Live data processing method, device, electronic device and storage medium

Abstract

The present disclosure relates to a live broadcast data processing method, device, electronic device and storage medium, the method comprising: obtaining a first audio and video stream of a target live broadcast room and account association information of a target account in the target live broadcast room; the target account is any participating account in the target live broadcast room; the account association information is used to indicate the information display style of the target account; according to the account association information, target rendering material information corresponding to the target account is determined; the target rendering material information is used to render the first audio and video stream; the first audio and video stream and the target rendering material information are sent to a terminal corresponding to the target account; the present disclosure sends the obtained first audio and video stream and the target rendering material matching the information display style of the target terminal to the terminal corresponding to the target account, so that the terminal can obtain a live broadcast video matching the information display style of the target account; and the live broadcast video screen has diversity.

Description

Technical Field

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

[0002] In related technologies, live streaming involves the host producing content, which is then forwarded to the audience via audio and video encoding and decoding in the cloud for easy viewing. This method is used, for example, in live broadcasts involving real people and virtual live broadcasts using digital humans. During these live broadcasts, the live images and audio are fixed and monotonous. Summary of the Invention

[0003] The present disclosure provides a live broadcast data processing method, device, electronic device, and storage medium to at least solve the problem of single live broadcast images and single live broadcast audio in related technologies. The technical solution of the present disclosure is as follows:

[0004] According to a first aspect of an embodiment of the present disclosure, a live broadcast data processing method is provided, comprising obtaining a first audio and video stream of a target live broadcast room and account association information of a target account in the target live broadcast room; the target account is any participating account in the target live broadcast room; the account association information is used to indicate an information display style of the target account;

[0005] Determining target rendering material information corresponding to the target account according to the account association information; the target rendering material information is used to render the first audio and video stream;

[0006] The first audio and video stream and the target rendering material information are sent to the terminal corresponding to the target account.

[0007] In a possible implementation, a second audio and video stream sent by a first account is received; the first account is an account to which the target live broadcast room belongs;

[0008] The second audio and video stream is preprocessed to obtain the first audio and video stream.

[0009] In a possible implementation, determining the target rendering material information corresponding to the target account according to the account association information includes:

[0010] Acquire preset material configuration information, where the preset material configuration information includes a plurality of preset materials;

[0011] selecting, from the plurality of preset materials, a preset material that satisfies a first preset condition as a target material based on the account association information; the first preset condition being a condition that matches the information display style of the target account;

[0012] The target rendering material information is generated based on the target material.

[0013] In a possible implementation, the preset material configuration information includes a preset similarity configuration mode, and selecting a preset material that meets a first preset condition from the plurality of preset materials as a target material includes:

[0014] Based on the preset similarity configuration mode, the account association information of the target account is subjected to similarity comparison processing with the plurality of preset materials respectively, to obtain similarity data corresponding to each of the plurality of preset materials;

[0015] Selecting target similarity data that meets a second preset condition from the plurality of similarity data;

[0016] The preset material corresponding to the target similarity data is determined as the target material.

[0017] In one possible implementation, the account association information includes at least two of time information, location information, social information, and visual preference information. The similarity comparison processing of the account association information of the target account with the plurality of preset materials based on a preset similarity configuration method to obtain similarity data corresponding to each of the plurality of preset materials includes:

[0018] Obtaining similarity configuration modes corresponding to the time information, the location information, the social information, and the visual preference information, respectively, from the preset similarity configuration modes;

[0019] Based on the similarity configuration modes corresponding to the time information, the location information, the social information, and the visual preference information, respectively, the time information, the location information, the social information, and the visual preference information are subjected to similarity comparison processing with the plurality of preset materials to obtain time similarity data, location similarity data, social similarity data, and visual preference similarity data corresponding to the plurality of preset materials;

[0020] For each preset material, at least two of the time similarity data, location similarity data, social similarity data, and visual preference similarity data corresponding to the preset material are weighted to obtain similarity data corresponding to each of the plurality of preset materials.

[0021] In a possible implementation, obtaining the account association information of the target account in the target live broadcast room includes:

[0022] Obtaining at least one image associated with the target account;

[0023] Obtaining at least two of time information, location information, and visual feature information corresponding to each of the at least one image, and social information corresponding to the target account; the time information is the time when the image was taken, the location information is the location where the image was taken, and the social information is the social relationships of the target account;

[0024] The account association information of the target account is generated according to at least two of the time information, the location information, the social information, and the visual feature information.

[0025] In a possible implementation, preprocessing the second audio and video stream to obtain the first audio and video stream includes:

[0026] Rendering the second audio and video stream to obtain first texture coordinate information corresponding to each image frame in the second audio and video stream;

[0027] The first audio and video stream is obtained based on the second audio and video stream and the first texture coordinate information corresponding to each image frame in the second audio and video stream.

[0028] According to a second aspect of an embodiment of the present disclosure, a live broadcast data processing method is provided, which is applied to a target terminal, and the method includes:

[0029] Receive target rendering material information and a first audio and video stream of a target live broadcast room; the target rendering material information is rendering material information corresponding to a target account; the target account is any participating account in the target live broadcast room, and the target account corresponds to the target terminal;

[0030] Rendering the first audio and video stream according to the target rendering material information to obtain a target audio and video stream;

[0031] The target audio and video stream is displayed on the target live broadcast page of the target live broadcast room; the target live broadcast page is the live broadcast page of the target live broadcast room on the target terminal.

[0032] In a possible implementation, the first audio and video stream is a preprocessed video stream; and the rendering processing on the first audio and video stream according to the target rendering material information to obtain the target audio and video stream includes:

[0033] Decoding the first audio and video stream to obtain a third audio and video stream and second texture coordinate information corresponding to each image frame in the third audio and video stream;

[0034] The target rendering material information is merged with the third audio and video stream according to the second texture coordinate information corresponding to each image frame in the third audio and video stream to obtain the target audio and video stream.

[0035] In a possible implementation, the rendering processing of the first audio and video stream according to the target rendering material information to obtain a target audio and video stream further includes:

[0036] Decoding the first audio and video stream to obtain a fourth audio and video stream;

[0037] Rendering the fourth audio and video stream to obtain third texture coordinate information corresponding to each image frame in the fourth audio and video stream;

[0038] The target rendering material information is merged with the fourth audio and video stream according to the third texture coordinate information corresponding to each image frame in the fourth audio and video stream to obtain the target audio and video stream.

[0039] In a possible implementation, before the target live broadcast page of the target live broadcast room displays the target audio and video stream, the method further includes:

[0040] Acquire multiple frames of images in the target audio and video stream;

[0041] Performing image enhancement processing on the multiple frames of images respectively to obtain multiple frames of target enhanced images;

[0042] A target enhanced audio and video stream is generated based on the multiple frames of target enhanced images.

[0043] According to a third aspect of an embodiment of the present disclosure, a live broadcast data processing device is provided, the device comprising: a first acquisition module configured to acquire a first audio and video stream of a target live broadcast room and account association information of a target account in the target live broadcast room; the target account is any participating account in the target live broadcast room; the account association information is used to indicate an information display style of the target account;

[0044] A first determining module is configured to determine target rendering material information corresponding to the target account according to the account association information; the target rendering material information is used to render the first audio and video stream;

[0045] The first sending module is configured to send the first audio and video stream and the target rendering material information to the terminal corresponding to the target account.

[0046] According to a fourth aspect of an embodiment of the present disclosure, a live broadcast data processing device is provided, which is applied to a target terminal, and the device includes:

[0047] A first receiving module is configured to receive target rendering material information and a first audio and video stream of a target live broadcast room; the target rendering material information is rendering material information corresponding to a target account; the target account is any participating account in the target live broadcast room, and the target account corresponds to the target terminal;

[0048] a video stream generation module configured to render the first audio and video stream according to the target rendering material information to obtain a target audio and video stream;

[0049] The data display module is configured to display the target audio and video stream on the target live broadcast page of the target live broadcast room; the target live broadcast page is the live broadcast page of the target live broadcast room on the target terminal.

[0050] According to a fifth aspect of the embodiments of the present disclosure, there is provided an electronic device, including:

[0051] a processor; a memory for storing instructions executable by the processor;

[0052] The processor is configured to execute the instructions to implement the method as described in any one of the first aspects above.

[0053] According to the sixth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any method described in the first aspect of the embodiment of the present disclosure.

[0054] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects: by sending the acquired first audio and video stream and the target rendering material matching the information display style of the target terminal to the terminal corresponding to the target account, so that the terminal can obtain the live video matching the information display style of the target account; making the live video picture and live audio sound diverse, meeting the personalized needs of the target account for the live picture and / or live sound.

[0055] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0057] Figure 1 It is a schematic diagram showing an application environment according to an exemplary embodiment.

[0058] Figure 2 The figure is a flowchart of a first live broadcast data processing method according to an exemplary embodiment.

[0059] Figure 3 The figure is a schematic diagram showing account association information of a target account according to an exemplary embodiment.

[0060] Figure 4 is a flowchart illustrating a second live broadcast data processing method according to an exemplary embodiment.

[0061] Figure 5 The present invention is a flowchart illustrating a method for obtaining account association information according to an exemplary embodiment.

[0062] Figure 6 The present invention is a flowchart illustrating a method for determining target rendering material information according to an exemplary embodiment.

[0063] Figure 7 The flowchart shows a method for determining a target material according to an exemplary embodiment.

[0064] Figure 8 The present invention is a flowchart illustrating a method for determining similarity data according to an exemplary embodiment.

[0065] Figure 9 is a flowchart illustrating a third live broadcast data processing method according to an exemplary embodiment.

[0066] Figure 10 The figure is a block diagram of a first live broadcast data processing device according to an exemplary embodiment.

[0067] Figure 11 It is a block diagram of a second live broadcast data processing device according to an exemplary embodiment.

[0068] Figure 12 The figure is a block diagram of an electronic device for processing live broadcast data according to an exemplary embodiment.

[0069] Figure 13 The figure is a block diagram of another electronic device for live broadcast data processing according to an exemplary embodiment. DETAILED DESCRIPTION

[0070] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0071] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure as detailed in the appended claims.

[0072] See also Figure 1 It shows a schematic diagram of the implementation environment provided by the embodiment of the present disclosure, which may include:

[0073] At least one host terminal 01, at least one viewer terminal 02, and at least one server 03. The at least one host terminal 01 and the at least one viewer terminal 02 can communicate with the at least one server 03 via wired or wireless means.

[0074] Server 03 may be the executor of the live data processing method. Optionally, Server 03 may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0075] The host terminal 01 can provide the first audio and video stream of the target live broadcast room to the server 03. The host terminal 01 can include, but is not limited to, electronic devices such as smartphones, desktop computers, tablet computers, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices. The operating system running on the host terminal 01 can include, but is not limited to, Android, iOS, Linux, Windows, Unix, etc.

[0076] Viewer terminal 02 may be a receiving end for the first audio / video stream and the target rendering material information. Viewer terminal 02 may include, but is not limited to, electronic devices such as smartphones, desktop computers, tablet computers, laptop computers, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices. Operating systems running on viewer terminal 02 may include, but are not limited to, Android, iOS, Linux, Windows, and Unix.

[0077] In an optional embodiment, the host terminal 01 may include an audio and video acquisition unit and a first audio and video codec unit; the viewer terminal 02 may include a first rendering unit and a second audio and video codec unit; and the server 03 may include a third audio and video codec unit, a second driver unit, and a data processing unit.

[0078] The data processing unit can be used to process the data sent by the second driving unit and the third audio and video encoding and decoding unit. In one example, the data processing unit can be a data processing center in the server 03, which is used to perform data interaction with the viewer terminal 02.

[0079] The second driving unit can be used to obtain account association information of the target account in the target live broadcast room.

[0080] In one example, the host terminal 01 may further include a first driving unit; the first driving unit may be used to recognize the host's expressions, movements, and voice information; and integrate the host's expressions, movements, and voice information with the virtual person to drive the virtual person to move.

[0081] The viewer terminal 02 may further include an image enhancement processing unit.

[0082] The server 03 may further include a second rendering unit.

[0083] The second rendering unit is used to preprocess the second audio and video stream sent by the first account.

[0084] It should be noted that the following figure shows a possible order of steps, which is not actually limited to this order. Some steps can be executed in parallel without relying on each other. The user information (including but not limited to user device information, user personal information, user behavior information, etc.) and data (including but not limited to data for display, data for training, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0085] Figure 2 is a flow chart showing a first method for processing live broadcast data according to an exemplary embodiment. Figure 2As shown, the first live broadcast data processing method is used in a server and includes the following steps.

[0086] In step S21, the first audio and video stream of the target live broadcast room and the account association information of the target account in the target live broadcast room are obtained.

[0087] In the disclosed embodiments, the target account is any participating account in the target livestream room; account-associated information indicates the target account's information display preferences. For example, this information may be information associated with the target account that characterizes the target account's information display preferences. As an example, information display preferences may include display style, display background, display color, display layout, display window size, etc., which are not limited in this disclosure. As an example, account-associated information may include at least one of time information, location information, social information, and visual preference information.

[0088] The time information may refer to the time when the image associated with the target account was taken. The image associated with the target account may refer to an image in which the target account has performed a preset operation. As an example, the preset operation may include operations such as taking a photo, following, and liking.

[0089] The location information may refer to the location of the shooting location of the image; wherein the location of the shooting location may be the latitude and longitude information of the shooting location.

[0090] Social information can represent the target account's social relationships. As an example, social relationships can be represented using a social topology graph. For example, each account corresponds to a social topology graph, and the social topology graph can be a graph with the target account as the root node. As an example, the social topology graph for the target account is a graph with the target account as the root node. The nodes of the social topology graph can include nodes corresponding to the target account and nodes corresponding to the target account's associated accounts. As an example, the target account's associated accounts can include first-level associated accounts, second-level associated accounts, and third-level associated accounts. A first-level associated account can refer to an account that has a first-preset social operation with the target account. As an example, the first-preset social operation can include voice, chat, like, and follow operations. A second-level associated account can be a first-level associated account of a first-level associated account; and a third-level associated account can be a first-level associated account of a second-level associated account. As an example, edges can be constructed between the target account and a first-level associated account, between a first-level associated account and a second-level associated account, and between a second-level associated account and a third-level associated account associated with the second-level associated account. A third-level associated account associated with a second-level associated account may refer to an account that has a second preset social operation with the second-level associated account; the second preset social operation may include voice, chat, like, follow, etc. As an example, the third-level associated account associated with two different second-level associated accounts may be the same third-level associated account.

[0091] Visual preference information can represent the target account's preferences for the aesthetic attributes of images; this visual preference information can be derived based on the visual feature information of images interacted with by the target account. Specifically, visual feature information can represent the aesthetic attributes of an image; for example, it can indicate aesthetic attributes such as color, harmonics, lighting, depth of field, visual balance, and object emphasis. The first audio and video stream can represent the host's movements and speech; it can be a live stream of a virtual person or a live stream of a real person. The first audio and video stream can include both a video stream and an audio stream.

[0092] like Figure 3 This is a schematic diagram of the account association information of a target account according to an exemplary embodiment. In the figure, image1(t, loc, a-feat) represents the time information (t), location information (loc), and visual preference information (a-feat) in the account association information of the target account. User1-user5 represent network nodes of social information in the account association information of the target account. Among them, user1 represents the target account; user2 represents the first-level associated account of the target account; user3 represents the first-level associated account of user2; user4 represents the first-level associated account associated with user3 and the first-level associated account associated with user5. Correspondingly, user2's first-level associated account user3 can be the second-level associated account of the target account user1; and the first-level associated account user4 associated with user3 and user5 can be the third-level associated account of the target account user1.

[0093] In an optional embodiment, a second audio and video stream sent by a first account can be received; the second audio and video stream can be determined as the first audio and video stream; wherein, the first account can be the account to which the target live broadcast room belongs; and the terminal corresponding to the first account can be the anchor terminal.

[0094] In another optional embodiment, the second audio and video stream sent by the first account may be received, and the second audio and video stream may be pre-processed to obtain the first audio and video stream.

[0095] In an optional embodiment, at least one image associated with the target account may be obtained, and the account association information of the target account may be determined based on the image. If there is only one image, the at least one image associated with the target account may be a single image frame associated with the target account; if there are multiple images, the at least one image associated with the target account may be a video associated with the target account.

[0096] In another optional embodiment, historical browsing information associated with the target account may be obtained, and the account association information of the target account may be determined based on the historical browsing information.

[0097] In step S22, target rendering material information corresponding to the target account is determined according to the account association information.

[0098] In an embodiment of the present disclosure, the target rendering material information is used to render the first audio and video stream. The target rendering material information matches the information display style of the target account.

[0099] In an optional embodiment, multiple preset rendering material information may be obtained, and preset rendering material information that meets a second preset condition may be selected from the multiple preset rendering material information based on the account association information as the target rendering material information. The second preset condition may be a condition that matches the information display style indicated by the account association information.

[0100] In step S23, the first audio and video stream and the target rendering material information are sent to the terminal corresponding to the target account.

[0101] In an optional embodiment, the first audio and video stream and the target rendering material information may be sent to a terminal corresponding to the target account respectively.

[0102] In another optional embodiment, the first audio and video stream and the target rendering material information may be compressed together and then sent to a terminal corresponding to the target account.

[0103] In this embodiment, the present disclosure sends the acquired first audio and video stream and the target rendering material that matches the information display style of the target terminal to the terminal corresponding to the target account, so that the terminal can obtain the live video that matches the information display style of the target account; the live video picture and live audio sound have diversity, meeting the target account's personalized needs for the live picture and / or live sound.

[0104] Figure 4 is a flow chart of a second method for processing live broadcast data according to an exemplary embodiment. Figure 4 As shown, the following steps are included.

[0105] In step S41, a second audio and video stream sent by the first account is received.

[0106] In the embodiment of the present disclosure, the first account may be the account to which the target live broadcast room belongs; in one example, it may be the login account of the anchor end; correspondingly, the second audio and video stream may be the video stream sent by the anchor end to the server end.

[0107] In step S42, the second audio and video stream is preprocessed to obtain the first audio and video stream.

[0108] In an optional embodiment, the second audio and video stream may be rendered to obtain first texture coordinate information corresponding to each image frame in the second audio and video stream; the first audio and video stream may be obtained based on the first texture coordinate information corresponding to each image frame in the second audio and video stream. The rendering process may include vertex rendering and pixel rendering.

[0109] In one example, the first texture coordinate information acquisition step may include: performing vertex rendering processing and pixel rendering processing on the second audio and video stream in sequence to obtain first texture coordinate information corresponding to each image frame in the second audio and video stream.

[0110] In another example, the first texture coordinate information acquisition step may also include: decoding the second audio and video stream to obtain a fifth audio and video stream, rendering the fifth audio and video stream to obtain texture coordinate information corresponding to each image frame in the fifth audio and video stream, and determining the texture coordinate information corresponding to each image frame in the fifth audio and video stream as the first texture coordinate information corresponding to each image frame in the second audio and video stream.

[0111] Furthermore, the step of acquiring the first audio and video stream may include: mapping the first texture coordinate information corresponding to each image frame in the second audio and video stream to each image frame in the second audio and video stream to obtain the first audio and video stream.

[0112] By performing partial rendering processing on the second audio and video stream, the server and the viewer end perform different processing respectively, which can reduce the data processing amount of the server and the viewer end respectively.

[0113] In step S43, the account association information of the target account in the target live broadcast room is obtained.

[0114] In step S44, target rendering material information corresponding to the target account is determined according to the account association information.

[0115] In step S45, the first audio and video stream and the target rendering material information are sent to the terminal corresponding to the target account.

[0116] In an optional embodiment, further definitions of steps S43 to S45 may refer to the definitions of steps S21 to S23.

[0117] In this embodiment, the present disclosure can reduce the data processing load of the server and improve the distribution efficiency of the audio and video streams by pre-processing the received second audio and video stream and then sending it to the terminal corresponding to the target account.

[0118] Figure 5 This is a flowchart of a method for obtaining account association information according to an exemplary embodiment. Specifically, step S21 may include the following steps.

[0119] In step S51, at least one image associated with the target account is obtained;

[0120] In step S52, at least two of the time information, location information, visual feature information corresponding to at least one image and the social information corresponding to the target account are obtained.

[0121] In an optional embodiment, at least one image may be analyzed and processed to obtain time information, location information, and visual feature information corresponding to the image.

[0122] Identification information of a target account corresponding to at least one image may be obtained; and social information associated with the target account may be obtained based on the identification information.

[0123] In another optional embodiment, a preset neural network model can also be obtained, and at least one image can be input into the preset neural network model to obtain time information, location information, social information and visual feature information corresponding to at least one image; wherein the preset neural network model can be pre-configured; for example, it can be obtained by multiple training based on at least one image associated with the target account.

[0124] In step S53, account association information of the target account is generated based on at least two of the time information, location information, visual feature information, and social information corresponding to the target account.

[0125] In an optional embodiment, at least two of the time information, location information, social information, and visual feature information may be combined and processed to obtain the combined information, which is determined as the account association information.

[0126] In one example, time information, location information, social information, and visual feature information may be combined and processed to obtain the combined information, which may be determined as account association information.

[0127] In another optional embodiment, information display style associated materials of the target account may be generated based on at least two of time information, location information, social information, and visual feature information; and the information display style associated materials may be determined as account associated information.

[0128] In one example, information display style-related materials of a target account are generated based on time information, location information, social information, and visual feature information; and the information display style-related materials are determined as account-related information.

[0129] In this embodiment, the present disclosure analyzes the preferences of the target account from multiple dimensions, including time information, location information, social information, and visual feature information corresponding to the image, and then obtains the account association information of the target account, so that the obtained account association information can be more in line with the target account's information display style for video images and audio sounds when entering the target live broadcast room.

[0130] Figure 6 This is a flowchart of a method for determining target rendering material information according to an exemplary embodiment. Step S22 includes the following steps.

[0131] In step S61, preset material configuration information is obtained, where the preset material configuration information includes a plurality of preset materials;

[0132] In an embodiment of the present disclosure, the preset material configuration information may be pre-configured and used to select configuration information for rendering material information.

[0133] In step S62 , a preset material that meets a first preset condition is selected from a plurality of preset materials according to the account association information as a target material.

[0134] In the embodiment of the present disclosure, the first preset condition refers to a condition that matches the information display style of the target account;

[0135] In an optional embodiment, when the account association information is a combination of time information, location information, social information, and visual preference information, multiple similarity data between multiple preset materials and each combination information corresponding to the account association information can be obtained; and based on the multiple similarity data, a preset material that meets the first preset condition is selected from the multiple preset materials.

[0136] In another optional embodiment, when the account association information is an information display style associated material, a material matching the account association information may be selected from a plurality of preset materials and determined as the preset material satisfying the first preset condition.

[0137] In step S63 , target rendering material information is generated based on the target material.

[0138] In an optional embodiment, multiple preset reference materials corresponding to the target material can be obtained, and target rendering material information can be generated based on any of the multiple preset reference materials. The preset reference material can be a material with a similar style to the target material. This method can generate multiple different target rendering materials based on the same target material.

[0139] In another optional embodiment, the target material may be determined as target rendering material information.

[0140] In this embodiment, the present disclosure generates target rendering materials by selecting target materials that match the preferences of the target account, and can obtain rendering materials that are more closely matched with the matching style of the target account.

[0141] Figure 7 6 is a flowchart of a method for determining a target material according to an exemplary embodiment. Specifically, step 62 may include the following steps.

[0142] In this example, the preset material configuration information may further include a preset similarity configuration method, wherein the preset similarity configuration method is used to indicate a configuration method for calculating the similarity between the account association information of the target account and a plurality of preset materials.

[0143] In step S71 , based on a preset similarity configuration mode, the account association information of the target account is subjected to similarity comparison processing with a plurality of preset materials to obtain similarity data corresponding to each of the plurality of preset materials.

[0144] In an optional embodiment, when the account association information includes time information, location information, social information and visual preference information, the similarity data corresponding to each other of the multiple preset materials and the time information, location information, social information and visual preference information can be obtained according to the preset similarity configuration method; for a preset material, the similarity data corresponding to the preset material is obtained based on the similarity data corresponding to each other of the preset material and the time information, location information, social information and visual preference information.

[0145] In another optional embodiment, when the account-related information is information display style-related material, similarity data corresponding to each of a plurality of preset materials and the account-related information is obtained.

[0146] In step S72 , target similarity data that meets a second preset condition is selected from the plurality of similarity data.

[0147] In an optional embodiment, the second preset condition may be a similarity threshold range; for example, the similarity threshold condition may be that the similarity reaches 95% or more. Specifically, target similarity data that reaches the similarity threshold may be selected from multiple similarity data.

[0148] In another optional embodiment, the second preset condition may also refer to the maximum value among multiple similarity data. Specifically, the similarity data with the maximum value may be selected from the multiple similarity data as the target similarity data.

[0149] In step S73, the preset material corresponding to the target similarity data is determined as the target material.

[0150] In this embodiment, the present disclosure selects a target material from a plurality of preset materials by using the similarity between the preset material and the account association information. This method can obtain a target material with a high degree of matching with the target account.

[0151] Figure 8 4 is a flowchart of a method for determining similarity data according to an exemplary embodiment. Specifically, step S71 may include the following steps.

[0152] In step S81, similarity configuration modes corresponding to time information, location information, social information, and visual preference information are obtained from preset similarity configuration modes.

[0153] In the embodiment of the present disclosure, the preset similarity configuration mode includes multiple similarity configuration modes.

[0154] In step S82, based on the similarity configuration methods corresponding to the time information, location information, social information and visual preference information, the time information, location information, social information and visual preference information are respectively subjected to similarity comparison processing with multiple preset materials to obtain the time similarity data, location similarity data, social similarity data and visual preference similarity data corresponding to the multiple preset materials.

[0155] In one example, a method for determining time similarity data corresponding to each of the multiple preset materials may include: obtaining the first time corresponding to each of the multiple preset materials, performing similarity comparison analysis on the multiple first times and time information respectively, and obtaining the time similarity data corresponding to each of the multiple preset materials.

[0156] For example, the following function 1 can be used to calculate the time similarity:

[0157] Function 1:

[0158] Among them, f t Indicates time similarity, t1 indicates time information, t2 indicates the first time, and e indicates the natural base.

[0159] In one example, a method for determining position similarity data corresponding to multiple preset materials may include obtaining first position information of multiple preset materials, performing similarity comparison analysis on the multiple first position information and position information, and obtaining position similarity data corresponding to multiple preset materials.

[0160] In one example, a method for determining the social similarity data corresponding to each of the multiple preset materials may include: obtaining the associated accounts corresponding to each of the multiple preset materials, obtaining intimacy data between each associated account and the target account; and determining the social similarity data corresponding to each of the multiple preset materials based on each intimacy data.

[0161] Specifically, the communication frequency between each associated account and the target account during a target time period can be obtained; based on the comparison between the communication frequency and a preset frequency threshold, the intimacy data between each associated account and the target account can be determined. For example, the communication frequency can be the number of chats; the preset frequency threshold can be 100 chats.

[0162] For example, when the communication frequency is greater than or equal to the preset frequency threshold, the intimacy data is determined based on the communication frequency and the preset frequency threshold. The intimacy data can be a natural number greater than 0 and less than or equal to 1. When the communication frequency is less than the preset frequency threshold, the intimacy data is determined based on the shortest path between the associated account and the target account in the social network.

[0163] In one example, a method for determining visual preference similarity data corresponding to multiple preset materials may include: obtaining first visual preference information of multiple preset materials, performing similarity comparison analysis on the multiple first visual preference information and visual preference information, and obtaining visual preference similarity data corresponding to multiple preset materials.

[0164] For example, 512-dimensional features of the visual preference similarity data may be obtained, and the visual preference similarity data may be calculated based on the 512-dimensional features.

[0165] In step S83, for each preset material, at least two of the time similarity data, location similarity data, social similarity data, and visual preference similarity data corresponding to the preset material are weighted to obtain similarity data corresponding to each of the multiple preset materials.

[0166] In an optional example, each set of time similarity data, location similarity data, social similarity data, and visual preference similarity data is weighted to obtain similarity data corresponding to a preset material.

[0167] In one example, the following function 2 may be used to calculate similarity data:

[0168] Function 2: f score =alpha_t*f t +alpha_loc*f loc +alpha_social*f social +alpha_aes*f aes

[0169] f score Represents the similarity data corresponding to the preset material; alpha_t represents the coefficient of the time similarity data; alpha_loc represents the coefficient of the location similarity data; alpha_social represents the coefficient of the social similarity data; alpha_aes represents the coefficient of the visual preference similarity data. alpha_t, alpha_loc, alpha_social, and alpha_aes are all decimals in the range [0,1]. t represents the temporal similarity data; f loc Represents location similarity data; f social represents social similarity data; f aes Represents visual preference similarity data.

[0170] In one example, to achieve personalized portrait beautification, the coefficients for each target account are different. In an alternative example, each coefficient is given a default initial value. The coefficients are then adjusted based on the target account's feedback on the target rendered material using that coefficient. The feedback can indicate the target account's preference for the rendered result.

[0171] In this embodiment, the present disclosure determines the similarity data corresponding to the account-associated information by similarity data from multiple dimensions of the account-associated information, such as similarity data corresponding to each of the four dimensions of time, location, social, and visual preference; so as to facilitate the subsequent acquisition of more comprehensive and personalized rendering materials that are more in line with the current aesthetics of the target account.

[0172] Figure 9 is a flow chart of a third live data processing method according to an exemplary embodiment. Figure 9 As shown, the third live broadcast data processing method is used in a target terminal, which can be any terminal, and includes the following steps.

[0173] In step S91, target rendering material information and a first audio and video stream of a target live broadcast room are received;

[0174] In the embodiment of the present disclosure, the target rendering material information is the rendering material information corresponding to the target account; the target account is any participating account in the target live broadcast room, and the target account corresponds to the target terminal;

[0175] In step S92, the first audio and video stream is rendered according to the target rendering material information to obtain a target audio and video stream;

[0176] In an optional embodiment, when the first audio and video stream is a preprocessed video stream, the first audio and video stream can be decoded to obtain a third audio and video stream and first texture coordinate information corresponding to each image frame in the third audio and video stream; based on the first texture coordinate information corresponding to each image frame in the third audio and video stream, the target rendering material information is merged with the third audio and video stream to obtain the target audio and video stream.

[0177] In one example, the original material in each image frame can be replaced with the target rendering material information according to the first texture coordinate information corresponding to each image frame to obtain multiple first merged image frames; and the target audio and video stream can be obtained based on the multiple first merged image frames.

[0178] In another example, the transparency information of each image frame can also be obtained, and the target rendering material is mixed with each image frame according to the first texture coordinate information and transparency information corresponding to each image frame to obtain multiple second merged image frames; and the target audio and video stream is obtained based on the multiple second merged image frames.

[0179] By rendering the pre-processed audio and video streams, the data processing volume of the target terminal can be greatly reduced and the processing efficiency of the target terminal for live data can be improved.

[0180] In another optional embodiment, the first audio and video stream can be decoded to obtain a fourth audio and video stream; the fourth audio and video stream can be rendered to obtain second texture coordinate information corresponding to each image frame in the fourth audio and video stream; and based on the second texture coordinate information corresponding to each image frame in the fourth audio and video stream, the target rendering material information and the fourth audio and video stream can be merged to obtain the target audio and video stream.

[0181] By performing full-stage rendering processing on the audio and video streams of the target terminal, the target terminal's independent data processing capability can be improved, while the data processing volume of the server can be effectively reduced.

[0182] In step S93, the target audio and video stream is displayed on the target live broadcast page of the target live broadcast room.

[0183] In the embodiment of the present disclosure, the target live broadcast page is the live broadcast page of the target live broadcast room on the target terminal.

[0184] In an optional embodiment, when the target audio and video stream is a video stream, before displaying the target audio and video stream on the target live page of the target live room, the method may further include: obtaining multiple frames of images from the target audio and video stream; performing image enhancement processing on the multiple frames of images to obtain multiple frames of target enhanced images; and generating a target enhanced audio and video stream based on the multiple frames of target enhanced images. Correspondingly, the target enhanced audio and video stream is displayed on the target live page of the target live room.

[0185] By enhancing each frame of the rendered target video stream to obtain the target enhanced audio and video stream, the resolution of the picture displayed by the video stream can be effectively improved, thereby enhancing the visual effect.

[0186] In one example, AI (Artificial Intelligence) image enhancement can be used to perform image enhancement processing on multiple frames of images to obtain multiple frames of target enhanced images; specifically, it can include three steps: super resolution, AI noise reduction, and AI color enhancement.

[0187] In another optional embodiment, the target audio and video stream can be displayed directly on the target live broadcast page of the target live broadcast room.

[0188] In this embodiment, the present disclosure can display live audio and video that matches the information display style of the target account through the received first audio and video stream and the target rendering material that matches the information display style of the target account; and improve the target account's personalized needs for live broadcast images and live broadcast sounds.

[0189] Figure 10 FIG. 1 is a block diagram of a live data processing device according to an exemplary embodiment. Figure 10 , the apparatus may include:

[0190] The first acquisition module 101 is configured to acquire a first audio and video stream of a target live broadcast room and account association information of a target account in the target live broadcast room; the target account is any participating account in the target live broadcast room; the account association information is used to indicate the information display style of the target account;

[0191] A first determining module 102 is configured to determine target rendering material information corresponding to the target account based on the account association information; the target rendering material information is used to render the first audio and video stream;

[0192] The first sending module 103 is configured to send the first audio and video stream and the target rendering material information to the terminal corresponding to the target account.

[0193] In a possible implementation, the first obtaining module 101 includes:

[0194] The first receiving unit is configured to receive a second audio and video stream sent by a first account; the first account is the account to which the target live broadcast room belongs;

[0195] The preprocessing unit is configured to preprocess the second audio and video stream to obtain the first audio and video stream.

[0196] In a possible implementation, the first determining module 102 includes:

[0197] a configuration information acquiring unit, configured to acquire preset material configuration information, wherein the preset material configuration information includes a plurality of preset materials;

[0198] a target material selection unit configured to select, from the plurality of preset materials, a preset material that satisfies a first preset condition as a target material based on the account association information; the first preset condition being a condition that matches the information display style of the target account;

[0199] The first generating unit is configured to generate the target rendering material information based on the target material.

[0200] In a possible implementation, the preset material configuration information includes a preset similarity configuration mode, and the target material selection unit includes:

[0201] a comparison subunit configured to perform similarity comparison processing on the account association information of the target account and the plurality of preset materials based on the preset similarity configuration mode, and obtain similarity data corresponding to each of the plurality of preset materials;

[0202] a similarity data selection subunit, configured to select target similarity data that meets a second preset condition from the plurality of similarity data;

[0203] The first determining subunit is configured to determine the preset material corresponding to the target similarity data as the target material.

[0204] In one possible implementation, the account association information includes at least two of time information, location information, social information, and visual preference information, and the comparison subunit includes:

[0205] Obtaining similarity configuration modes corresponding to the time information, the location information, the social information, and the visual preference information, respectively, from the preset similarity configuration modes;

[0206] a comparison submodule configured to perform similarity comparison processing on the time information, the location information, the social information, and the visual preference information with the plurality of preset materials based on the similarity configuration modes corresponding to the time information, the location information, the social information, and the visual preference information, to obtain time similarity data, location similarity data, social similarity data, and visual preference similarity data corresponding to the plurality of preset materials;

[0207] The weighted processing submodule is configured to perform weighted processing on at least two of the time similarity data, location similarity data, social similarity data, and visual preference similarity data corresponding to each preset material to obtain similarity data corresponding to each of the multiple preset materials.

[0208] In a possible implementation, the first obtaining module 101 further includes:

[0209] a first acquiring unit, configured to acquire at least one image associated with the target account;

[0210] a second acquisition unit configured to acquire time information, location information, social information, and visual feature information corresponding to each of the at least one image; the time information being the time when the image was taken, the location information being the location where the image was taken, and the social information representing the social relationship of the target account;

[0211] The second generating unit is configured to generate the account association information of the target account based on at least two of the time information, the location information, the social information, and the visual feature information.

[0212] In a possible implementation, the preprocessing unit includes:

[0213] a rendering processing subunit, configured to perform rendering processing on the second audio and video stream to obtain first texture coordinate information corresponding to each image frame in the second audio and video stream;

[0214] The video stream generation subunit is configured to obtain the first audio and video stream based on the second audio and video stream and the first texture coordinate information corresponding to each image frame in the second audio and video stream.

[0215] Figure 11 FIG. 1 is a block diagram of a second live data processing device according to an exemplary embodiment. Figure 11 , the apparatus may include:

[0216] The first receiving module 111 is configured to receive target rendering material information and a first audio and video stream of a target live broadcast room; the target rendering material information is rendering material information corresponding to a target account; the target account is any participating account in the target live broadcast room, and the target account corresponds to the target terminal;

[0217] The video stream generating module 112 is configured to render the first audio and video stream according to the target rendering material information to obtain a target audio and video stream;

[0218] The data display module 113 is configured to display the target audio and video stream on the target live broadcast page of the target live broadcast room; the target live broadcast page is the live broadcast page of the target live broadcast room on the target terminal.

[0219] In a possible implementation, the first audio and video stream is a preprocessed video stream; the video stream generation module 112 includes:

[0220] a first decoding unit configured to decode the first audio and video stream to obtain a third audio and video stream and second texture coordinate information corresponding to each image frame in the third audio and video stream;

[0221] The first merging unit is configured to merge the target rendering material information with the third audio and video stream according to the second texture coordinate information corresponding to each image frame in the third audio and video stream to obtain the target audio and video stream.

[0222] In a possible implementation, the video stream generation module 112 further includes:

[0223] A second decoding unit is configured to decode the first audio and video stream to obtain a fourth audio and video stream;

[0224] a rendering unit configured to perform rendering processing on the fourth audio and video stream to obtain third texture coordinate information corresponding to each image frame in the fourth audio and video stream;

[0225] The second merging unit is configured to merge the target rendering material information with the fourth audio and video stream according to the third texture coordinate information corresponding to each image frame in the fourth audio and video stream to obtain the target audio and video stream.

[0226] In a possible implementation, the device further includes:

[0227] An image acquisition module is used to acquire multiple frames of images from the target audio and video stream;

[0228] An image enhancement module is configured to perform image enhancement processing on the multiple frames of images respectively to obtain multiple frames of target enhanced images;

[0229] The video stream generation module is configured to generate a target enhanced audio and video stream based on the multiple frames of target enhanced images.

[0230] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0231] Figure 12This is a block diagram of an electronic device for live data processing according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 12 As shown. The electronic device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for processing live data is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc.

[0232] Those skilled in the art will understand that Figure 12 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0233] Figure 13 is a block diagram of another electronic device for live data processing according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. Figure 13 As shown. The electronic device includes a processor, a memory, and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for processing live data is implemented.

[0234] Those skilled in the art will understand that Figure 13 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0235] In an exemplary embodiment, an electronic device is also provided, including: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the live broadcast data processing method as in the embodiment of the present disclosure.

[0236] In an exemplary embodiment, a computer-readable storage medium is also provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the live broadcast data processing method of the embodiment of the present disclosure. The computer-readable storage medium can be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0237] In an exemplary embodiment, a computer program product containing instructions is also provided, which, when executed on a computer, enables the computer to execute the method for processing live broadcast data in the embodiment of the present disclosure.

[0238] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, which can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present disclosure can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0239] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0240] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A live broadcast data processing method, characterized in that: The method comprises: Get the first audio and video stream of the target live broadcast room; Obtain at least one image associated with a target account in the target live broadcast room, where the target account is any participating account in the target live broadcast room; Obtaining at least two of time information, location information, and visual feature information corresponding to each of the at least one image, and social information corresponding to the target account; the time information being the time when the image was taken, the location information being the location where the image was taken, and the social information representing the social relationships of the target account; generating account association information of the target account based on at least two of the time information, the location information, the social information, and the visual feature information; the account association information is used to indicate an information display style of the target account; the information display style includes a display style of a live video screen of the target live broadcast room; Determining target rendering material information corresponding to the target account according to the account association information; the target rendering material information is used to render the first audio and video stream; The first audio and video stream and the target rendering material information are sent to the terminal corresponding to the target account.

2. The live broadcast data processing method according to claim 1, characterized in that: The obtaining of the first audio and video stream of the target live broadcast room includes: Receiving a second audio and video stream sent by a first account; the first account is the account to which the target live broadcast room belongs; The second audio and video stream is preprocessed to obtain the first audio and video stream.

3. The live broadcast data processing method according to claim 1 or 2, characterized in that: The determining, based on the account association information, target rendering material information corresponding to the target account includes: Acquire preset material configuration information, where the preset material configuration information includes a plurality of preset materials; selecting, from the plurality of preset materials, a preset material that satisfies a first preset condition as a target material based on the account association information; the first preset condition being a condition that matches the information display style of the target account; The target rendering material information is generated based on the target material.

4. The live broadcast data processing method according to claim 3, characterized in that: The preset material configuration information includes a preset similarity configuration mode, and the selecting a preset material that meets a first preset condition from the plurality of preset materials as a target material includes: Based on the preset similarity configuration mode, the account association information of the target account is respectively compared with the multiple preset materials to obtain similarity data corresponding to each of the multiple preset materials; the preset similarity configuration mode is used to indicate a configuration mode for calculating the similarity between the account association information of the target account and the multiple preset materials; Selecting target similarity data that meets a second preset condition from the plurality of similarity data; The preset material corresponding to the target similarity data is determined as the target material.

5. The live broadcast data processing method according to claim 4, characterized in that: The account association information includes at least two of time information, location information, social information, and visual preference information. The similarity comparison processing is performed on the account association information of the target account and the plurality of preset materials based on the preset similarity configuration method to obtain similarity data corresponding to each of the plurality of preset materials, including: Obtaining similarity configuration modes corresponding to the time information, the location information, the social information, and the visual preference information, respectively, from the preset similarity configuration modes; Based on the similarity configuration modes corresponding to the time information, the location information, the social information, and the visual preference information, respectively, the time information, the location information, the social information, and the visual preference information are subjected to similarity comparison processing with the plurality of preset materials to obtain time similarity data, location similarity data, social similarity data, and visual preference similarity data corresponding to the plurality of preset materials; For each preset material, at least two of the time similarity data, location similarity data, social similarity data, and visual preference similarity data corresponding to the preset material are weighted to obtain similarity data corresponding to each of the plurality of preset materials.

6. The live broadcast data processing method according to claim 2, characterized in that: The preprocessing of the second audio and video stream to obtain the first audio and video stream includes: Rendering the second audio and video stream to obtain first texture coordinate information corresponding to each image frame in the second audio and video stream; The first audio and video stream is obtained based on the second audio and video stream and the first texture coordinate information corresponding to each image frame in the second audio and video stream.

7. A live broadcast data processing method, characterized in that: Applied to a target terminal, the method includes: Receive target rendering material information and a first audio and video stream of a target live broadcast room; the target rendering material information is rendering material information corresponding to a target account; the target account is any participating account in the target live broadcast room, the target account corresponds to the target terminal, and the first audio and video stream is an audio and video stream generated by the live broadcast data processing method according to claim 1; Rendering the first audio and video stream according to the target rendering material information to obtain a target audio and video stream; The target audio and video stream is displayed on the target live broadcast page of the target live broadcast room; the target live broadcast page is the live broadcast page of the target live broadcast room on the target terminal.

8. The live broadcast data processing method according to claim 7, characterized in that: The first audio and video stream is a preprocessed video stream; The rendering process of the first audio and video stream according to the target rendering material information to obtain the target audio and video stream includes: Decoding the first audio and video stream to obtain a third audio and video stream and second texture coordinate information corresponding to each image frame in the third audio and video stream; The target rendering material information is merged with the third audio and video stream according to the second texture coordinate information corresponding to each image frame in the third audio and video stream to obtain the target audio and video stream.

9. The live broadcast data processing method according to claim 7, characterized in that: The rendering process of the first audio and video stream according to the target rendering material information to obtain the target audio and video stream further includes: Decoding the first audio and video stream to obtain a fourth audio and video stream; Rendering the fourth audio and video stream to obtain third texture coordinate information corresponding to each image frame in the fourth audio and video stream; The target rendering material information is merged with the fourth audio and video stream according to the third texture coordinate information corresponding to each image frame in the fourth audio and video stream to obtain the target audio and video stream.

10. The live broadcast data processing method according to claim 7, characterized in that: Before displaying the target audio and video stream on the target live broadcast page of the target live broadcast room, the method further includes: Acquire multiple frames of images in the target audio and video stream; Performing image enhancement processing on the multiple frames of images respectively to obtain multiple frames of target enhanced images; A target enhanced audio and video stream is generated based on the multiple frames of target enhanced images.

11. A live broadcast data processing device, characterized in that: The device comprises: The first acquisition module is configured to acquire the first audio and video stream of the target live broadcast room. The first acquisition module includes a first acquisition unit, a second acquisition unit and a second generation unit. The first acquisition unit is configured to acquire at least one image associated with a target account in the target live broadcast room, where the target account is any participating account in the target live broadcast room; the second acquisition unit is configured to acquire at least two of the time information, position information, visual feature information corresponding to each of the at least one image and the social information corresponding to the target account; the time information is the shooting time of the image, the position information is the location of the shooting location of the image, and the social information represents the social relationship of the target account; the second generation unit is configured to generate account association information of the target account based on at least two of the time information, the position information, the social information and the visual feature information; the account association information is used to indicate the information display style of the target account; the information display style includes the display style of the live video screen of the target live broadcast room; A first determining module is configured to determine target rendering material information corresponding to the target account according to the account association information; the target rendering material information is used to render the first audio and video stream; The first sending module is configured to send the first audio and video stream and the target rendering material information to the terminal corresponding to the target account.

12. A live broadcast data processing device, characterized in that: Applied to a target terminal, the device includes: A first receiving module is configured to receive target rendering material information and a first audio and video stream of a target live broadcast room; the target rendering material information is rendering material information corresponding to a target account; the target account is any participating account in the target live broadcast room, the target account corresponds to the target terminal, and the first audio and video stream is an audio and video stream generated by the live broadcast data processing method according to claim 1; a video stream generation module configured to render the first audio and video stream according to the target rendering material information to obtain a target audio and video stream; The data display module is configured to display the target audio and video stream on the target live broadcast page of the target live broadcast room; the target live broadcast page is the live broadcast page of the target live broadcast room on the target terminal.

13. A live data processing electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the live broadcast data processing method as described in any one of claims 1 to 10.

14. A computer-readable storage medium, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to execute the live broadcast data processing method according to any one of claims 1 to 10.

Images