Direct broadcasting room interaction method, equipment and device, storage medium and program product

Abstract

The invention relates to a live broadcast room interaction method, equipment and device, a storage medium and a program product, and relates to the technical field of artificial intelligence. The method comprises the following steps: receiving a virtual item description voice sent by a user corresponding to a first user account in a live broadcasting room; generating a virtual item described by the virtual item description voice based on the virtual item description voice; displaying a special effect of giving the virtual item to a second user account in the live broadcast room in a live broadcast interface corresponding to the live broadcast room; according to the scheme, the problems that an existing live broadcast interaction mode is single, operation is tedious and efficiency is low can be solved, the efficiency of presenting the virtual props in the live broadcast room is improved, user experience is enhanced, and the interaction effect between the user and the live broadcast room is improved.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of artificial intelligence technology, and particularly to a live broadcast room interaction method, device, apparatus, storage medium, and program product. Background Art

[0002] With the rapid development of the Internet live broadcast industry, more and more people relieve stress by watching live broadcasts. In a live broadcast room, the host user can show personal talents to the viewing users, and the viewing users can give gifts to the host user. After receiving the gifts, the host user can obtain substantial benefits.

[0003] In the related art, during the process of network live broadcast by the host user, a gift library can be displayed on the terminal device of the viewing user. The gift library contains various gifts with different values. The viewing user can click on the gifts in the gift library and select different types and quantities of gifts to give / reward. After receiving the gifts, the host user obtains the benefits corresponding to the gifts.

[0004] However, the above-mentioned gift-giving method in the live broadcast room is relatively single, the gift-giving efficiency in the live broadcast room is low, and the interaction effect between users and the live broadcast room is poor. Summary of the Invention

[0005] Embodiments of the present application provide a live broadcast room interaction method, device, apparatus, storage medium, and program product, which can improve the interaction effect between users and the live broadcast room. The technical solution is as follows:

[0006] On the one hand, a live broadcast room interaction method is provided. The method includes:

[0007] Receiving a virtual prop description voice sent by a user corresponding to a first user account in the live broadcast room;

[0008] Generating a virtual prop described by the virtual prop description voice based on the virtual prop description voice;

[0009] Displaying an effect of presenting the virtual prop to a second user account in the live broadcast room on a live broadcast interface corresponding to the live broadcast room.

[0010] On the other hand, a live broadcast room interaction apparatus is provided. The apparatus includes:

[0011] A description voice receiving module, configured to receive a virtual prop description voice sent by a user corresponding to a first user account in the live broadcast room;

[0012] A virtual prop generating module, configured to generate a virtual prop described by the virtual prop description voice based on the virtual prop description voice;

[0013] A gift special effect display module, configured to display, in a live interface corresponding to the live room, a special effect of giving the virtual item to a second user account in the live room.

[0014] In some embodiments, the virtual item generation module is configured to extract feature description information from the virtual item description voice; the feature description information includes type information and style information;

[0015] Generate a virtual item described by the virtual item description voice according to the feature description information.

[0016] In some embodiments, the virtual item generation module is configured to input the feature description information into a first item generation model, and obtain the virtual item described by the virtual item description voice output by the first item generation model.

[0017] In some embodiments, the virtual item generation module is configured to query a virtual item template library according to the feature description information, and obtain a virtual item template corresponding to the feature description information from the virtual item template library;

[0018] Input the virtual item template and the feature description information into a second item generation model, and obtain the virtual item described by the virtual item description voice output by the second item generation model.

[0019] In some embodiments, the apparatus further includes:

[0020] A preview interface display module, configured to display a virtual item preview interface before displaying, in a live interface corresponding to the live room, a special effect of giving the virtual item to a second user account in the live room; the virtual item preview interface is configured to display the generated virtual item;

[0021] A virtual item gift module, configured to, before displaying, in a live interface corresponding to the live room, a special effect of giving the virtual item to a second user account in the live room, in response to receiving a gift operation on the virtual item performed in the virtual item preview interface, give the virtual item to a second user account in the live room.

[0022] In some embodiments, the virtual item preview interface includes a gift quantity setting item, and the apparatus further includes:

[0023] A gift quantity setting module, configured to, before giving the virtual item to a second user account in the live room in response to receiving a gift operation on the virtual item performed in the virtual item preview interface, set the gift quantity of the virtual item in response to a setting operation on the gift quantity setting item.

[0024] The virtual item gifting module is configured to, in response to receiving the gifting operation performed in the virtual item preview interface, gift the virtual items in the gifting quantity to the second user account in the live streaming room.

[0025] In some embodiments, the virtual item preview interface includes at least two virtual items, and the at least two virtual items are different virtual items generated based on the virtual item description voice.

[0026] The virtual item gifting module is configured to, in response to a selection operation on at least one of the at least two virtual items, gift the selected at least one virtual item to the second user account in the live streaming room.

[0027] In some embodiments, the device further includes:

[0028] The virtual resource deduction module is configured to, before displaying the special effect of gifting the virtual item to the second user account in the live streaming room corresponding to the live streaming interface, in response to the gifting operation on the virtual item, deduct the virtual resources corresponding to the virtual item from the first user account.

[0029] In some embodiments, the quantity of the virtual resources corresponding to the virtual item is positively correlated with the complexity of the virtual item.

[0030] In some embodiments, the device further includes:

[0031] The recommended virtual item display module is configured to, before gifting the virtual item to the second user account in the live streaming room, when the quantity of the virtual resources in the first user account does not meet the quantity of the virtual resources corresponding to the virtual item, display at least two recommended virtual items; the at least two recommended virtual items are alternative virtual items generated based on the virtual item description voice; the quantity of the virtual resources corresponding to the recommended virtual items is lower than the quantity of the virtual resources corresponding to the virtual item.

[0032] The recommended virtual item gifting module is configured to, in response to a selection operation on at least one of the at least two recommended virtual items, gift the selected recommended virtual item to the second user account in the live streaming room.

[0033] In some embodiments, the virtual item generation module is configured to, when generating at least two identical virtual items exceeding a quantity threshold within a specified time period in the live streaming room based on the virtual item description voice, synthesize the at least two identical virtual items into an upgraded virtual item.

[0034] In some embodiments, the gift special effect display module is configured to display, in the live broadcast interface corresponding to the live broadcast room, a special effect of presenting the upgraded virtual item to a second user account in the live broadcast room.

[0035] In another aspect, a computer device is provided, which includes a processor and a memory. At least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the live broadcast room interaction method as described above.

[0036] In another aspect, a computer-readable storage medium is provided. At least one instruction, at least one program, a code set or an instruction set is stored in the storage medium, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the live broadcast room interaction method as described above.

[0037] In still another aspect, a computer program product is provided. The computer program product includes a computer program, and the computer program is stored in a computer-readable storage medium. The processor of the computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the live broadcast room interaction method provided in the above various optional implementation manners.

[0038] The technical solution provided by this application may include the following beneficial effects:

[0039] Users in the live broadcast room can describe the virtual item they want to give through voice, which simplifies the operation process of giving virtual items in the live broadcast room. The computer device generates a virtual item corresponding to the virtual item description voice through the virtual item description voice, with high accuracy. On the basis of simplifying the operation process, the generated virtual item can meet the personalized needs of users, effectively improving the efficiency of virtual item giving by users in the live broadcast room and enhancing the interaction effect between users and the live broadcast room.

[0040] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0042] Figure 1 It is a system composition diagram of the live broadcast room interaction method according to an embodiment of this application;

[0043] Figure 2It is a flowchart of a live - broadcast room interaction method provided by an embodiment of the present application;

[0044] Figure 3 It is a flowchart of a live - broadcast room interaction method provided by an embodiment of the present application;

[0045] Figure 4 It is a flowchart of a live - broadcast room interaction method provided by an embodiment of the present application;

[0046] Figure 5 It is a schematic diagram of a live - broadcast room interaction method provided by an embodiment of the present application;

[0047] Figure 6 It is a schematic diagram of a live - broadcast room interaction method provided by an embodiment of the present application;

[0048] Figure 7 It is a schematic diagram of a live - broadcast room interaction method provided by an embodiment of the present application;

[0049] Figure 8 It is a system diagram of a live - broadcast room interaction method provided by an embodiment of the present application;

[0050] Figure 9 It is a block diagram of a live - broadcast room interaction device provided by an exemplary embodiment of the present application;

[0051] Figure 10 It is a schematic structural diagram of a computer device provided by an exemplary embodiment of the present application. Detailed implementation

[0052] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application.

[0053] On the contrary, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0054] The present application proposes a live - broadcast room interaction solution. This solution can generate virtual items according to the virtual - item - description voice sent by the user corresponding to the first user account in the live - broadcast room, and in the live - broadcast room, give the generated virtual items to the second user account to improve the efficiency of virtual - item giving in the live - broadcast room and the efficiency of user interaction with the live - broadcast room.

[0055] Figure 1 It is a system composition diagram of a live - broadcast room interaction method related to an embodiment of the present application. As Figure 1As shown in the figure, the system includes a computer device 100, which can display or manage a live broadcast room 10. For example, the computer device 100 can be a server that supports live broadcast services, or the computer device 100 can be the terminal device of the host of the live broadcast room 10, or the computer device 100 can also be the terminal device of the audience in the live broadcast room 10, or the computer device 100 can include at least two of the above-mentioned server, the host's terminal device, and the audience's terminal device. The computer device 100 can obtain the virtual prop description voice sent by the user corresponding to the first user account in the live broadcast room 10, and generate a virtual prop described by the virtual prop description voice based on the virtual prop description voice; the user of the first user account can perform a gift operation on the generated virtual prop, and display special effects of giving the virtual prop to the second user account in the live broadcast room 10 on the live broadcast interface corresponding to the live broadcast room 10.

[0056] It should be noted that in the embodiments of the present application, the above solution is implemented by a single-sided device. Optionally, the above solution can also be implemented by the interaction of two-sided devices.

[0057] Figure 2 It is a flowchart of a live broadcast room interaction method provided by an embodiment of the present application. Among them, the live broadcast room interaction method can be executed by a computer device. For example, the computer device can be the computer device 100 shown above. Figure 1 The above live broadcast room interaction method can include step 210, step 220, and step 230, and the specific implementation is as follows:

[0058] Step 210: Receive the virtual prop description voice sent by the user corresponding to the first user account in the live broadcast room.

[0059] Among them, the above live broadcast room is a real-time video streaming platform, and the audience can watch the live broadcast content through the live broadcast room and interact with the host in the live broadcast room.

[0060] Among them, the above first user account is the account of the user who performs operations during the interaction in the live broadcast room. For example, it is the account of the audience user in the live broadcast room.

[0061] Among them, the above virtual prop description voice refers to the voice of the virtual prop that the user corresponding to the first user account hopes to give in the live broadcast room described by voice input. The virtual prop description voice can include information such as the specific type, style, or other characteristics of the virtual prop.

[0062] In the embodiments of the present application, the first user account can request and obtain the access permission of the microphone, input the virtual prop description voice through the microphone, and after the computer device receives the virtual prop description voice, use automatic speech recognition technology to convert the virtual prop description voice into text.

[0063] Step 220: Generate a virtual item described by the virtual item description voice based on the virtual item description voice.

[0064] Among them, the above virtual item is a digital item used for interaction or expression of support on the live streaming platform, and has different types and styles.

[0065] In the embodiments of the present application, the manifestation forms of the virtual items generated by the computer device include but are not limited to three-dimensional model files, two-dimensional images or icons, scripts or code snippets, and audio files.

[0066] Step 230: Display the special effects of presenting the virtual item to the second user account in the live streaming room on the corresponding live streaming interface of the live streaming room.

[0067] Among them, the above second user account is the target user account for receiving virtual items. In the embodiments of the present application, the above second user account may be the user account of the host in the current live streaming room, the user account of the management team of the live streaming room, or the user account of other viewers in the live streaming room.

[0068] Among them, the above live streaming interface is a visual interface for interaction between viewers and the host.

[0069] In the embodiments of the present application, the computer device responds to receiving a trigger instruction for a virtual item, and displays the special effects of presenting the virtual item to the second user account in the live streaming room on the corresponding live streaming interface of the live streaming room; the trigger instruction includes at least one of the following:

[0070] The virtual item description voice is obtained to meet the specified duration;

[0071] Obtain the specified voice command and / or gesture command executed by the user corresponding to the first user account;

[0072] The gift control of the target live streaming room is triggered.

[0073] Optionally, the computer device responds to obtaining that the virtual item description voice meets the specified duration, and displays the special effects of presenting the virtual item to the second user account in the live streaming room on the corresponding live streaming interface of the live streaming room.

[0074] In the embodiments of the present application, the user can trigger the presentation of virtual items by speaking specific voice instructions. For example, during the live streaming process, the user can speak the virtual item description voice of "present a rose". If the input of the virtual item description voice meets the specified duration (for example, more than 2 seconds), trigger the presentation of the virtual item (for example, a rose) to the second user account in the target live streaming room, and display the presentation special effects on the live streaming interface.

[0075] In the embodiments of the present application, the computer device triggers the display of a gift special effect by setting that the voice command needs to meet a certain duration, which can effectively reduce the possibility of accidental triggering and improve the accuracy of speech recognition.

[0076] Optionally, in response to receiving a specified voice and / or gesture command executed by a user corresponding to a first user account, the computer device displays a special effect of presenting a virtual item to a second user account in the live broadcast interface corresponding to the live broadcast room.

[0077] For example, the user corresponding to the first user account can make a specific gesture (such as a heart gesture) or say a specific voice command (such as "send a gift"). After the computer device recognizes the specified voice and / or gesture command, it automatically executes the operation of presenting the virtual item and displays the gift effect in the live broadcast interface.

[0078] In the embodiments of the present application, the gesture recognition function is extended, providing a novel interaction means for users and improving the interaction effect between users and the live broadcast room.

[0079] Optionally, in response to receiving a gift control (such as a gift control displayed in the live broadcast interface on the terminal device side corresponding to the first user account) being clicked, the computer device displays a special effect of presenting a virtual item to a second user account in the live broadcast interface corresponding to the live broadcast room.

[0080] In the embodiments of the present application, during the process of the user corresponding to the first user account watching the live broadcast, various interaction options and controls in the live broadcast interface can be seen. After the user corresponding to the first user account selects the virtual item to be presented and clicks the corresponding gift button, the computer device displays a special effect of presenting the selected virtual item to the second user account in the live broadcast interface.

[0081] In the embodiments of the present application, by directly clicking the gift button on the live broadcast interface, the operation steps are made more simple and fast, effectively ensuring the high efficiency of the interaction between the user and the live broadcast room.

[0082] In the embodiments of the present application, the users in the live broadcast room can describe the virtual item to be presented through voice, simplifying the operation process of presenting virtual items in the live broadcast room. The computer device generates a virtual item corresponding to the virtual item description voice through the virtual item description voice, with high accuracy. On the basis of simplifying the operation process, the generated virtual item can meet the personalized needs of users, effectively improving the efficiency of presenting virtual items by users in the live broadcast room and enhancing the interaction effect between users and the live broadcast room.

[0083] Based on Figure 2 please refer to Figure 3 Figure 3 ​It is a flowchart of an interactive method in a live broadcast room provided by an embodiment of the present application. The above step 220 can be implemented as step 220a and step 220b, specifically as follows:

[0084] Step 220a: Extract feature description information from the virtual prop description voice; the feature description information includes type information and style information.

[0085] Among them, the above feature description information is the attribute information used to describe the virtual prop extracted by the computer device from the virtual prop description voice, and the feature description information includes, but is not limited to, type information and style information.

[0086] Among them, the above type information is the information used to describe the basic category and / or functional attributes of the virtual prop. For example, virtual props can be divided into different types according to different functions. Virtual props of the weapon type can be swords or bows and arrows; virtual props of the tool type can be pickaxes or shovels; virtual props of the decoration type can be necklaces or hats.

[0087] Among them, the above style information is the information used to describe the appearance attributes of the virtual prop. The style information includes, but is not limited to, the color, material, shape, and decorative details of the virtual prop. For example, if the virtual prop is a sword, the style information of the sword can indicate that the sword body is silver with blue flame texture (color and material), the sword hilt is inlaid with gems (decorative details), and the overall shape is an arc design (shape).

[0088] In the embodiment of the present application, the computer device can use automatic speech recognition technology to convert the virtual prop description voice into text, analyze the text through natural language processing technology, and extract the type information and style information about the virtual prop in the virtual prop description voice.

[0089] Step 220b: Generate the virtual prop described by the virtual prop description voice according to the feature description information.

[0090] In the embodiment of the present application, the computer device can generate the virtual prop described by the virtual prop description voice through a machine learning model according to the feature description information; it can also obtain a virtual prop template by querying the virtual prop template library, and further generate the virtual prop described by the virtual prop description voice based on the virtual prop template.

[0091] In the embodiment of the present application, the computer device can extract feature description information including type information and style information from the virtual prop description voice. The specific type information and style information can accurately describe the detailed features of the virtual prop of the user's intention. The computer device generates the corresponding virtual prop according to the detailed features, which can effectively improve the accuracy of virtual prop generation.

[0092] Based on the solutions shown in any one or more of the above embodiments, step 220b can be implemented as follows: Input the feature description information into the first prop generation model, and obtain the virtual prop described by the virtual prop description voice output by the first prop generation model.

[0093] Among them, the above first prop generation model is a machine learning model capable of generating a virtual prop corresponding to the input feature description information.

[0094] Exemplarily, when the computer device receives the feature description information "red rose", it inputs the feature description information into the first prop generation model and obtains the red rose generated by the first prop generation model.

[0095] In some embodiments, the above first prop generation model is a generative language model. For example, in the LLM (Large Language Model) model, the computer device constructs a first prompt word according to the feature description information, inputs the first prompt word into the first prop generation model, and obtains the virtual prop output by the first prop generation model.

[0096] Exemplarily, when the computer device obtains the feature description information that is a blue rocket, the computer device constructs a first prompt word according to the feature description information: "Generate a blue rocket", inputs this prompt word into the generative language model, and obtains a detailed virtual prop description file output by the generative language model. The virtual prop description file includes 3D model data, texture maps, and animation sequences.

[0097] In the embodiments of the present application, the computer device directly inputs the feature description information into the first prop generation model. Since the machine learning model (the first prop generation model) has strong learning ability, the virtual prop can be directly generated through the first prop generation model, which greatly improves the generation efficiency of the virtual prop on the basis of ensuring the accuracy of the virtual prop generation.

[0098] Based on the solutions shown in any one or more of the above embodiments, step 220b can be implemented as follows: Query the virtual prop template library according to the feature description information, and obtain the virtual prop template corresponding to the feature description information from the virtual prop template library; Input the virtual prop template and the feature description information into the second prop generation model, and obtain the virtual prop described by the virtual prop description voice output by the second prop generation model.

[0099] Among them, the above virtual prop template library is a database storing at least two predefined virtual prop templates. In the embodiments of the present application, each virtual prop template contains basic prop design elements and parameters. In the embodiments of the present application, the computer device can adjust the virtual prop template according to specific requirements or perform secondary creation on the virtual prop template.

[0100] In the embodiments of the present application, after receiving the feature description information, the computer device converts the feature description information into a format suitable for querying. For example, the feature description information is converted into structured data (such as a JSON object), and the structured data is used as a query condition to search for a template matching the structured data in the virtual prop template library. The virtual prop template library can be constructed based on a database management system. In the virtual prop template library, each virtual prop template is provided with metadata tags (such as type, style) for efficient retrieval.

[0101] Among them, the above second prop generation model is a machine learning model capable of generating virtual props according to the input feature description information and virtual prop templates.

[0102] Exemplarily, the feature description information is "red rose". The virtual prop template library contains different types of flower templates (such as rose, peony, rose...). After receiving the feature description information, the computer device obtains the rose template from the virtual prop templates, and further inputs the rose template and the feature description information into the second prop generation model to obtain the red rose output by the second prop generation model.

[0103] In some embodiments, the above second prop generation model is a generative language model (such as an LLM model). The computer device constructs a second prompt word according to the feature description information, and inputs the second prompt word and the virtual prop template into the second prop generation model to obtain the virtual prop output by the second prop generation model.

[0104] Exemplarily, the computer device obtains the feature description information as a red heart. The computer device constructs a second prompt word according to the feature description information: "Generate a red heart with the heart template as a reference", and inputs the second prompt word and the heart template previously queried from the virtual prop template library into the generative language model (the second prop generation model) together to obtain a detailed virtual prop description file output by the second prop generation model. The virtual prop description file contains the optimized 3D model data, texture mapping, and animation sequence of the heart template.

[0105] In an embodiment of the present application, the computer device matches and queries in the virtual prop template library according to feature description information such as type information and / or style information, obtains the virtual prop template that best meets the user's needs, simplifies the generation process of virtual props by quickly obtaining the template, improves the efficiency of obtaining virtual props, inputs the selected virtual prop template and feature description information into the second prop generation model, and can further generate virtual props according to the user's needs on the virtual prop template, making the generated virtual props more accurate.

[0106] Based on Figure 2 , please refer to Figure 4 , Figure 4 is a flowchart of a live broadcast room interaction method provided by an embodiment of the present application. Before the above step 230, the method further includes step 226 and step 228, which are specifically as follows.

[0107] Step 226: Display a virtual prop preview interface; the virtual prop preview interface is used to display the generated virtual props.

[0108] Among them, when the above computer device is the terminal device corresponding to the first user account, the computer device can display a virtual prop preview interface; the above virtual prop preview interface is a user interface for displaying the virtual props generated by the computer device according to the user's voice description, and the virtual prop preview interface may include a detailed view, attribute information, and operation options of the virtual props.

[0109] In an embodiment of the present application, after the computer device obtains the generated virtual props, it converts the data of the virtual props into a format suitable for display, for example, an image or a 3D (Three–Dimensional) model, and constructs a virtual prop preview interface through front-end technology. In an embodiment of the present application, the virtual prop preview interface supports a dynamic adjustment function, that is, the user can adjust the virtual props in the virtual prop preview interface through specified operations. For example, the user can adjust the color or size of the virtual props by performing specified operations on the slider in the virtual prop preview interface.

[0110] Step 228: In response to receiving a gift operation on the virtual prop in the virtual prop preview interface, gift the virtual prop to the second user account in the live broadcast room.

[0111] Among them, the above gift operation is actually performed by the user on the virtual prop preview interface and is used to confirm the operation of gifting the virtual prop to the target user (i.e., the second user account).

[0112] In the embodiments of the present application, an event listener is set on the virtual prop preview interface, and the event listener can capture interactive operations of the user such as clicks and touches. For example, the virtual prop preview interface includes a "give" button. After the user clicks the "give" button, the virtual prop preview interface triggers an operation of giving the virtual prop to a second user account in the live broadcast room.

[0113] In some embodiments, the virtual prop preview interface further includes at least two preview items, and the preview items include but are not limited to visual effect previews and sound effect previews.

[0114] In the embodiments of the present application, the computer device performs secondary editing on the virtual prop in response to an editing operation on at least two preview items, and the secondary editing may be at least one of adjusting the special effect color, scaling the size, adjusting the animation speed, combining special effects, and modifying the appearance style.

[0115] In the embodiments of the present application, the virtual prop preview interface allows the user to intuitively view the generated virtual prop, ensuring that the previewed virtual prop meets the user's expected requirements, reducing the giving errors caused by generation errors or incorrect operations, enhancing the user's sense of participation and satisfaction. After receiving the user's giving operation, the virtual prop is given to the second user account in real time. Through an instant confirmation feedback mechanism, the user can give after confirming that the virtual prop is correct, increasing the controllability and flexibility of the operation, effectively ensuring the accuracy of the giving operation, and improving the interaction effect between the user and the live broadcast room.

[0116] Based on the solutions shown in any one or more of the above embodiments, the virtual prop preview interface includes a giving quantity setting item; before the above step 228, the computer device sets the giving quantity of the virtual prop in response to a setting operation on the giving quantity setting item; the above step 228 may be implemented as giving the virtual props of the giving quantity to the second user account in the live broadcast room in response to receiving a giving operation performed in the virtual prop preview interface.

[0117] Among them, the above giving quantity setting item is a functional component on the virtual prop preview interface, and the giving quantity setting item allows the user to specify the specific quantity of the virtual prop that they hope to give.

[0118] In the embodiments of the present application, the above giving quantity setting item may be in the form of a drop-down menu, an input box, or a slider, and the setting operation may be typing or voice input.

[0119] In the embodiments of the present application, the computer device configures an event listener for the giving quantity setting item. When the user adjusts the value, the event listener captures the user's setting operation and stores the newly set value of the giving quantity setting item in the memory or database.

[0120] In some embodiments, the computer device batch-sets the gift quantities of different types of virtual items in response to a setting operation on the gift quantity setting item; and in response to receiving a batch gift operation performed on different types of virtual items in the virtual item preview interface, batches and gifts the virtual items with the set gift quantity to a second user account in the live broadcast room.

[0121] In the embodiments of the present application, when the user completes the gift quantity setting and confirms the operation by clicking the "Gift" button or other interaction methods, a corresponding background logic processing flow is triggered.

[0122] In some embodiments, the computer device displays a secondary confirmation prompt message in response to receiving a gift operation on a virtual item performed in the virtual item preview interface. The secondary confirmation prompt message is used to remind the user whether to confirm to gift the virtual items corresponding to the quantity in the gift quantity setting item to a second user account in the live broadcast room; and in response to the user's confirmation operation on the secondary confirmation prompt message, gifts the virtual items with the set gift quantity to a second user account in the live broadcast room.

[0123] In the embodiments of the present application, by displaying the secondary confirmation prompt message, it is convenient for the user to directly view and confirm the quantity of virtual items to be gifted, avoiding gift errors caused by misoperations and losses to the user.

[0124] In the embodiments of the present application, a gift quantity setting item is added to the virtual item preview interface. The user can select the quantity of virtual items to be gifted through the gift quantity setting item, and according to the set gift quantity, the corresponding quantity of virtual items is personalized and gifted to the second user account in real time, providing an immediate and accurate feedback mechanism, effectively reducing incorrect gifting caused by misoperations, and improving the interaction effect between the user and the live broadcast room.

[0125] Based on the solutions shown in any one or more of the above embodiments, the virtual item preview interface includes at least two virtual items, and the at least two virtual items are different virtual items generated based on virtual item description voices; the above step 228 can be implemented as, in response to a selection operation on at least one of the at least two virtual items, gifting the selected at least one virtual item to a second user account in the live broadcast room.

[0126] Among them, the at least two virtual items are different types of virtual items generated by a item generation model based on the feature description information provided by the user, and the at least two virtual items may have different types (for example, flowers, rockets) or styles (for example, colors, patterns).

[0127] In the embodiments of the present application, the virtual item preview interface includes at least two virtual items. The at least two virtual items are virtual items generated based on feature description information. The at least two virtual items can be virtual items of the same type but different colors, or virtual items of the same color but different types, or virtual items that comprehensively consider all attributes and have the highest degree of relevance to the feature description information.

[0128] Optionally, the virtual item preview interface includes at least two virtual items of the same type. The at least two virtual items of the same type are virtual items of the same type but different colors generated based on feature description information.

[0129] Optionally, the virtual item preview interface includes at least two virtual items of the same color. The at least two virtual items of the same color are virtual items of the same color but different types generated based on feature description information.

[0130] Optionally, the virtual item preview interface includes at least two comprehensively recommended virtual items. The at least two comprehensively recommended virtual items are virtual items generated based on feature description information and have the highest degree of relevance to the feature description information.

[0131] In the embodiments of the present application, the computer device can generate at least two virtual items based on the feature description information for the user to select, giving the user more reference possibilities to select the virtual item that is closest to the requirement.

[0132] Among them, the above selection operation is a direct selection operation by the user on the virtual item. For example, the user directly clicks on the virtual item to select it.

[0133] In the embodiments of the present application, the user can select one or more virtual items in the virtual item preview interface and give them to the second user account in the live broadcast room.

[0134] In the embodiments of the present application, the user can directly view the virtual items generated by the virtual item description voices of multiple virtual items in the virtual item preview interface and select the most suitable virtual item from the multiple virtual items, effectively reducing the limitation caused by a single virtual item option and improving the interaction effect between the user and the live broadcast room.

[0135] Based on the solutions shown in any one or more of the above embodiments, before step 230, the computer device deducts the virtual resources corresponding to the virtual item in the first user account in response to the operation of giving the virtual item.

[0136] Among them, the above virtual resources are digital assets in the first user account that can be used to purchase or give virtual items, such as virtual gold coins and points.

[0137] In the embodiments of the present application, each user account in the live broadcast room can have virtual resources, and the virtual resources can be obtained by the user's offline / online recharge.

[0138] In the embodiments of the present application, each virtual item corresponds to a specified amount of virtual resources, and the user can exchange virtual resources with the balance of virtual resources in their own account.

[0139] In the embodiments of the present application, after the user performs a gift operation, the computer device verifies the user's identity information, confirms that the current gift operation is initiated by a legitimate first user account, verifies whether the first user account is normal, calculates the total amount of virtual resources required to be consumed according to the virtual item selected by the user and the quantity of the virtual item, and deducts the virtual resources from the first user account.

[0140] Exemplarily, the virtual item selected by the user corresponds to 5 points, and the selected gift quantity is 2. After the user performs the gift operation, the computer device deducts 10 points from the first user account.

[0141] In some embodiments, in response to a gift operation of a virtual item, the virtual resources corresponding to the virtual item are deducted from the first user account. In the case where the virtual resources in the first user account are insufficient to pay for the virtual item, virtual resource recharge information is displayed. The virtual resource recharge information includes the quantity of virtual resources still owed by the first user account in the case of paying for the virtual resources, which is used to prompt the user to recharge; optionally, the virtual resource recharge information includes a quick recharge entry, and the user can enter the quantity of virtual resources to be recharged for the quick recharge entry to achieve quick recharge.

[0142] In the embodiments of the present application, in the case of insufficient virtual resources, the user can quickly recharge to improve the gift efficiency of virtual items in the live broadcast room.

[0143] In the embodiments of the present application, the computer device automatically deducts the virtual resources corresponding to the virtual item from the first user account in response to the user's virtual item gift operation, ensuring the authenticity and effectiveness of each gift behavior of the virtual item in the live broadcast room, avoiding invalid or fraudulent interactions, and ensuring the interaction effect between the user and the live broadcast room.

[0144] Based on the solutions shown in any one or more of the above embodiments, the quantity of virtual resources corresponding to a virtual item is positively correlated with the complexity of the virtual item.

[0145] Among them, the above complexity level is the design complexity of virtual items, including but not limited to design complexity (e.g., the number of polygons of a 3D model, texture resolution), special effect complexity, such as the number and types of special effects (e.g., particle effects, light and shadow changes) and their rendering complexity, interaction complexity (e.g., whether the item includes interaction functions, such as click-triggered animations, sound effects), and so on.

[0146] In the embodiments of the present application, the higher the complexity level of a virtual item, the greater the consumption of virtual resources corresponding to the virtual item.

[0147] In the embodiments of the present application, virtual items with different complexity levels correspond to different amounts of virtual resources. Users can select virtual items with different complexity levels for gifting according to their actual needs and resource situations, which improves the interaction effect between users and the live broadcast room while meeting the needs of users at different levels.

[0148] Based on the solutions shown in any one or more of the above embodiments, before a computer device gifts a virtual item to a second user account in a live broadcast room, when the number of virtual resources of the first user account does not meet the number of virtual resources corresponding to the virtual item, at least two recommended virtual items are displayed; the at least two recommended virtual items are alternative virtual items generated based on the virtual item description voice; the number of virtual resources corresponding to the recommended virtual items is lower than the number of virtual resources corresponding to the virtual item; in response to a selection operation on at least one of the at least two recommended virtual items, the selected recommended virtual item is gifted to the second user account in the live broadcast room.

[0149] Among them, the above recommended virtual items are alternative virtual items recommended by the computer device when the virtual resources of the first user account are not sufficient to purchase or gift the target virtual item, and the number of virtual resources corresponding to the recommended items is lower than the number of virtual resources corresponding to the virtual item originally intended to be gifted by the user.

[0150] In the embodiments of the present application, the at least two recommended virtual items are virtual items generated based on feature description information, and the at least two recommended virtual items can be virtual items of the same type or virtual items of the same style.

[0151] In some embodiments, when the number of virtual resources of the first user account does not meet the number of virtual resources corresponding to the virtual item, at least two recommended virtual items of the same type as the virtual item are displayed; the at least two recommended virtual items of the same type as the virtual item are alternative virtual items generated based on the virtual item description voice; the number of virtual resources corresponding to the recommended virtual items is lower than the number of virtual resources corresponding to the virtual item.

[0152] In some embodiments, when the quantity of virtual resources of the first user account does not meet the quantity of virtual resources corresponding to the virtual item, at least two recommended virtual items with the same style as the virtual item are displayed; the at least two recommended virtual items with the same style as the virtual item are alternative virtual items generated based on the virtual item description voice; the quantity of virtual resources corresponding to the recommended virtual item is lower than the quantity of virtual resources corresponding to the virtual item.

[0153] Exemplarily, assume that the user wants to gift a complex "Magic Castle" virtual item to a second user account in the live streaming room, but the balance of virtual resources of the first user account corresponding to the user is insufficient. After the user clicks the "Gift" button, the computer device queries the balance of virtual resources of the first user account and finds that the balance of virtual resources of the first user account is insufficient to pay for the "Magic Castle". A prompt message indicating insufficient virtual resources is displayed, and the user is advised to view the recommended virtual items; feature description information (such as "castle", "magic") is extracted from the user's virtual item description voice; virtual item templates that match but have a lower resource consumption (such as "Small Magic Tower", "Magic Crystal Ball") are searched for in the virtual item template library, and at least two recommended virtual items are generated using the item generation model and displayed on the virtual item preview interface. User A selects a "Small Magic Tower" on the preview interface and clicks the "Confirm Gift" button. The computer device deducts the corresponding quantity of virtual resources from the first user account and records the transaction information, thus realizing the gift of the "Small Magic Tower" to the second user account in the live streaming room.

[0154] In the embodiments of the present application, when the quantity of virtual resources of the first user account does not meet the quantity of virtual resources corresponding to the virtual item, at least two recommended virtual items with the same attributes as the virtual item and with a quantity of virtual resources corresponding lower than that of the virtual item are displayed as alternative virtual items, ensuring that the user can still perform the gift operation even when the virtual resources are insufficient, realizing the interactive operation with the live streaming room, and effectively guaranteeing the interactive effect with the live streaming room.

[0155] Based on the solutions shown in any one or more of the above embodiments, step 220 can be implemented as synthesizing at least two identical virtual items into an upgraded virtual item within a specified time period in the live streaming room based on the virtual item description voice when the number of at least two identical virtual items generated exceeds the quantity threshold; step 230 can be implemented as displaying special effects of gifting the upgraded virtual item to the second user account in the live streaming interface corresponding to the live streaming room.

[0156] Among them, the above-specified time period is a specific time window set during the live streaming process, such as "the first 10 minutes after the host starts the live stream" or "the first 5 minutes of each hour".

[0157] Among them, the above quantity threshold is a numerical limit set by the computer device, which is used to represent how many identical virtual items need to be generated within a specified time period in the live broadcast room to trigger the synthesis operation.

[0158] Among them, the above upgraded virtual item is a higher-level virtual item generated by combining multiple identical virtual items. The upgraded virtual item has higher value and richer special effects.

[0159] In the embodiment of the present application, when the computer device generates at least two identical virtual items exceeding the quantity threshold within the specified time period in the live broadcast room based on the virtual item description voice, it marks at least two identical virtual items, and synthesizes the marked at least two identical virtual items into an upgraded virtual item according to the preset synthesis rules. For example, within 30 seconds, three identical "ordinary rockets" are generated, and according to the preset synthesis rules, the three identical "ordinary rockets" can be synthesized into one "luxury rocket".

[0160] In the embodiment of the present application, each upgraded virtual item has a corresponding gift-giving special effect, and different upgraded virtual items have different corresponding gift-giving special effects.

[0161] In the embodiment of the present application, through the synthesis mechanism, users can accumulate multiple identical items in a short time and upgrade them to higher-level virtual items, expanding the gift-giving methods and gift-giving effects of virtual items in the live broadcast room, and effectively ensuring the interaction effect between users and the live broadcast room.

[0162] Based on the solutions shown in any one or more of the above embodiments, please refer to Figure 5 , Figure 5 which is a schematic diagram of a live broadcast room interaction method provided by an embodiment of the present application.

[0163] Taking the interaction between the terminal device and the server as an example, the terminal device can be a personal computer device such as a tablet computer, a mobile phone, a desktop computer, a laptop computer, or a personal workstation.

[0164] The server is the server corresponding to the terminal device, which can be a server cluster dedicated to live broadcast services independently deployed in the cloud, a single server, or several servers, or a virtualization platform, or a cloud computing service center.

[0165] The terminal device and the server can be connected through a communication network. Optionally, the communication network is a wired network or a wireless network.

[0166] Optionally, the above-mentioned wireless network or wired network uses standard communication technologies and / or protocols. The network is usually the Internet, but can also be any network, including but not limited to any combination of a Local Area Network (LAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a mobile, wired or wireless network, a private network or a virtual private network. In some embodiments, technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. are used to represent the data exchanged through the network. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec), etc. can be used to encrypt all or some of the links. In other embodiments, customized and / or dedicated data communication technologies can be used to replace or supplement the above data communication technologies.

[0167] Exemplarily, as Figure 5 shown, the above terminal device can be a mobile phone 51, and the server can be a cloud server 52. The mobile phone 51 displays the live broadcast room A. The user logs in to his own account (i.e., the first user account) on the mobile phone 51 and watches the live broadcast room A using the identity of the first user account. When the user wants to reward / give gifts to the host in the live broadcast room A (i.e., the second user account), a description voice (i.e., virtual prop description voice) for describing the gift to be rewarded can be sent. After receiving the virtual prop description voice sent by the user, the mobile phone 51 uploads the virtual prop description voice to the cloud server 52. The cloud server 52 extracts the feature description information containing the type information and style information of the virtual prop from the virtual prop description voice, and generates a virtual prop corresponding to the virtual prop description voice based on the feature description information. In the embodiments of the present application, it can be generated in two ways: First, directly input the feature description information into the first prop generation model to directly obtain the virtual prop described by the virtual prop description voice output by the first prop generation model; Second, query the virtual prop template library according to the feature description information, and obtain the virtual prop template corresponding to the feature description information from the virtual prop template library; Input the virtual prop template and the feature description information into the second prop generation model, and obtain the virtual prop described by the virtual prop description voice output by the second prop generation model.

[0168] After the cloud server 52 generates a virtual item, it sends the virtual item to the mobile phone 51, and the generated virtual item is displayed in the virtual item preview interface in live room A. The virtual item preview interface includes a gift quantity setting item, and the user can perform a setting operation on the gift quantity setting item to set the gift quantity of the virtual item. In response to receiving the gift operation on the virtual item performed in the virtual item preview interface, the mobile phone 51 gifts the virtual items of the gift quantity to the second user account in live room A, and an effect of gifting the virtual item to the second user account in live room A is displayed in live room A.

[0169] In the embodiment of the present application, the user can customize virtual items through voice descriptions, enhancing the interactivity between the user and the live room through personalized interaction methods.

[0170] In some embodiments, in response to the gift operation on the virtual item, the virtual resources corresponding to the virtual item in the first user account are deducted; the quantity of the virtual resources corresponding to the virtual item is positively correlated with the complexity of the virtual item.

[0171] When the quantity of virtual resources in the first user account does not meet the quantity of virtual resources corresponding to the virtual item, the mobile phone 51 displays at least two recommended virtual items; the at least two recommended virtual items are alternative virtual items generated based on the virtual item description voice; the quantity of virtual resources corresponding to the recommended virtual item is lower than the quantity of virtual resources corresponding to the virtual item; in response to the selection operation on at least one of the at least two recommended virtual items, the selected recommended virtual item is gifted to the second user account in live room A.

[0172] Please refer to Figure 6 , Figure 6 which is a schematic diagram of an interactive method for a live room provided by an embodiment of the present application.

[0173] As Figure 6 shown in part (a) of, in live room A, it is shown that the first user account has 8 gold coins of virtual resources, and the generated virtual item requires 9 gold coins. When the virtual resources of the first user account are insufficient, at least two recommended virtual items are displayed. As Figure 6 shown in part (b) of, recommended virtual item 1 and recommended virtual item 2 are displayed. The number of gold coins consumed by these two recommended virtual items is lower than the number of gold coins of the initially generated virtual item. The user selects recommended virtual item 2 and then clicks to gift. As Figure 6 shown in part (c) of, 1 virtual item 2 is successfully gifted to the second user account in live room A, and at the same time, 6 gold coins are deducted, and the first user account still has 2 gold coins left.

[0174] In an embodiment of the present application, when it is detected that the user's virtual resources are insufficient to purchase the preferred virtual item, the mobile phone automatically displays an alternative solution that consumes fewer gold coins, that is, recommends a virtual item, ensuring that the user still has the opportunity to participate in the interaction. The recommended virtual item is personalized according to the user's initial selection, ensuring that the recommended virtual item can match the user's wishes and guaranteeing the interactivity between the user and the live broadcast room. Figure 1 to ensure the consistency between the user and the live broadcast room and guarantee the interactivity between the user and the live broadcast room.

[0175] In some embodiments, when the mobile phone 51 generates at least two identical virtual items exceeding the quantity threshold within a specified time period in the live broadcast room A based on the virtual item description voice, the mobile phone 51 synthesizes the at least two identical virtual items into an upgraded virtual item; and displays the special effect of presenting the upgraded virtual item to the second user account in the live broadcast room A in the corresponding live broadcast interface of the live broadcast room A.

[0176] Please refer to Figure 7 , Figure 7 which is a schematic diagram of a live broadcast room interaction method provided by an embodiment of the present application.

[0177] As Figure 7 shown in part (d) of, the mobile phone 51 generates 3 identical petals within a specified time period in the live broadcast room A based on the virtual item description voice. When the user clicks the gift button, the 3 identical petals are synthesized into a flower. As Figure 7 shown in part (e) of, the special effect of presenting the flower to the second user account in the live broadcast room A is displayed in the corresponding live broadcast interface of the live broadcast room A.

[0178] In an embodiment of the present application, the user can generate multiple identical virtual items within a specified time period through a voice command. When generating identical virtual items exceeding the quantity threshold, the multiple identical virtual items are automatically synthesized into an upgraded virtual item, increasing the diversity of the virtual item effects and also increasing the interactivity and fun between the user and the live broadcast room, which helps to improve the interaction effect between the user and the live broadcast room.

[0179] Based on the steps in the above Figures 2 to 4 embodiment, an embodiment of the present application shows a method for a live broadcast room gift generation gameplay and system based on AI (Artificial Intelligence) speech recognition.

[0180] Please refer to Figure 8 , Figure 8 which is a system diagram of a live broadcast room interaction method provided by an embodiment of the present application. As Figure 8 shown, the system includes a user interaction module 81, a speech recognition and parsing module 82, an AI special effect generation module 83, and a special effect sending and display module 84.

[0181] In the embodiments of the present application, there are multiple abbreviations. The following is an introduction to the abbreviations involved and their definitions.

[0182] 1. Live room: A virtual platform where users interact with the host.

[0183] 2. Voice description: The user describes the appearance of the gift to the system through voice.

[0184] 3. AI-generated special effects: Using artificial intelligence technology, automatically generate and display gift effects according to the user's voice description.

[0185] 4. Host: The user who interacts with the audience and publishes content mainly in the live room.

[0186] The above user interaction module 81 is used to receive the voice input by the user through the live platform and send the description content of the voice (for example, 999 budding roses) to the computer device based on the received voice.

[0187] The above voice recognition and parsing module 82 is used to perform real-time recognition and natural language processing on the user's voice command, and extract key information (such as quantity, gift type, style) from the voice command.

[0188] The above AI special effect generation module 83 is used to call the current AI models on the market according to the information described by the user, and generate gift special effects corresponding to the described information through the AI models. For example, input "999 budding roses" into the AI model, obtain the animation of 999 budding roses generated by the AI model, and render it as a dynamic special effect in real time.

[0189] The above special effect sending and display module 84 is used to send the generated gift special effects to the live room where the host is located, and display and present them in real time in the live video, making the interaction between the user and the host more intuitive and emotional.

[0190] In the embodiments of the present application, the above solution can generate dynamic gift-giving special effects based on the user's voice command in the live room, providing a brand-new way of gift-giving, enabling the user to describe the appearance of the gift through voice, and making the host feel the user's personalized intention; the above solution effectively improves the interest and visual effect of the interaction experience between the user and the live room by realizing the real-time dynamic special effect gift-giving function; the user does not need to manually adjust or operate the gift, saving the time of giving gifts in the live room and improving the gift-giving efficiency.

[0191] Please refer to Figure 9, which shows a block diagram of a live - broadcast room interaction device provided by an exemplary embodiment of the present application. The live - broadcast room interaction device can be implemented as all or part of a computer device in a hardware or a combination of hardware and software manner to implement all or part of the steps in the embodiments as described above Figures 2 to 4 as Figure 9 shown. The live - broadcast room interaction device includes:

[0192] A description voice receiving module 901, configured to receive a virtual - prop description voice issued by a user corresponding to a first user account in the live - broadcast room;

[0193] A virtual - prop generating module 902, configured to generate a virtual prop described by the virtual - prop description voice based on the virtual - prop description voice;

[0194] A gift - giving special - effect display module 903, configured to display a special effect of giving the virtual prop to a second user account in the live - broadcast room in the live - broadcast interface corresponding to the live - broadcast room.

[0195] In some embodiments, the virtual - prop generating module 902 is configured to extract feature description information from the virtual - prop description voice; the feature description information includes type information and style information;

[0196] Generate a virtual prop described by the virtual - prop description voice according to the feature description information.

[0197] In some embodiments, the virtual - prop generating module 902 is configured to input the feature description information into a first prop - generating model and obtain the virtual prop described by the virtual - prop description voice output by the first prop - generating model.

[0198] In some embodiments, the virtual - prop generating module 902 is configured to query a virtual - prop template library according to the feature description information and obtain a virtual - prop template corresponding to the feature description information from the virtual - prop template library;

[0199] Input the virtual - prop template and the feature description information into a second prop - generating model and obtain the virtual prop described by the virtual - prop description voice output by the second prop - generating model.

[0200] In some embodiments, the device further includes:

[0201] A preview - interface display module, configured to display a virtual - prop preview interface before displaying the special effect of giving the virtual prop to a second user account in the live - broadcast room in the live - broadcast interface corresponding to the live - broadcast room; the virtual - prop preview interface is used to display the generated virtual prop;

[0202] The virtual item gifting module is used to gift the virtual item to the second user account in the live broadcast room in response to receiving a gifting operation on the virtual item performed in the virtual item preview interface, before displaying the special effect of gifting the virtual item to the second user account in the corresponding live broadcast interface of the live broadcast room.

[0203] In some embodiments, the virtual item preview interface includes a gifting quantity setting item, and the device further includes:

[0204] The gifting quantity setting module is used to set the gifting quantity of the virtual item in response to a setting operation on the gifting quantity setting item, before gifting the virtual item to the second user account in the live broadcast room in response to receiving a gifting operation on the virtual item performed in the virtual item preview interface.

[0205] The virtual item gifting module is used to gift the virtual item with the gifting quantity to the second user account in the live broadcast room in response to a gifting operation performed in the virtual item preview interface.

[0206] In some embodiments, the virtual item preview interface includes at least two virtual items, and the at least two virtual items are different virtual items generated based on the virtual item description voice.

[0207] The virtual item gifting module is used to gift the at least one selected virtual item to the second user account in the live broadcast room in response to a selection operation on at least one of the at least two virtual items.

[0208] In some embodiments, the device further includes:

[0209] The virtual resource deduction module is used to deduct the virtual resources corresponding to the virtual item from the first user account in response to a gifting operation on the virtual item, before displaying the special effect of gifting the virtual item to the second user account in the corresponding live broadcast interface of the live broadcast room.

[0210] In some embodiments, the quantity of the virtual resources corresponding to the virtual item is positively correlated with the complexity of the virtual item.

[0211] In some embodiments, the device further includes:

[0212] The recommended virtual item display module is used to display at least two recommended virtual items before gifting the virtual item to the second user account in the live broadcast room, when the quantity of the virtual resources of the first user account does not meet the quantity of the virtual resources corresponding to the virtual item; the at least two recommended virtual items are alternative virtual items generated based on the virtual item description voice; the quantity of the virtual resources corresponding to the recommended virtual item is lower than the quantity of the virtual resources corresponding to the virtual item.

[0213] The recommended virtual item gift module is used to respond to a selection operation on at least one recommended virtual item among at least two recommended virtual items, and gift the selected recommended virtual item to a second user account in the live broadcast room.

[0214] In some embodiments, the virtual item generation module 902 is used to synthesize upgraded virtual items from at least two identical virtual items when generating more than a quantity threshold of at least two identical virtual items within a specified time period in the live broadcast room based on virtual item description voices.

[0215] In some embodiments, the gift special effect display module 903 is used to display the special effect of gifting the upgraded virtual item to a second user account in the live broadcast room in the live broadcast interface corresponding to the live broadcast room.

[0216] Please refer to Figure 10 , Figure 10 FIG. is a schematic structural diagram of a computer device provided by an exemplary embodiment of the present application. The computer device 1000 includes a central processing unit (CPU) 1001, a system memory 1004 including a random access memory (RAM) 1002 and a read-only memory (ROM) 1003, and a system bus 1005 connecting the system memory 1004 and the central processing unit 1001. The computer device 1000 further includes a basic input / output system (I / O system) 1006 for facilitating information transmission between various components within the computer, and a mass storage device 1007 for storing an operating system 1013, application programs 1014, and other program modules 1015.

[0217] The basic input / output system 1006 includes a display 1008 for displaying information and input devices 1009 such as a mouse and a keyboard for user input of information. Both the display 1008 and the input devices 1009 are connected to the central processing unit 1001 through an input / output controller 1010 connected to the system bus 1005. The basic input / output system 1006 may further include an input / output controller 1010 for receiving and processing inputs from multiple other devices such as a keyboard, a mouse, or an electronic stylus. Similarly, the input / output controller 1010 also provides output to a display screen, a printer, or other types of output devices.

[0218] The mass storage device 1007 is connected to the central processing unit 1001 through a mass storage controller (not shown) connected to the system bus 1005. The mass storage device 1007 and its associated computer-readable medium provide non-volatile storage for the computer device 1000. That is to say, the mass storage device 1007 may include a computer-readable medium (not shown) such as a hard disk or a CD-ROM (Compact Disc Read-Only Memory) drive.

[0219] Without loss of generality, computer-readable media may include computer storage media and communication media. Computer storage media includes volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes RAM (Random Access Memory), ROM (Read-Only Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory or other solid-state storage technologies, CD-ROM, DVD (Digital Video Disc) or other optical storage, magnetic tape cartridges, tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will understand that computer storage media is not limited to the above several types. The above-mentioned system memory 1004 and mass storage device 1007 may be collectively referred to as memory.

[0220] The computer device 1000 may be connected to the Internet or other network devices through a network interface unit 1011 connected to the system bus 1005.

[0221] The memory further includes one or more programs. The one or more programs are stored in the memory, and the central processing unit 1001 implements Figures 2 to 4 all or part of the steps in the method shown.

[0222] In an exemplary embodiment, a chip is further provided. The chip includes programmable logic circuits and / or program instructions, and when the chip runs on a computer device, it is used to implement all or part of the steps of the methods shown in the above various embodiments of the present application.

[0223] In an exemplary embodiment, a computer program product is further provided. The computer program product includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor reads and executes the computer instructions to implement all or part of the steps of the methods shown in the above various embodiments of the present application.

[0224] In an exemplary embodiment, a computer-readable storage medium is further provided. A computer program is stored in the computer-readable storage medium, and the computer program is loaded and executed by a processor to implement all or part of the steps of the methods shown in the above various embodiments of the present application.

[0225] Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware, or can be completed by a program instructing relevant hardware. The above program can be stored in a computer-readable storage medium, and the storage medium mentioned above can be a read-only memory, a magnetic disk, an optical disc, or the like.

[0226] Those skilled in the art should be able to realize that in the above one or more examples, the functions described in the embodiments of the present application can be implemented by hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. The computer-readable medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transfer of a computer program from one place to another. The storage media can be any available medium accessible by a general-purpose or special-purpose computer.

[0227] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A live broadcast room interaction method, characterized in that: The method comprises: Receiving a virtual prop description voice from a user corresponding to a first user account in the live broadcast room; Based on the virtual prop description speech, generating a virtual prop described by the virtual prop description speech; The special effect of giving the virtual prop to the second user account in the live broadcast room is displayed in the live broadcast interface corresponding to the live broadcast room.

2. The method according to claim 1, characterized in that The step of generating the virtual prop described by the virtual prop description speech based on the virtual prop description speech comprises: Extracting feature description information from the virtual prop description voice; the feature description information includes type information and style information; The virtual prop described by the virtual prop description voice is generated according to the feature description information.

3. The method according to claim 2, characterized in that Generating the virtual prop described by the virtual prop description voice according to the feature description information includes: The feature description information is input into a first prop generation model, and the virtual prop described by the virtual prop description voice output by the first prop generation model is obtained.

4. The method according to claim 2, characterized in that: Generating the virtual prop described by the virtual prop description voice according to the feature description information includes: According to the feature description information, query a virtual prop template library, and obtain a virtual prop template corresponding to the feature description information from the virtual prop template library; The virtual prop template and the feature description information are input into a second prop generation model, and the virtual prop described by the virtual prop description voice output by the second prop generation model is obtained.

5. The method according to claim 1, characterized in that Before displaying the special effect of presenting the virtual prop to the second user account in the live broadcast room in the live broadcast interface corresponding to the live broadcast room, the method further includes: Display a virtual prop preview interface; the virtual prop preview interface is used to display the generated virtual props; In response to receiving a gift operation for the virtual prop performed in the virtual prop preview interface, the virtual prop is gifted to a second user account in the live broadcast room.

6. The method according to claim 5, characterized in that The virtual item preview interface includes a gift quantity setting item, and in response to receiving a gift operation of the virtual item executed in the virtual item preview interface, before gifting the virtual item to the second user account in the live broadcast room, the method further includes: In response to a setting operation on the gift quantity setting item, setting the gift quantity of the virtual item; In response to receiving a gifting operation on the virtual prop executed in the virtual prop preview interface, gifting the virtual prop to a second user account in the live broadcast room includes: In response to receiving the gift operation performed in the virtual item preview interface, the gift quantity of the virtual item is gifted to a second user account in the live broadcast room.

7. The method according to claim 5, characterized in that The virtual prop preview interface includes at least two virtual props, and the at least two virtual props are different virtual props generated based on the virtual prop description voice; In response to receiving a gifting operation on the virtual prop executed in the virtual prop preview interface, gifting the virtual prop to a second user account in the live broadcast room includes: In response to a selection operation of at least one virtual prop among the at least two virtual props, the selected at least one virtual prop is presented to a second user account in the live broadcast room.

8. The method according to claim 1, characterized in that Before displaying the special effect of presenting the virtual prop to the second user account in the live broadcast room in the live broadcast interface corresponding to the live broadcast room, the method further includes: In response to the gifting operation of the virtual item, virtual resources corresponding to the virtual item in the first user account are deducted.

9. The method according to claim 8, characterized in that The number of virtual resources corresponding to the virtual props is positively correlated with the complexity of the virtual props.

10. The method according to claim 8, characterized in that Before giving the virtual prop to the second user account in the live broadcast room, the method further includes: In the case where the amount of virtual resources of the first user account does not meet the amount of virtual resources corresponding to the virtual prop, at least two recommended virtual props are displayed; the at least two recommended virtual props are substitute virtual props generated based on the virtual prop description voice; the amount of virtual resources corresponding to the recommended virtual prop is lower than the virtual resources corresponding to the virtual prop; The method further comprises: In response to a selection operation of at least one of the at least two recommended virtual props, the selected recommended virtual prop is presented to a second user account in the live broadcast room.

11. The method according to claim 1, characterized in that: The step of generating the virtual prop described by the virtual prop description speech based on the virtual prop description speech comprises: Based on the virtual prop description voice, when at least two identical virtual props exceeding a quantity threshold are generated within a specified time period of the live broadcast room, synthesizing the at least two identical virtual props into an upgraded virtual prop; The special effect of presenting the virtual prop to the second user account in the live broadcast room in the live broadcast interface corresponding to the live broadcast room includes: The special effect of presenting the upgraded virtual prop to the second user account in the live broadcast room is displayed in the live broadcast interface corresponding to the live broadcast room.

12. A live broadcast room interactive device, characterized in that: The device comprises: A description voice receiving module, used to receive a virtual prop description voice issued by a user corresponding to a first user account in the live broadcast room; A virtual prop generation module, used to generate the virtual prop described by the virtual prop description voice based on the virtual prop description voice; The gifting special effect display module is used to display the special effect of gifting the virtual props to the second user account in the live broadcast room in the live broadcast interface corresponding to the live broadcast room.

13. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores instructions, and the instructions are executed by the processor to implement the live broadcast room interaction method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The storage medium stores instructions, and the instructions are executed by a processor of a computer device to implement the live broadcast room interaction method as described in any one of claims 1 to 11.

15. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium; the computer instructions are read and executed by a processor of a computer device to implement the live broadcast room interaction method as described in any one of claims 1 to 11.

Images