Display method, device and equipment of interactive message in live broadcast room and storage medium

Abstract

Embodiments of the present application provide a display method and device for interactive messages in a live broadcast room, a live broadcast server and a live broadcast client, a live broadcast client plays a video stream corresponding to a live broadcast room sent by a live broadcast server in response to an access operation for the live broadcast room, and generates an interactive message filtering request for the live broadcast room when the number of real-time interactive messages in the live broadcast room is greater than a preset number threshold, the live broadcast server determines the live broadcast room corresponding to the interactive message filtering request in response to the interactive message filtering request sent by the live broadcast client, and acquires real-time interactive messages corresponding to the live broadcast room and a user feature label corresponding to a user account to which the live broadcast client belongs, then filters target interactive messages matching the user feature label from the real-time interactive messages, and returns the target interactive messages to the live broadcast client, and the live broadcast client displays the target interactive messages, so as to improve message filtering accuracy and personalized display.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a display method and a display device of interactive messages in a live broadcast room, an electronic device and a computer readable storage medium. BACKGROUND

[0002] In a live broadcast process, when the number of users watching the same live broadcast room is too large, and different users send a large amount of chat information in the live broadcast room, a user not only has difficulty in quickly obtaining chat information of interest from a large amount of chat information, but also has a risk of missing browsing chat information of interest due to too much chat information in the live broadcast room, thereby reducing the user experience of watching the live broadcast. SUMMARY

[0003] Embodiments of the present application provide a display method and a display device of interactive messages in a live broadcast room, an electronic device and a computer readable storage medium, to solve the problem that a user has difficulty in obtaining chat information of interest in a live broadcast room and has a risk of missing chat information of interest in the prior art, thereby reducing the user experience of watching the live broadcast.

[0004] Embodiments of the present application disclose a display method of interactive messages in a live broadcast room, the method is applicable to a live broadcast server, and the method comprises:

[0005] In response to an interactive message filtering request sent by a live broadcast client, a live broadcast room corresponding to the interactive message filtering request is determined, and real-time interactive messages corresponding to the live broadcast room and a user feature label corresponding to a user account to which the live broadcast client belongs are obtained, the interactive message filtering request is a request generated by the live broadcast client in response to a message quantity of the real-time interactive messages being greater than a preset quantity threshold;

[0006] Target interactive messages matched with the user feature label are filtered from the real-time interactive messages;

[0007] The target interactive messages are returned to the live broadcast client, and the live broadcast client is configured to display the target interactive messages while outputting a video stream corresponding to the live broadcast room.

[0008] Optionally, the obtaining of the real-time interactive messages corresponding to the live broadcast room and the user feature label corresponding to the user account to which the live broadcast client belongs comprises:

[0009] The real-time interactive messages corresponding to the live broadcast room and the message quantity of the real-time interactive messages are obtained.

[0010] obtaining attention information corresponding to the user account and historical behavior information, the attention information being information generated by the live client for representing user preferences in response to input operations of a user on a preference collection page;

[0011] generating a user feature label corresponding to the user account to which the live client belongs according to the attention information and / or the historical behavior information.

[0012] Optionally, the generating of the user feature label corresponding to the user account to which the live client belongs according to the attention information and / or the historical behavior information comprises:

[0013] taking a preference feature label corresponding to the attention information as the user feature label corresponding to the user account;

[0014] and / or taking a behavior information label corresponding to the historical behavior information as the user feature label corresponding to the user account.

[0015] Optionally, the live server comprises a label classification model, and the screening of a target interaction message matching the user feature label from the real-time interaction message comprises:

[0016] performing word segmentation processing on the real-time interaction message to split the real-time interaction message into at least one word segment, each word segment corresponding to a word segment feature;

[0017] if each word segment feature in the real-time interaction message is an invalid message feature, the real-time interaction message is discarded;

[0018] if at least one word segment feature in the real-time interaction message is a valid message feature, the valid message feature is input into the label classification model, and a message feature label corresponding to the valid message feature is output;

[0019] performing similarity calculation according to the message feature label and the user feature label to screen a target interaction message matching the user feature label from the real-time interaction message.

[0020] Optionally, the performing of the similarity calculation according to the message feature label and the user feature label to screen a target interaction message matching the user feature label from the real-time interaction message comprises:

[0021] extracting a first feature semantic of the message feature label and a second feature semantic of the user feature label, respectively;

[0022] performing semantic similarity calculation on the first feature semantic and the second feature semantic to obtain a label similarity between the message feature label and the user feature label.

[0023] The real-time interaction message with the label similarity greater than the preset similarity threshold is taken as a target interaction message matched with the user feature label.

[0024] The embodiment of the application further discloses a display method of interaction messages in a live broadcast room.

[0025] In response to an access operation on the live broadcast room, a video stream corresponding to the live broadcast room sent by a live broadcast server is played, and in a case where a message quantity of real-time interaction messages in the live broadcast room is greater than a preset quantity threshold, an interaction message filtering request for the live broadcast room is generated;

[0026] Target interaction messages returned by the live broadcast server in response to the interaction message filtering request are acquired, and the target interaction messages are displayed, the target interaction messages being messages filtered from the real-time interaction messages corresponding to the live broadcast room according to a user feature label corresponding to the live broadcast client by the live broadcast server.

[0027] Optionally, the live broadcast client comprises a preference collection page, the preference collection page comprising a plurality of preference labels, and further comprising:

[0028] In response to a selection operation on the preference label, at least one target preference label corresponding to the selection operation is determined, and attention information corresponding to a user account to which the live broadcast client belongs is generated according to label information corresponding to the target preference label;

[0029] The attention information is sent to the live broadcast server.

[0030] Optionally, the live broadcast client comprises a behavior information collection page, and further comprises:

[0031] In response to a user operation on the behavior information collection page, historical behavior information corresponding to the user operation is determined;

[0032] The historical behavior information is sent to the live broadcast server.

[0033] Optionally, the live broadcast client comprises a message display area, and the acquiring of the target interaction messages returned by the live broadcast server in response to the interaction message filtering request and the displaying of the target interaction messages comprise:

[0034] The target interaction messages returned by the live broadcast server in response to the interaction message filtering request and sending time sequences of the target interaction messages are acquired;

[0035] The target interaction messages are displayed in the message display area in an order of the sending time sequences.

[0036] The embodiment of the application further discloses a display device of interactive messages in a live room, the device is suitable for a live server, and the device comprises:

[0037] a user feature label obtaining module, configured to determine a live room corresponding to an interactive message filtering request in response to the interactive message filtering request generated by a live client in response to a message quantity of real-time interactive messages being greater than a preset quantity threshold, and obtain real-time interactive messages corresponding to the live room and a user feature label corresponding to a user account to which the live client belongs;

[0038] a target interactive message screening module, configured to screen a target interactive message matching the user feature label from the real-time interactive messages;

[0039] a target interactive message returning module, configured to return the target interactive message to the live client, and the live client is configured to display the target interactive message while outputting a video stream corresponding to the live room.

[0040] Optionally, the user feature label obtaining module comprises:

[0041] a message quantity obtaining sub-module, configured to obtain a message quantity of real-time interactive messages corresponding to the live room and the real-time interactive messages;

[0042] an information obtaining sub-module, configured to obtain attention information and historical behavior information corresponding to the user account, the attention information being information generated by the live client for representing user preferences in response to input operations of a user on a preference collection page;

[0043] a user feature label generating sub-module, configured to generate a user feature label corresponding to the user account to which the live client belongs according to the attention information and / or the historical behavior information.

[0044] Optionally, the user feature label generating sub-module is specifically configured to:

[0045] take a preference feature label corresponding to the attention information as the user feature label corresponding to the user account;

[0046] and / or take a behavior information label corresponding to the historical behavior information as the user feature label corresponding to the user account.

[0047] Optionally, the live server comprises a label classification model, and the target interactive message screening module comprises:

[0048] The word segmentation feature determination submodule is configured to perform word segmentation processing on the real-time interaction message, and split the real-time interaction message into at least one word segment, each word segment corresponding to a word segmentation feature;

[0049] The real-time interaction message elimination submodule is configured to eliminate the real-time interaction message if each word segmentation feature in the real-time interaction message is an invalid message feature.

[0050] The message feature label output submodule is configured to input the valid message feature into the label classification model and output a message feature label corresponding to the valid message feature if at least one word segmentation feature in the real-time interaction message is a valid message feature.

[0051] The target interaction message screening submodule is configured to perform similarity calculation according to the message feature label and the user feature label, and screen a target interaction message matching the user feature label from the real-time interaction message.

[0052] Optionally, the target interaction message screening submodule is specifically configured to:

[0053] extract a first feature semantic of the message feature label and a second feature semantic of the user feature label, respectively;

[0054] perform semantic similarity calculation on the first feature semantic and the second feature semantic to obtain a label similarity between the message feature label and the user feature label;

[0055] The real-time interaction message with the label similarity greater than a preset similarity threshold is taken as the target interaction message matching the user feature label.

[0056] The application also discloses a display device for interaction messages in a live broadcast room, which is suitable for a live broadcast client and comprises:

[0057] The interaction message filtering request generation module is configured to, in response to an access operation on a live broadcast room, play a video stream corresponding to the live broadcast room sent by a live broadcast server, and generate an interaction message filtering request for the live broadcast room if the number of real-time interaction messages in the live broadcast room is greater than a preset number threshold.

[0058] The target interaction message display module is configured to obtain a target interaction message returned by the live broadcast server in response to the interaction message filtering request, and display the target interaction message, the target interaction message being a message screened from real-time interaction messages corresponding to the live broadcast room by the live broadcast server according to a user feature label corresponding to the live broadcast client.

[0059] Optionally, the live broadcast client comprises a preference collection page, the preference collection page comprises a plurality of preference tags, and the device further comprises:

[0060] A focus information generation module is configured to, in response to a selection operation on the preference tags, determine at least one target preference tag corresponding to the selection operation, and generate focus information corresponding to a user account of the live broadcast client according to tag information corresponding to the target preference tag.

[0061] A focus information sending module is configured to send the focus information to the live broadcast server.

[0062] Optionally, the live broadcast client comprises a behavior information collection page, and the device further comprises:

[0063] A historical behavior information determination module is configured to, in response to a user operation on the behavior information collection page, determine historical behavior information corresponding to the user operation.

[0064] A historical behavior information sending module is configured to send the historical behavior information to the live broadcast server.

[0065] Optionally, the live broadcast client comprises a message display area, and the target interaction message display module is specifically configured to:

[0066] Obtain target interaction messages returned by the live broadcast server in response to the interaction message filtering request, and a sending time sequence of the target interaction messages.

[0067] Display the target interaction messages in the message display area in the order of the sending time sequence.

[0068] An electronic device is also disclosed, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus.

[0069] The memory is configured to store a computer program.

[0070] The processor is configured to execute the program stored on the memory, so as to implement the method described in the embodiments of the present application.

[0071] A computer readable storage medium is also disclosed, which stores instructions, when executed by one or more processors, causes the processor to execute the method described in the embodiments of the present application.

[0072] The embodiments of the present application have the following advantages:

[0073] In the embodiment of the present application, the method is suitable for the live broadcast server and the live broadcast client, the live broadcast client plays the video stream corresponding to the live broadcast room sent by the live broadcast server in response to the access operation to the live broadcast room, and generates an interaction message filtering request for the live broadcast room when the number of real-time interaction messages in the live broadcast room is greater than a preset number threshold, the live broadcast server determines the live broadcast room corresponding to the interaction message filtering request in response to the interaction message filtering request sent by the live broadcast client, and obtains the real-time interaction messages corresponding to the live broadcast room and the user feature label corresponding to the user account of the live broadcast client, then filters the target interaction messages matching the user feature label from the real-time interaction messages, and returns the target interaction messages to the live broadcast client, and the live broadcast client displays the target interaction messages, the live broadcast client sends the interaction message filtering request to the live broadcast server when the number of real-time interaction messages is greater than the preset number threshold, so that the user can quickly obtain the interested messages in a large number of real-time interaction messages, at the same time, the live broadcast server filters the real-time interaction messages according to the user feature label of the live broadcast client to obtain the corresponding target interaction messages, and then filters different real-time interaction messages for different live broadcast clients, which improves the accuracy of message filtering, and displays the filtered target interaction messages in the live broadcast client, and realizes the process of personalized display for different live broadcast clients. BRIEF DESCRIPTION OF DRAWINGS

[0074] Figure 1 is a step flow chart of a display method of interaction messages in a live broadcast room provided in the embodiment of the present application;

[0075] Figure 2 is a step flow chart of a display method of interaction messages in a live broadcast room provided in the embodiment of the present application;

[0076] Figure 3 is a schematic diagram of processing real-time interaction messages between the live broadcast client and the live broadcast server provided in the embodiment of the present application;

[0077] Figure 4 is a structural block diagram of a display device of interaction messages in a live broadcast room provided in the embodiment of the present application;

[0078] Figure 5 is a structural block diagram of a display device of interaction messages in a live broadcast room provided in the embodiment of the present application;

[0079] Figure 6 is a structural block diagram of an electronic device provided in the embodiment of the present application; DETAILED DESCRIPTION

[0080] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0081] Referring to Figure 1 , a step flow chart of a display method of an interactive message in a live room provided in an embodiment of the application is shown, which is applied to a live server and can specifically include the following steps:

[0082] Step 101, in response to an interactive message filtering request sent by a live client, determining a live room corresponding to the interactive message filtering request, and obtaining real-time interactive messages corresponding to the live room and user characteristic tags corresponding to a user account to which the live client belongs, the interactive message filtering request being a request generated by the live client in response to the number of messages of the real-time interactive messages being greater than a preset number threshold;

[0083] In the embodiment of the application, it can be applied to a live server, when the live server responds to an interactive message filtering request sent by a live client, it can first determine a live room corresponding to the interactive message filtering request, and then obtain real-time interactive messages corresponding to the live room and user characteristic tags corresponding to a user account to which the live client belongs.

[0084] Optionally, the live client can be a client for realizing live stream playing and real-time interactive information display, for example, the live client can be a smart phone terminal, a computer terminal, a tablet terminal and the like capable of communication, which at least includes a live stream playing module, a live room interactive information display, a live message processing system (a message extraction module, a message filtering module), wherein the live stream playing module can be used for video pull streaming to realize real-time playing of a video stream, the live room interactive information display can be used for requesting interactive information and displaying according to a server return, and the live message processing system can be used for filtering user interactive messages, the message extraction module can be used for extracting interactive messages from a message queue, and the message filtering module is used for automatically filtering live room interactive messages according to user preferences and returning to a live front end for display. The live server can be a server for providing a streaming live playing control service, which at least includes a streaming live video playing control module and a user big data analysis module, wherein the streaming live video playing control module can be used for providing data distribution, real-time transcoding, video recording, video real-time auditing and the like, and the user big data analysis module can be used for extracting user behavior data to realize classification of user characteristic tags.

[0085] The interaction message filtering request can be a request generated by the live streaming client in response to the number of real-time interaction messages being greater than a preset number threshold. The number of real-time interaction messages can be the number of real-time interaction messages sent in the live streaming room for each user account, and the preset number threshold can be a number value set in advance according to the actual needs of the relevant technical personnel. For example, the live streaming client detects that the number of real-time interaction messages sent by each user in the live streaming room is 12, and the preset number threshold is 10, and then the live streaming client can generate an interaction message filtering request for real-time interaction messages. The live streaming room can be a live streaming room including various different contents, such as a food live streaming room, a shopping live streaming room, a movie screening live streaming room, and the like. The real-time interaction message can be a message in the form of a barrage sent by each user in the live streaming room after logging into a corresponding user account on the live streaming client. The user feature label can be a label generated by the live streaming server by detecting user operations performed by each user account on the corresponding live streaming client, which is used to represent the preference characteristics of each user account.

[0086] In a specific implementation, the live streaming server can obtain the real-time interaction messages corresponding to the live streaming room and the number of real-time interaction messages in real time, then obtain the attention information and the historical behavior information corresponding to the user account sent by the live streaming client, and then generate the user feature label corresponding to the user account to which the live streaming client belongs according to the attention information and / or the historical behavior information,

[0087] Optionally, the attention information can be information generated by the live streaming client in response to the input operation of the user in the preference collection page, and the preference collection page can be a user account registration page or a corresponding floating window popped up during the live streaming process, etc. The present application does not make any limitation thereon. The preference collection page includes a plurality of preference options, such as food, movies, music, literature, artificial intelligence, and the like. The user can select the preference option in the preference collection interface or actively search for the corresponding preference information in the search bar. After the live streaming client responds to the input operation of the user in the preference collection page, the corresponding attention information can be generated based on the preference option or the preference information. For example, the user logs in to the user account A and inputs “movie” in the preference collection page, and then the live streaming client can generate the attention information “user account A likes movies”.

[0088] The historical behavior information can be information generated by the live streaming server by monitoring the user operations performed by the user when logging into a user account in the live streaming client at a time before the current time. For example, referring to the content of Table 1, the historical behavior of the user includes but is not limited to: watching video types, liking videos or posts, following video bloggers or topics, replying to messages related to videos or posts, and the like. If user A logs into user account A and repeatedly watches “food” type videos in the live streaming client, the live streaming server can generate the historical behavior information “user account A often browses food videos” according to the “repeatedly watches food type videos” of the user. If user B logs into user account B and browses “travel videos” through the live streaming client and likes the travel videos, the live streaming server can generate the historical behavior information “user account A likes travel videos” according to the “watches and likes travel type videos” of the user.

[0089] Watch video type Like Follow Reply

[0090] Table 1

[0091] Specifically, the live streaming server can take the preference feature label corresponding to the attention information as the user feature label corresponding to the user account, and / or take the behavior information label corresponding to the historical behavior information as the user feature label corresponding to the user account.

[0092] The user feature label is a label generated by the live streaming server to represent the user's preference according to the attention information and / or the historical behavior information, and at least includes a preference feature label and a behavior information label. The preference feature label can be a label matched successfully by the live streaming server by extracting a keyword from the attention information, and matching the keyword with a preset feature label. For example, the live streaming client sends the live streaming server the attention information “user account A likes movies”, the live streaming server can extract the keyword “likes movies” from the attention information, and then match the keyword “likes movies” with a preset feature label to obtain the preference feature label “user account A is interested in movies” for user account A. The behavior information label can be a label matched successfully by the live streaming server by matching the historical behavior information with preset behavior information in a preset feature label. For example, the live streaming server monitors the historical behavior information “often browses food videos” of the user through user account A in the live streaming client, and then matches the historical behavior information “often browses food videos” with preset behavior information in each preset feature label to determine that the behavior information label corresponding to the historical behavior information “often browses food videos” is “user account A is interested in food”.

[0093] Step 102, filtering target interaction messages matching the user feature label from the real-time interaction messages;

[0094] In the embodiments of the present application, the live broadcast server can filter at least one target interactive message from a plurality of real-time interactive messages through the user feature label, and the target interactive message can display the message corresponding to the user feature label to the live broadcast client.

[0095] In a specific implementation, the user big data analysis module in the live broadcast server at least includes a label classification model. The live broadcast server can perform word segmentation processing on the real-time interactive message, and then split the real-time interactive message into at least one word segment. Each word segment corresponds to a word segment feature. If each word segment feature in the real-time interactive message is an invalid message feature, the real-time interactive message is discarded. If at least one word segment feature in the real-time interactive message is a valid message feature, the valid message feature is input into the label classification model, and a message feature label corresponding to the valid message feature is output. The similarity between the message feature label and the user feature label is calculated, and the target interactive message matching the user feature label is filtered from the real-time interactive message.

[0096] Optionally, the word segment feature can be a feature corresponding to the word segment after the word segmentation processing on the real-time interactive message, which includes an invalid message feature and a valid message feature. The invalid message feature can be a feature without word meaning, such as an expression or a punctuation mark. The valid message feature can be a feature with word meaning, such as "movie", "food", "tourism", etc. The label classification model can be a model in the user big data analysis model that extracts the message feature label corresponding to the real-time interactive message by analyzing the valid message feature.

[0097] In an example of the present application, it is assumed that the live broadcast client corresponding to the user account A sends an interactive message filtering request to the live broadcast server, determines that the live broadcast room corresponding to the interactive message filtering request is a food live broadcast room, and simultaneously obtains that the number of real-time interactive messages in the food live broadcast room is 600, and the preset number threshold is 500. The live broadcast server can perform word segmentation processing on the 600 real-time interactive messages according to the user feature label "user account A is interested in food" corresponding to the user account A, and obtain the word segment features of each word segment. If there are 300 real-time interactive messages that are expressions or punctuation marks in the real-time interactive messages, the word segment features of the 300 real-time interactive messages are invalid message features, and the 300 real-time interactive messages are discarded from the live broadcast room. Then, the valid message features of the remaining 200 real-time interactive messages are input into the label classification model, and each message feature label corresponding to each valid message feature is output. The similarity between each message feature label and the user feature label "user account A is interested in food" is calculated, and the target interactive message interested in food is filtered from the remaining 200 real-time interactive messages.

[0098] Specifically, by extracting the first feature semantics of the message feature label and the second feature semantics of the user feature label respectively, the first feature semantics and the second feature semantics are subjected to semantic similarity calculation, and the label similarity between the message feature label and the user feature label is obtained. The real-time interaction message with a label similarity greater than a preset similarity threshold is taken as the target interaction message matched with the user feature label.

[0099] Optionally, the feature semantics can be the actual meaning of the feature label, which includes the first feature semantics corresponding to the message feature label and the second feature semantics corresponding to the user feature label. For example, the first feature semantics corresponding to the message feature label can be "real-time interaction message ① is a food-related message", "real-time interaction message ② is a tourism-related message", and "real-time interaction message ③ is a literature-related message". The second feature semantics corresponding to the user feature label can be "user feature label is a label related to food". The label similarity can be the similarity between the message feature label and the user feature label, which is used to determine whether the real-time interaction message is the target interaction message. The preset similarity threshold can be a similarity set in advance according to the actual needs of relevant technical personnel, for example, 60%, 80%, etc.

[0100] In another example of the present application, it is assumed that the user feature label of the user account A to which the live client belongs is "user account A is interested in food", there are at least one real-time interaction message ①, real-time interaction message ② and real-time interaction message ③ in the live room, and the word segmentation feature of the real-time interaction message ① is an effective message feature. The message feature label a is "real-time interaction message ① is a food-related message", the message feature label b is "real-time interaction message ② is a tourism-related message", and the message feature label c is "real-time interaction message ③ is a literature-related message" are extracted by the label classification model respectively. The message feature label a, the message feature label b and the message feature label c can be subjected to semantic similarity calculation with the user feature label, and the label similarity between the message feature label and the user feature label can be obtained. The size of the label similarity is: real-time interaction message ①> real-time interaction message ②> real-time interaction message ③, and the label similarity of the real-time interaction message ① is greater than the preset similarity threshold. Therefore, the real-time interaction message ① is taken as the target interaction message matched with the user feature label.

[0101] In step 103, the target interaction message is returned to the live client. The live client is used to display the target interaction message while outputting the video stream corresponding to the live room.

[0102] In the embodiment of the application, after the live server filters the target interactive message from the plurality of real-time interactive messages, the target interactive message can be returned to the live client sending the interactive message filtering request, and the live client can display the target interactive message in a corresponding display style while outputting the video stream corresponding to the live room.

[0103] Referring to Figure 2 , a step flowchart of a display method of an interactive message in a live room provided in the embodiment of the application is shown, which is applied to a live client and can specifically include the following steps:

[0104] Step 201, in response to an access operation on a live room, playing a video stream corresponding to the live room sent by a live server, and in a case where the number of real-time interactive messages in the live room is greater than a preset number threshold, generating an interactive message filtering request for the live room;

[0105] In the embodiment of the application, the live client can be applied, a user can perform an access operation on a live room through the live client to request a video stream corresponding to the live room from a live server, and in a case where the number of real-time interactive messages in the live room is greater than a preset number threshold, the live client can generate an interactive message filtering request for the current live room.

[0106] In an example of the application, it is assumed that the preset number threshold is 500, the user logs in a user account A in the live client, and performs an access operation on a live room by clicking a live link of the live room or directly selecting a live window of the live room in a live application, after the live server detects the access operation of the live client on the live room, the live server sends a video stream corresponding to the live room to the live client, and the live client can play the video stream, the live client obtains that there are 600 real-time interactive messages in the current live room, and can generate an interactive message filtering request for the current live room.

[0107] As an example, the live client includes a preference collection page, the preference collection page includes a plurality of preference tags, in response to a selection operation on a preference tag, at least one target preference tag corresponding to the selection operation is determined, and according to the tag information corresponding to the target preference tag, the attention information corresponding to the user account to which the live client belongs is generated, and the attention information is sent to the live server.

[0108] Optionally, the preference label can be different types of labels displayed in the preference collection page, for example, "robot", "chip", "communication" and the like of the science and technology category, "Chinese song", "pure music", "western rock" and the like of the music category, "home cooking", "cake", "western food" and the like of the food category, if the user selects the preference label of the music category, the selected preference label can be used as the target preference label. The label information can be the meaning information extracted from the target preference label, for example, the target preference label is "pure music", and the label information can be "related to music", so as to generate the attention information corresponding to the user account of the live client as "user account A likes music", and then the live client can send the attention information "user account A likes music" to the live server.

[0109] As another example, the live client further includes a behavior information collection page, and in response to a user operation on the behavior information collection page, historical behavior information corresponding to the user operation is determined and sent to the live server.

[0110] Optionally, the information collection page can be a page in which the user account is logged in and the user operation is performed in the live client, for example, in an application program for playing video streams of live rooms, the user repeatedly watches a certain type of video in the application program, and the live client can determine the historical behavior information corresponding to "the user repeatedly watches a certain type of video in the application program", and then sends the historical behavior information to the live server.

[0111] In step 202, the target interaction message returned by the live server in response to the interaction message filtering request is acquired, and the target interaction message is displayed, the target interaction message being a message filtered from the real-time interaction messages corresponding to the live room by the live server according to the user feature label corresponding to the live client.

[0112] In a specific implementation, the live client includes a message display area, the target interaction message returned by the live server in response to the interaction message filtering request can be acquired first, and the sending time sequence of the target interaction message is acquired, and then the target interaction message is displayed in the message display area in the order of the sending time sequence.

[0113] Optionally, the message display area can be displayed in the form of a message list, a barrage area, or a floating window at the top, bottom, left, or right area in the live client, and the present application does not limit this. The sending time sequence can be the sending time of the target interactive message, and the target interactive message is displayed in the message display area in the order of sending time, for example, there are target interactive message 1, target interactive message 2, and target interactive message 3, the sending time of target interactive message 1 is 16:30, the sending time of target interactive message 2 is 16:31, and the sending time of target interactive message 3 is 16:32, then target interactive message 1---target interactive message 2---target interactive message 3 are displayed in the message display area in the order.

[0114] It should be noted that the embodiments of the present application include but are not limited to the above examples, and it can be understood that those skilled in the art can also set up according to actual needs under the guidance of the idea of the embodiments of the present application, and the present application does not limit this.

[0115] In the embodiments of the present application, the live server and the live client are applicable, the live client responds to the access operation to the live room, then plays the video stream corresponding to the live room sent by the live server, and in the case that the number of real-time interactive messages in the live room is greater than the preset number threshold, generates an interactive message filtering request for the live room, the live server responds to the interactive message filtering request sent by the live client, determines the live room corresponding to the interactive message filtering request, and obtains the real-time interactive messages corresponding to the live room and the user feature label corresponding to the user account to which the live client belongs, then filters the target interactive message matching the user feature label from the real-time interactive messages, and returns the target interactive message to the live client, and the live client displays the target interactive message, the live client sends the interactive message filtering request to the live server when the number of real-time interactive messages is greater than the preset number threshold, so that the user can quickly obtain the interested message in a large number of real-time interactive messages, at the same time, the live server filters the real-time interactive messages according to the user feature label of the live client to obtain the corresponding target interactive message, and then different live clients filter different real-time interactive messages, which improves the accuracy of message filtering, and displays the filtered target interactive message in the live client, realizes the process of personalized display for different live clients.

[0116] In order for those skilled in the art to better understand the technical solutions of the embodiments of the present application, an example is used for illustrative description as follows:

[0117] Referring to Figure 3 , a schematic diagram of processing real-time interactive messages between a live client and a live server provided in the embodiments of the present application is shown, which is realized by the following steps:

[0118] S1, a user enters a live room and starts live video playing.

[0119] S2, the live server generates real-time interaction messages, and judges the number of the real-time interaction messages. When the number of the real-time interaction messages is greater than a preset number threshold, a message filtering algorithm is enabled.

[0120] S3, the live message processing module in the live server first acquires a user feature label. The user feature label is calculated and saved by a live background service of the live server.

[0121] S4, the user real-time interaction messages are acquired, and the current real-time interaction messages are acquired from a message queue.

[0122] S5, a similarity calculation algorithm is applied to calculate the matching degree between the real-time interaction messages and the user feature label. When calculating, a deep learning method can be applied to extract message feature labels of the real-time interaction messages.

[0123] S6, similarity calculation is performed on the message feature labels of the real-time interaction information and the user feature label. If the calculation result is greater than a preset similarity threshold, the real-time interaction message is taken as a target interaction message and returned to the live client for display. Otherwise, the real-time interaction message is filtered out and not displayed.

[0124] It should be noted that, for the method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the present application are not limited to the action sequence described, because according to the embodiments of the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions involved are not necessarily necessary for the embodiments of the present application.

[0125] Referring to Figure 4 , a structural block diagram of a display device for interaction messages in a live room is shown, which is suitable for a live server and can specifically include the following modules:

[0126] The user feature label acquisition module 401 is configured to, in response to an interaction message filtering request sent by a live client, determine a live room corresponding to the interaction message filtering request, and acquire real-time interaction messages corresponding to the live room and a user feature label corresponding to a user account to which the live client belongs. The interaction message filtering request is a request generated by the live client in response to the number of the real-time interaction messages being greater than a preset number threshold.

[0127] The target interactive message screening module 402 is configured to screen a target interactive message matching the user feature label from the real-time interactive messages.

[0128] The target interactive message returning module 403 is configured to return the target interactive message to the live client, and the live client is configured to display the target interactive message while outputting a video stream corresponding to the live room.

[0129] In an optional embodiment, the user feature label obtaining module 401 comprises:

[0130] The message quantity obtaining sub-module is configured to obtain a message quantity of the real-time interactive messages corresponding to the live room.

[0131] The information obtaining sub-module is configured to obtain attention information and historical behavior information corresponding to the user account, wherein the attention information is information generated by the live client to represent user preferences in response to input operations of a user on a preference collection page.

[0132] The user feature label generating sub-module is configured to generate a user feature label corresponding to the user account to which the live client belongs according to the attention information and / or the historical behavior information.

[0133] In an optional embodiment, the user feature label generating sub-module is specifically configured to:

[0134] take the preference feature label corresponding to the attention information as the user feature label corresponding to the user account;

[0135] and / or take a behavior information label corresponding to the historical behavior information as the user feature label corresponding to the user account.

[0136] In an optional embodiment, the live server comprises a label classification model, and the target interactive message screening module 402 comprises:

[0137] The word segmentation feature determining sub-module is configured to perform word segmentation processing on the real-time interactive message, split the real-time interactive message into at least one word segment, and cause each word segment to correspond to a word segmentation feature.

[0138] The real-time interactive message eliminating sub-module is configured to eliminate the real-time interactive message if each word segmentation feature in the real-time interactive message is an invalid message feature.

[0139] The message feature label outputting sub-module is configured to input the valid message feature into the label classification model and output a message feature label corresponding to the valid message feature if at least one word segmentation feature in the real-time interactive message is a valid message feature.

[0140] The target interactive message screening submodule is configured to: perform similarity calculation according to the message feature label and the user feature label, and screen a target interactive message matching the user feature label from the real-time interactive message.

[0141] In an optional embodiment, the target interactive message screening submodule is specifically configured to:

[0142] extract a first feature semantic of the message feature label and a second feature semantic of the user feature label, respectively;

[0143] perform semantic similarity calculation on the first feature semantic and the second feature semantic to obtain a label similarity between the message feature label and the user feature label;

[0144] the real-time interactive message with the label similarity greater than a preset similarity threshold is taken as the target interactive message matching the user feature label.

[0145] Referring to Figure 5 , a structural block diagram of a display device for interactive messages in a live broadcast room is shown, the device is suitable for a live broadcast client, and specifically can include the following modules:

[0146] An interactive message filtering request generation module 501 is configured to: in response to an access operation on a live broadcast room, play a video stream corresponding to the live broadcast room sent by a live broadcast server, and in a case where a message quantity of real-time interactive messages in the live broadcast room is greater than a preset quantity threshold, generate an interactive message filtering request for the live broadcast room;

[0147] A target interactive message display module 502 is configured to: acquire a target interactive message returned by the live broadcast server in response to the interactive message filtering request, and display the target interactive message, the target interactive message being a message screened from real-time interactive messages corresponding to the live broadcast room by the live broadcast server according to a user feature label corresponding to the live broadcast client.

[0148] In an optional embodiment, the live broadcast client includes a preference collection page, the preference collection page includes a plurality of preference labels, and the device further includes:

[0149] An attention information generation module is configured to: in response to a selection operation on the preference label, determine at least one target preference label corresponding to the selection operation, and generate attention information corresponding to a user account to which the live broadcast client belongs according to label information corresponding to the target preference label.

[0150] An attention information sending module is configured to: send the attention information to the live broadcast server.

[0151] In an optional embodiment, the live client comprises a behavior information collection page, and the apparatus further comprises:

[0152] a historical behavior information determination module configured to determine historical behavior information corresponding to a user operation on the behavior information collection page in response to the user operation;

[0153] a historical behavior information sending module configured to send the historical behavior information to the live server.

[0154] In an optional embodiment, the live client comprises a message display area, and the target interaction message display module 502 is specifically configured to:

[0155] obtain target interaction messages returned by the live server in response to the interaction message filtering request and sending time sequences of the target interaction messages;

[0156] display the target interaction messages in the message display area in the order of the sending time sequences.

[0157] For the apparatus embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the related parts refer to the part of the method embodiment.

[0158] In addition, the embodiment of the present application further provides an electronic device, which comprises a processor, a memory, and a computer program stored in the memory and executable on the processor. The computer program is executed by the processor to implement each process of the display method of the interaction message in the live room, and the same technical effects can be achieved. To avoid repetition, this will not be repeated here.

[0159] The embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program. The computer program is executed by the processor to implement each process of the display method of the interaction message in the live room, and the same technical effects can be achieved. To avoid repetition, this will not be repeated here. The computer readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0160] Figure 6 A structural schematic diagram of an electronic device for implementing various embodiments of the present application.

[0161] The electronic device 600 includes, but is not limited to, a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, a display unit 606, a user input unit 607, an interface unit 608, a memory 609, a processor 610, and a power supply 611, etc. Those skilled in the art can understand that the electronic device structure shown in the figure is not a limitation on the electronic device, and the electronic device can include more or less components than the figure, or combine certain components, or different component arrangements. In the embodiments of the present application, the electronic device includes, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle terminal, a wearable device, and a pedometer, etc. Figure 6 The electronic device structure shown in the figure is not a limitation on the electronic device, and the electronic device can include more or less components than the figure, or combine certain components, or different component arrangements. In the embodiments of the present application, the electronic device includes, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle terminal, a wearable device, and a pedometer, etc.

[0162] It should be understood that in the embodiments of the present application, the radio frequency unit 601 can be used for receiving and transmitting signals in the process of information or call, specifically, receiving downlink data from a base station for the processor 610 to process, and transmitting uplink data to the base station. Generally, the radio frequency unit 601 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc. In addition, the radio frequency unit 601 can also communicate with the network and other devices through a wireless communication system.

[0163] The electronic device provides wireless broadband Internet access for users through the network module 602, such as helping users to send and receive emails, browse web pages, and access streaming media, etc.

[0164] The audio output unit 603 can convert audio data received by the radio frequency unit 601 or the network module 602 or stored in the memory 609 into an audio signal and output as a sound. Moreover, the audio output unit 603 can also provide audio output related to a specific function performed by the electronic device 600 (for example, a call signal receiving sound, a message receiving sound, etc.). The audio output unit 606 includes a speaker, a buzzer, and a receiver, etc.

[0165] The input unit 604 is configured to receive audio or video signals. The input unit 604 can include a graphic processing unit (GPU) 6041 and a microphone 6042. The graphic processing unit 6041 processes image data of a still picture or a video obtained by an image capture apparatus (e.g., a camera) in a video capture mode or an image capture mode. The processed image frame can be displayed on the display unit 606. The image frame processed by the graphic processing unit 6041 can be stored in the memory 609 (or other storage medium) or transmitted via the radio frequency unit 601 or the network module 602. The microphone 6042 can receive sound and can process such sound as audio data. The processed audio data can be converted into a format that can be transmitted to a mobile communication base station via the radio frequency unit 601 in a telephone call mode.

[0166] The electronic device 600 further includes at least one sensor 605, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor, where the ambient light sensor can adjust the brightness of the display panel 6061 according to the brightness of ambient light, and the proximity sensor can turn off the display panel 6061 and / or the backlight when the electronic device 600 is moved to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), and when at rest, can detect the magnitude and direction of gravity, and can be used to identify the electronic device posture (such as screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, knock), and the like. The sensor 605 can also include a fingerprint sensor, a pressure sensor, an iris sensor, a molecular sensor, a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, and the like, which will not be described here.

[0167] The display unit 606 is configured to display information input by a user or information provided to the user. The display unit 606 can include a display panel 6061, which can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0168] The user input unit 607 can be used to receive inputted digital or character information, and to generate key signal input related to user settings of the electronic device and control of functions. Specifically, the user input unit 607 includes a touch panel 6071 and other input devices 6072. The touch panel 6071, also called a touch screen, can collect a user's touch operation (such as a user's operation on or near the touch panel 6071 using a finger, a stylus, or any suitable object or accessory) on or near it. The touch panel 6071 can include two parts, a touch detection device and a touch controller. The touch detection device detects the user's touch position and detects a signal caused by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into touch coordinates, and sends it to the processor 610, receives commands from the processor 610 and executes them. In addition, the touch panel 6071 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 6071, the user input unit 607 can also include other input devices 6072. Specifically, the other input devices 6072 can include, but are not limited to, a physical keyboard, function keys (such as volume control buttons, on / off buttons, etc.), trackballs, mice, joysticks, and the like, which will not be described here.

[0169] Further, the touch panel 6071 can be overlaid on the display panel 6061, and when the touch panel 6071 detects a touch operation on or near it, it transmits to the processor 610 to determine the type of touch event, and then the processor 610 provides corresponding visual output on the display panel 6061 according to the type of touch event. Although in the Figure 6 In the above embodiment, the touch panel 6071 and the display panel 6061 are implemented as two independent components to realize the input and output functions of the electronic device, but in some embodiments, the touch panel 6071 and the display panel 6061 can be integrated to realize the input and output functions of the electronic device, which is not limited here.

[0170] The interface unit 608 is an interface for connecting external devices to the electronic device 600. For example, the external devices can include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device having an identification module, an audio input / output (I / O) port, a video I / O port, an earphone port, and the like. The interface unit 608 can be used to receive input (e.g., data information, power, etc.) from external devices and transmit the received input to one or more elements within the electronic device 600, or can be used to transmit data between the electronic device 600 and external devices.

[0171] The memory 609 is used to store software programs and various data. The memory 609 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), and the like. In addition, the memory 609 can include a high-speed random access memory, and can also include a nonvolatile memory, for example, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device.

[0172] The processor 610 is a control center of the electronic device, connects all parts of the electronic device through various interfaces and lines, executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 609 and calling data stored in the memory 609, and thus performs overall monitoring on the electronic device. The processor 610 can include one or more processing units; preferably, the processor 610 can integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 610.

[0173] The electronic device 600 can further include a power supply 611 (such as a battery) for supplying power to various components; preferably, the power supply 611 can be logically connected to the processor 610 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system.

[0174] In addition, the electronic device 600 includes some functional modules which are not shown and will not be described herein.

[0175] It should be noted that, in this document, the term “comprising” or “including” or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article, or device. Without more limitations, the element defined by the statement “including a…” does not exclude the presence of additional identical elements in the process, method, article, or device including the element.

[0176] Those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for making a terminal (which can be a mobile phone, computer, server, air conditioner, or network device) execute the method described in each embodiment of the present application.

[0177] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the above-mentioned specific embodiments, and the above-mentioned specific embodiments are only illustrative, not restrictive. Those skilled in the art can make many forms without departing from the purpose of the present application and the scope protected by the claims under the inspiration of the present application, which all belong to the protection of the present application.

[0178] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the embodiments of the present application can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0179] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-mentioned system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0180] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0181] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0182] In addition, each functional unit in each embodiment of the application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit.

[0183] If the functions are realized 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 solutions of the application or the part of the prior art that contributes essentially or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the application. The foregoing storage medium includes various storage media that can store program codes, such as U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc.

[0184] The above is only a specific embodiment of the application, but the protection scope of the application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the application, which should be covered within the protection scope of the application. Therefore, the protection scope of the application should be subject to the protection scope of the claims.

Claims

1. A method for displaying interactive messages in a live streaming room, characterized in that, The method is applicable to live streaming servers and includes: In response to an interactive message filtering request sent by the live streaming client, the live streaming room corresponding to the interactive message filtering request is determined, and the real-time interactive message corresponding to the live streaming room and the user feature tag corresponding to the user account to which the live streaming client belongs are obtained. The interactive message filtering request is a request generated by the live streaming client in response to the number of messages in the real-time interactive message exceeding a preset number threshold. Filter out target interactive messages that match the user feature tags from the real-time interactive messages; The target interaction message is returned to the live streaming client, which displays the target interaction message while outputting the video stream corresponding to the live streaming room.

2. The method according to claim 1, characterized in that, The step of obtaining the real-time interactive messages corresponding to the live stream room and the user feature tags corresponding to the user account to which the live stream client belongs includes: Obtain the real-time interactive messages corresponding to the live broadcast room and the number of messages in the real-time interactive messages; Obtain the user account's following information and historical behavior information, wherein the following information is information generated by the live streaming client in response to the user's input operation on the preference collection page to characterize the user's preferences; Based on the attention information and / or the historical behavior information, generate user feature tags corresponding to the user account to which the live streaming client belongs.

3. The method according to claim 2, wherein generating a user feature tag corresponding to the user account to which the live streaming client belongs, based on the attention information and / or the historical behavior information, comprises: The preference feature tags corresponding to the attention information are used as the user feature tags corresponding to the user account; And / or, use the behavior information tags corresponding to the historical behavior information as user feature tags corresponding to the user account.

4. The method according to claim 1, characterized in that, The live streaming server includes a tag classification model, and the step of filtering target interactive messages that match the user feature tags from the real-time interactive messages includes: The real-time interactive message is segmented into at least one word, and each word corresponds to a word feature. If any of the word segmentation features in the real-time interactive message are invalid message features, then the real-time interactive message will be removed. If at least one of the word segmentation features in the real-time interactive message is a valid message feature, then the valid message feature is input into the tag classification model, and the message feature tag corresponding to the valid message feature is output. Based on the similarity calculation of the message feature tags and the user feature tags, target interactive messages that match the user feature tags are filtered out from the real-time interactive messages.

5. The method according to claim 4, characterized in that, The step of calculating similarity based on the message feature tags and the user feature tags, and filtering out target interactive messages that match the user feature tags from the real-time interactive messages, includes: Extract the first semantic feature of the message feature tag and the second semantic feature of the user feature tag respectively; The semantic similarity between the first feature semantic and the second feature semantic is calculated to obtain the tag similarity between the message feature tag and the user feature tag; Real-time interactive messages with a tag similarity greater than a preset similarity threshold are used as target interactive messages that match the user feature tags.

6. A method for displaying interactive messages in a live streaming room, characterized in that, include: In response to an access operation to the live room, play the video stream corresponding to the live room sent by the live server, and generate an interaction message filtering request for the live room if the number of real-time interaction messages in the live room exceeds a preset threshold. Obtain the target interactive message returned by the live streaming server in response to the interactive message filtering request, and display the target interactive message. The target interactive message is a message that the live streaming server filters out from the real-time interactive messages corresponding to the live streaming room based on the user feature tags corresponding to the live streaming client.

7. The method according to claim 6, characterized in that, The live streaming client includes a preference collection page, which includes several preference tags and further includes: In response to the selection operation for the preference tag, at least one target preference tag corresponding to the selection operation is determined, and the follow information corresponding to the user account to which the live streaming client belongs is generated based on the tag information corresponding to the target preference tag; The attention information is sent to the live streaming server.

8. The method according to claim 7, characterized in that, The live streaming client includes a behavior information collection page, and also includes: In response to a user action on the behavior information collection page, determine the historical behavior information corresponding to the user action; The historical behavior information is sent to the live streaming server.

9. The method according to claim 6, characterized in that, The live streaming client includes a message display area. The step of obtaining the target interactive message returned by the live streaming server in response to the interactive message filtering request, and displaying the target interactive message, includes: Obtain the target interactive message returned by the live streaming server in response to the interactive message filtering request, and the sending sequence of the target interactive message; The target interactive messages are displayed in the message display area according to the order in which they were sent.

10. A display device for interactive messages in a live streaming room, characterized in that, The device is suitable for live streaming servers and includes: The user feature tag acquisition module is used to respond to the interactive message filtering request sent by the live streaming client, determine the live streaming room corresponding to the interactive message filtering request, and obtain the real-time interactive message corresponding to the live streaming room and the user feature tag corresponding to the user account to which the live streaming client belongs. The interactive message filtering request is a request generated by the live streaming client in response to the number of messages in the real-time interactive message being greater than a preset number threshold. The target interaction message filtering module is used to filter out target interaction messages that match the user feature tags from the real-time interaction messages; The target interaction message return module is used to return the target interaction message to the live streaming client, and the live streaming client is used to display the target interaction message while outputting the video stream corresponding to the live streaming room.

11. A display device for interactive messages in a live streaming room, characterized in that, include: The interactive message filtering request generation module is used to respond to the access operation of the live room, play the video stream corresponding to the live room sent by the live server, and generate an interactive message filtering request for the live room when the number of real-time interactive messages in the live room is greater than a preset number threshold. The target interaction message display module is used to obtain the target interaction message returned by the live streaming server in response to the interaction message filtering request, and to display the target interaction message. The target interaction message is a message that the live streaming server filters out from the real-time interaction messages corresponding to the live streaming room based on the user feature tags corresponding to the live streaming client.

12. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is used to store computer programs; When the processor executes a program stored in the memory, it implements the method as described in any one of claims 1-5 or 6-9.

13. A computer-readable storage medium having instructions stored thereon that, when executed by one or more processors, cause the processors to perform the method as described in any one of claims 1-5 or 6-9.

Images