Interaction method and device based on virtual character, electronic equipment and storage medium
By using virtual characters to generate extended interactive live streams to answer user questions in the live broadcast room, the problem of low efficiency in manual answers in the live broadcast room is solved, and efficient and accurate answers are achieved, thus optimizing the user experience and interaction quality.
Patent Information
- Application Number
- CN202511589903.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-31
- Publication Date
- 2026-02-13
AI Technical Summary
In existing technologies, human responses in live streaming rooms are inefficient, heavily reliant on manual intervention, and cannot efficiently handle user questions on the public screen.
Virtual characters are used to detect user questions in the live stream, generate extended interactive live streams to answer them, and play them on the client before switching back to the main interactive live stream.
It improved response efficiency and accuracy, reduced reliance on manual intervention, optimized user experience, and enhanced the interactive quality and potential for collaboration in virtual spaces.
Smart Images

Figure CN121531149A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present disclosure relates to the technical field of large model, and particularly relates to the field of artificial intelligence such as natural language processing. BACKGROUND
[0002] With the development of technology, people can obtain required information or required articles from a live room. In the process of watching a live broadcast, people can input questions on a public screen of the live room to obtain corresponding reply information. In related technologies, artificial reading and replying to questions on the public screen are relied on, and the degree of artificial dependence is high, and the replying efficiency is poor. SUMMARY
[0003] The present disclosure provides an interaction method and device based on a virtual role, an electronic device and a storage medium.
[0004] According to a first aspect of the present disclosure, an interaction method based on a virtual role is provided, which is suitable for a server, and the method comprises: in response to detecting that a target account raises an article question for an article recommended in a main interactive live broadcast stream, acquiring reply information for replying to the article question, the target account being any account watching the main interactive live broadcast stream; based on the reply information, generating an extended interactive live broadcast stream for the target account, the extended interactive live broadcast stream being used for replying to the article question raised by the target account; and pushing the extended interactive live broadcast stream to a client logged in by the target account, wherein the client switches back to the main interactive live broadcast stream after playing the extended interactive live broadcast stream to the end.
[0005] According to a second aspect of the present disclosure, an interaction method based on a virtual role is provided, which is suitable for a client, and the method comprises: playing a main interactive live broadcast stream pulled from a server, the main interactive live broadcast stream recommending at least one article; in response to a question operation on any article recommended in the main interactive live broadcast stream, sending an article question for the article to the server; receiving an extended interactive live broadcast stream sent by the server, the extended interactive live broadcast stream being used for replying to the article question; playing the extended interactive live broadcast stream, and switching back to the main interactive live broadcast stream after playing the extended interactive live broadcast stream to the end.
[0006] According to a third aspect of the present disclosure, an interaction device based on a virtual role is provided, which is suitable for a server, and the device comprises: an acquisition module configured to acquire reply information for replying to an item question raised by a target account for an item recommended in a main interactive live streaming, the target account being any account watching the main interactive live streaming; a generation module configured to generate an extended interactive live streaming for the target account based on the reply information, the extended interactive live streaming being used to reply to the item question raised by the target account; and a pushing module configured to push the extended interactive live streaming to a client logged in by the target account, wherein the client switches back to the main interactive live streaming after playing the extended interactive live streaming to the end.
[0007] According to a fourth aspect of the present disclosure, an interaction device based on a virtual role is provided, which is suitable for a client, and the device comprises: a first playing module configured to play a main interactive live streaming pulled from a server, the main interactive live streaming recommending at least one item; a question module configured to send an item question for any item recommended in the main interactive live streaming to the server in response to a question operation on the item; a receiving module configured to receive an extended interactive live streaming sent by the server, the extended interactive live streaming being used to reply to the item question; and a second playing module configured to play the extended interactive live streaming and switch back to the main interactive live streaming after playing the extended interactive live streaming to the end.
[0008] According to a fifth aspect of the present disclosure, an electronic device is provided, which comprises at least one processor and a memory connected with the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the interaction method based on a virtual role suitable for a server according to the first aspect and / or the interaction method based on a virtual role suitable for a client according to the second aspect.
[0009] According to a sixth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the interaction method based on a virtual role suitable for a server according to the first aspect and / or the interaction method based on a virtual role suitable for a client according to the second aspect.
[0010] According to a seventh aspect of the present disclosure, a computer program product is provided, which comprises a computer program, and the computer program, when executed by a processor, implements the interaction method based on a virtual role suitable for a server according to the first aspect and / or the interaction method based on a virtual role suitable for a client according to the second aspect.
[0011] It should be understood that the matters described in this section are not intended to identify key or important features of the embodiments of the present disclosure, nor are they used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS
[0012] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them: Figure 1 Flowchart of a virtual role-based interaction method according to an embodiment of the present disclosure; Figure 2 Flowchart of a virtual role-based interaction method according to another embodiment of the present disclosure; Figure 3 Flowchart of a virtual role-based interaction method according to another embodiment of the present disclosure; Figure 4 Flowchart of a virtual role-based interaction method according to another embodiment of the present disclosure; Figure 5 Structure diagram of a virtual role-based interaction device according to an embodiment of the present disclosure; Figure 6 Structure diagram of a virtual role-based interaction device according to another embodiment of the present disclosure Figure 7 Schematic block diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0013] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, descriptions of well-known functions and structures are omitted in the following description.
[0014] Large Language Model (LLM) refers to a deep learning model trained using a large amount of text data, allowing the model to generate natural language text or understand the meaning of language text. These models can provide in-depth knowledge and language production on various topics by training on large data sets. The core idea is to learn the patterns and structures of natural language through large-scale unsupervised training, to a certain extent, to simulate the language cognition and generation process of human beings.
[0015] Natural Language Processing (NLP) is an important direction in the field of computer science and artificial intelligence. It studies various theories and methods that can realize effective communication between people and computers using natural language. Natural language processing is a scientific field that integrates linguistics, computer science, and mathematics. Natural language processing is mainly applied to machine translation, public opinion monitoring, automatic abstract, opinion extraction, text classification, question answering, text semantic comparison, speech recognition, Chinese OCR, etc.
[0016] Artificial Intelligence (AI) is an important driving force for the new round of technological revolution and industrial transformation. It is a new technical science that studies, develops and applies systems for simulating, extending and expanding human intelligence. Artificial intelligence is an important part of intelligent disciplines. It aims to understand the essence of intelligence and produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence is a very broad science, including robots, language recognition, image recognition, natural language processing, expert systems, machine learning, computer vision, etc.
[0017] It should be noted that the acquisition, storage, use, processing, etc. of data in the technical solutions of the present disclosure comply with relevant provisions of national laws and regulations, and do not violate public order and good customs.
[0018] Figure 1 The flowchart of the virtual role-based interaction method of an embodiment of the present disclosure is suitable for a server, as shown in Figure 1 The method comprises the following steps: S101, in response to detecting that a target account raises an item question for a recommended item in a main interactive live stream, obtaining reply information for replying to the item question, the target account being any account watching the main interactive live stream.
[0019] During the process of live streaming by a digital person, the digital person as the anchor can be determined as a virtual role as the anchor object of the live room as the main interactive live stream in the current scene. When a user raises a corresponding question on the public screen of the live room, the digital person virtual role in the current live room can reply to the corresponding question for the user.
[0020] Among them, the space for interaction through virtual roles such as live rooms can be determined as a virtual interaction space.
[0021] In the virtual interactive space, a related live stream can be played, and through the playing of the live stream, the live interaction of the virtual role as the host in the virtual interactive space to the user can be realized. In this scenario, the live stream can be determined as the main interactive live stream in the virtual interactive space.
[0022] During the playing of the main interactive live stream in the virtual interactive space, any watching account in the live room can ask questions about the recommended items in the live content. In the interactive area of the virtual interactive space, a question about the currently introduced and recommended items in the live room can be detected. The question can be determined as the item question detected during the playing of the main interactive live stream in the virtual interactive space. In this scenario, the account that asks the item question can be determined as the target account that asks the item question.
[0023] The detection of the item question can be performed through the barrage messages during the playing, or through the interactive messages in the interactive area. Here, no specific limitation is made.
[0024] In this scenario, the virtual interactive space needs to reply to the detected item question separately. The information used for replying to the item question can be obtained, which is the reply information of the item question.
[0025] The reply information can be filtered based on a preset question and answer knowledge database, or can be generated based on the model capability of a large model. Here, no specific limitation is made.
[0026] It should be noted that the number of item questions detected during the playing of the main interactive live stream can be multiple. In this scenario, multiple reply information of the multiple item questions can be generated respectively, that is, when multiple item questions are detected in the main interactive live stream, the multiple item information can be replied to separately and synchronously.
[0027] S102, based on the reply information, generating an extended interactive live stream for the target account, the extended interactive live stream being used for replying to the item question asked by the target account.
[0028] In the embodiments of the present disclosure, in order to reply to the item question based on the reply information, the corresponding extended live stream can be constructed based on the reply information, so as to obtain the corresponding extended interactive live stream.
[0029] Optionally, based on the live stream construction algorithm in the related art, the live stream required for the separate reply to the item question based on the reply information can be constructed, and the live stream is the extended interactive live stream of the reply information.
[0030] It can be understood that the playing of the extended interactive live streaming based on the reply information on the client of the corresponding target account can realize the separate live reply to the corresponding item question on the client.
[0031] S103, push the extended interactive live streaming to the client logged in by the target account, wherein the client switches back to the main interactive live streaming after playing the extended interactive live streaming.
[0032] The main interactive live streaming is normally played when the extended interactive live streaming is played, and the extended interactive live streaming is used to reply to the item question raised by the target account.
[0033] In the embodiments of the present disclosure, after obtaining the extended interactive live streaming to be played for replying to the item question, the extended interactive live streaming can be pushed to the client currently logged in by the target account sending the corresponding item question, and the extended interactive live streaming is played through the client to separately reply to the item question raised by the target account logged in on the client.
[0034] The extended interactive live streaming can be pushed to the client logged in by the target account based on the data pushing method in the related art through the preset data interaction link between the server and the client, so as to be played on the display interface of the client, and then separately reply to the user under the target account for the item question.
[0035] In the embodiments of the present disclosure, after the playing of the extended interactive live streaming on the client logged in by the target account ends, the display interface of the client can switch back to the display interface of the main interactive live streaming, so that the user under the target account can continue to watch the index content of the main interactive live streaming.
[0036] It should be noted that during the execution of the extended interactive live streaming, the main interactive live streaming of the virtual interactive space is normally played, that is, for the accounts without raising questions, the corresponding live content can be normally watched based on the main interactive live streaming played in the virtual interactive space, and the separate live reply to each item question does not affect the live content watched by other users without raising item questions in the virtual interactive space.
[0037] The interaction method based on virtual roles provided in the present disclosure generates corresponding reply information when detecting an item question, to reply to the target account that proposes the item question individually, and generates respective reply information of multiple item questions when detecting multiple item questions, and replies to the multiple item questions individually in a live broadcast, which realizes personalized answers to item questions, improves the reply accuracy of item questions, realizes synchronous live broadcast reply to multiple item questions, and compared with the related art that relies on manual reply, improves the reply efficiency and accuracy, reduces the degree of artificial dependence and reply cost, optimizes the reply experience of users, improves the interaction efficiency and quality of the virtual interaction space, improves the possibility of cooperation achievement in the scenario of achieving cooperation through the virtual interaction space, and further improves the completion rate and completion quality of the cooperation achievement index to be achieved, and improves the user stickiness.
[0038] In the above embodiments, regarding the reply to the at least one item question individually, the following can be combined Figure 2 It is further understood that Figure 2 The flowchart of the interaction method based on virtual roles of another embodiment of the present disclosure is suitable for a server, such as a server of a virtual interaction space, and as shown in the figure, the method comprises the following steps. Figure 2 The method comprises the following steps. S201, in response to detecting that a target account proposes an item question for a recommended item in a main interactive live broadcast stream, obtaining reply information for replying to the item question, the target account being any account watching the main interactive live broadcast stream.
[0039] In the embodiments of the present disclosure, during the playing process of the main interactive live broadcast stream, the watching account can perform other interactions, in this scenario, the detected interaction information needs to be screened to determine the item question that needs to be replied to in a live broadcast individually.
[0040] Optionally, in response to detecting the interaction information during the playing process of the main interactive live broadcast stream, obtaining a semantic analysis result of the interaction information.
[0041] In the embodiments of the present disclosure, the information sent by the watching account during the playing process of the main interactive live broadcast stream can be determined as the interaction information, in this scenario, the semantic analysis algorithm in the related art can be used to perform semantic analysis on multiple pieces of interaction information sent by the watching account respectively, to obtain the semantic analysis result of the interaction information.
[0042] Optionally, in response to the semantic analysis result indicating that the interaction information is item inquiry information, determining that the interaction information is an item question that needs to be replied to in a live broadcast.
[0043] In this embodiment of the disclosure, for any interactive information, when the semantic parsing result of the interactive information indicates that the interactive information is a query for relevant information of the corresponding item currently being introduced in the live broadcast room, the information can be identified as item query information, and then the item query information can be identified as the currently detected item question that needs to be answered separately in the live broadcast.
[0044] Optionally, in response to detecting an item query, the item query is analyzed to determine the query object corresponding to the item query.
[0045] In this embodiment of the disclosure, when an item question is detected, the item question can be analyzed based on information analysis methods in related technologies, and the keyword information of the item question can be determined based on the processing results of the analysis algorithm.
[0046] Specifically, when the question about an item is presented in text form, the text of the question can be analyzed using natural language processing methods in related technologies. When the question about an item is presented in speech form, the audio of the question can be analyzed using audio analysis algorithms in related technologies. No specific limitations are made here.
[0047] During the playback of the main interactive live stream in the virtual interactive space, information can be introduced for each of the multiple resource items set up in the virtual interactive space. In this scenario, when an item question inquires about the detailed information of a certain dimension of any of the multiple resource items, that resource item can be identified as the object of inquiry for that item question.
[0048] Optionally, the descriptive information of the inquiry object is obtained, and the candidate response information of each inquiry object is obtained based on the descriptive information.
[0049] In this embodiment of the disclosure, when asking about an item, the corresponding inquiry object is provided with corresponding descriptive information. The descriptive information may include the appearance description information of the inquiry object, the description information of the usage method, and the description information of the activities preset for the inquiry object, etc., which are not specifically limited here.
[0050] In this scenario, the description information of the object of inquiry can be filtered and queried to extract at least some information that can answer the question about the item. Then, based on the at least some information, the corresponding answer information can be constructed. The answer information obtained by the construction, which includes the at least some information filtered from the description information, can be determined as the candidate answer information for the question about the corresponding item.
[0051] Optionally, the response preferences of the target account that asked the question about the item are obtained, and the candidate response information of the question about the item is adjusted based on the response preferences to obtain response information that matches the response preferences. The response preferences include at least the response method preference and response language style preference of the target account.
[0052] In this embodiment of the disclosure, for questions about items, the target account that raises the question has a corresponding user profile. The user profile of the target account can be processed by the user profile parsing algorithm in the relevant technology, and then the target account's preferred answering methods and answering language style and other related information can be obtained based on the result of the algorithm processing.
[0053] In this scenario, the parsed information, such as the preferred response methods and language styles of the target account asking the item question, can be used to determine the target account's response preferences.
[0054] In this scenario, based on style adjustment algorithms in related technologies and the response preferences of the target account, the candidate response information for the question about the item can be adjusted according to preferences, and the adjusted response information can be determined as the response information for the question about the item.
[0055] S202, Based on the response information, generate an extended interactive live stream for the target account.
[0056] The extended interactive live stream is used to answer questions about items raised by the target account.
[0057] Optionally, based on the item-based question, candidate response video scripts associated with the anchor object in the main interactive live stream can be determined.
[0058] In this embodiment of the disclosure, the virtual interactive space has multiple question information items for possible questions, and the question information items that match the item question can be filtered from these multiple question information items.
[0059] In this scenario, after determining the question information item for the item question, the corresponding answer strategy can be obtained. Then, from the answer video templates corresponding to the answer strategy, the answer video templates associated with the anchor of the live stream in the main interactive live stream watched by the target account can be selected. The script corresponding to the answer video template can be determined as the candidate answer video script for the item question.
[0060] Specifically, the anchor object in the main interactive live stream can be identified as the virtual object used when giving individual replies.
[0061] Optionally, based on the response information, the candidate response video script is adjusted to obtain the target response video script.
[0062] In this embodiment of the disclosure, the script adjustment method in the related art can be used to adjust the candidate answer video script corresponding to the question of the item based on the answer information corresponding to the question of the item, and then determine the adjusted video script carrying the answer information as the target answer video script for the question of the item.
[0063] It should be noted that the target response video script includes information such as the response methods that the virtual character needs to use when responding, but no specific restrictions are made here.
[0064] Optionally, based on the target response video script, an extended interactive live stream is constructed to provide video responses to questions about the item.
[0065] In this embodiment of the disclosure, a corresponding live stream can be constructed based on a live stream construction algorithm in the related technology, which serves as an extended interactive live stream to be executed when a virtual character makes a separate response to a question about a corresponding item based on the response information.
[0066] S203 pushes the extended interactive live stream to the client logged in by the target account.
[0067] The client switches back to the main interactive live stream after playing the extended interactive live stream.
[0068] In this embodiment of the disclosure, the push of the extended interactive live stream to the client logged into by the target account can be understood in conjunction with the relevant content in the above embodiments, and will not be repeated here.
[0069] After pushing the extended interactive live stream to the target account's client, the following can be used to understand: Optionally, in response to receiving a request from the client to close the extended interactive area of the extended interactive live stream, a corresponding stop playback command is sent to the client.
[0070] In this embodiment of the disclosure, when the extended interactive live stream needs to be stopped on the client playing it, the client can send a corresponding close request to the server, and the server generates a corresponding stop playback instruction based on the received close request and sends it to the client.
[0071] In this scenario, the client can shut down the playback of the extended interactive live stream based on the received stop playback command.
[0072] Optionally, in response to receiving feedback that the extended interactive live stream has stopped playing, a command to resume playback of the main interactive live stream is sent to the client.
[0073] In this embodiment of the disclosure, after the client closes the extended interactive live stream being played on it, it can return the corresponding stop playback feedback to the server. After receiving the stop playback feedback, the server can determine that the currently playing individual live stream response on the client has ended. In this scenario, the client needs to resume playing the live content of the main interactive live stream.
[0074] Then, the server can send a command to resume playback of the main interactive live stream to the client. Once the client receives the command, it can resume displaying the live content of the main interactive live stream on its screen.
[0075] Optionally, in response to the extended interactive live stream stopping, the system obtains the response feedback information for the corresponding item questions and optimizes the responses to the item questions based on the response feedback information.
[0076] In this embodiment of the disclosure, after the extended interactive live stream stops playing, a satisfaction survey option can be popped up on the client of the target account that asked the question about the item, so as to obtain feedback information on user satisfaction.
[0077] In this scenario, the satisfaction level of users under the target account with the corresponding live broadcast response can be identified based on the response feedback information. Based on this satisfaction level, the relevant process of individual live broadcast responses to item questions based on virtual characters can be optimized, so that the optimized process can be used to achieve individual live broadcast responses to item questions based on virtual characters in the future.
[0078] The virtual role-based interaction method proposed in this disclosure adjusts candidate response information based on the target account's response preferences to obtain corresponding response information, improving the fit between response information and user preferences. It provides live responses to item-related questions, achieving personalized answers and improving response accuracy. When multiple item questions are detected, it generates separate response information for each question and provides individual live responses to each, achieving simultaneous live responses to multiple item questions. Compared to related technologies that rely on manual responses, this method improves response efficiency and accuracy, reduces reliance on manual responses and response costs, optimizes the user's response experience, and enhances the interaction efficiency and quality of the virtual interactive space. In scenarios where cooperation is achieved through the virtual interactive space, it increases the likelihood of successful cooperation, thereby improving the completion rate and quality of desired cooperation achievement indicators and increasing user stickiness.
[0079] This disclosure also proposes an interaction method based on virtual characters, which can be combined with... Figure 3 understand, Figure 3This is a flowchart illustrating another embodiment of the virtual character-based interaction method disclosed herein, applicable to a client, such as... Figure 3 As shown, the method includes: S301, Play the main interactive live stream pulled from the server, in which at least one item is recommended.
[0080] In this embodiment of the disclosure, the client watches the live content of the main interactive live stream on its display screen. The client can send a corresponding live stream viewing request to the server. After receiving the live stream viewing request, the server sends the main interactive live stream to the client for playback.
[0081] The main interactive live stream content may include recommendations and introductions of at least one item, enabling cooperation between the accounts watching the live stream content and the accounts distributing the corresponding item resources in the main interactive live stream.
[0082] S302, in response to a question about any item recommended in the main interactive live stream, sends an item question to the server.
[0083] In this embodiment of the disclosure, the account currently logged in to the client can watch the live content of the main interactive live stream. During the viewing of the live content, the user of the account currently logged in to the client can ask questions about any item recommended in the live stream. Specifically, based on the live interactive questioning method in related technologies, the user can input the corresponding question in the interactive area of the live stream room of the main interactive live stream to complete the questioning operation for any item.
[0084] In this scenario, the server can detect information in the interactive area of the live stream and select the corresponding items to ask questions based on the detection results.
[0085] S303 receives the extended interactive live stream sent by the server. The extended interactive live stream is used to answer questions about items.
[0086] In this embodiment of the disclosure, the reception of extended interactive live streams can be achieved based on the interaction link between the server and the client. Specifically, for the target account that raises a question about an item, the client logged into by the target account can only receive the extended interactive live stream corresponding to the question raised by the target account.
[0087] In this scenario, the extended interactive live stream contains the answer information for item-related questions raised by the target account currently logged in. Based on the received extended interactive live stream, the client can provide individual answers to item-related questions raised by users under the target account.
[0088] S304, Play extended interactive live stream, switch back to main interactive live stream after the extended interactive live stream has finished playing.
[0089] In this embodiment of the disclosure, for questions about items, the virtual interactive space can be set up with a corresponding live response area, which can be determined as an extended interactive area used when answering questions about items.
[0090] In this scenario, the client can play the received extended interactive live stream, allowing the virtual character to broadcast responses to item-related questions raised by the target account in the extended interactive area set up on the client, thus achieving a separate live response to the item-related question.
[0091] It should be noted that, as can be seen from the relevant content in the above embodiments, during the execution of the extended interactive live stream, the main interactive live stream of the virtual interactive space will play normally. In this scenario, when the extended interactive live stream played on the client is closed, the client can be switched from playing the content of the extended interactive live stream back to the live content corresponding to the main interactive live stream.
[0092] In other words, after the extended interactive live stream on the client is closed, the client's screen will return to display the live content of the main interactive live stream after the corresponding closing time of the extended interactive live stream. The logged-in account of the client can continue to watch the live content of the main interactive live stream.
[0093] The virtual character-based interaction method proposed in this disclosure provides individual live-streamed responses to item-related questions raised by target accounts on the client logged in by those accounts. This achieves personalized answers to item questions, optimizes the user's response experience, and improves the efficiency and quality of interaction in the virtual interactive space. When extending the interactive live stream for individual live-streamed responses, the main interactive live stream content is played normally, reducing the impact of item question responses on the main interactive live stream content. While optimizing the user's response experience, it also optimizes the live-stream viewing experience for users under other accounts. In scenarios where cooperation is achieved through the virtual interactive space, it increases the likelihood of cooperation, thereby improving the completion rate and quality of the required cooperation achievement indicators and enhancing user stickiness.
[0094] In the above embodiments, the virtual character-based interaction method applicable to the client can be combined with... Figure 4 To understand further, Figure 4 This is a flowchart illustrating another embodiment of the interaction method based on virtual characters disclosed herein, such as... Figure 4 As shown, the method includes: S401 plays an extended interactive live stream within a preset extended interactive area to answer questions about items raised by the target account through a preset virtual character.
[0095] The content of the response broadcast is based on the response information corresponding to the extended interactive live stream.
[0096] In this embodiment of the disclosure, based on the playback of the extended interactive live stream corresponding to the answer information of the question about the item, the corresponding extended interactive area can pop up on the current display page of the virtual interactive space, and virtual characters such as digital humans are set in the extended interactive area.
[0097] In this scenario, based on the playback of this extended interactive live stream, the virtual character can broadcast through voice announcements combined with digital human body movements and other operations. The broadcast content can be determined based on the response information corresponding to the extended interactive live stream.
[0098] It should be noted that the extended interactive area can be either the interactive display area corresponding to the main interactive live stream or a small window area set within the interactive display area of the main interactive live stream.
[0099] Optionally, the extended interactive area corresponding to the extended interactive live stream can be a small window area set in the display area of the main interactive live stream on the client used by the target account that asked the question about the corresponding item. In this scenario, the live stream response in the extended interactive area can be displayed simultaneously with the display area of the main interactive live stream.
[0100] Optionally, when displaying the virtual character's responses within the extended interactive area, the live content corresponding to the main interactive live stream is weakened. This weakening includes blurring the image and removing the sound from the display area corresponding to the main interactive live stream. In other words, when a virtual character in the extended interactive area answers a question about an item, the live video and audio in the main interactive live stream's display area can be weakened. This weakening process can include blurring the video and eliminating the audio in the main interactive live stream's display area to reduce the impact of the live content in the main interactive live stream's display area on the live responses displayed in the extended interactive area.
[0101] Optionally, the size of the extended interactive area can also be the same as the display area of the main interactive live stream. In this scenario, the extended interactive area can cover the display area of the main interactive live stream, so that the display area of the virtual interactive space only displays the live responses in the extended interactive area.
[0102] In this scenario, when displaying the virtual character's response broadcast within the extended interactive area, the live content corresponding to the main interactive live stream is weakened. This weakening includes screen overlay and sound cancellation processing on the display area corresponding to the main interactive live stream.
[0103] In other words, when a virtual character in the extended interactive area gives a live response, the display area of the main interactive live stream on the client of the target account that asked the question about the corresponding item can be directly turned off. This allows the extended interactive area to cover the display area of the virtual interactive space and eliminate the sound in the display area of the main interactive live stream, thus enabling users to receive a more accurate individual live response from the virtual character to their question about the item.
[0104] It should be noted that the weakening of the live content corresponding to the main interactive live stream mentioned above includes either blurring the image and removing the sound in the display area corresponding to the main interactive live stream, or covering the image and removing the sound in the display area corresponding to the main interactive live stream. These can be set based on user needs or other application scenarios, and are not specifically limited here.
[0105] S402, in response to detecting a request to close the extended interactive area of the extended interactive live stream, a request to close the extended interactive live stream is sent to the server.
[0106] In this embodiment of the disclosure, the extended interactive live stream is set with corresponding playback end conditions. The extended interactive area of the extended interactive live stream can be used to detect relevant playback end information. When the corresponding information is detected, it can be determined that the user under the target account needs to stop watching the live content of the extended interactive live stream.
[0107] In this scenario, the client can generate a close request for the extended interactive live stream and send the close request to the server.
[0108] Optionally, in response to the detection of a reply end keyword, the operation of the end option of the extended interactive live stream within the extended interactive area of the extended interactive live stream, and the failure to detect at least one of the following triggers within a set time after the virtual character in the extended interactive area has finished broadcasting the content of the live reply, the system determines that the extended interactive area of the extended interactive live stream has been closed, and generates a close request based on the close information.
[0109] In other words, when a user sends the corresponding end-of-response keyword in the extended interaction area, it can be determined that the user needs to stop the current live broadcast response. In this scenario, it can be determined that a close message has been detected in the extended interaction area.
[0110] Furthermore, when a user interacts with the preset end option in the extended interaction area, it can be determined that the user needs to stop the current live broadcast response. In this scenario, it can be determined that a close message has been detected in the extended interaction area.
[0111] Furthermore, if no user interaction information is detected within the set time after the virtual character in the extended interaction area has completed the broadcast of the target response information, it can be determined that the current user may not need to continue watching the virtual character's response broadcast. In this scenario, it can be determined that a close message has been detected in the extended interaction area.
[0112] In this embodiment of the disclosure, when at least one of the above three situations is detected, it can be determined that the user under the target account does not need to continue watching the live content of the currently playing extended interactive live stream. In this scenario, a corresponding close request can be generated based on the detected close information and sent to the server.
[0113] It should be noted that the conditions required to close the extended interactive area can include the three conditions mentioned above, as well as other settings, which are not specifically limited here.
[0114] S403, in response to receiving a stop playback command from the server, stops the playback of the extended interactive live stream and sends a corresponding stop playback feedback to the server.
[0115] In this embodiment of the disclosure, after the client sends a close request to the server, it can receive a stop playback instruction returned by the server. After receiving the stop playback instruction, the client can close the playback of the currently playing extended interactive live stream.
[0116] In this scenario, the client can also generate a corresponding stop playback feedback and return it to the server to inform the server that the extended interactive live stream currently playing on the client has been closed.
[0117] It should be noted that after the extended interactive live stream is closed, the client needs to restore the display of the live stream content. This can be understood in conjunction with the following: Optionally, the pause time of the extended interactive live stream can be obtained, and the live content of the main interactive live stream can be resumed after the pause time.
[0118] Optionally, the transition effect between the extended interactive area of the extended interactive live stream and the display area of the main interactive live stream is obtained. Based on the transition effect, the extended interactive area is closed and the main interactive live stream plays the live content after the pause time.
[0119] In this embodiment of the disclosure, the viewers in the display area of the main interactive live stream include not only users under the target account who asked questions about the item, but also users under other viewing accounts who did not ask questions about the item. In this scenario, when each extended interactive live stream is played separately, the main interactive live stream will also play the originally set live content normally.
[0120] In this scenario, when the extended interactive live stream on the client ends and returns to play the main interactive live stream, the main interactive live stream can contain content after the extended interactive live stream has stopped playing.
[0121] Specifically, the closing time of the extended interactive area of the extended interactive live stream on the client can be determined as the stop playback time of the extended interactive live stream.
[0122] In this scenario, the live content of the main interactive live stream's display area during the pause time can be obtained. On the client of the target account asking the question about the corresponding item, a transition effect is used to transition the display content of the last frame of the extended interactive area with the display content of the next frame of the main interactive live stream's display area at the pause time. This allows for a visual transition between the extended interactive area of the extended interactive live stream and the display area of the main interactive live stream on the client, so that the main interactive live stream's live content can be resumed after the extended interactive live stream ends.
[0123] The transition effect can be a fade-in / fade-out effect or other effects; no specific restrictions are made here.
[0124] The interactive method based on virtual characters proposed in this disclosure provides separate live-streamed answers to item-related questions raised by the target account on the client logged in by that account. This achieves personalized answers to item questions, optimizes the user's answering experience, and closes the live-streamed answers played separately on the client upon detecting the closure of the extended interactive live stream, improving the efficiency and quality of interaction in the virtual interactive space. The live-stream content corresponding to the main interactive live stream is restored based on transition effects, improving the aesthetics of the transition between the extended and main interactive live streams. While providing separate live-streamed answers in the extended interactive live stream, the live-stream content of the main interactive live stream plays normally, reducing the impact of item question answers on the main interactive live stream content. In addition to optimizing the user's answering experience, this method also optimizes the live-streaming viewing experience for users under other accounts, increasing user engagement.
[0125] An embodiment of this disclosure also proposes a virtual role-based interactive device suitable for a server. Since the virtual role-based interactive device suitable for a server proposed in this disclosure corresponds to the virtual role-based interactive methods suitable for a server proposed in the above embodiments, the implementation methods of the virtual role-based interactive methods suitable for a server proposed in the above disclosure are also applicable to the virtual role-based interactive device suitable for a server proposed in this disclosure. It will not be described in detail in the following embodiments.
[0126] Figure 5This is a schematic diagram of the structure of an interactive device based on virtual characters according to an embodiment of the present disclosure, applicable to a server, such as... Figure 5 As shown, the interactive device 500 based on virtual characters includes an acquisition module 51, a generation module 52, and a push module 53, wherein: The acquisition module 51 is used to respond to the detection of a question raised by a target account regarding an item recommended in the main interactive live stream, and to acquire the response information that answers the question regarding the item. The target account is any account that watches the main interactive live stream. The generation module 52 is used to generate an extended interactive live stream for the target account based on the response information. The extended interactive live stream is used to respond to the item questions raised by the target account. The push module 53 is used to push the extended interactive live stream to the client logged in by the target account. After the client finishes playing the extended interactive live stream, it switches back to the main interactive live stream.
[0127] In this embodiment of the disclosure, the generation module 52 is further configured to: determine, based on the item question, a candidate response video script associated with the anchor object in the main interactive live stream; adjust the candidate response video script based on the response information to obtain a target response video script; and construct an extended interactive live stream that provides video responses to the item question based on the target response video script.
[0128] In this embodiment of the disclosure, the acquisition module 51 is further configured to: in response to the detection of interactive information during the playback of the main interactive live stream, acquire the semantic parsing result of the interactive information; and in response to the semantic parsing result indicating that the interactive information is item inquiry information, determine that the interactive information is an item question that needs to be answered in the live stream.
[0129] In this embodiment of the disclosure, the acquisition module 51 is further configured to: in response to detecting an item question, analyze the item questions respectively to determine the inquiry object corresponding to each item question; acquire the description information of the inquiry object, and obtain the candidate response information of the inquiry object based on the description information; acquire the response preference of the target account that made the item question, and adjust the candidate response information of the item question based on the response preference to obtain response information that matches the response preference, wherein the response preference includes at least the preference of the response method corresponding to the target account and the preference of the response language style.
[0130] In this embodiment of the present disclosure, the device further includes a first control module, configured to: in response to receiving a request from the client to close the extended interactive area of the extended interactive live stream, send a corresponding stop playback command to the client; and in response to receiving feedback from the extended interactive live stream that it has stopped playing, send a resume playback command for the main interactive live stream to the client.
[0131] In this embodiment of the disclosure, the device further includes an optimization module, configured to: obtain response feedback information for the corresponding item question; and optimize the response to the item question based on the response feedback information.
[0132] The interactive device based on virtual characters disclosed herein provides individual live-streamed answers to item-related questions raised by target accounts on the client logged in by those target accounts. This achieves personalized answers to item questions, optimizes the user's answering experience, and improves the efficiency and quality of interaction in the virtual interactive space. When extending the interactive live stream for individual live-streamed answers, the main interactive live stream content is played normally, reducing the impact of item question answers on the main interactive live stream content. While optimizing the user's answering experience, it also optimizes the live-streaming viewing experience for users under other accounts. In scenarios where cooperation is achieved through the virtual interactive space, it increases the likelihood of cooperation, thereby improving the completion rate and quality of the required cooperation achievement indicators and enhancing user stickiness.
[0133] An embodiment of this disclosure also proposes a virtual character-based interactive device suitable for a client. Since the virtual character-based interactive device suitable for a client proposed in this disclosure corresponds to the virtual character-based interactive methods suitable for a client proposed in the above embodiments, the implementation methods of the virtual character-based interactive methods suitable for a client described above are also applicable to the virtual character-based interactive device suitable for a client proposed in this disclosure. It will not be described in detail in the following embodiments.
[0134] Figure 6 This is a schematic diagram of the structure of a virtual character-based interactive device according to another embodiment of the present disclosure, applicable to a client, such as... Figure 6 As shown, the interactive device 600 based on virtual characters includes a first playback module 61, a question module 62, a receiving module 63, and a second playback module 64, wherein: The first playback module 61 is used to play the main interactive live stream pulled from the server, in which at least one item is recommended; The question module 62 is used to respond to the questioning operation of any item recommended in the main interactive live stream by sending an item question to the server. The receiving module 63 is used to receive the extended interactive live stream sent by the server. The extended interactive live stream is used to answer questions about items. The second playback module 64 is used to play the extended interactive live stream and switch back to the main interactive live stream after the extended interactive live stream has finished playing.
[0135] In this embodiment of the present disclosure, the second playback module 64 is further configured to: play an extended interactive live stream in a preset extended interactive area to answer questions raised by the target account through a preset virtual character, wherein the content of the answer broadcast is based on the answer information corresponding to the extended interactive live stream.
[0136] In this embodiment of the disclosure, the extended interactive area can be either the interactive display area corresponding to the main interactive live stream or a small window area set in the interactive display area of the main interactive live stream.
[0137] In this embodiment of the disclosure, when displaying the virtual character's response broadcast within the extended interactive area, the live content corresponding to the main interactive live stream is weakened. The weakening includes one of blurring the image and eliminating the sound in the display area corresponding to the main interactive live stream, or covering the image and eliminating the sound in the display area corresponding to the main interactive live stream.
[0138] In this embodiment of the present disclosure, the second playback module 64 is further configured to: in response to detecting the closing information of the extended interactive area of the extended interactive live stream, send a closing request for the extended interactive live stream to the server; in response to receiving a stop playback instruction sent by the server, stop the playback of the extended interactive live stream and send a corresponding stop playback feedback to the server.
[0139] In this embodiment of the present disclosure, the second playback module 64 is further configured to: determine that the extended interactive area of the extended interactive live stream is closed when a reply end keyword is detected in the extended interactive area of the extended interactive live stream, the end option of the extended interactive live stream is operated, and the virtual character in the extended interactive area does not detect at least one of the user interaction information being triggered within a set time after the content of the live reply ends.
[0140] In this embodiment of the disclosure, the second playback module 64 is further configured to: obtain the stop playback time of the extended interactive live stream, and resume displaying the live content of the main interactive live stream after the stop playback time.
[0141] In this embodiment of the disclosure, the second playback module 64 is further configured to: acquire the transition effect between the extended interactive area of the extended interactive live stream and the display area of the main interactive live stream; and based on the transition effect, close the extended interactive area and transition to the live content played by the main interactive live stream after the playback stop time.
[0142] The interactive device based on virtual characters disclosed herein provides separate live-streamed answers to item-related questions raised by a target account on the client logged in by that account. This achieves personalized answers to item questions, optimizes the user's answering experience, and closes the live-streamed answers played separately on the client upon detecting the closure of the extended interactive live stream, thereby improving the interaction efficiency and quality of the virtual interactive space. The device also restores playback of the corresponding live content of the main interactive live stream based on transition effects, improving the aesthetics of the transition between the extended and main interactive live streams. While providing separate live-streamed answers in the extended interactive live stream, the main interactive live stream plays normally, reducing the impact of item question answers on the main interactive live stream's content. In addition to optimizing the user's answering experience, this also optimizes the live-streaming viewing experience for users under other accounts, increasing user engagement.
[0143] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
[0144] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0145] like Figure 7 As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 702 or a computer program loaded into random access memory (RAM) 703 from storage unit 708. The RAM 703 may also store various programs and data required for the operation of device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 704. Input / output (I / O) interface 705 is also connected to bus 704.
[0146] Multiple components in device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of monitors, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0147] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as virtual role-based interaction methods suitable for servers and / or virtual role-based interaction methods suitable for clients. For example, in some embodiments, virtual role-based interaction methods suitable for servers and / or virtual role-based interaction methods suitable for clients can be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by computing unit 701, one or more steps of the virtual role-based interaction method for servers and / or virtual role-based interaction method for clients described above can be performed. Alternatively, in other embodiments, computing unit 701 can be configured by any other suitable means (e.g., by means of firmware) to perform the virtual role-based interaction method for servers and / or virtual role-based interaction method for clients.
[0148] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0149] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0150] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0151] To initiate interaction with a user account, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user account; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user account can submit input to the computer. Other types of devices can also be used to initiate interaction with the user account; for example, feedback submitted to the user account can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user account can be received in any form (including voice input, speech input, or tactile input).
[0152] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user account computer with a graphical user interface or web browser through which a user account can interact with the implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.
[0153] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.
[0154] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.
[0155] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.
Claims
1. An interaction method based on virtual characters, applicable to a server, wherein, The method includes: In response to detecting a question raised by a target account regarding an item recommended in the main interactive live stream, obtain response information to answer the question, wherein the target account is any account that watches the main interactive live stream; Based on the response information, an extended interactive live stream is generated for the target account, which is used to respond to the item-related questions raised by the target account. The extended interactive live stream is pushed to the client logged in by the target account, wherein the client switches back to the main interactive live stream after playing the extended interactive live stream.
2. The method according to claim 1, wherein, The step of generating an extended interactive live stream for the target account based on the response information includes: Based on the question about the item, determine the candidate response video scripts associated with the anchor object in the main interactive live stream; Based on the response information, the candidate response video script is adjusted to obtain the target response video script; Based on the target response video script, an extended interactive live stream is constructed to provide video responses to questions about the item.
3. The method according to claim 2, wherein, The step of responding to detecting a question raised by a target account regarding an item recommended in the main interactive live stream, and obtaining response information to answer the question, before the target account is any account watching the main interactive live stream, further includes: In response to the detection of interactive information during the playback of the main interactive live stream, the results of semantic parsing of the interactive information are obtained; In response to the semantic parsing result indicating that the interaction information is an item inquiry, the interaction information is determined to be an item question that requires a live response.
4. The method according to claim 3, wherein, The response to detecting a question raised by a target account regarding an item recommended in the main interactive live stream, and obtaining response information to the question, wherein the target account is any account watching the main interactive live stream, includes: In response to detecting the item question, the item question is analyzed to determine the query object corresponding to the item question; Obtain the description information of the query object, and obtain the candidate response information of the query object based on the description information; The response preferences of the target account that asked the question about the item are obtained, and the candidate response information of the question about the item is adjusted based on the response preferences to obtain the response information that matches the response preferences. The response preferences include at least the preference for the response method and the preference for the response language style corresponding to the target account.
5. The method according to claim 1, wherein, After pushing the extended interactive live stream to the client logged in by the target account, the method further includes: In response to receiving a request from the client to close the extended interactive area of the extended interactive live stream, a corresponding stop playback command is sent to the client; In response to receiving feedback that the extended interactive live stream has stopped playing, a command to resume playback of the main interactive live stream is sent to the client.
6. The method according to any one of claims 1-5, wherein, The method further includes: In response to the termination of the extended interactive live stream, obtain the corresponding response feedback information for the question about the item; Based on the feedback information, the responses to the questions about the items are optimized.
7. An interaction method based on virtual characters, applicable to client-side applications, wherein, The method includes: Play the main interactive live stream pulled from the server, in which at least one item is recommended; In response to a question asked about any item recommended in the main interactive live stream, a question about that item is sent to the server. The system receives an extended interactive live stream sent from the server, which is used to answer questions about the item. Play the extended interactive live stream, and switch back to the main interactive live stream after the extended interactive live stream has finished playing.
8. The method according to claim 7, wherein, Playing the extended interactive live stream includes: The extended interactive live stream is played within a preset extended interactive area to answer questions about items raised by the target account through a preset virtual character. The content of the answer broadcast is based on the answer information corresponding to the extended interactive live stream.
9. The method according to claim 8, wherein, The extended interactive area can be either the interactive display area corresponding to the main interactive live stream or a small window area set in the interactive display area of the main interactive live stream.
10. The method according to claim 8, wherein, When the virtual character's response is displayed in the extended interactive area, the live content corresponding to the main interactive live stream is weakened. The weakening includes one of blurring the image and removing the sound in the display area corresponding to the main interactive live stream, or covering the image and removing the sound in the display area corresponding to the main interactive live stream.
11. The method according to claim 7, wherein, The step of playing the extended interactive live stream and switching back to the main interactive live stream after the extended interactive live stream has finished playing includes: In response to detecting the closure information of the extended interactive area of the extended interactive live stream, a closure request for the extended interactive live stream is sent to the server; In response to receiving a stop playback command from the server, the playback of the extended interactive live stream is stopped, and a corresponding stop playback feedback is sent to the server.
12. The method according to claim 11, wherein, The method further includes: In response to the detection of a reply end keyword within the extended interactive area of the extended interactive live stream, the operation of the end option of the extended interactive live stream, and the failure to detect at least one of the following user interaction information within a set time after the virtual character in the extended interactive area finishes broadcasting the live reply content, it is determined that the closed information of the extended interactive area of the extended interactive live stream has been detected.
13. The method according to claim 11, wherein, The method further includes: Obtain the stop playback time of the extended interactive live stream, and resume displaying the live content of the main interactive live stream after the stop playback time.
14. The method according to claim 13, wherein, The restoration and display of the main interactive live stream content after the playback stop time includes: Obtain the transition effect between the extended interactive area of the extended interactive live stream and the display area of the main interactive live stream; Based on the aforementioned transition effect, the extended interactive area is closed, and the main interactive live stream transitions to the live content played after the stop playback time.
15. An interactive device based on virtual characters, suitable for a server, wherein, The device includes: The acquisition module is used to respond to the detection of a target account asking a question about an item recommended in the main interactive live stream, and to acquire the response information that answers the question about the item. The target account is any account that watches the main interactive live stream. The generation module is used to generate an extended interactive live stream for the target account based on the response information. The extended interactive live stream is used to respond to the item questions raised by the target account. The push module is used to push the extended interactive live stream to the client logged in by the target account, wherein the client switches back to the main interactive live stream after playing the extended interactive live stream.
16. An interactive device based on a virtual character, suitable for a client, wherein, The device includes: The first playback module is used to play the main interactive live stream pulled from the server, wherein at least one item is recommended in the main interactive live stream; The question module is used to respond to a questioning operation on any item recommended in the main interactive live stream by sending an item question to the server for that item. The receiving module is used to receive the extended interactive live stream sent by the server, and the extended interactive live stream is used to answer questions about the item. The second playback module is used to play the extended interactive live stream and switch back to the main interactive live stream after the extended interactive live stream has finished playing.
17. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6 and / or 7-14.
18. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6 and / or 7-14.
19. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6 and / or 7-14.