Interactive information management method, interactive information display method, interactive information management device and interactive information display equipment

Abstract

The invention discloses an interactive information management method and device, an interactive information display method and device and equipment, and belongs to the technical field of information processing. The method comprises the following steps: acquiring voice data of an anchor user account in a live broadcast process of the anchor user account; determining target interaction information matched with the voice data from an interaction information stream, wherein the interaction information stream comprises at least two pieces of interaction information sent by the audience user account in the live broadcast process; and generating annotation information of the target interaction information, wherein the annotation information is used for triggering the target interaction information and other interaction information except the target interaction information in the interaction information flow to be displayed differently. According to the method, the target interaction information matched with the voice data of the anchor user account is displayed differently, so that the audience user account can clearly know whether the audience user account is concerned and responded by the anchor user account, and the interaction relevance between the anchor user account and the audience user account can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of information processing technology, and in particular to a management method, display method, device and equipment for interactive information. Background Art

[0002] With the rapid development of the live broadcast industry, the interaction between viewers and anchors has become a key factor in the live broadcast experience. The live broadcast interaction methods provided by related technologies mainly include: sending barrage, gift rewards, comments, chat sessions, etc.

[0003] Taking the sending of barrage as an example, the relevant technology uses a simple chronological arrangement to display the barrage sent by the audience during the live broadcast of the anchor. However, when there are a large number of viewers and barrages frequently pour in, the anchor is often unable to accurately respond to the audience's barrage, making it difficult for the audience to determine whether their barrage has been responded to. Therefore, how to enable the audience to identify the barrage responded by the anchor to further enhance the audience's interactive experience is an urgent problem to be solved. Summary of the invention

[0004] The embodiment of the present application provides a management method, display method, device and equipment for interactive information. The technical solution provided by the embodiment of the present application is as follows:

[0005] According to one aspect of an embodiment of the present application, a method for managing interactive information is provided, the method comprising:

[0006] During the live broadcast of the anchor user account, obtaining voice data of the anchor user account;

[0007] Determining target interactive information matching the voice data from an interactive information stream, wherein the interactive information stream includes at least two interactive information sent by a viewer user account during the live broadcast;

[0008] Generate annotation information of the target interaction information, where the annotation information is used to trigger the target interaction information to be displayed in a differentiated manner from other interaction information in the interaction information flow except the target interaction information.

[0009] According to one aspect of an embodiment of the present application, a method for displaying interactive information is provided, the method comprising:

[0010] During the live broadcast of the anchor user account, a live broadcast interface is displayed, wherein the live broadcast interface displays the live broadcast content of the anchor user account and an interactive information flow, wherein the interactive information flow includes at least two interactive information sent by the audience user account during the live broadcast;

[0011] When the anchor user account generates voice data, the target interaction information matching the voice data in the interaction information flow is displayed separately from other interaction information in the interaction information flow except the target interaction information.

[0012] According to one aspect of an embodiment of the present application, a device for managing interactive information is provided, the device comprising:

[0013] A voice data acquisition module, used to acquire voice data of the anchor user account during the live broadcast of the anchor user account;

[0014] A target information determination module, used to determine target interaction information matching the voice data from an interaction information stream, wherein the interaction information stream includes at least two pieces of interaction information sent by a viewer user account during the live broadcast;

[0015] The annotation information generating module is used to generate annotation information of the target interactive information, wherein the annotation information is used to trigger the target interactive information to be displayed separately from other interactive information in the interactive information flow except the target interactive information.

[0016] According to one aspect of an embodiment of the present application, a display device for interactive information is provided, the device comprising:

[0017] A live broadcast interface display module, used to display a live broadcast interface during the live broadcast of the anchor user account, wherein the live broadcast interface displays the live broadcast content of the anchor user account and an interactive information flow, wherein the interactive information flow includes at least two interactive information sent by the audience user account during the live broadcast;

[0018] The target information display module is used to distinguish the target interaction information matching the voice data in the interaction information flow from other interaction information in the interaction information flow except the target interaction information when the anchor user account generates voice data.

[0019] According to one aspect of an embodiment of the present application, a computer device is provided, comprising a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement the above-mentioned interactive information management method, or to implement the above-mentioned interactive information display method.

[0020] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is loaded and executed by a processor to implement the above-mentioned interactive information management method, or to implement the above-mentioned interactive information display method.

[0021] According to one aspect of the embodiments of the present application, a computer program product is provided, the computer program product comprising a computer program, the computer program being stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the above-mentioned method for managing interactive information, or the above-mentioned method for displaying interactive information.

[0022] The technical solution provided in the embodiments of the present application can bring the following beneficial effects:

[0023] During the live broadcast of the anchor user account, the target interactive information (i.e., the target interactive information that matches the voice data) that the anchor user account is responding to is determined based on the voice data of the anchor user account. Since there is a high correlation between the voice data and the target interactive information, such as the voice data generated when the anchor user account responds to the target interactive information, this is conducive to improving the matching accuracy of the target interactive information. And by displaying the target interactive information differently, the audience user account can clearly understand whether it has received the attention and response of the anchor user account, which is conducive to improving the interactive correlation between the anchor user account and the audience user account. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 is a schematic diagram of a computer system provided by an embodiment of the present application;

[0026] Figure 2 is a flow chart of a method for managing interactive information provided by an embodiment of the present application;

[0027] Figure 3 is a flow chart of a method for determining target interaction information provided by an embodiment of the present application;

[0028] Figure 4 is a flow chart of a method for displaying interactive information provided by an embodiment of the present application;

[0029] Figure 5 is a schematic diagram of a live broadcast interface provided by an embodiment of the present application;

[0030] Figure 6 is a schematic diagram of distinguishing and displaying target interactive information provided by an embodiment of the present application;

[0031] Figure 7 is a schematic diagram of distinguishing and displaying target interactive information provided by another embodiment of the present application;

[0032] Figure 8 is a schematic diagram of a method for managing interactive information provided by an embodiment of the present application;

[0033] Fig. 9 is a block diagram of an interactive information management device provided by an embodiment of the present application;

[0034] Fig.10 is a block diagram of an interactive information management device provided by another embodiment of the present application;

[0035] Fig.11 is a block diagram of a display device for interactive information provided by an embodiment of the present application;

[0036] Fig.12 It is a schematic diagram of the structure of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0037] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0038] Please refer to Figure 1 , which shows a schematic diagram of a computer system provided by an embodiment of the present application. The computer system can be implemented as a solution implementation environment of the technical solution provided by the embodiment of the present application, and the computer system may include: a first terminal device 10, a second terminal device 20 and a server 30.

[0039] The first terminal device 10 may be a terminal device used by an anchor user, who may be a user performing online live broadcasting and may be responsible for participating in a series of work contents such as planning, hosting, and audience interaction, as well as providing real-time broadcasting or interactive services such as audio and video, graphic information, etc. to audience users in the form of live broadcasting. Audience users are users who watch the live broadcasting of anchor users, and they may interact with anchor users online, such as the online interaction between audience users and anchor users includes at least one of the following: sending bullet screens, giving gifts, liking, commenting, and chatting.

[0040] The first terminal device 10 may be an electronic device such as a mobile phone, a tablet computer, a multimedia player, a PC (Personal Computer), an intelligent robot, a vehicle-mounted terminal device, an MP3 (Moving Picture Experts Group Audio Layer III, a dynamic image expert compression standard audio layer 3) player, an MP4 (Moving Picture Experts Group Audio Layer IV, a dynamic image expert compression standard audio layer 4) player, a wearable device, etc. The first terminal device 10 may be installed with a first client, which may be a client of any of the following applications: a live broadcast client, a music playback client, a game application, a social entertainment application, a simulation learning application, a shopping application, and an education and training client.

[0041] The above application may be an online application. For example, the client of the above application may be installed and run in different terminal devices for use by different users. Taking a music player application as an example, the music player application may be installed and run in different terminal devices in the form of a mobile client, a PC client, a web page, a mini program, etc.

[0042] Exemplarily, the anchor user can log in to the first client on the first terminal device 10 through the anchor user account to perform online live broadcast through the first client. The anchor user account can refer to a user account registered on any application with a live broadcast function, and the anchor user account has the authority to perform online live broadcast.

[0043] The second terminal device 20 may be a terminal device used by the audience user, and the second terminal device 20 may be an electronic device such as a mobile phone, a tablet computer, a multimedia player, a PC, an intelligent robot, a vehicle-mounted terminal device, an MP3 player, an MP4 player, a wearable device, etc. The second terminal device 20 may also be installed with the above-mentioned first client. Exemplarily, the audience user may log in to the first client on the second terminal device 20 through the audience user account, and watch the live broadcast of the anchor user online and interact with the anchor user online through the first client. The audience user account may refer to a user account registered on any application with the function of watching live broadcasts, and the audience user account does not have the permission to broadcast live online.

[0044] The server 30 is used to provide background services for the first client in the first terminal device 10 and the first client in the second terminal device 20. For example, the server 30 can be a background server of the above-mentioned application (such as a music playing application). The server 30 can be a single server, a server cluster composed of multiple servers, or a cloud computing service center.

[0045] The first terminal device 10 and the server 30 can communicate with each other through a network, and the second terminal device 20 and the server 30 can communicate with each other through a network. The first terminal device 10 and the second terminal device 20 can communicate with each other through the server 30, and the network can be a wired network or a wireless network.

[0046] Optionally, the computer system may include a plurality of first terminal devices 10 and a plurality of second terminal devices 20. The same first terminal device 10 may communicate with a plurality of second terminal devices 20 via a server 30. Exemplarily, a host user may create a live video broadcast room via a first client on the first terminal device 10, which refers to a virtual network space for displaying ongoing live audio and video content (i.e., live content). For example, a live video broadcast room may be used to display live audio and video content such as personal talent shows, sports events, game competitions, conference speeches, education and training. The live video broadcast room may display the live audio and video content from the perspective of the host user. Optionally, the live audio and video content may be generated by the host user, which is not limited in the embodiments of the present application.

[0047] The audience user can enter the video live broadcast room through the first client on the second terminal device 20 to watch the live broadcast content of the anchor user. Optionally, the audience user can send interactive information to the anchor user through the first client on the second terminal device 20, such as bullet screen, comments, chat information, etc. The interactive information sent by each audience user forms an interactive information flow, such as a bullet screen flow formed by bullet screen, a chat information flow formed by chat information, etc. The first terminal device 10 and each second terminal device 20 corresponding to the video live broadcast room all display the interactive information flow.

[0048] The first client on the first terminal device 10 can generate voice data when the anchor user responds to the interactive information. The first client on the first terminal device 10 sends the voice data to the server 30, and the server 30 determines the target interactive information that matches the voice data (i.e., the interactive information that the anchor user is responding to), and sends annotation information to each second terminal device 20 corresponding to the live video room, and the annotation information is used to indicate the distinguished display of the target interactive information. Each second terminal device 20 corresponding to the live video room distinguishes and displays the target interactive information to indicate the interactive information that the anchor user is responding to. This enables the viewer user account to clearly understand whether it has received attention and response from the anchor user account, which is conducive to improving the interactive relevance between the anchor user account and the viewer user account.

[0049] Optionally, the process of determining the target interactive information can also be executed by the first client. For example, after the first client obtains the voice data of the anchor user account and the interactive information flow, the target interactive information matching the voice data is determined from the interactive information flow. This embodiment of the present application is not limited to this.

[0050] The technical solution provided by the embodiment of the present application will be described below through a method embodiment. For matters not described in the method embodiment, reference can be made to the above embodiment.

[0051] Please refer to Figure 2 , which shows a flow chart of a method for managing interactive information provided by an embodiment of the present application. The execution subject of each step of the method can be Figure 1 The server shown in , or Figure 1 The terminal device shown in , such as the first client in the terminal device. Taking the execution subject of each step as a server as an example, the method includes at least one step in the following steps 201-203.

[0052] Step 201, during the live broadcast of the anchor user account, obtain the voice data of the anchor user account.

[0053] The anchor user account may refer to a user account registered on an application with a live broadcast function, and the anchor user account has the authority to broadcast live online. For example, after the anchor user logs in to the client of the live broadcast application through the anchor user account, the anchor user can open a video live broadcast room through the client to broadcast live online through the video live broadcast room, and the video live broadcast room can be used to display the live broadcast content of the anchor user in real time, such as the live audio and video generated by the anchor user.

[0054] The live broadcast content of the anchor user can be published with the anchor user account, and the live broadcast process of the anchor user account is the live broadcast process of the anchor user. The live broadcast process refers to the process of generating live broadcast content.

[0055] The above-mentioned voice data refers to data recorded and transmitted using voice as a carrier, which can be data converted from sound, speech, etc. and can be processed by computer equipment. Voice data is a time series data, such as recording the changes of sound on the time axis. Voice data can be collected by a voice acquisition device, such as the sound signal at each moment is collected by the voice acquisition device into a digital form to form a time series, and voice data can be generated. Optionally, the voice acquisition device includes at least one of the following: a microphone, a pickup box, and a microphone.

[0056] In an embodiment of the present application, the voice data of the anchor user account may refer to the voice data collected from the sound generated by the anchor user during the live broadcast, such as the voice data obtained by collecting the sound generated by the anchor user when responding to interactive information. Among them, interactive information may refer to the information generated by the interaction between the audience user and the anchor user during the live broadcast of the anchor user, such as the interactive information may be at least one of the following: barrage, comments, virtual gifts, chat information, voting, and likes. Among them, barrage may refer to the commentary subtitles that pop up during the live broadcast. The text content of the barrage can be simple words, words, or images, which is not limited in the embodiment of the present application.

[0057] Optionally, during the live broadcast of the anchor user account, the server can obtain the voice data of the anchor user account through the client logged in by the anchor user account. Exemplarily, the client logged in by the anchor user account can generate the voice data of the anchor user account in real time through the terminal device, and send the generated voice data to the server in real time. Alternatively, during the live broadcast of the anchor user account, the client logged in by the anchor user account generates the voice data of the anchor user account through the terminal device when detecting that the anchor user makes a sound, and sends the generated voice data to the server in real time. Alternatively, the client logged in by the anchor user account can also generate a voice data for each sentence or each paragraph of the anchor user, and send the generated voice data to the server in real time, which is not limited in the embodiments of the present application.

[0058] Step 202: determine target interactive information that matches the voice data from the interactive information stream, where the interactive information stream includes at least two interactive messages sent by the viewer user account during the live broadcast.

[0059] The interactive information flow refers to an information flow formed by interactive information. Exemplarily, each interactive information in the interactive information flow moves in the same direction, such as each interactive information in the interactive information flow moves from left to right on the screen in the order of generation time.

[0060] In the embodiment of the present application, the above-mentioned interactive information flow may refer to an information flow formed by all interactive information generated in the time period from the start time of the live broadcast to the current time. During the live broadcast, as the interactive information changes, the interactive information flow changes accordingly. For example, as the interactive information sent by the viewer user account increases, the length of the interactive information flow becomes longer. The length of the interactive information flow can be used to indicate the amount of interactive information included in the interactive information flow.

[0061] For example, taking interactive information as barrage as an example, during the live broadcast, the barrage sent by the audience user account is cancelled after moving from the right side to the left side of the screen in the order of sending time, thus forming a barrage flow.

[0062] The above-mentioned audience user account may refer to a user account registered on an application with a live broadcast viewing function. The audience user account does not have the permission to broadcast online, but only has the permission to watch live broadcasts. For example, an audience user can log in to the client of a live broadcast application through an audience user account, and enter the video live broadcast room opened by the anchor user account through the client to watch the live broadcast content of the anchor user in real time. Optionally, the same video live broadcast room can accommodate multiple audience user accounts. An anchor user is an audience user in the video live broadcast rooms of other anchor users (i.e., excluding his own video live broadcast room).

[0063] After entering the live video broadcast room of the host user account, the audience user account can also interact with the host user account in the live video broadcast room, such as by sending interactive messages to interact with the host user account.

[0064] The target interaction information matched with the voice data may refer to the interaction information that the anchor user account is responding to. Exemplarily, when the content (such as text content) indicated by the voice data includes the content indicated by the target interaction information, the voice data matches the target interaction information; when the content indicated by the voice data is the answer to the question indicated by the target interaction information, the voice data matches the target interaction information; when the content indicated by the voice data and the content indicated by the target interaction information belong to the same topic, the voice data matches the target interaction information, which is not limited in the embodiments of the present application.

[0065] In one example, reference Figure 3 , step 202 may also include the following sub-steps.

[0066] Step 202a: acquiring an interaction information set within a first time period from the interaction information flow, where the interaction information set includes at least one interaction information.

[0067] That is, at least one interactive information in the interactive information flow that is within the first time period is combined into an interactive information set, and whether the interactive information is within the first time period can be determined based on the generation time of the interactive information. The interactive information set refers to a collection or sequence of interactive information.

[0068] Optionally, the first time period is related to the voice data. Exemplarily, the voice data has a certain lag relative to the target interaction information, and the first time period can be determined based on the generation time of the voice data to ensure that the target interaction information is within the first time period, which is conducive to improving the determination accuracy of the target interaction information.

[0069] For example, the first time period is a time period that ends at the time when the voice data is generated. The embodiment of the present application does not limit the length of the first time period, which can be set and adjusted according to actual usage requirements. For example, the length of the first time period can be 5 minutes, 3 minutes, 2 minutes, 1 minute, etc.

[0070] Optionally, the first time period is related to the previous interaction information. The previous interaction information is the last target interaction information determined before the target interaction information. For example, after the anchor user responds to the previous interaction information, he can continue to respond to the interaction information after the previous interaction information. Then, the first time period can be determined based on the generation time of the previous interaction information to ensure that the target interaction information is within the first time period.

[0071] For example, the first time period is a time period starting at the time when the previous interactive information is generated. The embodiment of the present application does not limit the end time of the first time period, such as the end time of the first time period can be the current time or the time when the voice data is generated.

[0072] Step 202b: Determine the interactive information in the interactive information set that matches the voice data as the target interactive information.

[0073] Optionally, the voice data may be converted into audio text, and then the audio text and the interactive information may be matched to obtain the target interactive information. The audio text is used to describe the voice content corresponding to the voice data in a text style, such as the audio text is used to describe the sound emitted by the anchor user in a text style, such as the words spoken by the anchor user, the text expressed, etc.

[0074] Exemplarily, the process of determining the target interaction information may include the following contents:

[0075] 1. Extracting semantic features of speech data and extracting semantic features of at least one interactive information respectively.

[0076] Semantic features refer to features used to characterize the meaning of text, which capture the meaning in the text. Optionally, the semantic features can exist in the form of feature vectors, such as word vectors, phrase vectors, or sentence vectors, which encode the meaning of the text.

[0077] For speech data, the speech data can be first converted into audio text, and then feature extraction can be performed on the audio text to obtain the semantic features of the speech data.

[0078] Exemplarily, the speech data is converted into audio text by using the Automatic Speech Recognition (ASR) technology, and then the semantic features of the audio text are extracted by using the Natural Language Processing (NLP) technology to obtain the semantic features of the speech data.

[0079] Optionally, the speech data can be converted into audio text by a speech recognition model constructed based on speech recognition technology. The speech recognition model may refer to a machine learning model that has been trained to recognize speech data. Optionally, the speech recognition model can be constructed based on at least one of the following: CNN (Convolutional Neural Network), Transformer (a deep learning model based on self-attention mechanism), RNN (Recurrent Neural Network), DNN (Deep Neural Networks), WavLM (a speech pre-training model), UniSpeech (a model for speech recognition).

[0080] The semantic features of the audio text can be extracted by a text processing model constructed based on natural language processing technology. The text processing model may refer to a machine learning model that has been trained to extract the semantic features of the text. Optionally, the text processing model can be constructed based on at least one of the following: CNN, Transformer, RNN, DNN, LLM (Large Language Model).

[0081] For example, encode speech data to obtain encoded data of speech data, input the encoded data of speech data into a speech recognition model, and the speech recognition model obtains audio text based on the encoded data of speech data, and input the encoded data of audio text into a text processing model, and the text processing model extracts semantic features of the audio text based on the encoded data of audio text.

[0082] For any interactive information in at least one interactive information, encode the text content corresponding to the interactive information to obtain the encoded data of the interactive information, input the encoded data of the interactive information into a text processing model, and the text processing model extracts the semantic features of the interactive information based on the encoded data of the interactive information.

[0083] 2. Calculate the similarity between the semantic feature of at least one interactive information and the semantic feature of the speech data to obtain the semantic similarity of at least one interactive information.

[0084] The semantic similarity is used to indicate the similarity between the semantic features of the voice data and the semantic features of the interactive information. The greater the semantic similarity of the interactive information, the higher the similarity between the interactive information and the voice data, that is, the more relevant the interactive information is to the voice data.

[0085] Optionally, the semantic similarity calculation method may include at least one of the following: cosine similarity, Euclidean distance, Manhattan distance, and any calculation method capable of calculating the similarity between two vectors.

[0086] Exemplarily, for any interactive information in the at least one interactive information, a cosine similarity algorithm is used to calculate the similarity between the semantic features of the interactive information and the semantic features of the speech data to obtain the semantic similarity of each of the interactive information.

[0087] For example, a first dot product between the semantic features of the interactive information and the semantic features of the voice data, and a second dot product between the modulus of the semantic features of the interactive information and the modulus of the semantic features of the voice data are obtained, and the semantic similarity of each interactive information is obtained by dividing the first dot product by the second dot product.

[0088] 3. Based on semantic similarity, determine the target interaction information that matches the voice data from the interaction information set.

[0089] The greater the semantic similarity of the interactive information, the greater the probability that the interactive information is the target interactive information that the anchor user is responding to. Optionally, the target interactive information can be determined from the interactive information with higher semantic similarity.

[0090] Exemplarily, the method for determining the target interaction information may include at least one of the following:

[0091] 1. Obtain a maximum semantic similarity among the semantic similarities of at least one interactive information; when the maximum semantic similarity is greater than or equal to a first threshold, determine the interactive information with the maximum semantic similarity in the interactive information set as the target interactive information.

[0092] The first threshold value can be used to determine whether the voice data is used to respond to the interactive information. The first threshold value can be set and adjusted according to actual usage requirements, and the embodiment of the present application does not limit this. Optionally, the interactive information with the greatest semantic similarity in the interactive information set can be one or more, that is, the number of target interactive information can be one or more.

[0093] For example, at least one interactive message is sorted in descending order of semantic similarity to obtain an interactive message sequence, and the semantic similarity of the first interactive message in the interactive message sequence is determined as the maximum semantic similarity. When the maximum semantic similarity is greater than or equal to the first threshold, it can be determined that the voice data is used to respond to the interactive message, and the first interactive message in the interactive message sequence can be determined as the target interactive message.

[0094] Optionally, when the maximum semantic similarity is less than the first threshold, the determination of the target interactive information is stopped, that is, it can be determined that the voice data is not used to respond to the interactive information. The first threshold is used to determine whether the voice data is used to respond to the interactive information, and only when the voice data is used to respond to the interactive information, the target interactive information is determined, which is conducive to reducing the workload required to determine the target interactive information and improving the accuracy of the target interactive information.

[0095] 2. Determine the interactive information in the interactive information set whose semantic similarity is greater than or equal to the second threshold as the target interactive information.

[0096] The second threshold value can be used to determine whether the interactive information matches the voice data. The second threshold value can be set and adjusted according to actual usage requirements, and the embodiment of the present application does not limit this. When the semantic similarity of the interactive information is greater than or equal to the second threshold value, it can be determined that the interactive information matches the voice data.

[0097] Optionally, when there is no interactive information with a semantic similarity greater than or equal to a second threshold in the interactive information set, it can be determined that there is no interactive information matching the voice data in the interactive information set, and the determination of the target interactive information is stopped.

[0098] The embodiment of the present application realizes automatic matching of target interaction information and voice data through a semantic feature matching algorithm, without the need for manual determination of the target interaction information, which is beneficial to improving the accuracy and efficiency of determining the target interaction information.

[0099] Step 203: Generate annotation information of the target interactive information, where the annotation information is used to trigger the target interactive information to be displayed in a differentiated manner from other interactive information in the interactive information flow except the target interactive information.

[0100] The server may determine the display style to which the target interactive information is to be adjusted, and generate annotation information of the target interactive information based on the display style. The display style may be used to distinguish the target interactive information, that is, the display style of the target interactive information is different from the display style of other interactive information. For different voice data, the interactive information flow is different, and other interactive information is also different.

[0101] Exemplarily, the target interactive information may be adjusted to display in at least one of the following ways:

[0102] 1. Bold the characters in the target interactive information.

[0103] For example, when the text in the barrage is displayed in a non-bold style, the text in the target barrage is adjusted to a bold style to distinguish it from other barrages.

[0104] 2. Increase the font size of the characters in the target interactive information.

[0105] For example, when the text in the barrage is displayed in a small font size (such as size 4), the text in the target barrage is adjusted to a large font size (such as size 2) to distinguish it from other barrages.

[0106] 3. Change the color of the characters in the target interactive information.

[0107] For example, when the text in the barrage is displayed in black, the color of the text in the target barrage is adjusted to other colors, such as red, blue, yellow, etc., to distinguish it from other barrages.

[0108] 4. Continuously display target interactive information at the set location.

[0109] Among them, the setting position can be set and adjusted according to actual use requirements, and the embodiments of the present application are not limited to this. Exemplarily, the setting position includes at least one of the following: top display, center display, and bottom display. For example, the target bullet screen can be set to the top to continuously display the target bullet screen at the top of the live broadcast interface. The live broadcast interface refers to an interface for displaying live broadcast content, which can be the user interface provided by the above-mentioned first client.

[0110] 5. Display a graph consisting of target interactive information.

[0111] Optionally, the various parts of the graphic are formed by the same target interactive information. For example, the target bullet screen is spliced ​​into a graphic for display to distinguish it from other bullet screens. The graphic can be in the shape of a person, an animal, or a building, which is not limited in the embodiment of the present application.

[0112] Optionally, the graphic may be related to the target interactive information. For example, if the target interactive information is related to a cat, a cat-shaped pattern composed of the target interactive information may be displayed to distinguish it from other bullet comments.

[0113] 6. Highlight target interaction information.

[0114] For example, highlight the target barrage to distinguish it from other barrages.

[0115] Optionally, the display mode to which the target interactive information can be adjusted can also be a combination of at least two of the above display modes, which is not limited in the embodiment of the present application.

[0116] The embodiment of the present application distinguishes and displays the target interactive information to highlight the interactive information being responded to by the anchor user, thereby ensuring that the audience user can clearly know which interactive information the anchor user is responding to, which is conducive to enhancing the audience user's sense of participation and live broadcast interactivity, thereby improving the liveliness of the live broadcast room. In addition, the responded audience user can quickly respond to the anchor user, which is conducive to improving the interaction efficiency between the audience user and the anchor user, thereby improving the viewing experience of the audience user.

[0117] In one example, the process of generating annotation information may include the following:

[0118] 1. According to the type of the target interactive information, determine the display mode to which the target interactive information is adjusted.

[0119] The embodiment of the present application does not limit the classification standard of the types of interactive information. Exemplarily, the type of interactive information can be determined based on the sentence type of the text in the interactive information, and the type of interactive information can include at least one of the following: question type, blessing type, statement type, and exclamation type.

[0120] Optionally, each type corresponds to a different display mode. For example, when the target interactive information type is an exclamation type, the characters in the target interactive information can be bolded; when the target interactive information type is a blessing type, a graphic composed of the target interactive information (such as a flower shape) can be displayed. When the target interactive information type is a question type, the target interactive information can be continuously displayed at a set position.

[0121] 2. Generate annotation information based on the display method.

[0122] Optionally, the generated annotation information is used to trigger adjustment of display of the target interactive information in the above-determined display manner to distinguish it from other interactive information.

[0123] Exemplarily, the generated annotation information includes identification information of the display mode and identification information of the target interaction information, so as to indicate that the target interaction information is adjusted to be displayed in the above-determined display mode. The identification information of the display mode is used to uniquely identify the display mode, and the identification information of the target interaction information is used to uniquely identify the target interaction information.

[0124] In one example, the process of generating the annotation information may also include the following:

[0125] 1. Identify the emotional information of the target interactive information.

[0126] The emotion information is used to indicate the emotion expressed by the text in the target interactive information. Exemplarily, the emotion information may include at least one of the following: positive emotion, neutral emotion, and negative emotion.

[0127] Optionally, the sentiment information of the target interactive information can be identified by a sentiment analysis model constructed based on natural language processing technology. The sentiment analysis model can refer to a machine learning model that has been trained for sentiment analysis. Optionally, the sentiment analysis model can be constructed based on at least one of the following: CNN, Transformer, RNN, DNN, LLM.

[0128] For example, the target interaction information is encoded to obtain encoded data of the target interaction information, the encoded data of the target interaction information is input into a sentiment analysis model, and the sentiment analysis model obtains sentiment information of the target interaction information based on the encoded data of the target interaction information.

[0129] 2. Determine the display mode to which the target interactive information is adjusted based on the emotional information.

[0130] Optionally, different emotional information corresponds to different display modes. The embodiment of the present application does not limit the corresponding relationship between emotional information and display modes, which can be set and adjusted according to actual use requirements.

[0131] For example, when the emotional information of the target interactive information is positive, the color of the characters in the target interactive information can be changed, such as to warm tones; when the emotional information of the target interactive information is negative, the color of the characters in the target interactive information can also be changed, such as to cool tones.

[0132] 3. Generate annotation information based on the display method.

[0133] Optionally, the generated annotation information is used to trigger adjustment of display of the target interactive information in the above-determined display manner to distinguish it from other interactive information.

[0134] Optionally, the display style determination method can be flexibly set according to the background configuration to adapt to different live broadcast scene requirements, which is conducive to improving the flexibility of display style determination. For example, the server determines the display style determination method according to the live broadcast scene requirements, and then uses the display style determination method to determine the display style of the target interactive information.

[0135] Optionally, the method for determining the display style can also be customized by the host user or the audience user. For example, the audience user can customize the method for determining the display style according to the live broadcast scene requirements or the host user's preferences and generate configuration information. The configuration information is sent to the server, and the server sets the method for determining the display style based on the configuration information. By supporting the customized setting of the method for determining the display style, it is conducive to improving the flexibility of determining the display style and stimulating the interest of the audience user in watching the live broadcast.

[0136] Optionally, after generating the annotation information of the target interactive information, the server sends the annotation information to the terminal devices used by each viewer user, and the terminal devices used by each viewer user display the target interactive information based on the annotation information. Each viewer user is a viewer user who watches the live broadcast content of the anchor user.

[0137] After generating the annotation information of the target interactive information, the server may also send the annotation information to the terminal device used by the anchor user. The terminal device used by the anchor user distinguishes and displays the target interactive information based on the annotation information.

[0138] During the live broadcast of the anchor user account, the anchor user account can generate multiple voice data in sequence, and the target interaction information also changes dynamically with the change of the voice data. Optionally, the annotation information of the target interaction information can also be used to trigger the cancellation of the previously displayed interaction information, that is, to replace the previously displayed interaction information with the previously displayed target interaction information.

[0139] In the embodiment of the present application, the processing method of each voice data is the same. For the convenience of description and explanation, the embodiment of the present application only takes the processing process of a certain voice data as an example for description.

[0140] In summary, the technical solution provided by the embodiment of the present application determines the target interactive information (i.e., the target interactive information matching the voice data) that the host user account is responding to during the live broadcast of the host user account based on the voice data of the host user account. Since there is a high correlation between the voice data and the target interactive information, such as the voice data generated when the host user account responds to the target interactive information, this is conducive to improving the matching accuracy of the target interactive information. And by displaying the target interactive information differently, the audience user account can clearly understand whether it has received the attention and response of the host user account, which is conducive to improving the interactive correlation between the host user account and the audience user account.

[0141] In some embodiments, after converting the voice data into audio text, the embodiment of the present application may further filter the interactive information in combination with the keywords in the audio text to improve the accuracy of determining the target interactive information, and the above step 202 may further include the following contents:

[0142] 1. Convert the voice data into audio text, which is used to describe the voice content corresponding to the voice data in a text style.

[0143] The process of obtaining the audio text is the same as that in the above embodiment and will not be repeated here.

[0144] 2. Extract at least one keyword from the audio text.

[0145] Keywords may refer to words that play a key or core role in an audio text, such as verbs, adjectives, nouns, numerals, etc.

[0146] Optionally, verbs, adjectives, nouns, numerals, etc. in the audio text may be determined as keywords.

[0147] Optionally, at least one keyword can be extracted from the audio text by a machine learning model. Exemplarily, the machine learning model can be at least one of the following: CNN, Transformer, RNN, DNN, LLM. The embodiment of the present application does not limit the keyword extraction method.

[0148] 3. The interactive information in the interactive information set that matches at least one keyword is determined as preliminary screening interactive information to obtain a preliminary screening interactive information set.

[0149] The initial screening interaction information set is a set or sequence consisting of initial screening interaction information.

[0150] Optionally, the interactive information set including the interactive information of at least one of the above-mentioned at least one keyword can be determined as the preliminary screening interactive information, or the interactive information set including at least one of the above-mentioned at least one keyword can be determined as the preliminary screening interactive information. This embodiment of the present application is not limited to this.

[0151] 4. Based on semantic similarity, determine the target interaction information that matches the voice data from the initial screening interaction information set.

[0152] Optionally, the preliminary screening interaction information set includes at least one preliminary screening interaction information. The maximum semantic similarity among the semantic similarities of the at least one preliminary screening interaction information can be obtained; when the maximum semantic similarity is greater than or equal to a first threshold, the preliminary screening interaction information with the maximum semantic similarity in the preliminary screening interaction information set is determined as the target interaction information. When the maximum semantic similarity is less than the first threshold, the determination of the target interaction information is stopped.

[0153] Optionally, the initially screened interaction information whose semantic similarity is greater than or equal to a second threshold in the initially screened interaction information set is determined as the target interaction information.

[0154] In a feasible example, the interactive information that includes at least one of the above keywords in the interactive information set can be directly determined as the target interactive information without using a semantic matching method, which is conducive to improving the efficiency of determining the target interactive information.

[0155] In some embodiments, after obtaining the interactive information set, the embodiment of the present application may further combine the video data of the anchor user account to more comprehensively screen the interactive information, thereby assisting the voice data to more accurately determine the target interactive information, thereby improving the accuracy of determining the target interactive information. The above step 202 may further include the following contents:

[0156] 1. Obtain the video data of the live broadcast user account. The video data is used to record the behavior of the anchor user account.

[0157] Video data may refer to a sequence formed by a group of continuous images on a time axis. Optionally, each voice data corresponds to a video data, and the time period to which the video data corresponding to the voice data belongs is the same as the time period to which the voice data belongs. Then, the video generating device may generate a frame of image for the live broadcast content of the anchor user at each moment in the time period, and the video data corresponding to the voice data may be obtained.

[0158] Optionally, the time period to which the video data corresponding to the voice data belongs may also be the first time period mentioned above. The video generation device includes at least one of the following: a camera, a still camera.

[0159] Optionally, during the live broadcast of the anchor user account, the server may obtain the video data of the anchor user account through the client logged in by the anchor user account. For example, the client logged in by the anchor user account may generate the video data corresponding to the voice data while generating the voice data of the anchor user account through the terminal device, and send the generated voice data and video data to the server in real time.

[0160] In the embodiment of the present application, the video data corresponding to the voice data can be used to describe the live broadcast content when the anchor user responds to the target interactive information, and the live broadcast content includes the behavior of the anchor user when responding to the target interactive information. Therefore, there is also a certain correlation between the video data corresponding to the voice data and the target interactive information.

[0161] 2. Determine the interactive information in the interactive information set that matches the video data as candidate interactive information to obtain a candidate interactive information set.

[0162] The candidate interaction information set refers to a set or sequence of candidate interaction information. The candidate interaction information set may include at least one candidate interaction information.

[0163] In one example, the interaction information that matches the action corresponding to the video data may be determined as candidate interaction information. Exemplarily, the process of determining the candidate interaction information may include the following:

[0164] (1) Identify the action sequence of the anchor user account from the video data.

[0165] The embodiment of the present application does not limit the above action sequence.

[0166] Optionally, the above action sequence may include the actions of various limbs of the anchor user, such as the above action sequence may include various actions performed by the anchor user such as dancing, imitating actions, imitating animals, etc. in response to the target interactive information.

[0167] Optionally, the above action sequence may include the mouth movements of the anchor user, for example, the above action sequence may include a series of mouth movements of the anchor user when reading text in the target interactive information.

[0168] Optionally, the above action sequence may include facial movements of the anchor user, such as the above action sequence may include a series of facial movements (such as forming corresponding expressions) produced by the anchor user after reading the text in the target interactive information.

[0169] (2) The interactive information in the interactive information set that matches the action sequence is determined as candidate interactive information.

[0170] Optionally, the interactive information set used to describe the above action sequence (such as the actions of each limb) is determined as candidate interactive information. The interactive information set includes the text described by the above action sequence (such as the text corresponding to the mouth action) as candidate interactive information; the interactive information set includes the expression described by the above action sequence (such as the expression formed by the facial action) as candidate interactive information, which is not limited in this embodiment of the application.

[0171] In one example, the interactive information that matches the viewpoint corresponding to the video data may be determined as candidate interactive information. Exemplarily, the process of determining the candidate interactive information may also include the following contents:

[0172] (1) Identify the viewpoint sequence of the anchor user account on the screen from the video data.

[0173] Among them, the viewpoint in the viewpoint sequence is the intersection between the line of sight of the anchor user account and the screen.

[0174] Optionally, the viewpoint of each frame image in the video data may be identified through an image processing model, and then the viewpoints of each frame image may be sorted in chronological order to obtain a viewpoint sequence.

[0175] The image processing model can be implemented as at least one of the following: CNN, Transformer, RNN, DNN, BERT (Bidirectional Encoder Representation From Transformers), vision model (Swin-Transformer, ViT (Vision Transformer), V-MOE (Vision Mixture-of-Experts)), CLIP (Contrastive Language-Image Pre-training).

[0176] (2) The interactive information in the interactive information set that matches the viewpoint sequence is determined as candidate interactive information.

[0177] Optionally, for each viewpoint in the viewpoint sequence, the candidate interaction information is determined based on the interaction information within a preset range centered on the viewpoint, wherein the preset range can be set and adjusted according to actual use requirements, and the embodiment of the present application does not limit this.

[0178] There is a high probability that target interactive information exists within a preset range centered on the viewpoint. Screening interactive information based on the viewpoint sequence is helpful to improve the accuracy of screening interactive information.

[0179] 3. The candidate interaction information that matches the voice data in the candidate interaction information set is determined as the target interaction information.

[0180] Optionally, candidate interaction information whose semantic features match the semantic features of the speech data in the candidate interaction information set is determined as target interaction information.

[0181] The embodiment of the present application can reduce the workload of the voice matching method by filtering interactive information through keywords or video data, thereby facilitating improving the efficiency of determining target interactive information. In addition, interactive information can be more comprehensively filtered through keywords or video data, thereby facilitating improving the accuracy of determining target interactive information.

[0182] In some embodiments, when the number of target interaction information is at least two, the embodiment of the present application may further include the following content:

[0183] 1. Determine the first category ranking of at least two target interaction information according to their respective sending times.

[0184] Optionally, at least two target interaction information are sorted in order of sending time to obtain a first information sequence, and the arrangement numbers of the at least two target interaction information in the first information sequence are determined as the first category ranking of the at least two target interaction information.

[0185] The higher the first category ranking of the target interactive information, the earlier the target interactive information is sent.

[0186] 2. Determine the second category ranking of the at least two target interaction information according to the semantic similarity of the at least two target interaction information.

[0187] Optionally, at least two target interaction information are sorted in descending order of semantic similarity to obtain a second information sequence, and the arrangement numbers of the at least two target interaction information in the second information sequence are determined as the second category ranking of the at least two target interaction information.

[0188] The higher the second category ranking of the target interactive information is, the greater the possibility that the target interactive information is the interactive information that the anchor user is responding to.

[0189] 3. Determine the third category ranking of at least two target interaction information according to their respective interaction rates.

[0190] The interaction rate is used to indicate the frequency of interaction between the host user account and the viewer user account that sent the target interaction information. The higher the interaction rate, the greater the probability that the host user will respond to the viewer user account.

[0191] Optionally, at least two target interaction information are sorted in descending order of interaction rate to obtain a third information sequence, and the arrangement numbers of the at least two target interaction information in the third information sequence are determined as the third category rankings of the at least two target interaction information respectively.

[0192] The higher the third category ranking of the target interactive information is, the greater the possibility that the target interactive information is the interactive information that the anchor user is responding to.

[0193] 4. For each target interaction information, the final ranking of the target interaction information is determined based on the first category ranking, the second category ranking and the third category ranking of the target interaction information.

[0194] The embodiment of the present application does not limit the method for determining the final ranking.

[0195] Optionally, the first ranking, the second ranking and the third ranking of the target interactive information are weighted and summed to obtain the final ranking of the target interactive information. The weight parameters corresponding to the first ranking, the second ranking and the third ranking can be set and adjusted according to experience values.

[0196] Optionally, the sum of the first-category ranking, the second-category ranking, and the third-category ranking of the target interactive information may also be determined as the final ranking of the target interactive information.

[0197] Optionally, the average of the first category ranking, the second category ranking, and the third category ranking of the target interactive information may be determined as the final ranking of the target interactive information.

[0198] 5. For the first target interaction information with the smallest final ranking among the at least two target interaction information, generate first annotation information.

[0199] The probability that the first target interactive information with the smallest final ranking is the interactive information to which the anchor user is responding is the highest, and the first target interactive information with the smallest final ranking can be directly determined as the interactive information to which the anchor user is responding.

[0200] For other target interaction information except the first target interaction information among at least two target interaction information, there is similarity between the other target interaction information and the first target interaction information. For example, the other target interaction information may be the same as the first target interaction information, or may include partial content corresponding to the first target interaction information, or may be related to the first target interaction information. The embodiments of the present application do not limit this.

[0201] The first annotation information refers to the annotation information of the first target interactive information. Exemplarily, the generated annotation information may be directly determined as the first annotation information.

[0202] 6. For other target interaction information except the first target interaction information in the at least two target interaction information, generate second annotation information.

[0203] The second annotation information refers to the annotation information of other target interactive information. The second annotation information can be obtained by adjusting the annotation information generated above, such as reducing the degree of difference of the display mode indicated by the annotation information, to obtain the second annotation information. The degree of difference is used to indicate the degree to which the display mode of the target interactive information is adjusted.

[0204] Optionally, the degree of distinction corresponding to the second annotation information is smaller than the degree of distinction corresponding to the first annotation information, that is, the display difference between the other target interactive information and the other interactive information is smaller than the display difference between the first target interactive information and the other interactive information. The display mode indicated by the second annotation information can be set and adjusted according to actual usage requirements, and the embodiments of the present application are not limited to this.

[0205] Exemplarily, the display mode indicated by the second annotation information is different from the display mode indicated by the first annotation information, but the type of the display mode indicated by the second annotation information is the same as the type of the display mode indicated by the first annotation information.

[0206] For example, when the display method corresponding to the target interaction information is to highlight the target interaction information, the first annotation information is used to indicate that the first target interaction information is highlighted with a first brightness, and the second annotation information is used to indicate that other target interaction information is displayed with a second brightness, and the value of the second brightness is smaller than the value of the first brightness, and the value of the second brightness is greater than the value of the brightness of other interaction information.

[0207] For another example, when the display method corresponding to the target interactive information is to increase the font size of the characters in the target interactive information, the first annotation information is used to indicate that the first target interactive information is displayed in an enlarged first font size, and the second annotation information is used to indicate that other target interactive information is displayed in an enlarged second font size, and the value of the second font size is smaller than the value of the first font size, and the value of the second font size is larger than the value of the font size of other interactive information.

[0208] The technical solution provided in the embodiment of the present application is helpful in stimulating the interest of audience users in interacting, thereby improving user stickiness, by distinguishing and displaying the first target interaction information with the highest final ranking in a more obvious display manner, and distinguishing and displaying other target interaction information in a less obvious display manner.

[0209] Please refer to Figure 4 , which shows a flow chart of a method for displaying interactive information provided by an embodiment of the present application. The execution subject of each step of the method can be Figure 1 The terminal device shown in is a client in the terminal device. Taking the execution subject of each step as the client as an example, the method includes at least one step in the following steps 401-402.

[0210] Step 401, during the live broadcast of the anchor user account, a live broadcast interface is displayed, in which the live broadcast content of the anchor user account and an interactive information flow are displayed, and the interactive information flow includes at least two interactive information sent by the audience user account during the live broadcast.

[0211] The live broadcast interface may refer to an interface for displaying the live broadcast content of the anchor user account, such as a live broadcast interface that can be used to display the live audio and video of the anchor user account in real time. Optionally, the live broadcast interface may be a user interface provided by the above-mentioned first client. In the embodiment of the present application, the above-mentioned live broadcast interface may refer to a user interface provided by the first client logged in by the anchor user account, or it may be a user interface provided by the first client logged in by the audience user account, that is, the execution subject of each step in the embodiment of the present application may be the first client logged in by the anchor user account, or it may be the first client logged in by the audience user account.

[0212] The live broadcast content, interactive information flow and interactive information are the same as those described in the above embodiment. The contents not described in the embodiment of this application can be referred to the above embodiment and will not be repeated here.

[0213] Optionally, the live broadcast interface may also display at least one of the following: information of the anchor user, information of the audience user, interactive information of the audience user (such as bullet screen, chat information, virtual gifts, etc.), and operation controls for implementing different functions. Figure 5 The live broadcast interface 500 includes a display layer and a control layer. The display layer displays the live broadcast content, chat information flow and barrage flow of the anchor user, and the control layer displays the anchor user's information query entrance, barrage query entrance, virtual gift sending controls, barrage sending controls, etc.

[0214] Among them, each bullet comment in the bullet comment stream can be moved from the right side to the left side of the live broadcast interface in the order of sending time and then be cancelled. The chat information in the chat information stream can be moved from the bottom side to the top side of the chat session area in the order of sending time and then be cancelled.

[0215] Step 402, when the anchor user account generates voice data, the target interaction information matching the voice data in the interaction information flow is displayed separately from other interaction information in the interaction information flow except the target interaction information.

[0216] Optionally, when the anchor user account generates voice data, the client sends the voice data to the server, the server determines the target interaction information that matches the voice data from the interactive information flow, and generates annotation information for the target interaction information, the server sends the annotation information of the target interaction information to the client, and the client displays the target interaction information that matches the voice data in the interactive information flow based on the annotation information of the target interaction information, distinguishing it from other interactive information in the interactive information flow except the target interaction information.

[0217] The method for determining the target interaction information is the same as that described in the above embodiment. The contents not described in the embodiment of the present application can be referred to the above embodiment and will not be repeated here.

[0218] Exemplarily, the target interactive information annotation information includes the target interactive information identification information and the display mode identification information, so as to instruct the client to use the display mode to distinguish the target interactive information and normally display other interactive information. Optionally, for the previous interactive information, the client also resumes normal display of the previous interactive information.

[0219] For example, refer to Figure 6When the barrage 501 in the barrage stream displayed on the live broadcast interface 500 is the target barrage, the client bolds and enlarges the characters in the barrage 501, and displays other barrages in the barrage stream normally, so as to distinguish the barrage 501 from other barrages in the barrage stream.

[0220] When the chat information 502 in the chat information stream displayed on the live broadcast interface 500 is the target chat information, the client displays each character in the chat information 502 in bold, and displays other chat information in the chat information stream normally, so as to distinguish the chat information 502 from other chat information in the chat information stream.

[0221] Optionally, during the live broadcast of the anchor user account, as the voice data is updated, the target interactive information is also updated accordingly, thereby dynamically adjusting and displaying the interactive information responded by the anchor user.

[0222] In one example, the embodiment of the present application may also include the following content:

[0223] 1. When the anchor user account generates the first voice data, the second target interaction information matching the first voice data in the interaction information flow is displayed separately from other interaction information in the interaction information flow except the second target interaction information.

[0224] The first voice data may refer to any voice data generated by the anchor user account during the live broadcast process. The second target interaction information refers to the target interaction information that matches the first voice data in the interaction information flow corresponding to the first voice data.

[0225] The client distinguishes and displays the second target interactive information according to the annotation information of the second target interactive information, and displays other interactive information in the interactive information flow normally. For other interactive information, normal display means not adjusting the display mode, and for the previous interactive information, normal display means restoring the display mode to be the same as the display mode of other interactive information.

[0226] 2. When the host user account generates the second voice data, cancel the distinguished display of the second target interactive information, and distinguish the third target interactive information matching the second voice data in the interactive information flow from other interactive information in the interactive information flow except the third target interactive information.

[0227] The second voice data may refer to the first voice data generated after the first voice data. The target interaction information used to respond to the second voice data is different from the target interaction information used to respond to the first voice data.

[0228] The third target interaction information refers to the target interaction information that matches the second voice data in the interaction information flow corresponding to the second voice data, that is, the third target interaction information is the interaction information responded to by the second voice data. After the third target interaction information is determined, the second target interaction information can be called the previous interaction information of the third target interaction information.

[0229] Canceling the distinguished display of the second target interactive information may refer to resuming normal display of the second target interactive information. The client may distinguish and display the third target interactive information according to the annotation information of the third target interactive information, and normally display other interactive information in the interactive information flow.

[0230] For example, refer to Figure 7 When the target barrage is changed from barrage 501 to barrage 503, the client cancels the distinguishing display of barrage 501, bolds and enlarges the characters in barrage 503, and displays other barrages in the barrage stream normally, to indicate that the host user has completed the response to barrage 501 and is responding to barrage 503.

[0231] When the target chat message is changed from chat message 502 to chat message 504, the client cancels the distinctive display of chat message 502, that is, cancels the bolding of each character in chat message 502, as well as the bold display of each character in chat message 504 and the normal display of other chat messages in the chat message stream, to indicate that the host user has completed the response to chat message 502 and is responding to chat message 504.

[0232] In summary, the technical solution provided by the embodiment of the present application determines the target interactive information (i.e., the target interactive information matching the voice data) that the host user account is responding to during the live broadcast of the host user account based on the voice data of the host user account. Since there is a high correlation between the voice data and the target interactive information, such as the voice data generated when the host user account responds to the target interactive information, this is conducive to improving the matching accuracy of the target interactive information. And by displaying the target interactive information differently, the audience user account can clearly understand whether it has received the attention and response of the host user account, which is conducive to improving the interactive correlation between the host user account and the audience user account.

[0233] In some embodiments, the technical solution provided in the embodiment of the present application is described by taking the interactive information as a bullet screen as an example. Figure 8 , then the embodiments of the present application may also include the following contents:

[0234] The first client logged in by the anchor user account is recorded as anchor client 802, the client logged in by the audience user account is recorded as audience client 801, and the backend server of the first client is recorded as server 803. Optionally, the first client may refer to a music player application with a live broadcast function.

[0235] 1. The anchor client 802 opens the video live broadcast room.

[0236] In response to the host user's operation of opening the video live broadcast room, the host client 802 opens the video live broadcast room and displays the live broadcast interface of the video live broadcast room from the host user's perspective. The live broadcast interface is used to display the live broadcast content of the host user and the barrage stream generated during the live broadcast.

[0237] 2. Viewer client 801 enters the live video broadcast room.

[0238] The audience client 801 enters the live video room in response to the audience user's entry operation on the live video room, and displays the live broadcast interface of the live video room from the audience user's perspective.

[0239] 3. When the anchor user account generates the first voice data, the anchor client 802 sends the first voice data to the server 803.

[0240] 4. The server 803 determines a second target bullet comment that matches the first voice data from the bullet comment stream.

[0241] Optionally, the server 803 extracts semantic features of the first voice data and semantic features of each barrage in the barrage stream; calculates the similarity between the semantic features of each barrage and the semantic features of the first voice data, to obtain the semantic similarity of each barrage; obtains a barrage set within a first time period from the barrage stream, the barrage set including at least one barrage, the first time period being a time period with the generation time of the first voice data as the end time; and determines the barrage in the barrage set whose semantic similarity is greater than or equal to a second threshold as the second target barrage matching the first voice data.

[0242] 5. The server 803 generates first annotation information for the second target bullet comment.

[0243] The server 803 determines the display mode to which the second target bullet screen is adjusted according to the type of the second target bullet screen, and generates first annotation information of the second target bullet screen based on the display mode. The first annotation information is used to indicate that the second target bullet screen is displayed differently, and other bullet screens are displayed normally.

[0244] 6. The server 803 sends the first marking information to the viewer client 801 and the anchor client 802 respectively.

[0245] 7. The audience client 801 displays the second target bullet screen in a differentiated manner based on the first annotation information.

[0246] 8. The anchor client 802 distinguishes and displays the second target barrage based on the first annotation information.

[0247] 9. When the anchor user account generates the second voice data, the anchor client 802 sends the second voice data to the server 803.

[0248] The second voice data may refer to the first voice data generated by the anchor user after the first voice data.

[0249] 10. The server 803 determines a third target barrage matching the second voice data from the barrage stream.

[0250] Optionally, the server 803 extracts semantic features of the second voice data and semantic features of each barrage in the barrage stream; calculates the similarity between the semantic features of each barrage and the semantic features of the second voice data, to obtain the semantic similarity of each barrage; obtains a barrage set within a second time period from the barrage stream, the barrage set including at least one barrage, and the second time period is a time period with the generation time of the second voice data as the end time; and determines the barrage in the barrage set whose semantic similarity is greater than or equal to the second threshold as the third target barrage that matches the second voice data.

[0251] 11. The server 803 generates second annotation information for the third target bullet screen.

[0252] The server 803 determines the display mode to which the third target bullet screen is adjusted according to the type of the third target bullet screen, and generates second annotation information of the third target bullet screen based on the display mode. The second annotation information is used to indicate that the third target bullet screen is displayed differently, and other bullet screens are displayed normally.

[0253] 12. The server 803 sends the second annotation information to the viewer client 801 and the anchor client 802 respectively.

[0254] 13. Based on the second annotation information, the audience client 801 cancels the distinguishing display of the second target bullet screen, and distinguishes the display of the third target bullet screen.

[0255] 14. Based on the second annotation information, the anchor client 802 cancels the distinguishing display of the second target barrage, and distinguishes the display of the third target barrage.

[0256] In summary, the technical solution provided by the embodiment of the present application determines the target interactive information (i.e., the target interactive information matching the voice data) that the host user account is responding to during the live broadcast of the host user account based on the voice data of the host user account. Since there is a high correlation between the voice data and the target interactive information, such as the voice data generated when the host user account responds to the target interactive information, this is conducive to improving the matching accuracy of the target interactive information. And by displaying the target interactive information differently, the audience user account can clearly understand whether it has received the attention and response of the host user account, which is conducive to improving the interactive correlation between the host user account and the audience user account.

[0257] The following are device embodiments of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0258] Please refer to Fig. 9 , which shows a block diagram of an interactive information management device provided by an embodiment of the present application. The device has the function of implementing the above-mentioned interactive information management method example, and the function can be implemented by hardware, or by hardware executing corresponding software. The device can be the computer device introduced above, or it can be set in a computer device. The device 900 may include: a voice data acquisition module 901, a target information determination module 902 and a labeling information generation module 903.

[0259] The voice data acquisition module 901 is used to obtain the voice data of the anchor user account during the live broadcast of the anchor user account.

[0260] The target information determination module 902 is used to determine target interaction information matching the voice data from the interaction information stream, wherein the interaction information stream includes at least two pieces of interaction information sent by the viewer user account during the live broadcast.

[0261] The annotation information generating module 903 is used to generate annotation information of the target interactive information, where the annotation information is used to trigger the target interactive information to be displayed in a differentiated manner from other interactive information in the interactive information flow except the target interactive information.

[0262] In some embodiments, Fig.10 As shown, the target information determination module 902 includes: an information set acquisition submodule 902a and a target information determination submodule 902b.

[0263] The information set acquisition submodule 902a is used to obtain an interactive information set within a first time period from the interactive information flow, wherein the interactive information set includes at least one interactive information, wherein the first time period is a time period with the generation time of the voice data as the end time or the first time period is a time period with the generation time of the previous interactive information as the start time, and the previous interactive information is the last target interactive information determined before the target interactive information.

[0264] The target information determination submodule 902b is used to determine the interactive information in the interactive information set that matches the voice data as the target interactive information.

[0265] In some embodiments, the target information determination submodule 902b is used to:

[0266] Extracting semantic features of the voice data, and respectively extracting semantic features of each of the at least one interactive information;

[0267] Calculating the similarity between the semantic feature of each of the at least one interactive information and the semantic feature of the voice data respectively, to obtain the semantic similarity of each of the at least one interactive information, wherein the semantic similarity is used to indicate the degree of similarity between the semantic feature of the voice data and the semantic feature of the interactive information;

[0268] Based on the semantic similarity, the target interaction information matching the voice data is determined from the interaction information set.

[0269] In some embodiments, the target information determination submodule 902b is further used to:

[0270] Acquire a maximum semantic similarity among the semantic similarities of the at least one interactive information; when the maximum semantic similarity is greater than or equal to a first threshold, determine the interactive information with the maximum semantic similarity in the interactive information set as the target interactive information;

[0271] Alternatively, the interactive information in the interactive information set whose semantic similarity is greater than or equal to a second threshold is determined as the target interactive information.

[0272] In some embodiments, Fig.10 As shown, the target information determination module 902 also includes: an audio text acquisition submodule 902c, a keyword acquisition submodule 902d and a preliminary screening information acquisition submodule 902e.

[0273] The audio text acquisition submodule 902c is used to convert the voice data into audio text, and the audio text is used to describe the voice content corresponding to the voice data in a text style.

[0274] The keyword acquisition submodule 902d is used to extract at least one keyword from the audio text.

[0275] The preliminary screening information acquisition submodule 902e is used to determine the interactive information matching the at least one keyword in the interactive information set as preliminary screening interactive information, and obtain a preliminary screening interactive information set.

[0276] The target information determination submodule 902b is further used to determine the target interaction information matching the voice data from the primary screening interaction information set based on the semantic similarity.

[0277] In some embodiments, Fig.10 As shown, the target information determination module 902 further includes: a video data acquisition submodule 902f and a candidate information acquisition submodule 902g.

[0278] The video data acquisition submodule 902f is used to obtain the video data of the live broadcast user account, and the video data is used to record the behavior of the anchor user account.

[0279] The candidate information acquisition submodule 902g is used to determine the interactive information in the interactive information set that matches the video data as candidate interactive information, so as to obtain a candidate interactive information set.

[0280] The target information determination submodule 902b is further configured to determine the candidate interaction information in the candidate interaction information set that matches the voice data as the target interaction information.

[0281] In some embodiments, the candidate information acquisition submodule 902g is used to:

[0282] Identify an action sequence of the anchor user account from the video data; and determine the interaction information in the interaction information set that matches the action sequence as the candidate interaction information;

[0283] Alternatively, a viewpoint sequence of the anchor user account on the screen is identified from the video data, wherein the viewpoint in the viewpoint sequence is the intersection between the line of sight of the anchor user account and the screen; and the interactive information in the interactive information set that matches the viewpoint sequence is determined as the candidate interactive information.

[0284] In some embodiments, the annotation information generating module 903 is used to:

[0285] When the number of the target interaction information is at least two, determining the first category ranking of each of the at least two target interaction information according to the sending time of each of the at least two target interaction information;

[0286] Determining a second category ranking of at least two target interaction information according to respective semantic similarities of at least two target interaction information;

[0287] Determine a third category ranking of at least two target interaction information according to their respective interaction rates, wherein the interaction rate is used to indicate the interaction frequency between the anchor user account and the viewer user account that sent the target interaction information;

[0288] For each of the target interaction information, determining a final ranking of the target interaction information based on the first category ranking, the second category ranking, and the third category ranking of the target interaction information;

[0289] For the first target interaction information with the smallest final ranking among the at least two target interaction information, generating first annotation information;

[0290] For other target interaction information except the first target interaction information among at least two target interaction information, second annotation information is generated, and a display mode indicated by the second annotation information is different from the display mode indicated by the first annotation information.

[0291] In some embodiments, the annotation information generating module 903 is further used to:

[0292] Determining, according to the type of the target interactive information, a display mode to which the target interactive information is adjusted, each type corresponding to a different display mode; and generating the annotation information based on the display mode;

[0293] Alternatively, the emotional information of the target interactive information is identified; based on the emotional information, a display mode to which the target interactive information is adjusted is determined; and based on the display mode, the annotation information is generated.

[0294] In summary, the technical solution provided by the embodiment of the present application determines the target interactive information (i.e., the target interactive information matching the voice data) that the host user account is responding to during the live broadcast of the host user account based on the voice data of the host user account. Since there is a high correlation between the voice data and the target interactive information, such as the voice data generated when the host user account responds to the target interactive information, this is conducive to improving the matching accuracy of the target interactive information. And by displaying the target interactive information differently, the audience user account can clearly understand whether it has received the attention and response of the host user account, which is conducive to improving the interactive correlation between the host user account and the audience user account.

[0295] Please refer to Fig.11, which shows a block diagram of a display device for interactive information provided by an embodiment of the present application. The device has the function of implementing the above-mentioned interactive information display method example, and the function can be implemented by hardware, or by hardware executing corresponding software. The device can be the computer device introduced above, or it can be set in a computer device. The device 1100 can include: a live broadcast interface display module 1101 and a target information display module 1102.

[0296] The live broadcast interface display module 1101 is used to display a live broadcast interface during the live broadcast of the anchor user account, wherein the live broadcast interface displays the live broadcast content of the anchor user account and an interactive information flow, wherein the interactive information flow includes at least two interactive information sent by the audience user account during the live broadcast;

[0297] The target information display module 1102 is used to distinguish the target interaction information matching the voice data in the interaction information flow from other interaction information in the interaction information flow except the target interaction information when the anchor user account generates voice data.

[0298] In some embodiments, the target information display module 1102 is used to:

[0299] In the case where the anchor user account generates first voice data, second target interaction information matching the first voice data in the interaction information flow is displayed separately from other interaction information in the interaction information flow except the second target interaction information;

[0300] When the anchor user account generates second voice data, the second target interaction information is not displayed in a differentiated manner, and the third target interaction information matching the second voice data in the interaction information flow is displayed in a differentiated manner from other interaction information in the interaction information flow except the third target interaction information.

[0301] In summary, the technical solution provided by the embodiment of the present application determines the target interactive information (i.e., the target interactive information matching the voice data) that the host user account is responding to during the live broadcast of the host user account based on the voice data of the host user account. Since there is a high correlation between the voice data and the target interactive information, such as the voice data generated when the host user account responds to the target interactive information, this is conducive to improving the matching accuracy of the target interactive information. And by displaying the target interactive information differently, the audience user account can clearly understand whether it has received the attention and response of the host user account, which is conducive to improving the interactive correlation between the host user account and the audience user account.

[0302] It should be noted that the device provided in the above embodiment only uses the division of the above functional modules as an example to implement its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and their specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0303] Please refer to Fig.12 , which shows a schematic diagram of the structure of a computer device provided by an embodiment of the present application. The computer device can be any electronic device with data calculation, processing and storage functions, and the computer device can be implemented as Figure 1 The first terminal device 10 / the second terminal device 20 / the server 30 in the computer system shown in the figure may specifically include the following contents.

[0304] The computer device 1200 includes a central processing unit (such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit) and an FPGA (Field Programmable Gate Array)) 1201, a system memory 1204 including a RAM (Random-Access Memory) 1202 and a ROM (Read-Only Memory) 1203, and a system bus 1205 connecting the system memory 1204 and the central processing unit 1201. The computer device 1200 also includes a basic input / output system (Input / Output System, I / O system) 1206 for helping various devices in the server to transmit information, and a large-capacity storage device 1207 for storing an operating system 1213, application programs 1214 and other program modules 1215.

[0305] The basic input / output system 1206 includes a display 1208 for displaying information and an input device 1209 such as a mouse and a keyboard for user inputting information. The display 1208 and the input device 1209 are connected to the central processing unit 1201 through an input / output controller 1210 connected to the system bus 1205. The basic input / output system 1206 may also include an input / output controller 1210 for receiving and processing inputs from a plurality of other devices such as a keyboard, a mouse, or an electronic stylus. Similarly, the input / output controller 1210 also provides output to a display screen, a printer, or other types of output devices.

[0306] The mass storage device 1207 is connected to the central processing unit 1201 via a mass storage controller (not shown) connected to the system bus 1205. The mass storage device 1207 and its associated computer readable medium provide non-volatile storage for the computer device 1200. That is, the mass storage device 1207 may include a computer readable medium (not shown) such as a hard disk or a CD-ROM (Compact Disc Read-Only Memory) drive.

[0307] Without loss of generality, the computer-readable medium may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory or other solid-state storage technology, CD-ROM, DVD (Digital Video Disc) or other optical storage, cassettes, tapes, disk storage or other magnetic storage devices. Of course, those skilled in the art will know that the computer storage medium is not limited to the above. The above-mentioned system memory 1204 and mass storage device 1207 can be collectively referred to as memory.

[0308] According to the embodiment of the present application, the computer device 1200 can also be connected to a remote computer on the network through a network such as the Internet. That is, the computer device 1200 can be connected to the network 1212 through the network interface unit 1211 connected to the system bus 1205, or the network interface unit 1211 can be used to connect to other types of networks or remote computer systems (not shown).

[0309] The memory also includes a computer program, which is stored in the memory and configured to be executed by one or more processors to implement the above-mentioned interactive information management method or interactive information display method.

[0310] In some embodiments, a computer-readable storage medium is further provided, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the computer program is used to implement the above-mentioned interactive information management method or interactive information display method.

[0311] Optionally, the computer readable storage medium may include: ROM (Read-Only Memory), RAM (Random-Access Memory), SSD (Solid State Drives) or optical disks, etc. Among them, the random access memory may include ReRAM (Resistance Random Access Memory) and DRAM (Dynamic Random Access Memory).

[0312] In some embodiments, a computer program product is further provided, the computer program product comprising a computer program, the computer program being stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the above-mentioned interactive information management method or interactive information display method.

[0313] It should be understood that the "multiple" mentioned in this article refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. In addition, the step numbers described in this article only illustrate a possible execution sequence between the steps. In some other embodiments, the above steps may not be executed in the order of the numbers, such as two steps with different numbers are executed at the same time, or two steps with different numbers are executed in the opposite order to the diagram. The embodiments of the present application are not limited to this.

[0314] The above description is only an exemplary embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for managing interactive information, characterized in that: The method comprises: During the live broadcast of the anchor user account, obtaining voice data of the anchor user account; Determining target interactive information matching the voice data from an interactive information stream, wherein the interactive information stream includes at least two interactive information sent by a viewer user account during the live broadcast; Generate annotation information of the target interaction information, where the annotation information is used to trigger the target interaction information to be displayed in a differentiated manner from other interaction information in the interaction information flow except the target interaction information.

2. The method according to claim 1, characterized in that The determining, from the interactive information stream, target interactive information matching the voice data comprises: Acquire an interaction information set within a first time period from the interaction information flow, the interaction information set including at least one interaction information, wherein the first time period is a time period with the generation time of the voice data as the end time or the first time period is a time period with the generation time of previous interaction information as the start time, and the previous interaction information is the last target interaction information determined before the target interaction information; The interactive information in the interactive information set that matches the voice data is determined as the target interactive information.

3. The method according to claim 2, characterized in that The step of determining the interactive information in the interactive information set that matches the voice data as the target interactive information includes: Extracting semantic features of the voice data, and respectively extracting semantic features of each of the at least one interactive information; Calculating the similarity between the semantic feature of each of the at least one interactive information and the semantic feature of the voice data respectively, to obtain the semantic similarity of each of the at least one interactive information, wherein the semantic similarity is used to indicate the degree of similarity between the semantic feature of the voice data and the semantic feature of the interactive information; Based on the semantic similarity, the target interaction information matching the voice data is determined from the interaction information set.

4. The method according to claim 3, characterized in that The determining, based on the semantic similarity, the target interaction information matching the voice data from the interaction information set includes: Acquire a maximum semantic similarity among the semantic similarities of the at least one interactive information; when the maximum semantic similarity is greater than or equal to a first threshold, determine the interactive information with the maximum semantic similarity in the interactive information set as the target interactive information; or, The interactive information in the interactive information set whose semantic similarity is greater than or equal to a second threshold is determined as the target interactive information.

5. The method according to claim 3, characterized in that: Before determining the target interaction information matching the voice data from the interaction information set based on the semantic similarity, the method further includes: Converting the voice data into an audio text, wherein the audio text is used to describe the voice content corresponding to the voice data in a text style; Extracting at least one keyword from the audio text; Determine the interactive information in the interactive information set that matches the at least one keyword as preliminary screening interactive information, to obtain a preliminary screening interactive information set; The determining, based on the semantic similarity, the target interaction information matching the voice data from the interaction information set includes: Based on the semantic similarity, the target interaction information matching the voice data is determined from the initially screened interaction information set.

6. The method according to claim 2, characterized in that Before determining the interactive information in the interactive information set that matches the voice data as the target interactive information, the method further includes: Obtaining video data of the live broadcast user account, where the video data is used to record the behavior of the anchor user account; Determine the interactive information in the interactive information set that matches the video data as candidate interactive information to obtain a candidate interactive information set; The step of determining the interactive information in the interactive information set that matches the voice data as the target interactive information includes: The candidate interaction information in the candidate interaction information set that matches the voice data is determined as the target interaction information.

7. The method according to claim 6, characterized in that The step of determining the interactive information in the interactive information set that matches the video data as candidate interactive information to obtain the candidate interactive information set includes: Identify an action sequence of the anchor user account from the video data; and determine the interaction information in the interaction information set that matches the action sequence as the candidate interaction information; or, A viewpoint sequence of the anchor user account on the screen is identified from the video data, wherein the viewpoint in the viewpoint sequence is the intersection between the line of sight of the anchor user account and the screen; and the interactive information in the interactive information set that matches the viewpoint sequence is determined as the candidate interactive information.

8. The method according to any one of claims 1 to 7, characterized in that: The generating of the annotation information of the target interactive information includes: When the number of the target interaction information is at least two, determining the first category ranking of each of the at least two target interaction information according to the sending time of each of the at least two target interaction information; Determining a second category ranking of at least two target interaction information according to respective semantic similarities of at least two target interaction information; Determine a third category ranking of at least two target interaction information according to their respective interaction rates, wherein the interaction rate is used to indicate the interaction frequency between the anchor user account and the viewer user account that sent the target interaction information; For each of the target interaction information, determining a final ranking of the target interaction information based on the first category ranking, the second category ranking, and the third category ranking of the target interaction information; For the first target interaction information with the smallest final ranking among the at least two target interaction information, generating first annotation information; For other target interaction information except the first target interaction information among at least two target interaction information, second annotation information is generated, and a display mode indicated by the second annotation information is different from the display mode indicated by the first annotation information.

9. The method according to any one of claims 1 to 7, characterized in that: The generating of the annotation information of the target interactive information includes: Determining, according to the type of the target interactive information, a display mode to which the target interactive information is adjusted, each type corresponding to a different display mode; and generating the annotation information based on the display mode; or, Identify the emotional information of the target interactive information; determine the display mode to which the target interactive information is adjusted based on the emotional information; and generate the annotation information based on the display mode.

10. A method for displaying interactive information, characterized in that: The method comprises: During the live broadcast of the anchor user account, a live broadcast interface is displayed, wherein the live broadcast interface displays the live broadcast content of the anchor user account and an interactive information flow, wherein the interactive information flow includes at least two interactive information sent by the audience user account during the live broadcast; When the anchor user account generates voice data, the target interaction information matching the voice data in the interaction information flow is displayed separately from other interaction information in the interaction information flow except the target interaction information.

11. The method according to claim 10, characterized in that When the anchor user account generates voice data, the target interaction information matching the voice data in the interaction information flow is displayed separately from other interaction information in the interaction information flow except the target interaction information, including: In the case where the anchor user account generates first voice data, second target interaction information matching the first voice data in the interaction information flow is displayed separately from other interaction information in the interaction information flow except the second target interaction information; When the anchor user account generates second voice data, the second target interaction information is not displayed in a differentiated manner, and the third target interaction information matching the second voice data in the interaction information flow is displayed in a differentiated manner from other interaction information in the interaction information flow except the third target interaction information.

12. An interactive information management device, characterized in that: The device comprises: A voice data acquisition module, used to acquire voice data of the anchor user account during the live broadcast of the anchor user account; A target information determination module, used to determine target interaction information matching the voice data from an interaction information stream, wherein the interaction information stream includes at least two pieces of interaction information sent by a viewer user account during the live broadcast; The annotation information generating module is used to generate annotation information of the target interactive information, wherein the annotation information is used to trigger the target interactive information to be displayed separately from other interactive information in the interactive information flow except the target interactive information.

13. A display device for interactive information, characterized in that: The device comprises: A live broadcast interface display module, used to display a live broadcast interface during the live broadcast of the anchor user account, wherein the live broadcast interface displays the live broadcast content of the anchor user account and an interactive information flow, wherein the interactive information flow includes at least two interactive information sent by the audience user account during the live broadcast; The target information display module is used to distinguish the target interaction information matching the voice data in the interaction information flow from other interaction information in the interaction information flow except the target interaction information when the anchor user account generates voice data.

14. A computer device, characterized in that: The computer device comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the method according to any one of claims 1 to 11.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which is loaded and executed by a processor to implement the method according to any one of claims 1 to 11.

16. A computer program product, characterized in that The computer program product comprises a computer program, wherein the computer program is stored in a computer-readable storage medium, and a processor reads and executes the computer program from the computer-readable storage medium to implement the method according to any one of claims 1 to 11.

Images