Live broadcast interaction method and device, electronic equipment and storage medium

Abstract

The invention provides a live broadcast interaction method and device, electronic equipment and a storage medium, and the method comprises the steps: displaying a live broadcast image of a live broadcast room through terminal equipment logged in by an audience account; the live broadcast picture displays a target task being executed by an anchor account in the live broadcast room; obtaining specified account information of the audience account based on the interaction request of the audience account, and determining role attributes of a to-be-generated target virtual object based on the specified account information; and based on the role attribute, generating a target virtual object in the live broadcast picture, and controlling the target virtual object to assist the anchor account in executing the target task. In the mode, the target virtual object with personalized characteristics is generated for the audience account in the live broadcast picture of the live broadcast room, and the target virtual object is controlled to assist the anchor account in executing the target task, so that the personalized experience of audience users in interaction in the live broadcast room is improved, the participation degree and the user stickiness of the audience users are improved, and the user experience is improved. And the utilization rate of live broadcast room resources is improved.

Description

Technical Field

[0001] The present invention relates to the field of live broadcast technology, and in particular to a live broadcast interactive method, device, electronic equipment and storage medium. Background Art

[0002] In the live broadcast room, various interactive game play methods are usually set up, such as asking the anchor user to perform game tasks such as killing monsters. When the anchor user performs the game task, the audience can help the anchor by liking, commenting, and sending gifts. After the audience user helps the anchor, some virtual objects not controlled by the player can be automatically triggered to appear in the live broadcast room to help the anchor kill monsters. In this interactive method, the audience user participation is low and the interactive experience is poor, which is not conducive to improving the audience user participation and user stickiness, and causes a waste of live broadcast room resources. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a live broadcast interaction method, device, electronic device and storage medium to enhance the personalized experience of audience users in the interaction in the live broadcast room, improve the participation and user stickiness of audience users, and improve the utilization rate of live broadcast room resources.

[0004] In a first aspect, an embodiment of the present invention provides a live broadcast interaction method, the method comprising: displaying a live broadcast screen of a live broadcast room on a terminal device logged in through an audience account; the live broadcast screen displays a target task being executed by an anchor account in the live broadcast room; based on an interaction request of the audience account, obtaining designated account information of the audience account, and determining role attributes of a target virtual object to be generated based on the designated account information; based on the role attributes, generating a target virtual object in the live broadcast screen, and controlling the target virtual object to assist the anchor account in executing the target task.

[0005] In a second aspect, an embodiment of the present invention provides a live broadcast interactive device, which includes: a first display module, which is used to display a live broadcast screen of a live broadcast room on a terminal device logged in through an audience account; the live broadcast screen displays a target task being executed by an anchor account in the live broadcast room; a first determination module, which is used to obtain designated account information of the audience account based on an interactive request of the audience account, and determine the role attributes of a target virtual object to be generated based on the designated account information; a first control module, which is used to generate a target virtual object in the live broadcast screen based on the role attributes, and control the target virtual object to assist the anchor account in executing the target task.

[0006] In a third aspect, an embodiment of the present invention provides an electronic device, characterized in that it includes a processor and a memory, the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the above-mentioned live interactive method.

[0007] In a fourth aspect, an embodiment of the present invention provides a machine-readable storage medium, which stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to implement the above-mentioned live interactive method.

[0008] The embodiments of the present invention bring the following beneficial effects:

[0009] The above-mentioned live interactive method, device, electronic device and storage medium display the live screen of the live broadcast room through the terminal device logged in by the audience account; the live screen displays the target task being executed by the anchor account in the live broadcast room; based on the interactive request of the audience account, the designated account information of the audience account is obtained, and based on the designated account information, the role attributes of the target virtual object to be generated are determined; based on the role attributes, the target virtual object is generated in the live broadcast screen, and the target virtual object is controlled to assist the anchor account in executing the target task.

[0010] In this way, when the host account is executing the target task, the live broadcast room can receive interaction requests from the audience account, and generate a target virtual object with personalized characteristics for the audience account in the live broadcast screen according to the specified account information of the audience account that sends the interaction request, and control the target virtual object to assist the host account in executing the target task, thereby improving the personalized experience of audience users in the interaction in the live broadcast room, improving the participation and user stickiness of audience users, and improving the utilization rate of live broadcast room resources.

[0011] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0012] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0014] Figure 1 A flowchart of a live interactive method provided by an embodiment of the present invention;

[0015] Figure 2A schematic diagram of a target model provided by an embodiment of the present invention;

[0016] Figure 3 A schematic diagram of a live interactive device provided by an embodiment of the present invention;

[0017] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] Based on this, an embodiment of the present invention provides a live broadcast interaction method, device, electronic device and storage medium, and the technology can be applied to live broadcast room interaction scenarios.

[0020] To facilitate understanding of this embodiment, a live interactive method disclosed in an embodiment of the present invention is first introduced in detail. The execution subject of this method may be a server deployed on a live broadcast platform, such as Figure 1 As shown, the live interactive method includes the following steps:

[0021] Step S102: The terminal device logged in through the viewer account displays the live broadcast screen of the live broadcast room; the live broadcast screen displays the target task being executed by the anchor account in the live broadcast room;

[0022] The audience account can enter the live broadcast room through the terminal device to watch the live broadcast screen of the live broadcast room. The live broadcast screen shows the target task being executed by the anchor account. In one method, a virtual game scene is displayed in the live broadcast screen, such as the virtual game scene displayed after the anchor account starts the live broadcast room game. In the virtual game scene, the anchor account is controlling the corresponding virtual object to perform the target task, such as the monster-killing task; in another method, a virtual live broadcast scene can be displayed in the live broadcast screen, and the anchor account performs the target task in the virtual live broadcast scene in the image of a virtual anchor.

[0023] Step S104: based on the interactive request of the viewer account, obtaining the designated account information of the viewer account, and determining the role attribute of the target virtual object to be generated based on the designated account information;

[0024] The audience account can send an interactive request in the live broadcast room. The sending of the interactive request indicates that the audience account is willing to assist the anchor account in performing the target task. Specifically, the interactive request can be issued in the form of a like, a positive comment barrage, or a gift. For example, when the audience account sends a virtual gift that can be used to assist the anchor account in performing the target task to the anchor account, it can be considered that the audience account has sent an interactive request to the live broadcast room, and the interactive request contains information about the virtual gift. The above-mentioned designated account information is information containing personalized characteristics of the audience account, which can be behavioral characteristic information of the audience account in the live broadcast room, such as the level of the virtual gift given in the live broadcast, the online active time, and the number of comments; it can also be personalized identification information of the audience account, such as account avatar, ID photo uploaded by the audience account, etc. The above-mentioned target virtual object is a personalized virtual object generated for the audience account in the live broadcast room. The personalization of the virtual object can refer to the difference in appearance, or it can refer to the difference in attributes unique to the target virtual object, such as the game life value of the target virtual object or the difference in the attack skills of the target virtual object. The audience account can also control the actions made by the target virtual object in the live broadcast room or game scene through the terminal device, such as moving, attacking the target object, etc. The character attribute of the target virtual object is generated according to the specified account information and can be used to generate the target virtual object. Specifically, the character attribute may include one or more of a first character attribute indicating the survivability of the target virtual object and model data indicating the model characteristics of the target virtual object. For example, the character attribute may be the game life value of the target virtual object determined by the level of the virtual gift given by the audience account; the character attribute may be the model data of the target virtual object generated by the certificate information of the audience account and the corresponding game character data.

[0025] In this step, after receiving an interaction request from an audience account in the live broadcast room, the designated account information with personalized features of the audience account is obtained according to the interaction request of the audience account, and then, according to the designated account information, the role attributes of the target virtual object to be generated are determined to generate the target virtual object. The role attributes can be the game life value of the target virtual object, the attack skills that the target virtual object can release in the game, or the model data indicating the model features of the target virtual object. The role attributes of these target virtual objects are differentiated and personalized because they are determined by the designated account information with personalized features of the audience account.

[0026] Step S106: Based on the role attributes, a target virtual object is generated in the live broadcast screen, and the target virtual object is controlled to assist the anchor account in performing the target task.

[0027] By having differentiated and personalized role attributes, a target virtual object that meets the characteristics of the viewer account is generated for the viewer account in the live broadcast screen.

[0028] In one approach, the character attribute may be only the first character attribute indicating the survivability of the target virtual object, such as the game life value of the target virtual object. Here, a character model may be pre-designed and stored in the server. After determining that the target virtual object has the first game life value through the designated account information of the viewer account, the character model is displayed in the live broadcast room as the model image of the target virtual object. At the same time, the character model is associated with the first game life value, and a target virtual object having a model image of the character model and the first game life value is obtained in the live broadcast room.

[0029] In another way, the character attribute may include a first character attribute indicating the survivability of the target virtual object and model data indicating the model characteristics of the target virtual object. For example: the game life value of the target virtual object and the model data of the target virtual object. For example, after determining the model data of the target virtual object through the designated account information of the viewer account and determining that the target virtual object has a first game life value, a target model corresponding to the target virtual object is generated according to the model data, and at the same time, the target model is associated with the first game life value, and a target virtual object having a model image of the target model and the first game life value is obtained in the live broadcast room.

[0030] Of course, the role attributes may also only include model data indicating the model features of the target virtual object. The model data of the target virtual object is determined through the specified account information of the audience account, and the target model corresponding to the target virtual object is generated according to the model data, so as to obtain a target virtual object whose model image is the target model in the live broadcast room.

[0031] After generating a target virtual object in the live broadcast screen, the audience account can also control the sending of relevant data through the terminal device where the audience account is located, and control the target virtual object in the live broadcast room to move, attack and other actions to assist the anchor account in performing the target task.

[0032] The above-mentioned live interactive method displays the live screen of the live broadcast room through a terminal device logged in by a viewer account; the live screen displays the target task being executed by the anchor account in the live broadcast room; based on the interactive request of the viewer account, the designated account information of the viewer account is obtained, and based on the designated account information, the role attributes of the target virtual object to be generated are determined; based on the role attributes, the target virtual object is generated in the live screen, and the target virtual object is controlled to assist the anchor account in executing the target task.

[0033] In this way, when the host account is executing the target task, the live broadcast room can receive interaction requests from the audience account, and generate a target virtual object with personalized characteristics for the audience account in the live broadcast screen according to the specified account information of the audience account that sends the interaction request, and control the target virtual object to assist the host account in executing the target task, thereby improving the personalized experience of audience users in the interaction in the live broadcast room, improving the participation and user stickiness of audience users, and improving the utilization rate of live broadcast room resources.

[0034] In one method, the interaction request of the viewer account includes: a gift sending request issued by the viewer account in the live broadcast room; wherein the gift sending request is used to: send a virtual gift to the anchor account, and the virtual gift is used to assist the anchor account in performing the target task.

[0035] In this method, the interactive request can be a gift sending request issued by the viewer account in the live broadcast room, and the gift sending request is used to send a virtual gift to the anchor account that can assist the anchor account in performing the target task. The interactive request contains information about the virtual gift, such as the level of the virtual gift.

[0036] That is, when the viewer account sends a virtual gift to the anchor account that can be used to assist the anchor account in performing the target task, it can be considered that the viewer account has sent an interaction request in the live broadcast room. For example, if the anchor account is performing a task of attacking a target object, and the viewer account sends the anchor account equipment used to attack the target object, it is considered that the viewer account has sent an interaction request.

[0037] In one embodiment, the designated account information includes: attribute information of a virtual gift sent by a viewer account to a host account, and / or account identification information of the viewer account.

[0038] The above virtual gifts are virtual gifts sent by the viewer account to the anchor account that can be used to assist the anchor account in performing the target task. The attribute information of the virtual gift can be information reflecting the value of the virtual gift, such as the level of the virtual gift, or the number of points, game coins and other resources required for the viewer user to redeem the virtual gift. The account identification information of the above viewer account includes the account avatar, the ID photo uploaded by the viewer account, etc.

[0039] Here, the specified account information may include the attribute information of the virtual gift sent by the viewer account to the host account and the account identification information of the viewer account, or it may only include the attribute information of the virtual gift sent by the viewer account to the host account, or the account identification information of the viewer account.

[0040] The following embodiments provide specific implementation methods for determining the character attributes of a target virtual object to be generated.

[0041] In one embodiment, the role attribute may include a first role attribute indicating the survivability of the target virtual object. The first role attribute of the target virtual object may be determined in the following manner:

[0042] Based on the attribute information of the virtual gift sent from the viewer account to the anchor account, a first character attribute indicating the survivability of the target virtual object to be generated is determined.

[0043] Here, the first character attribute indicating the target virtual object to be generated can be determined based on the attribute information of the virtual gift sent from the viewer account to the anchor account. The first character attribute indicates the survivability of the target virtual object. For example, the first character attribute can be related to the game life of the target virtual object and the combat capability in the game, such as the target virtual object's health in the game, the target virtual object's attack skills in the game, the target virtual object's weapons and equipment in the game, the target virtual object's character type, etc.

[0044] Specifically, based on the attribute information of the virtual gift, the game life value of the target virtual object is determined; and / or, based on the attribute information of the virtual gift, the attack skills that can be cast by the target virtual object are determined.

[0045] The game life value of the target virtual object directly affects the game life of the target virtual object, and can be the "blood volume" or "life value" of the target virtual object in the game. The first character attribute includes the game life value of the target virtual object and the attack skills that the target virtual object can cast, or only includes the game life value of the target virtual object or one of the attack skills that the target virtual object can cast. It is understandable that in the execution of the task, the higher the game life value and the more harmful the attack skills that can be cast, the longer the target virtual object survives in the game.

[0046] Here, several resource intervals can be divided in advance according to the attribute information of the virtual gifts that can be sent in the live broadcast room. For example, if the attribute information of the virtual gift is the level of the virtual gift, multiple gift level intervals can be divided in advance according to the level of all virtual gifts that can be sent in the live broadcast room, and each gift level interval is used as a resource interval. If the attribute information of the virtual gift is the number of points, game coins and other resources required for the audience user to redeem the virtual gift, multiple resource exchange quantity intervals can be divided in advance according to the resource exchange quantity corresponding to all virtual gifts that can be sent in the live broadcast room, and each resource exchange quantity interval is used as a resource interval.

[0047] Then, a correspondence between game health and resource intervals, and a correspondence between attack skills and resource intervals is created. After determining the attribute information of the virtual gift sent by the viewer account to the anchor account, determine the first interval in the resource interval where the attribute information of the virtual gift is located, and determine the game health corresponding to the first interval as the game health of the target virtual object; or, determine the attack skill corresponding to the first interval as the attack skill that the target virtual object can cast.

[0048] In one example, for the game life value of the target virtual object, the amount of resources required to exchange virtual gifts in the attribute information can be directly determined as the game life value of the target virtual object.

[0049] In this method, the survival ability of the target virtual object in the game is determined based on the attribute information of the virtual gifts sent from the viewer account to the anchor account. The different attribute information of the virtual gifts sent by the viewer account will result in different survival abilities of the target virtual object in the game, which can bring different gaming experiences to the viewer account. At the same time, it will also have different impacts on the gaming behavior of the anchor, enriching the live broadcast content of the live broadcast room.

[0050] In one embodiment, the character attributes may include model data indicating model features of the target virtual object. The model data of the target virtual object may be determined in the following manner:

[0051] Based on the attribute information of the virtual gift and the account identification information, the model data of the target virtual object to be generated is determined; wherein the model data is used to indicate the model features of the target virtual object.

[0052] The account identification information of the above-mentioned audience account includes the account avatar, the ID photo uploaded by the audience account, etc. According to the attribute information of the virtual gift and the account identification information, the model data of the target virtual object to be generated can be determined; the model data can be used to indicate the model features of the target virtual object.

[0053] Specifically, based on the resource interval where the attribute information is located, a first model corresponding to the attribute information is determined; based on the first model and the account identification information, model data of the target virtual object is determined.

[0054] Here, several resource intervals can be divided in advance according to the attribute information of the virtual gifts that can be sent in the live broadcast room, and a corresponding relationship between the resource intervals and the role models can be created. For example, the attribute information includes the number of points required to redeem the virtual gifts. Here, when the point redemption number interval is preset to [1,100], the corresponding role model is soldier A; when the point redemption number interval is [101,200], the corresponding role model is soldier B; when the point redemption number interval is [201,300], the corresponding role model is soldier C. According to the point redemption number interval in which the attribute information of the virtual gift sent from the viewer account to the anchor account is located, the role model corresponding to the interval is determined as the first model. The first model can be understood as the initial model image of the target virtual object, and needs to be personalized according to the first model to obtain the model data of the target virtual object.

[0055] Specifically, through a preset image processing technology, avatar information is extracted from the account identification information, and based on a pre-trained feature extraction model, facial features of the viewer account are extracted from the avatar information; wherein the facial features of the viewer account include facial organ features of the viewer account, facial contours of the viewer account and facial expressions of the viewer account; the facial features of the viewer account are fused with the first model through a fusion tool to obtain model data of the target virtual object.

[0056] The preset image processing technology may be OpenCV (Open Source Computer Vision Library) technology. The feature extraction model may be a VGG or ResNet neural network model. The fusion tool may be a 3D modeling tool or a 2D image processing tool, such as Blender or Photoshop.

[0057] That is to say, the avatar of the viewer account can be extracted from the account avatar or the ID photo uploaded by the viewer account through OpenCV graphics processing technology, and then the facial features of the viewer account can be obtained by extracting features from the extracted avatar using a pre-trained feature extraction model. The facial features of the viewer account include the facial organ features of the viewer account, such as eyes, ears, nose and other organ features; the facial features also include the facial contours of the viewer account, such as face shape, chin line, etc.; the facial features also include facial expressions such as smiles, frowns, etc. Further, the facial features of the viewer account are fused with the first model through a fusion tool to obtain the model data of the target virtual object, so as to ensure that the model image generated by the model data can accurately reflect the facial features of the user.

[0058] Specifically, the model facial features of the first model in the first model are obtained, and the model facial features are fused with the facial features of the audience account through a fusion tool to determine the fused model facial features; wherein the model facial features include the facial organ features of the first model, the facial contour of the first model and the facial expression of the first model; the model facial features of the first model in the first model are replaced with the fused model facial features to obtain a target model, and the model data of the target model is determined as the model data of the target virtual object.

[0059] That is to say, the model facial features of the first model in the first model are obtained, and the model facial features are fused with the facial features of the audience account through a fusion tool to obtain fused model facial features, and then, the model facial features of the first model in the first model are replaced with the fused model facial features to obtain a target model, and the model data of the target model is determined as the model data of the target virtual object, that is, the model image of the target virtual object is the target model.

[0060] Specifically, the fusion process of the model facial features and the facial features of the viewer account includes:

[0061] The facial organ features of the audience account are fused with the facial organ features of the first model through a fusion tool to obtain fused facial organ features; the facial contour of the first model and the facial contour of the audience account are fused through a fusion tool to obtain a fused facial contour; the facial expression of the first model is adjusted to the facial expression of the audience account through the fusion tool to obtain a fused facial expression; based on the fused facial organ features, the fused facial contour and the fused facial expression, the fused model facial features are generated.

[0062] In this method, the facial organ features of the viewer account and the facial organ features of the first model can be fused through a fusion tool to obtain fused facial organ features; the facial contour of the first model and the facial contour of the viewer account can be matched and adjusted to obtain a fused facial contour; the facial expression of the first model can be adjusted to the facial expression of the viewer account to obtain a fused facial expression. Then, based on the fused facial organ features, the fused facial contour and the fused facial expression, the fused model facial features are generated.

[0063] Finally, the model facial features of the first model in the first model are replaced with the fused model facial features to obtain the target model, and the model data of the target model is determined as the model data of the target virtual object. Based on the model data, a target model including the facial features of the viewer account can be generated.

[0064] In order to further improve the personalized characteristics of the target model, after obtaining the target model, the attribute information of the head decoration and the position information of the head decoration can continue to be obtained from the avatar information extracted from the account identification information; based on the attribute information of the head decoration, the head decoration model is determined; based on the position information of the decoration, the first model position in the target model is determined, and the head decoration model is hung at the first model position, and the model data of the target model with the head decoration model hung is determined as the model data of the target virtual object.

[0065] The head decoration may be a hat, glasses, earrings or other decorations worn by the user. The attribute information of the head decoration includes the color and shape of the head decoration. The position information of the first model position in the target model corresponds one-to-one to the position information of the head decoration.

[0066] Here, the attribute information and position information of the head decoration are extracted from the account avatar or the ID photo uploaded by the audience account, and the head decoration model is first determined based on the attribute information of the head decoration. Then, based on the position information of the head decoration, the first model position corresponding to the position information is determined in the target model, and then, the head decoration model is hung at the first model position, and the target model after the head decoration model is hung is used as the model corresponding to the target virtual object, and the model data of the model is determined as the model data of the target virtual object.

[0067] For example, Figure 2 As shown, if the user in the account avatar wears a hat on his head, then a hat of the same shape will also be generated on the top of the target model's head, and the target model with the hat will be determined as the model of the target virtual object, and the model data is the model data of the target virtual object.

[0068] In this method, the facial features and ornaments worn by the audience account are obtained from the account avatar or the ID photo uploaded by the audience account, and the facial features of the model of the target virtual object are made more consistent with the facial features of the audience account through a fusion tool. By generating a corresponding ornament model on the model of the target virtual object, the model image of the target virtual object is made more vivid and personalized, which can enhance the user's sense of participation and interactivity.

[0069] In one embodiment, if the character attributes include: a first character attribute indicating the survivability of a target virtual object to be generated and model data of the target virtual object.

[0070] Based on the first character attributes and the model data of the target virtual object, a target virtual object is generated in the live broadcast room.

[0071] That is, when the character attributes include a first character attribute indicating the survivability of a target virtual object to be generated and model data of the target virtual object, the target virtual object can be generated in the live broadcast room according to the first character attribute and the model data of the target virtual object.

[0072] For example, after determining the model data of the target virtual object and the first game life value of the target virtual object through the designated account information of the audience account, a target model corresponding to the target virtual object is generated according to the model data. At the same time, the target model is associated with the first game life value, and a target virtual object with a model image as the target model and the first game life value is obtained in the live broadcast room.

[0073] In this method, the role attributes of the target virtual object are determined by the designated account information of the viewer account, and a target virtual object with personalized characteristics of the viewer account is generated for the viewer account in the live broadcast room, thereby enhancing the personalized experience of the viewer user in the interaction in the live broadcast room, improving the participation and user stickiness of the viewer user, and improving the utilization rate of the live broadcast room resources.

[0074] The following embodiments provide specific implementation methods for controlling a target virtual object to assist a host account in performing a target task.

[0075] Obtain action instructions of the target virtual object, generate object actions of the target virtual object based on the action instructions, and control the target virtual object to assist the anchor account in performing the target task.

[0076] The above-mentioned action instructions can be generated by data uploaded by the terminal device where the viewer account is located. The viewer account can control the terminal device, such as the controls displayed on the live broadcast interface on the touch terminal device or the tilting terminal device. The terminal device uploads the corresponding data to the server according to the behavior of the viewer account, and generates action instructions in the server to control the target virtual object in the live broadcast room to make corresponding object actions. The action instructions can be attack instructions, movement instructions, etc. The server controls the target virtual object in the live broadcast room to make corresponding object actions according to the action instructions. In one way, when the action instruction is an attack instruction, the server can control the target virtual object in the live broadcast screen to cast the castable attack skills according to the attack instruction. In one way, when the action instruction is a movement instruction, the movement instruction contains a movement direction, and the server can control the target virtual object in the live broadcast room to move in the movement direction according to the movement instruction.

[0077] Here, data uploaded by the terminal device where the viewer account is located is received, action instructions for the target virtual object are generated based on the data, and object actions of the target virtual object in the live broadcast screen are controlled and generated based on the action instructions. The object actions performed by the target virtual object assist the anchor account in performing the target task.

[0078] For example, the target task performed by the anchor account is to kill monsters. The audience account can operate the terminal device, which uploads corresponding data to the server according to the behavior of the audience account and generates action instructions in the server to control the target virtual object to approach the monster and automatically cast attack skills to help the anchor account kill monsters.

[0079] In one method, the action instruction includes a moving direction, and the moving direction is determined by the device tilt parameter uploaded by the terminal device where the viewer account is located; the target virtual object is controlled to move in the moving direction in the live broadcast screen, and in response to meeting the first assistance condition, the target virtual object is controlled to assist the anchor account to perform the target task.

[0080] The above-mentioned first assisting condition is related to the target task. For example, if the target task performed by the anchor account is to attack the target object, the first assisting condition may be related to the relative position or distance between the target virtual object and the target object in the live broadcast screen. When the first assisting condition is met, the target virtual object may be controlled to assist the anchor account in attacking the target object.

[0081] In this method, the action instruction includes a moving direction, which can be determined by the device tilt parameter uploaded by the terminal device where the viewer account is located. Here, after the target virtual object is generated in the live broadcast room, the terminal where the viewer account is located automatically activates the gyroscope function in the terminal device and starts to collect the device tilt parameters of the terminal device. At this time, the viewer account can tilt the terminal device, and the terminal device sends the collected device tilt parameters to the server. The server generates the moving direction in the action instruction according to the device tilt parameters uploaded by the terminal device, and controls the target virtual object to move in the moving direction in the live broadcast screen. When the first assistance condition is met, the target virtual object is controlled to assist the anchor account in performing the target task.

[0082] For example, the target task performed by the anchor account is to attack the target object. After the target virtual object is generated in the live broadcast screen, the terminal where the audience account is located automatically activates the gyroscope function in the terminal device and starts to collect the device tilt parameters of the terminal device. At this time, when the terminal device of the audience account is tilted to the right, the terminal device collects the device tilt parameters and sends them to the server. The server generates an action instruction to move right according to the device tilt parameters uploaded by the terminal device, and controls the target virtual object to move to the right in the live broadcast room. When the distance between the target virtual object and the target object meets the attack distance of the target object, the target virtual object can be automatically triggered to attack the target object.

[0083] In this way, the audience account can control the movement of the target virtual object forward, backward, left and right by tilting the terminal device, and automatically trigger the target virtual object to assist the anchor account in performing the target task, thereby enhancing the personalized experience of the audience users in the interaction in the live broadcast room, increasing the audience users' participation and user stickiness, and improving the utilization rate of the live broadcast room resources.

[0084] In one method, the target task includes a host account attacking a target object; the character attributes include: the target virtual object can cast a first attack skill; in response to the distance between the target virtual object and the target object being no greater than a specified distance threshold, controlling the target virtual object to launch an attack skill toward the target object.

[0085] Here, the target task includes the anchor account attacking the target object, and the role attribute of the target virtual object is that the target virtual object determined by the designated account information of the viewer account has the ability to cast the first attack skill. Therefore, when the distance between the target virtual object and the target object is not greater than the designated distance threshold, the target virtual object can be controlled to launch the first attack skill at the target object. The designated distance threshold can be the attack distance of the first attack skill. When the distance between the target virtual object and the target object is within the attack distance of the first attack skill, the target virtual object is automatically triggered to launch the first attack skill at the target object.

[0086] In this method, personalized role attributes are determined based on the specified account information of the viewer account that sends the interactive request, and a target virtual object with personalized characteristics of the viewer account is generated for the viewer account in the live broadcast screen based on the role attributes. The target virtual object has personalized role attributes, and the viewer user can use the role attributes to control the target virtual object to assist the anchor account in performing the target task, thereby producing some personalized influence on the anchor's game behavior, improving the personalized experience, and thus the viewer user's experience in the interactive game.

[0087] Corresponding to the above method embodiment, see Figure 3 A live interactive device is shown, the device comprising:

[0088] The first display module 302 is used to display the live broadcast screen of the live broadcast room on the terminal device logged in through the viewer account; the live broadcast screen displays the target task being executed by the anchor account in the live broadcast room;

[0089] A first determination module 304 is used to obtain designated account information of the viewer account based on the interaction request of the viewer account, and determine the role attribute of the target virtual object to be generated based on the designated account information;

[0090] The first control module 306 is used to generate a target virtual object in the live broadcast screen based on the character attributes, and control the target virtual object to assist the anchor account in performing the target task.

[0091] In this way, when the host account is executing the target task, the live broadcast room can receive interaction requests from the audience account, and generate a target virtual object with personalized characteristics for the audience account in the live broadcast screen according to the specified account information of the audience account that sends the interaction request, and control the target virtual object to assist the host account in executing the target task, thereby improving the personalized experience of audience users in the interaction in the live broadcast room, improving the participation and user stickiness of audience users, and improving the utilization rate of live broadcast room resources.

[0092] The above-mentioned interaction requests of the audience account include: gift sending requests issued by the audience account in the live broadcast room; among which, the gift sending request is used to: send virtual gifts to the anchor account, and the virtual gifts are used to assist the anchor account to perform the target task.

[0093] The above-mentioned designated account information includes: attribute information of the virtual gift sent by the viewer account to the anchor account, and / or account identification information of the viewer account.

[0094] The first determination module is used to determine the first character attribute indicating the survivability of the target virtual object to be generated based on the attribute information of the virtual gift sent from the viewer account to the anchor account.

[0095] The above-mentioned device also includes a second determination module, which is used to determine the game life value of the target virtual object based on the attribute information of the virtual gift; and / or, based on the attribute information of the virtual gift, determine the attack skills that the target virtual object can cast.

[0096] The second determination module is used to determine the model data of the target virtual object to be generated based on the attribute information and account identification information of the virtual gift; wherein the model data is used to indicate the model features of the target virtual object.

[0097] The above-mentioned device also includes a third determination module, which is used to determine the first model corresponding to the attribute information based on the resource interval where the attribute information of the virtual gift is located; and determine the model data of the target virtual object based on the first model and account identification information.

[0098] The above-mentioned device also includes a fourth determination module, which is used to extract avatar information from the account identification information through a preset image processing technology, and extract the facial features of the audience account from the avatar information based on a pre-trained feature extraction model; wherein the facial features of the audience account include facial organ features of the audience account, facial contours of the audience account and facial expressions of the audience account; the facial features of the audience account are fused with the first model through a fusion tool to obtain model data of the target virtual object.

[0099] The above-mentioned device also includes a fifth determination module, which is used to obtain the model facial features of the first model in the first model, and fuse the model facial features with the facial features of the audience account through a fusion tool to determine the fused model facial features; wherein the model facial features include the facial organ features of the first model, the facial contour of the first model and the facial expression of the first model; the model facial features of the first model in the first model are replaced with the fused model facial features to obtain the target model, and the model data of the target model is determined as the model data of the target virtual object.

[0100] The above-mentioned device also includes a sixth determination module, which is used to fuse the facial organ features of the audience account with the facial organ features of the first model through a fusion tool to obtain fused facial organ features; fuse the facial contour of the first model and the facial contour of the audience account through a fusion tool to obtain a fused facial contour; adjust the facial expression of the first model to the facial expression of the audience account through the fusion tool to obtain a fused facial expression; generate a fused model facial feature based on the fused facial organ features, the fused facial contour and the fused facial expression.

[0101] The above-mentioned device also includes a seventh determination module, which is used to extract attribute information of the head decoration and position information of the head decoration from the avatar information; determine the head decoration model based on the attribute information of the head decoration; determine the first model position in the target model based on the position information of the head decoration, hang the head decoration model at the first model position, and determine the model data of the target model on which the head decoration model is hung as the model data of the target virtual object.

[0102] The above-mentioned character attributes include: a first character attribute indicating the survivability of the target virtual object to be generated, and model data of the target virtual object; the above-mentioned first control module is used to generate the target virtual object in the live broadcast screen based on the first character attribute and the model data of the target virtual object.

[0103] The above-mentioned first control module is also used to obtain action instructions of the target virtual object, generate object actions of the target virtual object based on the action instructions, and control the target virtual object to assist the anchor account in performing the target task.

[0104] The above-mentioned action instruction includes a moving direction, and the moving direction is determined by the device tilt parameter uploaded by the terminal device where the viewer account is located; the above-mentioned device also includes a second control module, which is used to control the target virtual object to move in the moving direction in the live broadcast screen, and in response to meeting the first assistance condition, control the target virtual object to assist the anchor account to perform the target task.

[0105] The above-mentioned target task includes the anchor account attacking the target object; the character attributes include: the target virtual object can cast a first attack skill; the above-mentioned device also includes a third control module, which is used to control the target virtual object to launch the first attack skill towards the target object in response to the distance between the target virtual object and the target object being not greater than a specified distance threshold.

[0106] This embodiment also provides an electronic device, including a processor and a memory, wherein the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the above-mentioned live interactive method.

[0107] See also Figure 4 As shown, the electronic device or live broadcast server includes a processor 100 and a memory 101. The memory 101 stores machine executable instructions that can be executed by the processor 100. The processor 100 executes the machine executable instructions to implement the rendering method of the above-mentioned gift special effects.

[0108] Further, Figure 4 The electronic device shown further includes a bus 102 and a communication interface 103 , and the processor 100 , the communication interface 103 and the memory 101 are connected via the bus 102 .

[0109] The memory 101 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 102 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0110] The processor 100 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 100. The above processor 100 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 101, and the processor 100 reads the information in the memory 101 and completes the steps of the method of the above embodiment in combination with its hardware.

[0111] The processor in the above-mentioned electronic device can implement the following operations of the above-mentioned live interactive method by executing machine executable instructions: displaying the live screen of the live broadcast room on a terminal device logged in through an audience account; the live broadcast screen displays the target task being executed by the anchor account in the live broadcast room; based on the interactive request of the audience account, obtaining the designated account information of the audience account, and determining the role attributes of the target virtual object to be generated based on the designated account information; based on the role attributes, generating the target virtual object in the live broadcast screen, and controlling the target virtual object to assist the anchor account in executing the target task.

[0112] In this way, when the host account is executing the target task, the live broadcast room can receive interaction requests from the audience account, and generate a target virtual object with personalized characteristics for the audience account in the live broadcast screen according to the specified account information of the audience account that sends the interaction request, and control the target virtual object to assist the host account in executing the target task, thereby improving the personalized experience of audience users in the interaction in the live broadcast room, improving the participation and user stickiness of audience users, and improving the utilization rate of live broadcast room resources.

[0113] The above-mentioned interaction requests of the audience account include: gift sending requests issued by the audience account in the live broadcast room; among which, the gift sending request is used to: send virtual gifts to the anchor account, and the virtual gifts are used to assist the anchor account to perform the target task.

[0114] The above-mentioned designated account information includes: attribute information of the virtual gift sent by the viewer account to the anchor account, and / or account identification information of the viewer account.

[0115] The processor in the above-mentioned electronic device can implement the following operations of the above-mentioned live interactive method by executing machine executable instructions: based on the attribute information of the virtual gift sent by the audience account to the anchor account, determine the first character attribute indicating the survivability of the target virtual object to be generated.

[0116] The processor in the above-mentioned electronic device can implement the following operations of the above-mentioned live interactive method by executing machine executable instructions: determining the game life value of the target virtual object based on the attribute information of the virtual gift; and / or determining the attack skills that the target virtual object can cast based on the attribute information of the virtual gift.

[0117] The processor in the above-mentioned electronic device can implement the following operations of the above-mentioned live interactive method by executing machine executable instructions: determining the model data of the target virtual object to be generated based on the attribute information and account identification information of the virtual gift; wherein the model data is used to: indicate the model characteristics of the target virtual object.

[0118] The processor in the above-mentioned electronic device can implement the following operations of the above-mentioned live interactive method by executing machine executable instructions: determining a first model corresponding to the attribute information based on the resource interval where the attribute information of the virtual gift is located; determining the model data of the target virtual object based on the first model and account identification information.

[0119] The processor in the above-mentioned electronic device can implement the following operations of the above-mentioned live interactive method by executing machine-executable instructions: extracting avatar information from account identification information through preset image processing technology, and extracting facial features of the viewer account from the avatar information based on a pre-trained feature extraction model; wherein the facial features of the viewer account include facial organ features of the viewer account, facial contours of the viewer account and facial expressions of the viewer account; the facial features of the viewer account are fused with the first model through a fusion tool to obtain model data of the target virtual object.

[0120] The processor in the above-mentioned electronic device can implement the following operations of the above-mentioned live interactive method by executing machine-executable instructions: obtaining the model facial features of the first model in the first model, and fusing the model facial features with the facial features of the audience account through a fusion tool to determine the fused model facial features; wherein the model facial features include the facial organ features of the first model, the facial contour of the first model and the facial expression of the first model; replacing the model facial features of the first model in the first model with the fused model facial features to obtain the target model, and determining the model data of the target model as the model data of the target virtual object.

[0121] The processor in the above-mentioned electronic device can implement the following operations of the above-mentioned live interactive method by executing machine executable instructions: fusing the facial organ features of the audience account with the facial organ features of the first model through a fusion tool to obtain fused facial organ features; fusing the facial contour of the first model and the facial contour of the audience account through a fusion tool to obtain a fused facial contour; adjusting the facial expression of the first model to the facial expression of the audience account through the fusion tool to obtain a fused facial expression; generating fused model facial features based on the fused facial organ features, the fused facial contour and the fused facial expression.

[0122] The processor in the above-mentioned electronic device can implement the following operations of the above-mentioned live interactive method by executing machine executable instructions: extracting attribute information of the head decoration and position information of the head decoration from the avatar information; determining the head decoration model based on the attribute information of the head decoration; determining the first model position in the target model based on the position information of the head decoration, hanging the head decoration model at the first model position, and determining the model data of the target model on which the head decoration model is hung as the model data of the target virtual object.

[0123] The above-mentioned character attributes include: a first character attribute indicating the survivability of the target virtual object to be generated, and model data of the target virtual object; the processor in the above-mentioned electronic device, by executing machine-executable instructions, can implement the following operations of the above-mentioned live interactive method: based on the first character attribute and the model data of the target virtual object, generate the target virtual object in the live broadcast screen.

[0124] The processor in the above-mentioned electronic device can implement the following operations of the above-mentioned live interactive method by executing machine executable instructions: obtaining action instructions of the target virtual object, generating object actions of the target virtual object based on the action instructions, and controlling the target virtual object to assist the anchor account in performing the target task.

[0125] The above-mentioned action instruction includes a moving direction, and the moving direction is determined by the device tilt parameter uploaded by the terminal device where the viewer account is located; the processor in the above-mentioned electronic device, by executing machine-executable instructions, can implement the following operations of the above-mentioned live interactive method: control the target virtual object to move in the moving direction in the live broadcast screen, and in response to satisfying the first assistance condition, control the target virtual object to assist the anchor account in performing the target task.

[0126] The above-mentioned target task includes the anchor account attacking the target object; the character attributes include: the target virtual object can cast a first attack skill; the processor in the above-mentioned electronic device, by executing machine-executable instructions, can implement the following operations of the above-mentioned live interactive method: in response to the distance between the target virtual object and the target object being not greater than the specified distance threshold, control the target virtual object to launch the first attack skill towards the target object.

[0127] This embodiment also provides a machine-readable storage medium, which stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to implement the above-mentioned live broadcast interactive method.

[0128] The machine executable instructions stored in the above-mentioned machine-readable storage medium can be executed to implement the following operations in the above-mentioned live interactive method: displaying the live screen of the live broadcast room on a terminal device logged in through an audience account; the live broadcast screen displays the target task being executed by the anchor account in the live broadcast room; based on the interactive request of the audience account, obtaining the designated account information of the audience account, and determining the role attributes of the target virtual object to be generated based on the designated account information; based on the role attributes, generating the target virtual object in the live broadcast screen, and controlling the target virtual object to assist the anchor account in executing the target task.

[0129] In this way, when the host account in the live broadcast room is executing the target task, the live broadcast room can receive interaction requests from the audience account in the live broadcast room, and generate a target virtual object with personalized characteristics of the audience account for the audience account in the live broadcast screen according to the designated account information of the audience account that sends the interaction request, and control the target virtual object to assist the host account in executing the target task, thereby improving the personalized experience of audience users in the interaction in the live broadcast room, improving the participation and user stickiness of audience users, and improving the utilization rate of live broadcast room resources.

[0130] The above-mentioned interaction requests of the audience account include: gift sending requests issued by the audience account in the live broadcast room; among which, the gift sending request is used to: send virtual gifts to the anchor account, and the virtual gifts are used to assist the anchor account to perform the target task.

[0131] The above-mentioned designated account information includes: attribute information of the virtual gift sent by the viewer account to the anchor account, and / or account identification information of the viewer account.

[0132] The machine executable instructions stored in the above-mentioned machine-readable storage medium can implement the following operations in the above-mentioned live interactive method by executing the machine executable instructions: based on the attribute information of the virtual gift sent from the audience account to the anchor account, determine the first character attribute indicating the survivability of the target virtual object to be generated.

[0133] The machine executable instructions stored in the above-mentioned machine-readable storage medium can implement the following operations in the above-mentioned live interactive method by executing the machine executable instructions: determining the game life value of the target virtual object based on the attribute information of the virtual gift; and / or determining the attack skills that can be cast by the target virtual object based on the attribute information of the virtual gift.

[0134] The machine executable instructions stored in the above-mentioned machine-readable storage medium can implement the following operations in the above-mentioned live interactive method by executing the machine executable instructions: determining the model data of the target virtual object to be generated based on the attribute information and account identification information of the virtual gift; wherein the model data is used to: indicate the model characteristics of the target virtual object.

[0135] The machine executable instructions stored in the above-mentioned machine-readable storage medium can be executed to implement the following operations in the above-mentioned live interactive method: based on the resource interval where the attribute information of the virtual gift is located, determine the first model corresponding to the attribute information; based on the first model and account identification information, determine the model data of the target virtual object.

[0136] The machine executable instructions stored in the above-mentioned machine-readable storage medium can implement the following operations in the above-mentioned live interactive method by executing the machine executable instructions: extracting avatar information from account identification information through preset image processing technology, and extracting facial features of the viewer account from the avatar information based on a pre-trained feature extraction model; wherein the facial features of the viewer account include facial organ features of the viewer account, facial contours of the viewer account and facial expressions of the viewer account; and fusing the facial features of the viewer account with the first model through a fusion tool to obtain model data of the target virtual object.

[0137] The machine executable instructions stored in the above-mentioned machine-readable storage medium can implement the following operations in the above-mentioned live interactive method by executing the machine executable instructions: obtaining the model facial features of the first model in the first model, and fusing the model facial features with the facial features of the audience account through a fusion tool to determine the fused model facial features; wherein the model facial features include the facial organ features of the first model, the facial contour of the first model and the facial expression of the first model; replacing the model facial features of the first model in the first model with the fused model facial features to obtain the target model, and determining the model data of the target model as the model data of the target virtual object.

[0138] The machine executable instructions stored in the above-mentioned machine-readable storage medium can implement the following operations in the above-mentioned live interactive method by executing the machine executable instructions: fusing the facial organ features of the viewer account with the facial organ features of the first model through a fusion tool to obtain fused facial organ features; fusing the facial contour of the first model and the facial contour of the viewer account through a fusion tool to obtain a fused facial contour; adjusting the facial expression of the first model to the facial expression of the viewer account through the fusion tool to obtain a fused facial expression; generating fused model facial features based on the fused facial organ features, the fused facial contour and the fused facial expression.

[0139] The machine executable instructions stored in the above-mentioned machine-readable storage medium can implement the following operations in the above-mentioned live interactive method by executing the machine executable instructions: extracting the attribute information of the head decoration and the position information of the head decoration from the avatar information; determining the head decoration model based on the attribute information of the head decoration; determining the first model position in the target model based on the position information of the head decoration, hanging the head decoration model at the first model position, and determining the model data of the target model on which the head decoration model is hung as the model data of the target virtual object.

[0140] The above-mentioned character attributes include: a first character attribute indicating the survivability of the target virtual object to be generated, and model data of the target virtual object; the machine executable instructions stored in the above-mentioned machine-readable storage medium can implement the following operations in the above-mentioned live interactive method by executing the machine executable instructions: based on the first character attribute and the model data of the target virtual object, generate the target virtual object in the live screen.

[0141] The machine executable instructions stored in the above-mentioned machine-readable storage medium can be executed to implement the following operations in the above-mentioned live interactive method: obtaining action instructions of the target virtual object, generating object actions of the target virtual object based on the action instructions, and controlling the target virtual object to assist the anchor account in performing the target task.

[0142] The above-mentioned action instruction includes a moving direction, and the moving direction is determined by the device tilt parameter uploaded by the terminal device where the viewer account is located; the machine executable instructions stored in the above-mentioned machine-readable storage medium can realize the following operations in the above-mentioned live interactive method by executing the machine executable instructions: control the target virtual object to move in the moving direction in the live broadcast screen, and in response to satisfying the first assistance condition, control the target virtual object to assist the anchor account in performing the target task.

[0143] The above-mentioned target task includes the anchor account attacking the target object; the character attributes include: the target virtual object can cast a first attack skill; the machine executable instructions stored in the above-mentioned machine-readable storage medium can implement the following operations in the above-mentioned live interactive method by executing the machine executable instructions: in response to the distance between the target virtual object and the target object being not greater than the specified distance threshold, controlling the target virtual object to launch a first attack skill towards the target object.

[0144] The computer program products of the live interactive method, device, electronic device and storage medium provided in the embodiments of the present invention include a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods in the previous method embodiments. The specific implementation can be found in the method embodiments, which will not be repeated here.

[0145] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0146] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0147] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0148] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0149] Finally, it should be noted that the above embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art who is familiar with the technical field can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A live interactive method, characterized in that: The method comprises: The terminal device logged in through the viewer account displays the live screen of the live broadcast room; the live screen displays the target task being executed by the anchor account in the live broadcast room; Based on the interaction request of the audience account, obtaining designated account information of the audience account, and determining the role attribute of the target virtual object to be generated based on the designated account information; Based on the character attributes, a target virtual object is generated in the live broadcast screen, and the target virtual object is controlled to assist the anchor account in performing the target task.

2. The method according to claim 1, characterized in that The interactive request of the audience account includes: a gift sending request issued by the audience account in the live broadcast room; wherein, the gift sending request is used to: send a virtual gift to the anchor account, and the virtual gift is used to assist the anchor account to perform the target task.

3. The method according to claim 1, characterized in that The designated account information includes: attribute information of the virtual gift sent by the viewer account to the anchor account, and / or account identification information of the viewer account.

4. The method according to claim 3, characterized in that The step of determining the role attributes of the target virtual object to be generated based on the designated account information includes: Based on the attribute information of the virtual gift sent by the viewer account to the anchor account, a first character attribute indicating the survivability of the target virtual object to be generated is determined.

5. The method according to claim 4, characterized in that The step of determining a first character attribute indicating the survivability of a target virtual object to be generated based on the attribute information of the virtual gift sent by the viewer account to the anchor account includes: Determining the game life value of the target virtual object based on the attribute information of the virtual gift; And / or, based on the attribute information of the virtual gift, determining the attack skills that the target virtual object can cast.

6. The method according to claim 3, characterized in that The step of determining the role attributes of the target virtual object to be generated based on the designated account information includes: Based on the attribute information of the virtual gift and the account identification information, model data of the target virtual object to be generated is determined; wherein the model data is used to indicate model features of the target virtual object.

7. The method according to claim 6, characterized in that The step of determining model data of a target virtual object to be generated based on the attribute information of the virtual gift and the account identification information includes: Determining a first model corresponding to the attribute information based on the resource interval where the attribute information of the virtual gift is located; Based on the first model and the account identification information, model data of the target virtual object is determined.

8. The method according to claim 7, characterized in that The step of determining the model data of the target virtual object based on the first model and the account identification information includes: Extracting the head portrait information from the account identification information by using a preset image processing technology; Based on the pre-trained feature extraction model, extract the facial features of the viewer account from the avatar information; wherein the facial features of the viewer account include facial organ features of the viewer account, facial contours of the viewer account, and facial expressions of the viewer account; The facial features of the audience account are fused with the first model through a fusion tool to obtain model data of the target virtual object.

9. The method according to claim 8, characterized in that The step of fusing the facial features of the viewer account with the first model through a fusion tool to obtain the model data of the target virtual object includes: Acquire the model facial features of the first model in the first model, and fuse the model facial features with the facial features of the viewer account through a fusion tool to determine the fused model facial features; wherein the model facial features include facial organ features of the first model, the facial contour of the first model, and the facial expression of the first model; The model facial features of the first model in the first model are replaced with the fused model facial features to obtain a target model, and the model data of the target model is determined as the model data of the target virtual object.

10. The method according to claim 9, characterized in that The step of fusing the model facial features with the facial features of the viewer account to determine the fused model facial features includes: fusing the facial organ features of the viewer account with the facial organ features of the first model through a fusion tool to obtain fused facial organ features; fusing the facial contour of the first model and the facial contour of the viewer account using a fusion tool to obtain a fused facial contour; adjusting the facial expression of the first model to the facial expression of the viewer account by a fusion tool to obtain a fused facial expression; Based on the fused facial organ features, the fused facial contour and the fused facial expression, fused model facial features are generated.

11. The method according to claim 9, characterized in that After obtaining the target model, the method includes: Extracting attribute information of the head decoration and position information of the head decoration from the avatar information; Determining a head decoration model based on the attribute information of the head decoration; Based on the position information of the head decoration, a first model position in the target model is determined, the head decoration model is mounted at the first model position, and the model data of the target model on which the head decoration model is mounted is determined as the model data of the target virtual object.

12. The method according to claim 1, characterized in that The character attributes include: a first character attribute indicating the survivability of a target virtual object to be generated, and model data of the target virtual object; The step of generating a target virtual object in the live broadcast screen based on the character attributes includes: Based on the first character attributes and the model data of the target virtual object, a target virtual object is generated in the live broadcast screen.

13. The method according to claim 1, characterized in that The step of controlling the target virtual object to assist the anchor account in performing the target task includes: Obtain an action instruction of the target virtual object, generate an object action of the target virtual object based on the action instruction, and control the target virtual object to assist the anchor account in performing the target task.

14. The method according to claim 13, characterized in that The action instruction includes a moving direction, and the moving direction is determined by a device tilt parameter uploaded by a terminal device where the viewer account is located; The step of generating an object action of the target virtual object based on the action instruction, and controlling the target virtual object to assist the anchor account in performing the target task includes: The target virtual object is controlled to move in the moving direction in the live broadcast screen, and in response to satisfying a first assistance condition, the target virtual object is controlled to assist the anchor account in performing the target task.

15. The method according to claim 14, characterized in that The target task includes the anchor account attacking the target object; the character attributes include: the target virtual object can cast a first attack skill; In response to satisfying the first assistance condition, the step of controlling the target virtual object to assist the anchor account in performing the target task includes: In response to the distance between the target virtual object and the target object being not greater than a specified distance threshold, the target virtual object is controlled to launch the first attack skill toward the target object.

16. A live interactive device, characterized in that: The device comprises: The first display module is used to display the live broadcast screen of the live broadcast room on the terminal device logged in through the viewer account; the live broadcast screen displays the target task being executed by the anchor account in the live broadcast room; A first determination module, configured to obtain designated account information of the viewer account based on an interaction request of the viewer account, and determine a role attribute of a target virtual object to be generated based on the designated account information; The first control module is used to generate a target virtual object in the live broadcast screen based on the character attributes, and control the target virtual object to assist the anchor account in performing the target task.

17. An electronic device, characterized in that: It includes a processor and a memory, the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the live interactive method described in any one of claims 1-15.

18. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores machine-executable instructions. When the machine-executable instructions are called and executed by the processor, the machine-executable instructions prompt the processor to implement the live interactive method described in any one of claims 1-15.

Images