objects in the communication group also send a conversation message, the reception time of the conversation message will be recorded. If the reception time falls within a preset time interval and the conversation message contains "Happy Birthday", the virtual image of the other object and the corresponding virtual props will be displayed in the interactive screen. In addition, the terminal can also display a countdown, a specified upper limit, and the number of currently displayed virtual images in the interactive screen, as shown in Figures (a) and (b) of Figure 6.

[0110] In one embodiment, the number of other objects is at least two. In order to highlight the main characteristics of the second object, during the display process, the terminal displays the virtual images of each other object on both sides or around the location of the second object as the center.

[0111] For example, virtual images of other objects are displayed on both sides of the location of the second object; or, virtual images of other objects are displayed around the location of the second object.

[0112] There are three ways to enable the group photo function:

[0113] Method 1: Enable semantic detection before sending session messages.

[0114] In one embodiment, the interaction method is applied to a terminal held by a first object. During the process of the first object inputting a conversation message, the input conversation content is detected to obtain a first detection result. When the first detection result contains key information and prompt information for the second object, the function of displaying a virtual avatar for group photo interaction is enabled.

[0115] Among them, the group photo interaction function (hereinafter referred to as the group photo function) can be a function that allows users to interact and take group photos. When the group photo function is enabled, an interactive screen containing virtual information can be displayed, and after the corresponding conditions are met, the interactive screen can be captured to obtain a group photo image or group photo video.

[0116] When inputting session content, the terminal can check the input session content at short intervals, such as once every 5 seconds or 10 seconds.

[0117] For example, while a user is typing text in an input box, a check can be performed every 5 seconds. It should be noted that the intervals between checks should not be too short to avoid invalid checks being performed before the user has typed the next character.

[0118] In another embodiment, when the first detection result contains key information and prompts for the second object, a group photo confirmation page is displayed, supporting a pop-up confirmation prompt during the input process to enhance the user-friendly interaction process; in response to the confirmation operation triggered on the group photo confirmation page, the function of displaying a virtual avatar for group photo interaction is enabled, thereby enabling corresponding interaction with the user's authorization, which helps to improve the user experience.

[0119] In response to the conditions or states on which the operation being performed depends, one or more operations may be performed in real time or with a set delay when the conditions or states on which they depend are met; unless otherwise specified, there is no restriction on the order in which the multiple operations are performed.

[0120] Method 2: Enable semantic detection after sending the session message.

[0121] In one embodiment, after receiving a first session message from a first object, the terminal detects whether the first session message contains key information and prompts for a second object. If it does, the terminal activates the function of displaying a virtual avatar for photo interaction and then displays the interactive screen corresponding to the key information.

[0122] In addition, if the first session message contains key information and prompts for the second person, the terminal can first display a group photo confirmation page, and in response to the confirmation operation triggered on the group photo confirmation page, enable the function of displaying virtual avatars for group photo interaction.

[0123] Method 3: Activate via specific voice control or manual operation.

[0124] In one embodiment, the interaction method is applied to a terminal held by a first object, which receives a control voice from the first object. When the control voice contains a command to start a group photo, the function for displaying a virtual image for group photo interaction is activated; or, in response to a triggered group photo start operation, the function for displaying a virtual image for group photo interaction is activated.

[0125] Among them, the control voice can be the voice issued by the first object, and the group photo start command can be the command to start the group photo function.

[0126] The terminal performs speech recognition on the control voice to obtain speech recognition text, and then detects whether the speech recognition text contains a group photo activation command. The group photo activation command can be "activate group photo function", and the group photo function is activated according to the group photo activation command.

[0127] In the above embodiments, the input conversation content is detected, and the group photo function is activated when the detection result meets the conditions, thereby activating the group photo function in advance. Moreover, it supports pop-up confirmation prompts for activating the group photo during the input process, which improves the user-friendly interaction process. In addition, the group photo function can also be activated by voice control and manual operation, and the group photo function can be activated seamlessly by triggering the content of the conversation message after sending the conversation message, so as to avoid disturbing the user during the interaction. In addition, it can also be activated in a conscious way.

[0128] In one embodiment, the method is applied to a terminal holding a first object. After receiving the first session message, as shown in Figure 7, the method further includes:

[0129] S702, perform information detection on the first session message to obtain the second detection result.

[0130] S704, when the second detection result indicates that the first session message contains key information and prompts for the second object, the group photo confirmation page is displayed.

[0131] The group photo confirmation page can be a page provided to users to confirm whether they want to take a group photo. This group photo confirmation page can include confirmation controls and cancellation controls.

[0132] S706, in response to a confirmation operation triggered on the group photo confirmation page, displays an interactive screen corresponding to key information.

[0133] In one embodiment, in response to an operation triggered on the confirmation control of the group photo confirmation page, the terminal enables the function of displaying a virtual avatar for group photo interaction, and then displays an interactive screen corresponding to the key information. In response to an operation triggered on the cancel control of the group photo confirmation page, the terminal does not display the interactive screen corresponding to the key information.

[0134] In one embodiment, the interactive screen also includes a group photo template. Therefore, during the display of the interactive screen, the terminal first displays the group photo template corresponding to the key information; then sends a virtual image acquisition request to the server; receives the virtual images of the first object and the second object from the server in response to the virtual image acquisition request; and displays the virtual images of the first object and the second object.

[0135] The group photo template can be a background image that matches the key information and is used for virtual objects to take a group photo. For example, if the key information is "Happy Birthday", then the group photo template can be a background image with a birthday atmosphere or birthday elements.

[0136] In one embodiment, in addition to requesting the virtual image of the first object from the server, the terminal can also obtain the virtual image of the first object locally. For example, the virtual image of the first object can be cached locally, so that the terminal can directly obtain the virtual image of the first object locally when it needs to be displayed.

[0137] In one embodiment, the first object and the second object are members of a communication group. After the first object sends a first session message and displays an interactive screen, the terminal sends target information to the server. The target information includes the identification information of the group photo template, the object information of the first object, and the object information of the second object. The target information is used to instruct the server to send the identification information and the virtual image corresponding to each object information to the terminals of other objects in the communication group, so as to display the group photo template and the virtual image corresponding to each object information (i.e., the virtual image of the first object and the virtual image of the second object) on the terminals of other objects.

[0138] In one embodiment, after the interaction is completed, a group photo image or video can be captured and then stored. Specifically, the terminal captures images or videos of the interactive screen to obtain a group photo image or video; or, it records the waiting time, and when the waiting time reaches a preset time condition, it captures images or videos of the interactive screen to obtain a group photo image or video; or, it counts the number of objects in the interactive screen, and when the number of objects reaches a preset number condition, it captures images or videos of the interactive screen to obtain a group photo image or video.

[0139] During image or video capture, selection can be made according to actual needs, such as displaying a selection page to choose whether to capture an image or video format. The selection page can be displayed on the side of the first object, the side of the second object, or on all terminals that have sent data containing key information.

[0140] For video capture, you can configure the video recording duration and recording nodes, and then export the video format file based on the built-in rendering engine (such as the Sequencer component in UE4).

[0141] For image capture, the captured group photo image can be a dynamic image or a static image. For dynamic images, the configuration information contains a node array of keyframes, which can be used to generate group photos of these keyframes by default. In addition, users can also take screenshots themselves, such as by calling the screenshot capability of the rendering engine (UE4's Scene Capture component) to obtain group photos.

[0142] In one embodiment, the acquisition of video or images can be performed at a fixed location or at a dynamic location. Specifically, the terminal uses a virtual camera to capture images or videos of the interactive scene at a fixed location to obtain a group photo image or video; or, the virtual camera uses a virtual camera to capture images or videos of the interactive scene along a target path to obtain a group photo image or video.

[0143] The target path can be a pre-set collection route or a path manually set by the user (such as the first object) during the collection process.

[0144] When capturing images or videos, a virtual capture device (such as a virtual mobile phone or tablet computer) and a virtual user or virtual user's hand operating the capture device can be displayed on the session page. Various virtual images and virtual props in the interactive screen are displayed on the capture device's screen, as shown in Figure 8.

[0145] In one embodiment, after capturing a group photo or video, the terminal can save the group photo or video to the album of each object in the interactive screen; or, save the group photo or video to the album of the communication group, where the communication group is the group to which each object in the interactive screen belongs, and the conversation page is the group chat page of the communication group.

[0146] In addition, after the group photo image or video is saved, the terminal can display a message indicating that the saving is complete, as shown in Figure 9.

[0147] To better understand the technical solution of this application, the following description is provided in conjunction with Figures 3A, 5, 6, 8, 9, and 10. As shown in Figure 10, the group photography method of this application is as follows:

[0148] S1, User A edits and sends a session message;

[0149] S2, User A's client detects whether the session messages contain keywords that trigger the group photo function;

[0150] In this context, User A's client can refer to the instant messaging application used by User A.

[0151] S3, User A's client displays a confirmation pop-up;

[0152] S4, User A clicks OK, and then selects the corresponding group photo template;

[0153] S5, User A's client renders the group photo module in the group photo interface;

[0154] S6, User A's client requests the virtual characters of User A and the user being mentioned from the server, as shown in Figure 3A;

[0155] S7, the server returns the virtual characters of user A and the user who was mentioned;

[0156] S8, User A's client displays the virtual characters of User A and the user being tagged;

[0157] S9, User A's client sends the group photo template ID, User A's communication account and the user being tagged to the server;

[0158] S10, the server returns the group photo template ID, the virtual characters of user A and the user being tagged to user B's client;

[0159] S11, User B's client renders the group photo template on the group photo interface and displays the virtual characters of User A and the user being tagged.

[0160] S12, User B sends a session message with a trigger keyword;

[0161] S13, User B's client detects whether the session message sent by User B contains keywords;

[0162] S14, if included, user B's client requests user B's virtual character from the server;

[0163] S15, the server returns user B's virtual character to user B's client;

[0164] S16, User B's client displays User B's virtual character in the group photo interface;

[0165] S17, User B's client sends the group photo template ID and User B's virtual character to the server;

[0166] S18, the server sends the group photo template ID and user B's virtual avatar to user A's client;

[0167] S19, User A's client displays User B's virtual character in the group photo interface, as shown in Figures 5 and 6.

[0168] When the countdown reaches 0 or the number reaches the specified threshold, the group photo video or image will be captured, as shown in Figure 8. The captured group photo video or image will then be saved in the group album, and a prompt message will be displayed, as shown in Figure 9.

[0169] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0170] Based on the same inventive concept, this application also provides an interactive device for implementing the interactive method in the communication scenario described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the interactive device in the communication scenario provided below can be found in the limitations of the interactive method in the communication scenario described above, and will not be repeated here.

[0171] In one embodiment, as shown in FIG11, an interactive device for a communication scenario is provided, comprising: a first display module 1102, a second display module 1104, and a third display module 1106, wherein:

[0172] The first display module 1102 is used to display the first session message sent by the first object in the session page of the application;

[0173] The second display module 1104 is used to display an interactive screen corresponding to the key information when the first session message contains key information and prompt information for the second object. The interactive screen includes a virtual image of the first object and a virtual image of the second object.

[0174] The third display module 1106 is used to display virtual props in the interactive screen when the first session message contains virtual props; or, when the first session message contains virtual emoticons, to display at least one virtual image in the interactive screen displaying an emoticon corresponding to the virtual emoticon.

[0175] In one embodiment, as shown in FIG12, the device further includes:

[0176] The receiving module 1108 is used to receive the first session message sent by the first object;

[0177] The first display module 1102 is further configured to display the first session message on the session page of the application when the first session message is a text-type or image-text-type session message; and to display a media identifier for representing the first session message on the session page when the first session message is an audio-type or video-type session message.

[0178] In one embodiment, as shown in FIG12, the device further includes:

[0179] The fourth display module 1110 is used to display virtual props on the virtual image of the second object to indicate that the second object is the protagonist.

[0180] In one embodiment, the first session message is a text-type or image-text-type session message;

[0181] The fourth display module 1110 is also used to, when the first session message contains target interaction information, retrieve the target virtual prop corresponding to the target interaction information from the emoticon library and display the retrieved target virtual prop in the interaction screen; or, generate the corresponding target virtual prop based on the target interaction information and display the generated target virtual prop in the interaction screen.

[0182] In one embodiment, the first session message is an audio or video session message; as shown in Figure 12, the apparatus further includes:

[0183] The recognition module 1112 is used to perform speech recognition on the first conversation message to obtain the speech recognition text;

[0184] The fourth display module 1110, when the speech recognition text contains target interactive information, retrieves the target virtual prop corresponding to the target interactive information from the expression library and displays the target virtual prop in the interactive screen.

[0185] In the above embodiments, a first conversation message sent by a first object is displayed on the application's conversation page. When the first conversation message contains key information and prompts for a second object, an interactive screen corresponding to the key information and including the virtual avatars of the first and second objects will be displayed. This not only enables interaction at the message level but also links the virtual avatars of the participating objects, allowing them to interact with each other, which is beneficial for improving the interaction effect. In addition, if the first conversation message contains virtual props, the virtual props are displayed in the interactive screen; or, if the first conversation message contains virtual emoticons, at least one virtual avatar in the interactive screen displays an emoticon corresponding to the virtual emoticon, thereby increasing the interactive atmosphere and encouraging more objects to participate in the interaction, effectively improving the interaction rate.

[0186] In one embodiment, the first object and the second object are members of a communication group; as shown in FIG12, the device further includes:

[0187] The fifth display module 1114 is used to display second session messages sent by other objects in the communication group on the session page; when the second session message contains key information or information corresponding to the key information, the virtual image of other objects is displayed on the interactive screen.

[0188] In one embodiment, as shown in FIG12, the device further includes:

[0189] The acquisition module 1116 is used to acquire the reception time of the second session message when it receives a second session message sent by other objects in the communication group;

[0190] The fifth display module 1114 is also used to display virtual images of other objects in the interactive screen when the second session message contains key information or information corresponding to the key information and the receiving time meets the preset time condition.

[0191] In one embodiment, the number of other objects is at least two;

[0192] The fifth display module 1114 is also used to display virtual images of other objects on both sides or around the second object, with the location of the second object as the center.

[0193] In one embodiment, as shown in FIG12, the device further includes:

[0194] The first detection module 1118 is used to detect the input session content during the process of the first object inputting session messages and obtain the first detection result.

[0195] The first activation module 1120 is used to activate the function of displaying a virtual avatar for group photo interaction when the first detection result contains key information and prompt information for the second object; or, when the first detection result contains key information and prompt information for the second object, to display a group photo confirmation page; and to activate the function of displaying a virtual avatar for group photo interaction in response to a confirmation operation triggered on the group photo confirmation page.

[0196] In one embodiment, as shown in FIG12, the device further includes:

[0197] Receiver module 1108 is used to receive control voice sent by the first object;

[0198] The second activation module 1122 is used to activate the function of displaying a virtual image for group photo interaction when the control voice includes a group photo activation command; or, in response to the triggered group photo activation operation, to activate the function of displaying a virtual image for group photo interaction.

[0199] In one embodiment, as shown in FIG12, the device further includes:

[0200] The second detection module 1124 is used to perform information detection on the first session message and obtain a second detection result;

[0201] The second display module 1104 is further configured to display a group photo confirmation page when the second detection result indicates that the first session message contains key information and prompt information for the second object; and to display an interactive screen corresponding to the key information in response to a confirmation operation triggered on the group photo confirmation page.

[0202] In one embodiment, the interactive screen also includes a group photo template;

[0203] The second display module 1104 is also used to display a group photo template corresponding to key information; send a virtual image acquisition request to the server; receive the virtual images of the first object and the second object from the server in response to the virtual image acquisition request; and display the virtual images of the first object and the second object.

[0204] In one embodiment, the first object and the second object are members of a communication group, as shown in FIG12. The device further includes:

[0205] The sending module 1126 is used to send target information to the server. The target information includes the identification information of the group photo template, the object information of the first object, and the object information of the second object. The target information is used to instruct the server to send the identification information and the virtual image corresponding to each object information to the terminals of other objects in the communication group, so as to display the group photo template and the virtual image corresponding to each object information on the terminals of other objects.

[0206] In one embodiment, as shown in FIG12, the device further includes:

[0207] The acquisition module 1128 is used to acquire images or videos of the interactive screen to obtain group photos or videos; or, to record the waiting time, and when the waiting time reaches a preset time condition, to acquire images or videos of the interactive screen to obtain group photos or videos; or, to count the number of objects in the interactive screen, and when the number of objects reaches a preset number condition, to acquire images or videos of the interactive screen to obtain group photos or videos.

[0208] In one embodiment, the acquisition module 1128 is further configured to acquire images or videos of the interactive scene at a fixed position using a virtual camera to obtain a group photo image or video; or, to acquire images or videos of the interactive scene along a target path using a virtual camera to obtain a group photo image or video.

[0209] In one embodiment, as shown in FIG12, the device further includes:

[0210] Storage module 1130 is used to save group photos or group videos in the albums of each object in the interactive screen; or, to save group photos or group videos in the albums of communication groups, where communication groups are the groups in which each object in the interactive screen belongs, and the conversation page is the group chat page of the communication group.

[0211] The modules in the interactive devices described above can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0212] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram is shown in Figure 13. The computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an interactive method in a communication scenario. The display unit of the computer device is used to form a visually visible image. It can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0213] Those skilled in the art will understand that the structure shown in Figure 13 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0214] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the interaction method in the above-described communication scenario.

[0215] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the interaction method in the above-described communication scenario.

[0216] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the interaction method in the above-described communication scenario.

[0217] It should be noted that 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 application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0218] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0219] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above 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.

[0220] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An interaction method in a communication scenario, wherein, The method includes: Display the first session message sent by the first object in the application's session page; When the first session message contains key information and prompts for the second object, an interactive screen corresponding to the key information is displayed. The interactive screen includes the virtual image of the first object and the virtual image of the second object. If the first conversation message contains a virtual item, the virtual item is displayed in the interactive screen; or, if the first conversation message contains a virtual emoticon, at least one virtual character in the interactive screen displays an emoticon corresponding to the virtual emoticon.

2. The method according to claim 1, wherein, The method further includes: Receive the first session message sent by the first object; The step of displaying the first session message sent by the first object on the application's session page includes: When the first session message is a text-type or image-text-type session message, the first session message is displayed on the application's session page; When the first session message is an audio or video session message, a media identifier representing the first session message is displayed on the session page.

3. The method according to claim 1 or 2, wherein, After displaying the interactive screen corresponding to the key information, the method further includes: On the virtual image of the second object, virtual props are displayed to indicate that the second object is the protagonist.

4. The method according to any one of claims 1 to 3, wherein, The first session message is a text or image type session message; the method further includes: If the first session message contains target interaction information, retrieve the target virtual item corresponding to the target interaction information from the emoji library, and display the retrieved target virtual item in the interaction screen; or... Based on the target interaction information, a corresponding target virtual item is generated, and the generated target virtual item is displayed in the interaction screen.

5. The method according to any one of claims 1 to 4, wherein, The first object and the second object are members of a communication group; After displaying the interactive screen corresponding to the key information, the method further includes: The session page displays second session messages sent by other objects in the communication group; When the second session message contains the key information or information corresponding to the key information, the virtual image of the other object is displayed in the interactive screen.

6. The method according to claim 5, wherein, The method further includes: Upon receiving a second session message sent by another object in the communication group, the reception time of the second session message is obtained; When the second session message contains the key information or information corresponding to the key information, displaying the virtual image of the other object in the interactive screen includes: When the second session message contains the key information or information corresponding to the key information, and the receiving time meets the preset time condition, the virtual image of the other object is displayed in the interactive screen.

7. The method according to claim 6, wherein, The number of other objects is at least two; displaying the virtual images of the other objects in the interactive screen includes: With the location of the second object as the center, virtual images of the other objects are displayed on both sides or around the second object.

8. The method according to any one of claims 1 to 7, wherein, The first session message is an audio or video session message, and the method further includes: The first conversation message is subjected to speech recognition to obtain the speech-recognized text. The method further includes: when the speech recognition text contains target interaction information, obtaining the target virtual prop corresponding to the target interaction information from the expression library, and displaying the target virtual prop in the interaction screen.

9. The method according to any one of claims 1 to 8, wherein, The method is applied to a terminal held by the first object, and the method further includes: During the process of the first object inputting a conversation message, the input conversation content is detected to obtain a first detection result; When the first detection result contains the key information and the prompt information for the second object, the function to display a virtual avatar for photo interaction is enabled; or... When the first detection result contains the key information and the prompt information for the second object, a group photo confirmation page is displayed; in response to the confirmation operation triggered on the group photo confirmation page, the function for displaying a virtual image for group photo interaction is enabled.

10. The method according to any one of claims 1 to 9, wherein, The method is applied to the terminal held by the first object; Before displaying the first session message sent by the first object in the application's session page, the method further includes: Upon receiving a control voice command from the first object, if the control voice command includes a command to start a group photo, activate the function for displaying a virtual avatar for interactive group photo taking; or... In response to the triggered group photo activation operation, the group photo function for displaying the virtual avatar is activated.

11. The method according to any one of claims 1 to 10, wherein, The method is applied to a terminal held by the first object, and the method further includes: The first session message is subjected to information detection to obtain a second detection result; When the first session message contains key information and a prompt message for the second object, displaying the interactive screen corresponding to the key information includes: When the second detection result indicates that the first session message contains key information and prompts for the second object, a group photo confirmation page is displayed. In response to the confirmation operation triggered on the group photo confirmation page, an interactive screen corresponding to the key information is displayed.

12. The method according to claim 11, wherein, The interactive screen also includes a group photo template; the interactive screen displaying the key information includes: Display the group photo template corresponding to the key information; Send a virtual avatar retrieval request to the server; Receive the virtual images of the first object and the second object as a response from the server to the virtual image acquisition request; Display the virtual images of the first object and the second object.

13. The method according to claim 12, wherein, The first object and the second object are members of a communication group, and the method further includes: Send target information to the server, the target information including the identification information of the group photo template, the object information of the first object, and the object information of the second object; The target information is used to instruct the server to send the identification information and the virtual image corresponding to each object information to the terminals of other objects in the communication group, so as to display the group photo template and the virtual image corresponding to each object information on the terminals of the other objects.

14. The method according to any one of claims 1 to 13, wherein, After displaying the interactive screen corresponding to the key information, the method further includes: The interactive screen is captured as an image or video to obtain a group photo image or video; or, Record the waiting time, and when the waiting time reaches a preset time condition, capture images or videos of the interactive screen to obtain a group photo image or video; or... The number of objects in the interactive screen is counted. When the number of objects reaches a preset condition, the interactive screen is captured as an image or video to obtain a group photo image or video.

15. The method according to claim 14, wherein, The step of capturing images or videos of the interactive screen to obtain group photos or group videos includes: The interactive scene is captured by a virtual camera at a fixed location, resulting in a group photo image or video; or... The virtual camera captures images or videos of the interactive scene along the target path to obtain group photos or videos.

16. The method according to claim 14 or 15, wherein, The method further includes: The group photo image or video can be saved in the photo album of each object in the interactive screen; or... The group photo or video is saved in the album of the communication group, which is the group in which the objects in the interactive screen are located, and the conversation page is the group chat page of the communication group.

17. An interactive device in a communication scenario, wherein, The device includes: The first display module is used to display the first session message sent by the first object in the session page of the application; The second display module is used to display an interactive screen corresponding to the key information when the first session message contains key information and prompt information for the second object. The interactive screen includes a virtual image of the first object and a virtual image of the second object. The third display module is configured to display the virtual prop in the interactive screen when the first conversation message contains the virtual prop; or, when the first conversation message contains the virtual emoticon, display at least one virtual character in the interactive screen displaying an emoticon corresponding to the virtual emoticon.

18. A computer device comprising a memory and a processor, wherein the memory stores a computer program, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 16.

19. A computer-readable storage medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 16.

20. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 16.

Images