Live broadcast method and device, storage medium and electronic device

Abstract

The present disclosure discloses a live broadcast method and device, a storage medium and an electronic device, and relates to the field of computer application technology. The live broadcast method includes: obtaining audience questions during the live broadcast of the anchor; matching the audience questions with at least one preset question to obtain the preset question corresponding to the audience question; determining the preset answer corresponding to the audience question based on the preset question corresponding to the audience question and the preset answer corresponding to the preset question; based on the preset answer corresponding to the audience question, cooperating with the anchor to display the preset answer corresponding to the audience question. The present disclosure obtains audience questions during the live broadcast of the anchor, and obtains the preset answer corresponding to the audience question by matching the audience questions with the preset questions, thereby achieving the purpose of the anchor promptly answering the questions raised by the audience during the live broadcast, increasing the interactive experience of the audience, and improving the live broadcast effect.

Description

Technical Field

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

[0002] With the development of network technology, the popularity of the live broadcast industry continues to rise. Compared with traditional media, online live broadcast has the advantages of fast response and strong sociality, and thus has a wide range of applications in different fields. As an emerging technology of online live broadcast technology, virtual anchors use the actions of real actors combined with motion capture programs and preset virtual images to generate and output live videos for different live broadcast themes. Compared with traditional real anchors, virtual anchors can set virtual anchor images according to different needs. For the audience, virtual anchors are more novel and interesting, with a wider audience and better live broadcast effects.

[0003] However, since virtual anchors need to be operated by real actors, the interaction between virtual anchors and audiences depends on real actors. Virtual anchors cannot answer questions raised by audiences during the live broadcast in real time. Due to the special nature of real people, it takes a certain amount of time to think about questions. Both real anchors and virtual anchors are unable to respond to audience questions in a timely manner, which reduces the audience's interactive experience during the live broadcast and thus leads to a decline in the live broadcast effect. Summary of the invention

[0004] In view of this, the present disclosure provides a live broadcast method and device, a storage medium and an electronic device to improve the interactive experience of the audience during the live broadcast process.

[0005] In a first aspect, an embodiment of the present disclosure provides a live broadcast method, including: obtaining audience questions during a live broadcast by a host; matching the audience questions with at least one preset question to obtain the preset questions corresponding to the audience questions; determining the preset answers corresponding to the audience questions based on the preset questions corresponding to the audience questions and the preset answers corresponding to the preset questions; and cooperating with the host to display the preset answers corresponding to the audience questions based on the preset answers corresponding to the audience questions.

[0006] In combination with the first aspect, in certain implementations of the first aspect, there are multiple audience questions, each audience question corresponds to a preset answer, and based on the preset answers corresponding to the audience questions, cooperating with the host to display the preset answers corresponding to the audience questions, including: determining audience behavior data corresponding to each of the multiple audience questions, wherein the audience behavior data is used to characterize the importance of the audience questions; determining a display order of the preset answers corresponding to each of the multiple audience questions based on the audience behavior data corresponding to each of the multiple audience questions; cooperating with the host to display the preset answers corresponding to each of the multiple audience questions in sequence based on the preset answers corresponding to each of the multiple audience questions and the display order of the preset answers corresponding to each of the multiple audience questions.

[0007] In combination with the first aspect, in certain implementations of the first aspect, the audience behavior data includes the audience behavior data of each of the multiple audience members, and based on the audience behavior data corresponding to each of the multiple audience questions, determining the display order of the preset answers corresponding to each of the multiple audience questions, including: for each of the multiple audience questions, determining the weight of the audience behavior data of each of the multiple audience members corresponding to the audience question and the number of times each of the multiple audience members has posted an audience question based on the audience behavior data corresponding to the audience question; determining the total weight corresponding to the audience question based on the weight of the audience behavior data of each of the multiple audience members corresponding to the audience question and the number of times each of the multiple audience members has posted an audience question; and determining the display order of the preset answers corresponding to each of the multiple audience questions based on the total weight corresponding to each of the multiple audience questions.

[0008] In combination with the first aspect, in certain implementations of the first aspect, the audience behavior data includes multiple types of behavior data, and based on the audience behavior data corresponding to the audience question, the weights of the audience behavior data of multiple audiences corresponding to the audience question are determined, including: for each of the multiple audiences, determining at least one type of behavior data included in the audience behavior data of the audience; based on the at least one type of behavior data, determining the number of occurrences of the behavior corresponding to each of the at least one type of behavior data; determining the behavior weight corresponding to each of the at least one type of behavior data; determining the weight of the audience behavior data of the audience based on the number of occurrences of the behavior corresponding to each of the at least one type of behavior data and the behavior weight corresponding to each of the at least one type of behavior data.

[0009] In combination with the first aspect, in certain implementations of the first aspect, determining the behavior weight corresponding to each of at least one type of behavior data includes: determining the behavior occurrence time node corresponding to each of at least one type of behavior data; determining the behavior attenuation coefficient corresponding to each of at least one type of behavior data based on the behavior attenuation function, the behavior occurrence time node corresponding to each of at least one type of behavior data, and the current time node, the behavior attenuation coefficient can characterize the degree to which the behavior weight corresponding to each of at least one type of behavior data decays over time; determining the behavior weight corresponding to each of at least one type of behavior data based on the preset weight corresponding to each of at least one type of behavior data and the behavior attenuation coefficient.

[0010] In combination with the first aspect, in certain implementation methods of the first aspect, based on the preset answers corresponding to each of the multiple audience questions and the display order of the preset answers corresponding to each of the multiple audience questions, the host is cooperated to display the preset answers corresponding to each of the multiple audience questions in sequence, including: based on the preset answers corresponding to each of the multiple audience questions and the corresponding action data and voice data of the host, generating answer videos corresponding to each of the multiple audience questions; based on the answer videos corresponding to each of the multiple audience questions, displaying the preset answers corresponding to each of the multiple audience questions in sequence.

[0011] In combination with the first aspect, in certain implementations of the first aspect, before matching the audience question with at least one preset question to obtain the preset question corresponding to the audience question, the live broadcast method also includes: determining a preset question and answer question bank based on the live broadcast content, wherein the preset question and answer question bank includes at least one preset question and a preset answer corresponding to each of the at least one preset question.

[0012] In combination with the first aspect, in certain implementations of the first aspect, during the live broadcast of the host, before obtaining audience questions, the live broadcast method also includes: constructing an image of the host; based on the image of the host, determining an action library and a voice library corresponding to the image of the host, the action library including action labels, and the voice library including timbre and intonation; and generating a live video based on the live broadcast content, the image of the host, the action library and the voice library.

[0013] In combination with the first aspect, in certain implementations of the first aspect, a live video is generated based on the live content, the host image, the action library and the voice library, including: based on the live content, inserting action label data and emotion label data into the live content; based on the live content, the host image, the action label data and the action library, determining the host's animation part; based on the live content, the emotion label data and the voice library, determining the host's voice part; generating a live video based on the host's animation part and the host's voice part.

[0014] In a second aspect, an embodiment of the present disclosure provides a live broadcast device, which includes: an acquisition module, used to acquire audience questions during the live broadcast of the host; a matching module, used to match the audience questions with at least one preset question to obtain the preset questions corresponding to the audience questions; a determination module, used to determine the preset answers corresponding to the audience questions based on the preset questions corresponding to the audience questions and the preset answers corresponding to the preset questions; and a display module, used to cooperate with the host to display the preset answers corresponding to the audience questions based on the preset answers corresponding to the audience questions.

[0015] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor, wherein the processor is used to execute the method mentioned in the first aspect.

[0016] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the method mentioned in the first aspect.

[0017] The live broadcast method provided by the present disclosure obtains audience questions during the live broadcast of the anchor, matches the preset questions corresponding to the audience questions, determines the preset answers corresponding to the audience questions based on the preset questions and the preset answers corresponding to the preset questions, and finally cooperates with the anchor to display the preset answers corresponding to the audience questions based on the preset answers, thereby achieving the purpose of the anchor interacting with the audience in a timely manner during the live broadcast process, thereby improving the audience's interactive experience during the live broadcast process. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other purposes, features and advantages of the present disclosure will become more apparent by describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure.

[0019] Figure 1 Shown is a schematic diagram of an application scenario provided by an embodiment of the present disclosure.

[0020] Figure 2 The figure is a flow chart of a live broadcast method provided by an embodiment of the present disclosure.

[0021] Figure 3 The figure is a flow chart of a method of cooperating with a host to present preset answers to audience questions based on preset answers to audience questions provided by an embodiment of the present disclosure.

[0022] Figure 4 The figure is a flowchart of determining the display order of preset answers corresponding to multiple audience questions based on audience behavior data corresponding to the multiple audience questions provided by an embodiment of the present disclosure.

[0023] Figure 5 The figure is a flow chart of determining the weights of the audience behavior data of each of a plurality of audience members corresponding to an audience question based on the audience behavior data corresponding to the audience question provided by an embodiment of the present disclosure.

[0024] Figure 6 The figure is a schematic diagram of a flow chart for determining a behavior weight corresponding to at least one type of behavior data provided by an embodiment of the present disclosure.

[0025] Figure 7The figure shows a flow chart of an embodiment of the present disclosure, which provides preset answers corresponding to multiple audience questions, a display order of the preset answers corresponding to multiple audience questions, and cooperates with the host to sequentially display the preset answers corresponding to multiple audience questions.

[0026] Figure 8 The figure is a flow chart of another live broadcast method provided by an embodiment of the present disclosure.

[0027] Fig. 9 The figure is a flow chart of generating a live video based on live content, anchor image, action library and voice library provided by an embodiment of the present disclosure.

[0028] Fig.10 The figure is a flow chart of another live broadcast method provided by an embodiment of the present disclosure.

[0029] Fig.11 Shown is a schematic structural diagram of a live broadcast device provided by an embodiment of the present disclosure.

[0030] Fig.12 Shown is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0032] With the development of Internet technology, the live broadcast industry has become increasingly popular. Compared with traditional paper media and television media, online live broadcast has the advantages of fast response, strong sociality, wide audience, and fast transmission speed, so it has been widely used in different fields, such as new product release technology, online education, e-commerce, radio and television new media, etc.

[0033] As an emerging technology in live broadcasting, virtual anchors generate and output live broadcast videos for different live broadcasting themes by combining the movements of real actors with motion capture programs and using preset virtual images. They have the advantages of strong controllability, high sustainability, novelty and fun. Compared with traditional real anchors, virtual anchors can set up virtual anchor images according to different needs, which is more novel and interesting for the audience. In addition, virtual anchors can preset virtual anchor images according to the audience of the live broadcast theme, expanding the scope of the audience and thus improving the live broadcast effect.

[0034] However, traditional virtual anchors need to be processed in combination with professional action equipment and corresponding programs. The live broadcast process requires professional personnel to debug, and it is easy for the action to not match the real actor, which reduces the viewing experience of the live broadcast. In addition, since the interaction between the virtual anchor and the audience depends on the operation of the real actor, the special nature of the real actor cannot continue the live broadcast for a long time. During the rest period of the real actor, the virtual anchor cannot interact with the audience and cannot answer the questions raised by the audience in real time. In addition, due to the special nature of real people, it takes a certain amount of time to think about the questions. Both real anchors and virtual anchors are unable to respond to the audience's questions in time, which reduces the audience's interactive experience during the live broadcast, resulting in a decline in the live broadcast effect and restricting the further development of the live broadcast industry.

[0035] Combine the following Figure 1 The application scenario of an embodiment of the present disclosure is briefly introduced.

[0036] Figure 1 FIG. 1 is a schematic diagram of an application scenario of an embodiment of the present disclosure. Figure 1 Specifically, the scene of the anchor performing live broadcast includes a server 110, an audience terminal 120 and a live broadcast terminal 130 respectively connected to the server 110 for communication, and the server 110 is used to execute the live broadcast method mentioned in the embodiment of the present disclosure.

[0037] Exemplarily, in actual applications, the server 110 responds to the live broadcast start instruction of the live broadcast terminal 130, obtains the audience question of the audience terminal 120, matches the audience question with at least one preset question, obtains the preset question corresponding to the audience question, and determines the preset answer corresponding to the audience question based on the preset question corresponding to the audience question and the preset answer corresponding to the preset question; based on the preset answer corresponding to the audience question, the preset answer is sent to the live broadcast terminal 130, and the anchor at the live broadcast terminal 130 displays the preset answer to the audience question and synchronizes the displayed content to the server 110, so that the server 110 synchronizes the displayed content to the audience terminal 120, and the audience can understand the answer to the question through the audience terminal 120.

[0038] For example, the anchor of the live broadcast terminal 130 can be an anchor of a virtual image, an anchor of a virtual real person image constructed based on a real person image, or a real person anchor. For example, the audience terminal 120 and the live broadcast terminal 130 mentioned above include but are not limited to computer terminals such as desktop computers and laptop computers and mobile terminals such as tablet computers and mobile phones. The server 110 can refer to an independent physical server, a server cluster composed of multiple servers, or a cloud server capable of cloud computing, etc.

[0039] Combine the following Figures 2 to 10A brief introduction to the live broadcast method disclosed in the present invention is given.

[0040] Figure 2 FIG. 1 is a flow chart of a live broadcast method provided by an embodiment of the present disclosure. Figure 2 As shown, the live broadcast method provided by the embodiment of the present disclosure includes the following steps.

[0041] Step S210, obtaining audience questions during the host's live broadcast.

[0042] Exemplarily, the anchor may be a virtual anchor or a real anchor. Exemplarily, the audience question may be directly obtained from the audience's comments and bullet screens, or the content of the comments and bullet screens may be identified through keywords to obtain relevant audience questions.

[0043] Step S220, matching the audience question with at least one preset question to obtain the preset question corresponding to the audience question.

[0044] For example, after obtaining the audience's question, the audience's question is matched with the preset question through a text matching algorithm or a matching model. The selected matching model may be a BERT (Bidirectional Encoder Representation from Transformers) model.

[0045] For example, when using the BERT model to match audience questions with preset questions, it is first necessary to use a large amount of text data to train the BERT model, and then directly input the audience question text used for training into the model to obtain the semantic vector or intermediate hidden layer vector of the preset question text, and calculate the cosine similarity between the vector and the preset question to obtain the similarity between the audience question and the preset question. Specifically, the similarity between the audience question and the preset question can be obtained by the following formula 1-1.

[0046]

[0047] In formula 1-1, similarity is the similarity between the audience question and the preset question, A and B are the embedding vector of the text context of the audience question and the embedding vector of the preset question, respectively.

[0048] When calculating the similarity between the audience's questions and the preset questions, we first need to set a threshold t s , when the calculated similarity is greater than the threshold t s In the question list, if the similarity between the preset question 1 P1 and the audience question P is greater than the similarity between the question 2 P2 and the audience question, then the preset question 1 is the most matching question, and its corresponding answer is the preset answer corresponding to the audience question; if the similarity between the audience question and all preset questions is less than the threshold t s, then there is no matching problem. Specifically, the best matching problem can be calculated using the following formula 1-2.

[0049]

[0050] In formula 1-2, it is assumed that the preset questions corresponding to the audience's questions are only P1 and P2, and S1 and S2 are the similarities between P1 and P2 and the audience's question P, respectively, and P' is the most matching question.

[0051] Step S230, based on the preset question corresponding to the audience question and the preset answer corresponding to the preset question, determine the preset answer corresponding to the audience question.

[0052] Exemplarily, there can be multiple audience questions, and multiple audience questions can respond to the same preset question, and the preset question corresponds to the live content. For example, in the live content, "The History of the Development of Artificial Intelligence and Future Outlook", the corresponding preset questions mainly include the development history of the field of artificial intelligence. The preset question can be "What is the definition of artificial intelligence", and the corresponding audience questions can be "What is artificial intelligence", "What does artificial intelligence do", and "What can artificial intelligence be used for". Multiple audience questions are related, and the preset question is the same, and the corresponding answer is also the same.

[0053] For example, if N live broadcast topics are selected, the preset question list corresponding to each topic has a number of 1 to M. A maximum N×M question matrix can be constructed, and the number of all preset questions for the topic can be determined according to the following formula 1-3.

[0054]

[0055] In formula 1-3, ∏ represents the total number of all preset questions, and correspondingly, the number of answers corresponding to all preset questions is N.

[0056] Exemplarily, in actual application, the question analysis engine completes the above-mentioned part of matching the audience question with the preset question, specifically, by matching the question that is most similar to the audience question, thereby determining the answer corresponding to the preset question.

[0057] Step S240, based on the preset answers corresponding to the audience's questions, cooperate with the host to display the preset answers corresponding to the audience's questions.

[0058] Exemplarily, based on the preset answers corresponding to the audience's questions, the virtual anchor displays the preset answers corresponding to the audience's questions through corresponding actions and voice. The preset answers can be displayed through the virtual anchor's voice broadcast, or displayed at a fixed position on the live broadcast screen. The virtual anchor guides the audience to view the relevant answer content through actions, or the real anchor broadcasts the answers corresponding to the questions based on the preset answers.

[0059] The live broadcast method provided by the disclosed embodiment obtains audience questions during the live broadcast process of the anchor, matches the audience questions with preset questions, obtains answers corresponding to the audience questions, and cooperates with the anchor to present them, thereby achieving the purpose of interaction between the anchor and the audience and solving the problem that the anchor cannot promptly answer questions raised by the audience during the live broadcast process.

[0060] Figure 3 The figure shows a flow chart of cooperating with the anchor to display the preset answers corresponding to the audience questions based on the preset answers corresponding to the audience questions provided by an embodiment of the present disclosure. Figure 3 As shown, the embodiments of the present disclosure provide preset answers based on audience questions, and cooperate with the host to display the preset answers corresponding to audience questions, including the following steps.

[0061] Step S310: determining audience behavior data corresponding to each of a plurality of audience questions.

[0062] The audience behavior data is used to characterize the importance of audience questions. There are multiple audience questions, and each audience question corresponds to a preset answer.

[0063] Exemplarily, audience behavior data includes audience operation data during the live broadcast, such as the audience's speaking frequency, like frequency, reward frequency, and other behaviors. Different behaviors have different importance to the audience. The higher the importance of the audience's behavior, the more important the question raised by the audience.

[0064] Step S320: determining the display order of the preset answers corresponding to the multiple audience questions based on the audience behavior data corresponding to the multiple audience questions.

[0065] Exemplarily, based on the audience behavior data corresponding to each of the multiple audience questions, the importance of the multiple audiences corresponding to the multiple audience questions is determined, and based on the importance of the audiences, the order of preset answers to each of the multiple audience questions is determined. The higher the importance of the audience, the higher the order of the audience questions corresponding to the audience.

[0066] Step S330, based on the preset answers corresponding to the multiple audience questions and the display order of the preset answers corresponding to the multiple audience questions, cooperate with the host to display the preset answers corresponding to the multiple audience questions in sequence.

[0067] Exemplarily, according to the order of the audience questions obtained as described above, the order of the preset answers corresponding to the multiple audience questions is determined, and according to the order of the preset answers, the host cooperates with the host to display the preset answers corresponding to the multiple audience questions in turn.

[0068] The disclosed embodiment determines the display order of preset answers to the audience's questions through the audience's behavioral data, so that during the live broadcast, the questions of the audience who actively participate in the interaction can be answered in order, which can increase the audience's interactive experience, increase the audience's interest in watching the live broadcast, and improve the effect of the live broadcast.

[0069] Figure 4 FIG. 1 is a flow chart of determining the display order of preset answers corresponding to multiple audience questions based on audience behavior data corresponding to multiple audience questions provided by an embodiment of the present disclosure. Figure 4 As shown, the embodiment of the present disclosure provides a method for determining the display order of preset answers corresponding to multiple audience questions based on audience behavior data corresponding to multiple audience questions, which includes the following steps.

[0070] Step S410 , for each of the multiple audience questions, based on the audience behavior data corresponding to the audience question, determine the weights of the audience behavior data of the multiple audiences corresponding to the audience question and the number of times the multiple audiences have posted the audience question.

[0071] For example, the audience behavior data may include audience likes data, audience speaking frequency data, audience likes data, and audience stay watching time data. The weight of the audience behavior data can be determined by operators and data personnel assigning different weights to different behaviors. The number of times multiple audiences post audience questions includes the number of times each audience post the same audience question and the number of times a single audience post the same audience question.

[0072] Step S420 , determining a total weight corresponding to the audience question based on the weights of the audience behavior data of each of the plurality of audience members corresponding to the audience question and the number of times each of the plurality of audience members has posted the audience question.

[0073] Exemplarily, the total weight corresponding to the audience's questions can be determined by the following formula 1-4.

[0074]

[0075] In formula 1-4, R represents the total weight corresponding to a viewer question, n represents the total number of viewers matching the question, Q i represents the weight of the audience behavior data of the i-th audience, C i Indicates the number of times this audience member has posted a question.

[0076] Step S430: determining the display order of the preset answers corresponding to the multiple audience questions based on the total weights corresponding to the multiple audience questions.

[0077] Exemplarily, based on the total weights of each of the multiple audience questions, the preset answers corresponding to the audience questions with higher total weights are displayed in an earlier order.

[0078] The disclosed embodiment determines the order of displaying preset answers to multiple questions by the total weights corresponding to the audience's questions, which can reflect the degree of attention paid to different questions during the live broadcast, and can give priority to displaying questions with high attention, further improving the audience's interactive experience, thereby increasing the fun of the live broadcast and improving the effect of the live broadcast.

[0079] Figure 5 FIG. 1 is a flow chart of determining the weights of the audience behavior data of multiple audience members corresponding to an audience question based on the audience behavior data corresponding to the audience question provided by an embodiment of the present disclosure. Figure 5 As shown, the embodiment of the present disclosure provides the following steps for determining the weights of the audience behavior data of each of the multiple audience members corresponding to the audience question based on the audience behavior data corresponding to the audience question.

[0080] Step S510: for each of the multiple viewers, determining at least one type of behavior data included in the viewer behavior data of the viewer.

[0081] Exemplarily, the types of behavior data may be like behavior, comment behavior, and reward behavior.

[0082] Step S520: Based on at least one type of behavior data, determine the number of times a behavior corresponding to each of the at least one type of behavior data occurs.

[0083] Exemplarily, for the above three types of behavior data contained in each viewer, the number of like behaviors, the number of comment behaviors, and the number of reward behaviors of the viewer are determined.

[0084] Step S530: determining a behavior weight corresponding to each of at least one type of behavior data.

[0085] Exemplarily, the weights of the above-mentioned likes, comments, and rewards are determined based on the weights defined by operators or data personnel; or, the importance of each behavior to the audience is determined based on the live broadcast history data, thereby determining the weights of the above-mentioned likes, comments, and rewards.

[0086] Step S540 , determining the weight of the audience behavior data of the audience based on the number of behavior occurrences corresponding to each of the at least one type of behavior data and the behavior weight corresponding to each of the at least one type of behavior data.

[0087] Exemplarily, the weight of the audience behavior data of the audience may be determined by the following formula 1-5.

[0088]

[0089] In formula 1-5, Q represents the weight of the audience's audience behavior data, n represents the total number of behavior types corresponding to the behavior data, and T(t) i represents the behavior attenuation coefficient of the i-th behavior at time t, β i represents the preset weight corresponding to the i-th type of behavior data, S i Indicates the number of occurrences of the ith behavior corresponding to the behavior data. n can be selected as n=3 here, which means there are three behaviors: like, comment, and reward.

[0090] The disclosed embodiments determine the weight of the audience's behavior data by the number of behavior occurrences corresponding to at least one type of behavior data and the behavior weight corresponding to at least one type of behavior data. The weight of the audience's behavior data can be determined according to the needs during the actual live broadcast process, and the audience with high interaction enthusiasm during the live broadcast can be further determined, thereby improving the interactive effect of the live broadcast.

[0091] Figure 6 FIG. 1 is a flow chart of determining the behavior weight corresponding to each of at least one type of behavior data provided by an embodiment of the present disclosure. Figure 6 As shown in one embodiment of the present disclosure, determining the behavior weight corresponding to each of at least one type of behavior data includes the following steps.

[0092] Step S610: determining a behavior occurrence time node corresponding to at least one type of behavior data.

[0093] Exemplarily, the start time of the live broadcast is used as the starting point of the time node to determine the time node at which the behavior corresponding to each type of behavior data occurs; or the time point from the live broadcast to the fixed content is used as the starting point of the time node.

[0094] Step S620, determining a behavior decay coefficient corresponding to each of the at least one type of behavior data based on the behavior decay function, the behavior occurrence time node corresponding to each of the at least one type of behavior data, and the current time node.

[0095] The behavior decay coefficient can characterize the degree to which the behavior weight corresponding to each of at least one type of behavior data decays over time.

[0096] For example, when the live broadcast time is long, the audience's behavior will also be different depending on the live broadcast content, and the impact of the live broadcast time on the audience's behavior needs to be considered. During the live broadcast process, there may be different topics, and the impact of different live broadcast topics on the audience's behavior also needs to be considered. During the time period of different topics, the audience's initial behavior is not greatly affected by the live broadcast content. Through the behavior attenuation function, the impact of the audience's initial behavior is weakened, and the weight of the audience's behavior in the live broadcast of the topic can be measured to the greatest extent.

[0097] Step S630: determining the behavior weight corresponding to each of the at least one type of behavior data based on the preset weight and the behavior attenuation coefficient corresponding to each of the at least one type of behavior data.

[0098] For example, the behavior attenuation coefficient can be determined by the following formula 1-6, that is, formula 1-6 is a behavior attenuation function, the above

[0099] β in formula 1-5 i It may be a preset weight corresponding to each of at least one type of behavior data.

[0100]

[0101] In formula 1-6, T(t) represents the behavior attenuation coefficient, t0 represents the initial moment, H represents the weight of a behavior that changes over time, H is set to 0 to indicate that as time goes by, the weight of a behavior eventually changes to 0, T0 represents the initial weight, and α is an arbitrary constant, for example, 0.25 or 0.5, etc. Different values ​​can represent different attenuation effects.

[0102] The disclosed embodiment determines the behavior weight corresponding to at least one type of behavior data through the preset weight and behavior attenuation coefficient corresponding to at least one type of behavior data, which can reflect the weight of different types of behavior under the influence of live broadcast time. The behavior weight can more objectively express the audience's behavior, weaken the impact of the audience's initial behavior, more objectively evaluate the audience's behavior, and improve the efficiency of live broadcast interaction.

[0103] Figure 7 The figure shows a flow chart of displaying the preset answers corresponding to the multiple audience questions in sequence in cooperation with the anchor according to the preset answers corresponding to the multiple audience questions provided by an embodiment of the present disclosure. Figure 7 As shown, the embodiments of the present disclosure provide preset answers corresponding to multiple audience questions, a display order of the preset answers corresponding to multiple audience questions, and cooperate with the host to sequentially display the preset answers corresponding to multiple audience questions, including the following steps.

[0104] Step S710, based on the preset answers of the multiple audience members, the corresponding action data and voice data of the host, generate answer videos corresponding to the multiple audience questions.

[0105] Exemplarily, the voice data includes data such as pitch and timbre. The action data and voice data corresponding to the anchor may correspond to the live content, for example, the action data, pitch and timbre corresponding to the virtual anchor of the live content may be selected; or the action data, pitch and timbre corresponding to the pre-set virtual anchor corresponding to the question may be selected according to actual needs to generate answer videos corresponding to multiple audience questions. The answer video of the real anchor may be generated according to the pitch, timbre and corresponding action data preset in the fixed live content part of the real anchor, and according to the image of the real anchor, to generate answer videos corresponding to multiple audience questions.

[0106] Step S720, based on the answer videos corresponding to the multiple audience questions, the preset answers corresponding to the multiple audience questions are displayed in sequence.

[0107] Exemplarily, the answer video can be generated sequentially according to the questions, and the preset answers corresponding to multiple audience questions can be displayed sequentially; or it can be generated once according to the audience questions, and the preset answers corresponding to multiple audience questions can be displayed sequentially during the live answering session.

[0108] In some embodiments, in the answering session set during the live broadcast process, a question number limit or a time limit can be set in the answering session according to the needs. If a time limit is set, the number of questions answered within a fixed time is calculated by a corresponding algorithm. During the calculation process, by setting a threshold t K , determine whether the question is answered, the specific calculation formula is as follows 1-7.

[0109]

[0110] In formula 1-7, K indicates whether to answer the next question in the question list. When K=1, the answer is given, and when K=0, the answer is not given. t1 indicates the time required to answer the next question in the question list, t2 indicates the remaining time of the question-answering session, and t K is a preset threshold. When the difference between the time required to answer the next question in the question list and the remaining time of the question-answering session is less than the threshold, the next question is answered; when the difference between the time required to answer the next question in the question list and the remaining time of the question-answering session is greater than the threshold, the next question in the question list is skipped.

[0111] The disclosed embodiment can achieve the purpose of the host answering the audience's questions in a timely manner and further enhance the audience's interactive experience by sequentially displaying the preset answers corresponding to the multiple audience questions based on the answer videos corresponding to the multiple audience questions.

[0112] In some embodiments, before matching the audience question with at least one preset question to obtain the preset question corresponding to the audience question, the live broadcast method further includes: determining a preset question and answer question bank based on the live broadcast content, wherein the preset question and answer question bank includes at least one preset question and a preset answer corresponding to each of the at least one preset question. Exemplarily, corresponding preset questions and answers corresponding to each of the preset questions are generated for the live broadcast theme, and a preset answer bank is determined. The disclosed embodiment determines a preset answer question bank through the live broadcast content, and the preset questions and answers corresponding to each of the preset questions are in line with the live broadcast theme, which can make the host more efficient in answering questions.

[0113] Figure 8 FIG. 1 is a flow chart of another live broadcast method provided by an embodiment of the present disclosure. Figure 2 Based on the embodiment shown, Figure 8 The embodiment shown is described below in detail. Figure 8 The embodiment shown and Figure 2 The differences and similarities of the illustrated embodiments are not described in detail.

[0114] like Figure 8 The live broadcast method provided by an embodiment of the present disclosure is shown. During the live broadcast process, before the host obtains audience questions, the live broadcast method also includes the following steps.

[0115] Step S810, constructing the anchor image.

[0116] Exemplarily, the anchor image can be a constructed 2D or 3D virtual anchor image or a real person image. The construction of the virtual anchor image includes steps such as character modeling, material mapping, and bone binding and skinning. The modeling of the anchor image can use 3D modeling software, such as Maya software, Blender software, etc. to make a basic model, and the constructed basic model contains the three-dimensional data of the character. The material mapping step needs to construct the surface color, shadow, brightness and other characteristics of the character model. The bone binding and skinning step builds a skeletal system based on the 3D model to support the generation of limb movements of the 3D model.

[0117] Step S820, based on the anchor image, determine the action library and voice library corresponding to the anchor image.

[0118] The action library includes action labels, and the voice library includes timbre and intonation.

[0119] Exemplarily, the action library and voice library corresponding to the anchor image can be customized according to needs, or customized according to the voice of a real anchor. The voice library can be a selection of existing timbre or tone, or a customized exclusive timbre and tone. Specifically, the internal speech synthesis engine analyzes and deconstructs the existing voice fragments through a deep learning model, thereby obtaining the timbre, tone and other characteristics of the corresponding voice fragments, and constructing an exclusive voice library. Exemplarily, the voice library can be generated according to a dedicated speech synthesis engine. By inputting multiple recording data, the speech synthesis engine generates pronunciation data that matches the timbre of the recording data. The pronunciation data can be configured with multiple parameters such as speech speed, pauses, breathing, pauses, etc. according to needs. The action generation engine generates an action library based on a virtual or real image combined with a list of available actions.

[0120] Step S830, generating a live video based on the live content, the host image, the action library and the voice library.

[0121] For example, the live broadcast content includes the broadcast text of the anchor's live broadcast process, which is a text that can be broadcast for a long time and has a small length limit. Based on the broadcast text, the anchor image combines the actions in the action library and the timbre and tone selected from the voice library to generate a live video.

[0122] The disclosed embodiment generates a live video through live content, host image, action library and voice library. The host image can be produced according to demand, and the host's corresponding actions, timbre and tone can also be customized according to the live content. The generated live video can meet the live broadcast needs of different themes.

[0123] Fig. 9 FIG. 1 is a flow chart of generating a live video based on live content, anchor image, action library and voice library provided by an embodiment of the present disclosure. Fig. 9 As shown, the embodiment of the present disclosure provides a method for generating a live video based on live content, anchor image, action library and voice library, which includes the following steps.

[0124] Step S910: inserting action tag data and emotion tag data into the live content based on the live content.

[0125] Exemplarily, at the location where the live content needs it, settings are made to insert action tag data and emotion tag data. Action tags can be identified by the virtual anchor broadcast engine to achieve the purpose of generating anchor actions at the corresponding location. Exemplarily, action tag data and emotion tag data are inserted into the live content, which can be "This product contains multiple functions, first: [gesture-label one] voice broadcast, second: [gesture-label two] 2D broadcast, third: [gesture-label three] [emo_st emotion-happy] real person broadcast", and the live content is parsed by the subsequent broadcast engine into a broadcast video corresponding to a real person or virtual image,

[0126] Step S920, determining the anchor's animation part based on the live broadcast content, anchor image, action tag data and action library.

[0127] Exemplarily, the animation part of the anchor is determined according to the video generation engine. The action tags in the position action library corresponding to the live content are parsed through the video generation engine. The corresponding actions of the real person or virtual image anchor are synchronously displayed at the action tag position to determine the animation part of the anchor.

[0128] Step S930, determining the host's voice part based on the live broadcast content, emotion tag data and voice library.

[0129] Exemplarily, the speech part of the anchor is determined by the speech synthesis engine. Specifically, the pronunciation data of the selected voice library and the audio corresponding to the live content are determined by the speech synthesis engine. The speech synthesis engine includes multiple modules: speech feature coding module, text coding module, and speech generation module. Among them, the speech feature coding module combines the fusion features such as the gender characteristics, age characteristics, and regional characteristics of the speaker to characterize the timbre of the virtual anchor's pronunciation. The speech generation module inputs the speech generation model by the fusion feature coding and text coding set to output the live voice of the virtual anchor. The speech generation model includes speech spectrum generation and speech vocoder. The speech spectrum can be generated by the corresponding speech synthesis technology (Text To Speech, TTS) model, such as Tacotron2, deepvoice3, by reading the audio data, obtaining the time domain signal, and using the short-time Fourier transform (STFT) algorithm to perform spectrum calculation. The vocoder is used to analyze the timbre characteristics of the audio signal and output the live content. The corresponding emotions of real people or virtual images are displayed in the emotion label position. The emotion label can also indicate the speech speed, pitch, stress, pause and other configurations of the virtual anchor of the live content when indicating speech synthesis. The initial parameter settings are performed according to the configuration requirements. The emotion label can be added through the speech synthesis engine. Specifically, the text encoding module in the speech synthesis engine can identify and analyze the live content and add the emotion label at the required position.

[0130] Step S940, generating a live video based on the host's animation part and the host's voice part.

[0131] The disclosed embodiment inserts action tag data and emotion tag data into live broadcast content, generates the host's animation part through the action library and action tags, and determines the host's voice part through the voice library and emotion tags, which can make the live broadcast video more realistic and increase the authenticity of subsequent interactions, thereby improving the audience's interactive experience.

[0132] Fig.10FIG. 2 is a flow chart of another live broadcast method provided by an embodiment of the present disclosure. Fig.10 As shown, another live broadcast method provided by an embodiment of the present disclosure includes the following steps.

[0133] Step S1010, constructing the anchor image.

[0134] Step S1020, determining the action library and voice library according to the host image.

[0135] Step S1030, prepare live broadcast content and a question and answer library related to the live broadcast content.

[0136] Step S1040, generating a live video using a broadcast engine according to the live content and the host's image.

[0137] Step S1050, when the live broadcast starts, start monitoring the live broadcast situation and obtain audience questions during the live broadcast process.

[0138] Step S1060: Analyze the audience's question and determine the answer corresponding to the audience's question.

[0139] Step S1070, based on the answers corresponding to the audience's questions, cooperate with the anchor to display the answers to the audience's questions.

[0140] The specific implementation of steps S1010 to S1070 can refer to the above embodiment and will not be repeated here.

[0141] Combine the following Fig.11 A brief introduction to the live broadcast device disclosed in the present invention is given.

[0142] Fig.11 FIG. 1 is a schematic diagram of the structure of a live broadcast device provided by an embodiment of the present disclosure. Fig.11 As shown, the live broadcast device 1100 provided by the embodiment of the present disclosure includes an acquisition module 1101, a matching module 1102, a determination module 1103 and a display module 1104. Specifically, the acquisition module 1101 is used to acquire audience questions during the live broadcast of the anchor; the matching module 1102 is used to match the audience questions with at least one preset question to obtain the preset questions corresponding to the audience questions; the determination module 1103 is used to determine the preset answers corresponding to the audience questions based on the preset questions corresponding to the audience questions and the preset answers corresponding to the preset questions; the display module 1104 is used to cooperate with the anchor to display the preset answers corresponding to the audience questions based on the preset answers corresponding to the audience questions.

[0143] In some embodiments, the display module 1104 is also used to determine audience behavior data corresponding to each of the multiple audience questions, wherein the audience behavior data is used to characterize the importance of the audience questions; based on the audience behavior data corresponding to each of the multiple audience questions, determine the display order of the preset answers corresponding to each of the multiple audience questions; based on the preset answers corresponding to each of the multiple audience questions and the display order of the preset answers corresponding to each of the multiple audience questions, cooperate with the host to display the preset answers corresponding to each of the multiple audience questions in sequence.

[0144] In some embodiments, the display module 1104 is also used to determine, for each audience question among the multiple audience questions, the weight of the audience behavior data of the multiple audiences corresponding to the audience question and the number of times the multiple audiences have each posted the audience question based on the audience behavior data corresponding to the audience question; determine the total weight of the audience question based on the weight of the audience behavior data of the multiple audiences corresponding to the audience question and the number of times the multiple audiences have each posted the audience question; and determine the display order of the preset answers corresponding to the multiple audience questions based on the total weight of the multiple audience questions.

[0145] In some embodiments, the display module 1104 is also used to determine, for each of the multiple viewers, at least one type of behavior data included in the audience behavior data of the audience; based on the at least one type of behavior data, determine the number of behavior occurrences corresponding to each of the at least one type of behavior data; determine the behavior weight corresponding to each of the at least one type of behavior data; based on the number of behavior occurrences corresponding to each of the at least one type of behavior data and the behavior weight corresponding to each of the at least one type of behavior data, determine the weight of the audience behavior data of the audience.

[0146] In some embodiments, the display module 1104 is also used to determine the behavior weight corresponding to each of at least one type of behavior data, including: determining the behavior occurrence time node corresponding to each of at least one type of behavior data; determining the behavior decay coefficient corresponding to each of at least one type of behavior data based on the behavior decay function, the behavior occurrence time node corresponding to each of at least one type of behavior data, and the current time node, the behavior decay coefficient can characterize the degree to which the behavior weight corresponding to each of at least one type of behavior data decays over time; determining the behavior weight corresponding to each of at least one type of behavior data based on the preset weight and behavior decay coefficient corresponding to each of at least one type of behavior data.

[0147] In some embodiments, the display module 1104 is also used to generate answer videos corresponding to multiple audience questions based on the preset answers of multiple audience members, the host's corresponding action data and voice data; based on the answer videos corresponding to multiple audience questions, the preset answers corresponding to multiple audience questions are displayed in turn.

[0148] In some embodiments, the acquisition module 1101 is also used to determine a preset question and answer question bank based on the live broadcast content, wherein the preset question and answer question bank includes at least one preset question and a preset answer corresponding to each of the at least one preset question.

[0149] In some embodiments, the acquisition module 1101 is also used to construct an anchor image; based on the anchor image, determine the action library and voice library corresponding to the anchor image, the action library includes action labels, and the voice library includes timbre and intonation; based on the live content, anchor image, action library and voice library, generate live video.

[0150] In some embodiments, the acquisition module 1101 is also used to insert action label data and emotion label data into the live broadcast content based on the live broadcast content; determine the animation part of the host based on the live broadcast content, the host's image, the action label data and the action library; determine the voice part of the host based on the live broadcast content, the emotion label data and the voice library; generate a live video based on the animation part of the host and the voice part of the host.

[0151] Fig.12 Shown is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Fig.12 Shown is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. Fig.12 The electronic device 1200 shown (the electronic device 1200 may be a computer device) includes a memory 1201, a processor 1202, a communication interface 1203 and a bus 1204. The memory 1201, the processor 1202 and the communication interface 1203 are connected to each other through the bus 1204.

[0152] The memory 1201 may be a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM). The memory 1201 may store a program. When the program stored in the memory 1201 is executed by the processor 1202, the processor 1202 and the communication interface 1203 are used to execute each step of the live broadcast method of the embodiment of the present disclosure.

[0153] The processor 1202 can adopt a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), a graphics processing unit (GPU) or one or more integrated circuits to execute relevant programs to implement the functions that need to be performed by each unit in the live broadcast device of the embodiment of the present disclosure.

[0154] The processor 1202 may also be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the live broadcast method disclosed in the present invention may be completed by an integrated logic circuit of hardware or software instructions in the processor 1202. The above-mentioned processor 1202 may also be a general-purpose processor, a digital signal processor (Digital Signal Processing, DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in a decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 1201, and the processor 1202 reads the information in the memory 1201, and combines its hardware to complete the functions required to be performed by the units included in the live broadcast device of the embodiment of the present disclosure, or executes the live broadcast method of the method embodiment of the present disclosure.

[0155] The communication interface 1203 uses a transceiver such as, but not limited to, a transceiver to implement communication between the electronic device 1200 and other devices or a communication network. For example, audience questions can be obtained through the communication interface 1203.

[0156] The bus 1204 may include a path for transmitting information between various components of the electronic device 1200 (eg, the memory 1201 , the processor 1202 , and the communication interface 1203 ).

[0157] It should be noted that although Fig.12The electronic device 1200 shown only shows a memory, a processor, and a communication interface, but in the specific implementation process, those skilled in the art should understand that the electronic device 1200 also includes other devices necessary for normal operation. At the same time, according to specific needs, those skilled in the art should understand that the electronic device 1200 may also include hardware devices for implementing other additional functions. In addition, those skilled in the art should understand that the electronic device 1200 may also include only the devices necessary to implement the embodiments of the present disclosure, and does not necessarily include Fig.12 All devices shown in .

[0158] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0159] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0160] In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0161] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0163] In addition, the embodiments of the present disclosure may also be a computer-readable storage medium, on which computer program instructions are stored, and the computer program instructions, when executed by the processor, enable the processor to perform the steps in the method according to various embodiments of the present disclosure described above in this specification. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in various embodiments of the present disclosure. The readable storage medium may include, for example, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of the aforementioned storage medium include: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, or any suitable combination of the above.

[0164] The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, which should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A live broadcast method, characterized in that: include: Get audience questions during the anchor's live broadcast; Matching the audience question with at least one preset question to obtain the preset question corresponding to the audience question; Determine a preset answer corresponding to the audience question based on the preset question corresponding to the audience question and the preset answer corresponding to the preset question; There are multiple audience questions, each of which corresponds to a preset answer. The method further includes: Determine audience behavior data corresponding to each of the plurality of audience questions, wherein the audience behavior data includes audience behavior data of each of the plurality of audience members, and the audience behavior data includes multiple types of behavior data; For each of the audience questions and for each of the audience members, determine at least one type of behavior data included in the audience behavior data of the audience; based on the at least one type of behavior data, determine the number of behavior occurrences corresponding to each of the at least one type of behavior data; determine the behavior occurrence time nodes corresponding to each of the at least one type of behavior data; based on the behavior decay function, the behavior occurrence time nodes corresponding to each of the at least one type of behavior data and the current time node, determine the behavior decay coefficient corresponding to each of the at least one type of behavior data; based on the preset weight corresponding to each of the at least one type of behavior data and the behavior decay coefficient, determine the behavior weight corresponding to each of the at least one type of behavior data; based on the number of behavior occurrences corresponding to each of the at least one type of behavior data and the behavior weight corresponding to each of the at least one type of behavior data, determine the weight of the audience behavior data of the audience; based on the audience behavior data corresponding to the audience question, determine the number of times each of the multiple audience members has posted the audience question; Determine a total weight corresponding to the audience question based on the weights of the audience behavior data of each of the plurality of audience members corresponding to the audience question and the number of times each of the plurality of audience members has posted the audience question; Determining, based on the total weights corresponding to the multiple audience questions, a display order of the preset answers corresponding to the multiple audience questions; Based on the preset answers corresponding to each of the multiple audience questions and the display order of the preset answers corresponding to each of the multiple audience questions, cooperate with the host to display the preset answers corresponding to each of the multiple audience questions in sequence.

2. The live broadcast method according to claim 1, characterized in that: The audience behavior data is used to characterize the importance of audience questions.

3. The live broadcast method according to claim 1, characterized in that: The method of displaying the preset answers corresponding to the multiple audience questions in sequence based on the preset answers corresponding to the multiple audience questions and the display order of the preset answers corresponding to the multiple audience questions, and cooperating with the host to display the preset answers corresponding to the multiple audience questions in sequence, includes: Generate answer videos corresponding to the questions of the multiple audience members based on the preset answers of the multiple audience members, the action data and voice data of the host; Based on the answer videos corresponding to the multiple audience questions, the preset answers corresponding to the multiple audience questions are displayed in sequence.

4. The live broadcast method according to any one of claims 1 to 3, characterized in that: Before matching the audience question with at least one preset question to obtain the preset question corresponding to the audience question, the method further includes: Based on the live broadcast content, a preset question and answer question bank is determined, wherein the preset question and answer question bank includes the at least one preset question and a preset answer corresponding to each of the at least one preset question.

5. The live broadcast method according to any one of claims 1 to 3, characterized in that: In the live broadcast process of the anchor, before obtaining the audience's questions, it also includes: Build the anchor image; Based on the anchor image, determining an action library and a voice library corresponding to the anchor image, wherein the action library includes action labels, and the voice library includes timbre and intonation; A live video is generated based on the live content, the host image, the action library and the voice library.

6. The live broadcast method according to claim 5, characterized in that: The generating of live video based on live content, the anchor image, the action library and the voice library includes: Based on the live broadcast content, inserting action label data and emotion label data into the live broadcast content; Determining an animation part of the anchor based on the live broadcast content, the anchor image, the action tag data and the action library; Determining the speech part of the anchor based on the live broadcast content, the emotion tag data and the speech library; The live video is generated based on the animation part of the host and the voice part of the host.

7. A live broadcast device, characterized in that: include: The acquisition module is used to obtain audience questions during the live broadcast of the anchor; A matching module, used for matching the audience question with at least one preset question to obtain the preset question corresponding to the audience question; A determination module, configured to determine a preset answer corresponding to the audience question based on the preset question corresponding to the audience question and the preset answer corresponding to the preset question; A display module, used to cooperate with the anchor to display the preset answers corresponding to the audience questions based on the preset answers corresponding to the audience questions; There are multiple audience questions, each of which corresponds to a preset answer, and the display module is further used for: Determine audience behavior data corresponding to each of the plurality of audience questions, wherein the audience behavior data includes audience behavior data of each of the plurality of audience members, and the audience behavior data includes multiple types of behavior data; For each of the audience questions and for each of the audience members, determine at least one type of behavior data included in the audience behavior data of the audience; based on the at least one type of behavior data, determine the number of behavior occurrences corresponding to each of the at least one type of behavior data; determine the behavior occurrence time nodes corresponding to each of the at least one type of behavior data; based on the behavior decay function, the behavior occurrence time nodes corresponding to each of the at least one type of behavior data and the current time node, determine the behavior decay coefficient corresponding to each of the at least one type of behavior data; based on the preset weight corresponding to each of the at least one type of behavior data and the behavior decay coefficient, determine the behavior weight corresponding to each of the at least one type of behavior data; based on the number of behavior occurrences corresponding to each of the at least one type of behavior data and the behavior weight corresponding to each of the at least one type of behavior data, determine the weight of the audience behavior data of the audience; based on the audience behavior data corresponding to the audience question, determine the number of times each of the multiple audience members has posted the audience question; Determine a total weight corresponding to the audience question based on the weights of the audience behavior data of each of the plurality of audiences corresponding to the audience question and the number of times each of the plurality of audiences has posted the audience question; Determining, based on the total weights corresponding to the multiple audience questions, a display order of the preset answers corresponding to the multiple audience questions; Based on the preset answers corresponding to each of the multiple audience questions and the display order of the preset answers corresponding to each of the multiple audience questions, cooperate with the host to display the preset answers corresponding to each of the multiple audience questions in sequence.

8. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor, Wherein, the processor is used to execute a live broadcast method as described in any one of claims 1 to 6 above.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute a live broadcast method as described in any one of claims 1 to 6.

Images