Method and apparatus for live streaming assistance, device, computer readable storage medium, and product

Abstract

Embodiments of the present disclosure provide a method and apparatus for live streaming assistance, a device, a computer readable storage medium, and a product. The method comprises: obtaining a live streaming assistance request, and, on the basis of the live streaming assistance request, displaying a preset function list, the function list comprising at least one live streaming assistance function; in response to a selection operation of a streamer user in the function list, determining at least one target assistance function selected by the streamer user; obtaining live streaming data matching the at least one target assistance function, the live streaming data comprising at least one among live streaming voice data, live streaming comment data, and associated data of live streaming content; and inputting the live streaming data into a preset language model, and, on the basis of a data processing result outputted by the language model, performing a live streaming assistance operation. Therefore, a live streaming assistance function can be provided for a streamer user in a personalized manner on the basis of a selection operation of the streamer user, so that the streamer user does not need to organize language to perform live streaming operation, thereby improving a live streaming effect and live streaming efficiency.

Description

Live broadcast auxiliary method, device, equipment, computer-readable storage medium and product

[0001] This application claims priority to Chinese Patent Application No. 202311623198.4 filed on November 30, 2023, and the contents of the above-mentioned Chinese patent application disclosure are hereby incorporated by reference in their entirety as a part of this application. Technical Field

[0002] The embodiments of the present disclosure relate to a live broadcast assistance method, apparatus, device, computer-readable storage medium, and product. Background Art

[0003] With the continuous development of internet technology, live streaming has gradually become part of users' lives. More and more users are using it to engage in interactive activities with their audiences, such as conversations, interviews, and product demonstrations. Live streaming is also increasingly being used in e-commerce, where hosts can introduce products through live streaming, allowing viewers to gain a more detailed understanding of the products.

[0004] However, during live streaming, some anchors often have poor text organization and expression skills, which results in a dull atmosphere in the live streaming room and poor live streaming results. Therefore, how to assist anchors in live streaming to improve the live streaming effect has become an urgent problem to be solved. Summary of the Invention

[0005] The embodiments of the present disclosure provide a live broadcast assistance method, apparatus, device, computer-readable storage medium, and product.

[0006] In a first aspect, an embodiment of the present disclosure provides a live broadcast assistance method, comprising:

[0007] Obtaining a live broadcast assistance request, and displaying a preset function list based on the live broadcast assistance request, wherein the function list includes at least one live broadcast assistance function;

[0008] In response to a selection operation by the anchor user in the function list, determining at least one target auxiliary function selected by the anchor user;

[0009] Acquire live broadcast data matching the at least one target auxiliary function, wherein the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and associated data of live broadcast content;

[0010] The live broadcast data is input into a preset language model, and live broadcast auxiliary operations are performed based on the data processing results output by the language model.

[0011] In a second aspect, an embodiment of the present disclosure provides a live broadcast auxiliary device, comprising:

[0012] an acquisition module, configured to acquire a live broadcast assistance request, and display a preset function list based on the live broadcast assistance request, wherein the function list includes at least one live broadcast assistance function;

[0013] A determination module, configured to determine at least one target auxiliary function selected by the anchor user in response to a selection operation by the anchor user in the function list;

[0014] a processing module, configured to obtain live broadcast data matching the at least one target auxiliary function, wherein the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and associated data of live broadcast content;

[0015] The auxiliary module is used to input the live broadcast data into a preset language model and perform live broadcast auxiliary operations based on the data processing results output by the language model.

[0016] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0017] The memory stores computer-executable instructions;

[0018] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the live broadcast assistance method described in the first aspect and various possible designs of the first aspect.

[0019] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the live broadcast assistance method described in the first aspect and various possible designs of the first aspect is implemented.

[0020] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the live broadcast assistance method described in the first aspect and various possible designs of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, a brief introduction will be given below to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] FIG1 is a schematic diagram of the system architecture on which the present disclosure is based;

[0023] FIG2 is a flow chart of a live broadcast assistance method provided by an embodiment of the present disclosure;

[0024] FIG3 is a flow chart of a live broadcast assistance method provided by another embodiment of the present disclosure;

[0025] FIG4 is a flow chart of a live broadcast assistance method provided by another embodiment of the present disclosure;

[0026] FIG5 is a flow chart of a live broadcast assistance method provided by another embodiment of the present disclosure;

[0027] FIG6 is a flow chart of a live broadcast assistance method provided by another embodiment of the present disclosure;

[0028] FIG7 is a schematic structural diagram of a live broadcast auxiliary device provided by an embodiment of the present disclosure;

[0029] FIG8 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0031] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0032] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0033] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0034] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0035] In order to solve the technical problem of poor live broadcast effect caused by the host user's weak expressive ability, the present disclosure provides a live broadcast assistance method, device, equipment, computer-readable storage medium and product.

[0036] It should be noted that the live broadcast assistance method, device, equipment, computer-readable storage medium and product provided by the present disclosure can be applied in any live broadcast scenario.

[0037] Current online live streaming typically requires hosts to organize their own language to introduce products and interact with viewers. For hosts with poor verbal skills, poor communication with viewers can lead to subpar live streaming and a lack of engagement in their livestreams.

[0038] In the process of solving the above-mentioned technical problems, the inventors discovered through research that, in order to improve the live broadcast effect, multiple auxiliary live broadcast functions can be pre-set. Each auxiliary live broadcast function can process the live broadcast data generated during the live broadcast using a preset language model to generate a data processing result for auxiliary live broadcast. The host can directly perform live broadcast operations based on this data processing result, avoiding the need to organize the language for live broadcast. The language model can be pre-trained using big data and can flexibly generate logically coherent and clearly expressed data processing results based on the live broadcast data. Therefore, auxiliary live broadcast based on this data processing result can achieve a higher-quality live broadcast effect.

[0039] The inventors further discovered that, in order to enable live streaming more flexibly, a function list can be displayed based on a user-triggered auxiliary live streaming request, displaying multiple auxiliary live streaming functions for the user to select. Furthermore, an auxiliary live streaming operation can be performed based on at least one target auxiliary live streaming function selected by the user.

[0040] FIG1 is a schematic diagram of the system architecture on which the present disclosure is based. As shown in FIG1 , the system architecture on which the present disclosure is based includes at least a terminal device 11 for performing live broadcast operations and a server 12 , wherein the server 12 is pre-installed with a trained language model.

[0041] Based on the above system architecture, in response to a live broadcast assistance request triggered by a live broadcast user on terminal device 11, a list of functions can be displayed on terminal device 11 for the user to select. After the user selects at least one target assistance function, the live broadcast data generated by the live broadcast user can be obtained. The live broadcast data is sent to server 12, where it is processed based on a language model preset in server 12 to obtain a data processing result. This data processing result can then be used to assist the live broadcast.

[0042] FIG2 is a flow chart of a live broadcast assistance method provided by an embodiment of the present disclosure. As shown in FIG2 , the method includes:

[0043] Step 201: Obtain a live broadcast assistance request, and display a preset function list based on the live broadcast assistance request, wherein the function list includes at least one live broadcast assistance function.

[0044] The implementation entity of this embodiment is a live broadcast assistance device. This live broadcast assistance device can be coupled to a terminal device used for live broadcasting. This device can perform live broadcast assistance operations based on a preset language model, based on at least one target auxiliary function selected by the host user. The language model can be coupled to the terminal device. Alternatively, the language model can be coupled to a server that is communicatively connected to the terminal device.

[0045] In this embodiment, the host user can trigger a live broadcast assistance request during the live broadcast process. For example, the host user can trigger an auxiliary live broadcast control preset on the display interface to initiate an auxiliary live broadcast request.

[0046] Accordingly, the live broadcast assistance device can receive a live broadcast assistance request. To reduce the difficulty of live broadcasting for the anchor user, at least one live broadcast assistance function can be pre-provided. Among them, the live broadcast assistance function includes but is not limited to a virtual assistant function, a prompting function, and an intelligent customer service function.

[0047] After receiving the live broadcast assistance request, a preset function list may be displayed, wherein the function list displays at least one live broadcast assistance function, so that the user can select the live broadcast assistance function according to actual needs.

[0048] Step 202: In response to a selection operation of the anchor user in the function list, determine at least one target auxiliary function selected by the anchor user.

[0049] In this embodiment, after the function list is displayed, the host user can select a live broadcast auxiliary function according to actual needs. In response to the host user's selection operation in the function list, at least one live broadcast auxiliary function selected by the host user can be determined as at least one target auxiliary function.

[0050] The live broadcast assistance function can be implemented independently or in combination. For example, when the host user selects the virtual assistant function and the prompt function, the virtual assistant can ask the host user a question, and the host user can answer the virtual assistant's question. If the host user is unable to answer the question, the prompt function can display the answer information on a preset prompt device, allowing the host user to perform live broadcast operations based on the answer information displayed by the prompt device.

[0051] Step 203: Acquire live broadcast data that matches the at least one target auxiliary function, wherein the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and associated data of live broadcast content.

[0052] In this embodiment, in order to achieve different live broadcast assistance effects, different live broadcast data can be obtained for different live broadcast assistance functions.

[0053] Optionally, live broadcast data matching at least one target auxiliary function can be obtained, where the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and data associated with the live broadcast content. The live broadcast voice data can be the language data of the host user during the live broadcast, the live broadcast comment data can be the comments posted by the audience in the comment area, and the live broadcast content can be at least one product associated with the live broadcast. The associated data of the live broadcast content includes, but is not limited to, product introductions, product attributes, product discount information, and other content.

[0054] Step 204: input the live broadcast data into a preset language model, and perform live broadcast auxiliary operations based on the data processing results output by the language model.

[0055] In this embodiment, a language model can be pre-set. This language model can be a deep learning model pre-trained using a large amount of text data, capable of generating natural language text or understanding the meaning of language text. This language model can handle a variety of natural language tasks, such as text classification, question answering, and conversation.

[0056] Therefore, after the live broadcast data is obtained, the live broadcast data can be input into a preset language model, and live broadcast auxiliary operations can be performed based on the data processing results output by the language model.

[0057] As an implementable approach, a unified language model can be used for data processing. Alternatively, for different auxiliary live broadcast functions, the live broadcast data corresponding to the auxiliary live broadcast function can be used to conduct targeted training on the language model to obtain language models corresponding to the different auxiliary live broadcast functions. During the auxiliary live broadcast process, different language models can be used for data processing for different functions. This disclosure does not impose any restrictions on this.

[0058] The live broadcast assistance method provided in this embodiment displays a preset function list after receiving a live broadcast assistance request, including at least one live broadcast assistance function. Live broadcast data is acquired based on at least one target assistance function selected by the host user, and the acquired live broadcast data is input into a preset language model. The language model processes the live broadcast data to obtain a data processing result, which can be used to assist the live broadcast. This allows personalized assistance functions to be provided to the host user based on their selection, eliminating the need for the host user to organize their own language for live broadcast operations, thereby improving live broadcast effectiveness and efficiency.

[0059] Optionally, the target auxiliary function may be a virtual assistant function. Under the virtual assistant function, a virtual assistant with a virtual three-dimensional image may be pre-set. The virtual assistant may read the data processing results output by the language model to interact with the anchor user and increase the interest of the live broadcast process.

[0060] Under the virtual assistant function, the virtual assistant can raise questions regarding at least one live broadcast content corresponding to the live broadcast, so that the host user can answer the questions based on the questions raised by the virtual assistant.

[0061] Alternatively, under the virtual assistant function, the host user can ask questions about at least one live broadcast content corresponding to the live broadcast, so that the virtual assistant can answer the questions raised by the host user based on the data processing results output by the language model.

[0062] FIG3 is a flow chart of a live broadcast assistance method provided by another embodiment of the present disclosure. Based on any of the above embodiments, as shown in FIG3 , the target assistance function may be a virtual assistant function. The virtual assistant may raise questions regarding at least one live broadcast content corresponding to the live broadcast. Step 203 includes:

[0063] Step 301: Determine at least one live broadcast content corresponding to the live broadcast, and obtain associated data of the at least one live broadcast content, wherein the associated data includes one or more of attribute information, description information, and virtual resource information of the live broadcast content.

[0064] Step 302: Acquire live voice data of the host user during the live broadcast process, and convert the live voice data into text content based on a preset voice recognition algorithm. The live voice data includes questions raised by the host user based on the live broadcast content.

[0065] Step 303: Determine the associated data of the at least one live broadcast content and the text content corresponding to the live broadcast voice data as the live broadcast data.

[0066] In this embodiment, under the virtual assistant function, the virtual assistant can raise questions regarding at least one live broadcast content corresponding to the live broadcast, so that the host user can answer the questions based on the questions raised by the virtual assistant.

[0067] To enable the virtual assistant to respond to the host's questions, at least one live content corresponding to the live broadcast can be determined and associated data for the at least one live content can be obtained. The associated data includes one or more of the live content's attribute information, description information, and virtual resource information. Live voice data from the host during the live broadcast can be obtained and converted into text based on a preset speech recognition algorithm. The live voice data includes questions posed by the host based on the live content. The associated data for the at least one live content and the text corresponding to the live voice data can be determined as live data.

[0068] Optionally, during the process of acquiring live broadcast language data, the voice of the host user can be identified, and question voices associated with the live broadcast content can be extracted as live broadcast language data. Any method can be used to achieve the recognition of question voices, and this disclosure does not limit this. For example, keywords associated with the live broadcast content and the host user's tone can be identified, and voice data containing keywords and with a questioning tone can be extracted.

[0069] Further, based on any of the above embodiments, step 204 includes:

[0070] Acquire the auxiliary broadcast copy generated by the language model based on the live broadcast data, where the auxiliary broadcast copy is the reply content generated based on the question content.

[0071] The preset virtual assistant is controlled to simulate the body movements when reading the assistant copy and play the voice content corresponding to the assistant copy.

[0072] In this embodiment, after acquiring the live broadcast data, the live broadcast data can be input into a preset language model. The language model can respond to the host user's questions and generate a corresponding auxiliary broadcast copy. The auxiliary broadcast copy is the response content generated based on the question content.

[0073] In order to simulate the live broadcast effect of the interaction between the virtual assistant and the anchor user, the preset virtual assistant can be controlled to simulate the body movements when reading the assistant copy and play the voice content corresponding to the assistant copy.

[0074] The live broadcast assistance method provided in this embodiment provides users with a virtual assistant function, so that users can realize two-person live broadcast operations with a virtual assistant based on the virtual assistant function, and then can interact with the virtual assistant to better present the live broadcast content and improve the live broadcast effect.

[0075] FIG4 is a flow chart of a live broadcast assistance method provided by another embodiment of the present disclosure. Based on any of the above embodiments, as shown in FIG4 , the target assistance function may be a virtual assistant function. The virtual assistant can answer questions raised by the anchor user based on the data processing results output by the language model. Step 203 includes:

[0076] Step 401: Determine at least one live broadcast content corresponding to the live broadcast, and obtain associated data of the at least one live broadcast content, wherein the associated data includes one or more of attribute information, description information, and virtual resource information of the live broadcast content.

[0077] Step 402: Determine the associated data of the at least one live broadcast content as the live broadcast data.

[0078] In this embodiment, under the virtual assistant function, the host user can ask questions about at least one live broadcast content corresponding to the live broadcast, so that the virtual assistant can answer the questions raised by the host user based on the data processing results output by the language model.

[0079] To enable the language model to raise questions related to live content, at least one live content corresponding to the live broadcast may be determined, and associated data for the at least one live content may be obtained. The associated data may include one or more of attribute information, description information, and virtual resource information of the live content. The associated data for the at least one live content may be determined as live data.

[0080] For example, the live broadcast content may be product content, and the associated data may include product introduction information, product attribute information, and product-related discount information.

[0081] Further, based on any of the above embodiments, step 204 includes:

[0082] The live broadcast data is input into a preset language model.

[0083] Acquire a supporting copy generated by the language model based on the live broadcast data, where the supporting copy is question content generated based on associated data of the at least one live broadcast content.

[0084] When it is determined that the time for which the host user stops speaking exceeds a preset time threshold, the preset virtual assistant is controlled to simulate the body movements when reading the assistant copy and play the voice content corresponding to the assistant copy.

[0085] In this embodiment, in order to prevent the virtual assistant from interrupting the host user's speech with questions, when it is determined that the time when the host user stops speaking exceeds a preset time threshold, the virtual assistant can be controlled to simulate reading the assistant copy generated based on the live broadcast data to achieve interactive operations with the host user.

[0086] Language models are deep learning models pre-trained using large amounts of text data. They can generate natural language text or understand the meaning of text. Language models can handle a variety of natural language tasks, such as text classification, question-answering, and conversation. After live broadcast data is fed into the language model, it can output support text, which is generated based on the relevant data of at least one live broadcast content.

[0087] To simulate the live broadcast effect of a virtual assistant interacting with the host user, if the host user stops speaking for a predetermined time threshold, the preset virtual assistant can be controlled to simulate the body movements of reading the assistant's copy and play the corresponding voice content. This allows the host user to respond to the question after the virtual assistant asks it.

[0088] As an implementable method, the live broadcast data can be associated data of the live broadcast content, such as one or more of the attribute information, description information, and virtual resource information of the live broadcast content. The anchor user can set the associated data before starting the live broadcast, or the anchor user can change the associated data according to the real-time situation of the live broadcast content during the live broadcast. Therefore, the live broadcast data can be input into the language model before the anchor user starts the broadcast, or the updated live broadcast data can be input into the language model during the live broadcast, or the live broadcast data can be input into the language model after it is detected that the anchor user stops speaking. The present disclosure does not limit the execution order of the steps of inputting the live broadcast data into the language model.

[0089] The live broadcast assistance method provided in this embodiment provides users with a virtual assistant function, so that users can realize two-person live broadcast operations with a virtual assistant based on the virtual assistant function, and then can interact with the virtual assistant to better present the live broadcast content and improve the live broadcast effect.

[0090] Furthermore, based on any of the above embodiments, controlling the preset virtual assistant to simulate the body movements when reading the assistant copy and playing the voice content corresponding to the assistant copy includes:

[0091] The auxiliary broadcast copy is converted into the voice content through a preset text-to-speech algorithm.

[0092] Based on the voice content, the virtual assistant is driven to simulate the body movements when reading the assistant copy, the virtual assistant is rendered into a two-dimensional image, and the two-dimensional image is combined with the video frame of the current live broadcast.

[0093] The current live broadcast and the voice content are played simultaneously through video, audio and picture synchronization technology.

[0094] In this embodiment, after obtaining the auxiliary broadcast copy output by the language model, the auxiliary broadcast copy can be converted into voice content through a preset text-to-speech algorithm. Among them, any text-to-speech algorithm can be used to implement the conversion operation of the auxiliary broadcast copy, and this disclosure does not limit this.

[0095] Furthermore, after obtaining the language content, the virtual assistant can be driven based on the voice content to simulate the body movements when reading the assistant copy. The body movements include but are not limited to lip movements, hand movements, body movements, etc.

[0096] Furthermore, in order to achieve the effect of interaction between the virtual assistant and the anchor user, the three-dimensional virtual assistant can be rendered into multiple frames of two-dimensional images, and each frame of the two-dimensional image can be combined with the current live video frame in chronological order.

[0097] In order to ensure that the current live broadcast and voice content have consistent audio and video, the current live broadcast and voice content can be played simultaneously through video audio and video synchronization technology.

[0098] The live broadcast assistance method provided in this embodiment can simulate the live broadcast effect of the interaction between the virtual assistant and the anchor by displaying the image of the virtual assistant during the live broadcast and playing the voice content generated based on the assistant copy, so that the live broadcast process is no longer monotonous and boring, and can better introduce the live broadcast content, thereby improving the live broadcast effect.

[0099] Optionally, the target auxiliary function may include a prompting function. When a host user is performing a solo live broadcast, the host user may need to introduce a product or interact with the audience. To ensure that the host user can perform live broadcast operations smoothly, a data processing result for prompting can be generated based on the host data, and the prompting operation can then be performed based on the data processing result.

[0100] FIG5 is a flow chart of a live broadcast assistance method provided by another embodiment of the present disclosure. Based on any of the above embodiments, the target assistance function may include a prompting function. As shown in FIG5 , step 203 includes:

[0101] Step 501: Determine at least one live broadcast content corresponding to the live broadcast.

[0102] Step 502: Obtain associated data of the at least one live content, and determine the associated data of the at least one live content as the live data, wherein the associated data includes one or more of attribute information, description information, and virtual resource information of the live content.

[0103] In this embodiment, for some anchor users with poor language expression ability, when facing the camera, they may not know where to start speaking, nor how to continue speaking, let alone how to impress the audience. In order to solve the above problems, a prompting function can be provided.

[0104] When the target auxiliary function is a prompt function, at least one live content corresponding to the live broadcast can be determined. Associated data for the at least one live content is obtained and determined as live data. The associated data includes one or more of the following: attribute information, description information, and virtual resource information of the live content. For example, the live content can be product content. The associated data can include product introduction information, product attribute information, and product-related discount information.

[0105] The language model may be a pre-trained language model. After inputting the associated data, the language model may generate live broadcast copy related to the product that is logically coherent, information-rich, and fresh in expression based on the input product information.

[0106] Further, based on any of the above embodiments, step 204 includes:

[0107] Obtain the live broadcast text output by the language model.

[0108] Control a preset prompting device to display the live broadcast copy, so that the user can view the live broadcast copy on the prompting device.

[0109] In this embodiment, after obtaining the associated data of at least one live content, the associated data of at least one live content can be input into a language model. The language model can generate a live text that is logically coherent, rich in information, and fresh in expression based on the associated data of at least one live content.

[0110] Furthermore, a prompting device can be pre-set. After obtaining the live broadcast text output by the language model, the prompting device can be controlled to display the live broadcast text. Thus, the host user can perform a more high-quality live broadcast operation based on the live broadcast text displayed on the prompting device.

[0111] The live broadcast assistance method provided in this embodiment performs prompting operations based on the live broadcast content during the live broadcast process, thereby eliminating the need for the host user to organize language to perform live broadcast operations. The host user can perform live broadcast operations more smoothly based on the prompting content.

[0112] Optionally, this targeted assistance function may include a customer service assistance function. Repeatedly answering similar questions in the comment section during each live broadcast can seriously disrupt the merchant's live broadcast rhythm and reduce live broadcast efficiency. Therefore, the customer assistance function can extract comments related to the live broadcast in the comment section and respond to them based on the data processing results output by the language model, thereby improving the live broadcast effect.

[0113] FIG6 is a flow chart of a live broadcast assistance method provided by another embodiment of the present disclosure. Based on any of the above embodiments, the target assistance function may include a customer service assistance function. As shown in FIG6 , step 203 includes:

[0114] Step 601: Filter at least one target comment associated with at least one live broadcast content corresponding to the current live broadcast according to a preset filtering condition.

[0115] Step 602: Determine the at least one comment content as the live broadcast data.

[0116] In this embodiment, during the live broadcast, viewers can post comments based on their actual needs. Some comments may be related to the live broadcast content, while others may be social, emoji, or other comments unrelated to the live broadcast content. For example, the host may introduce a product during the live broadcast, and viewers can comment on the product, such as what materials the product is made of and how long it lasts. Alternatively, viewers can comment on other content, such as emojis or compliments to the host's comments.

[0117] During the live broadcast, if the host user frequently replies to repeated comments, it may lead to poor live broadcast results. If the host user does not reply to questions raised by the audience, it may cause the audience to have a poor experience of the live broadcast and lead to audience loss.

[0118] Therefore, the user can select the customer service assistance function as the target assistance function in the function list. The customer service assistance function can respond to the content related to the live broadcast content in the comment area.

[0119] Optionally, at least one target comment associated with at least one live broadcast content corresponding to the current live broadcast can be filtered according to preset filtering conditions. The preset filtering conditions may include extracting comment information at a preset time interval, extracting comments at a preset comment quantity interval, or identifying comments based on a preset keyword recognition model and extracting comments containing preset keywords associated with the live broadcast content. The host user can set the filtering conditions according to actual needs, and this disclosure does not impose any restrictions on this.

[0120] After obtaining at least one target comment content associated with at least one live broadcast content corresponding to the current live broadcast, the at least one comment content may be determined as the live broadcast data.

[0121] Further, based on any of the above embodiments, step 204 includes:

[0122] Obtain the reply text output by the language model for each comment content.

[0123] For each comment content, the reply text is displayed in a display area associated with the comment content.

[0124] In this embodiment, after obtaining at least one target review content, the at least one review content may be input into a preset language model, which may output a reply text to the review content.

[0125] Furthermore, for each comment content, a reply text may be displayed in the display area associated with the comment content. For example, the reply text may be displayed below the comment content so that the audience can view the reply text more intuitively.

[0126] Alternatively, for each comment, when displaying the reply text corresponding to the comment, the viewer who posted the comment may be reminded so that the viewer can view the reply text more intuitively.

[0127] The live broadcast assistance method provided in this embodiment filters the comments related to the live broadcast content and automatically replies based on the data processing results output by the language model, so that the host user does not need to reply to repetitive and low-quality questions during the live broadcast, avoiding the impact of replying to comments on the live broadcast process, and effectively improving the live broadcast effect.

[0128] Figure 7 is a structural diagram of the live broadcast assistance device provided by an embodiment of the present disclosure. As shown in Figure 7, the device includes: an acquisition module 71, a determination module 72, a processing module 73, and an auxiliary module 74. Among them, the acquisition module 71 is used to obtain a live broadcast assistance request, and display a preset function list based on the live broadcast assistance request, and the function list includes at least one live broadcast assistance function. The determination module 72 is used to determine at least one target auxiliary function selected by the anchor user in response to the selection operation of the anchor user in the function list. The processing module 73 is used to obtain live broadcast data matching the at least one target auxiliary function, wherein the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and related data of the live broadcast content. The auxiliary module 74 is used to input the live broadcast data into a preset language model, and perform live broadcast assistance operations based on the data processing results output by the language model.

[0129] Furthermore, based on any of the above embodiments, the target auxiliary function includes a virtual assistant function, and the processing module is used to: determine at least one live broadcast content corresponding to the current live broadcast, and obtain associated data of the at least one live broadcast content, wherein the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content. The live voice data of the anchor user during the live broadcast is obtained, and the live voice data is converted into text content based on a preset voice recognition algorithm, wherein the live voice data includes the content of questions raised by the anchor user based on the live broadcast content. The associated data of the at least one live broadcast content and the text content corresponding to the live voice data are determined as the live data.

[0130] Furthermore, based on any of the above embodiments, the auxiliary module is configured to: obtain an auxiliary broadcast copy generated by the language model based on the live broadcast data, wherein the auxiliary broadcast copy is a response generated based on the question content; control a preset virtual assistant to simulate the body movements of reading the auxiliary broadcast copy and play the voice content corresponding to the auxiliary broadcast copy.

[0131] Furthermore, based on any of the above embodiments, the target assistance function includes a virtual broadcast assist function, and the processing module is configured to: determine at least one live broadcast content corresponding to the current live broadcast, obtain associated data of the at least one live broadcast content, wherein the associated data includes one or more of attribute information, description information, and virtual resource information of the live broadcast content, and determine the associated data of the at least one live broadcast content as the live broadcast data.

[0132] Furthermore, based on any of the above embodiments, the auxiliary module is configured to: input the live broadcast data into a preset language model; obtain an auxiliary broadcast copy generated by the language model based on the live broadcast data, wherein the auxiliary broadcast copy is question content generated based on the associated data of the at least one live broadcast content; and, when it is determined that the time for which the host user has stopped speaking exceeds a preset time threshold, control a preset virtual assistant to simulate the body movements of reading the auxiliary broadcast copy and play the voice content corresponding to the auxiliary broadcast copy.

[0133] Furthermore, based on any of the above embodiments, the auxiliary module is configured to control a preset virtual assistant to simulate reading the auxiliary module, and is configured to: convert the assistant text into the voice content using a preset text-to-speech algorithm; drive the virtual assistant to simulate body movements when reading the assistant text based on the voice content; render the virtual assistant into a two-dimensional image; and combine the two-dimensional image with the video frame of the current live broadcast. The current live broadcast and the voice content are simultaneously played using video and audio synchronization technology.

[0134] Furthermore, based on any of the above embodiments, the target auxiliary function includes a prompting function, and the processing module is configured to: determine at least one live content corresponding to the live broadcast; obtain associated data of the at least one live content; and determine the associated data of the at least one live content as the live data, wherein the associated data includes one or more of attribute information, description information, and virtual resource information of the live content.

[0135] Furthermore, based on any of the above embodiments, the auxiliary module is configured to: obtain the live broadcast copy output by the language model, and control a preset prompting device to display the live broadcast copy, so that the user can view the live broadcast copy on the prompting device.

[0136] Furthermore, based on any of the above embodiments, the target auxiliary function includes a customer service auxiliary function, and the processing module is configured to: filter at least one target comment associated with at least one live broadcast content corresponding to the current live broadcast according to a preset filtering condition from at least one comment associated with the current live broadcast, and determine the at least one comment as the live broadcast data.

[0137] Furthermore, based on any of the above embodiments, the auxiliary module is configured to: obtain a reply text output by the language model for each comment content, and display the reply text in a display area associated with each comment content.

[0138] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0139] In order to implement the above embodiments, the embodiments of the present disclosure further provide a computer-readable storage medium, in which computer-executable instructions are stored. When the processor executes the computer-executable instructions, the live broadcast assistance method as described in any of the above embodiments is implemented.

[0140] In order to implement the above embodiments, the embodiments of the present disclosure further provide a computer program product, including a computer program, which, when executed by a processor, implements the live broadcast assistance method as described in any of the above embodiments.

[0141] In order to implement the above embodiment, the present disclosure further provides an electronic device, including: a processor and a memory;

[0142] The memory stores computer-executable instructions;

[0143] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the live broadcast assistance method as described in any of the above embodiments.

[0144] FIG8 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. The electronic device 800 may be a terminal device or a server. The terminal device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. The electronic device shown in FIG8 is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0145] As shown in Figure 8, the electronic device 800 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the electronic device 800 are also stored in the RAM 803. The processing device 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0146] Typically, the following devices may be connected to the I / O interface 805: an input device 806 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 808 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 809. The communication device 809 may allow the electronic device 800 to communicate with other devices wirelessly or by wire to exchange data. Although FIG8 shows an electronic device 800 having various devices, it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0147] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 809, or installed from the storage device 808, or installed from the ROM 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0148] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0149] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0150] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0151] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet Service Provider).

[0152] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0153] The units involved in the embodiments described in this disclosure may be implemented in software or hardware. In some cases, the name of a unit does not limit the unit itself. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses."

[0154] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0155] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0156] In a first aspect, according to one or more embodiments of the present disclosure, a live broadcast assistance method is provided, comprising: obtaining a live broadcast assistance request, and displaying a preset function list based on the live broadcast assistance request, wherein the function list includes at least one live broadcast assistance function; in response to a selection operation of the anchor user in the function list, determining at least one target assistance function selected by the anchor user; obtaining live broadcast data matching the at least one target assistance function, wherein the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and associated data of the live broadcast content; inputting the live broadcast data into a preset language model, and performing a live broadcast assistance operation based on a data processing result output by the language model.

[0157] According to one or more embodiments of the present disclosure, the target auxiliary function includes a virtual assistant function, and the obtaining of live broadcast data matching the at least one target auxiliary function includes: determining at least one live broadcast content corresponding to the current live broadcast, and obtaining associated data of the at least one live broadcast content, wherein the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content; obtaining the live voice data of the anchor user during the live broadcast, and converting the live voice data into text content based on a preset voice recognition algorithm, wherein the live voice data includes the content of questions raised by the anchor user based on the live broadcast content; and determining the associated data of the at least one live broadcast content and the text content corresponding to the live voice data as the live data.

[0158] According to one or more embodiments of the present disclosure, the live broadcast assistance operation is performed based on the data processing results output by the language model, including: obtaining the auxiliary broadcast copy generated by the language model based on the live broadcast data, the auxiliary broadcast copy is the reply content generated based on the question content; controlling the preset virtual assistant to simulate the body movements when reading the auxiliary broadcast copy and play the voice content corresponding to the auxiliary broadcast copy.

[0159] According to one or more embodiments of the present disclosure, the target auxiliary function includes a virtual assisting function, and the obtaining of live broadcast data matching the at least one target auxiliary function includes: determining at least one live broadcast content corresponding to the current live broadcast, and obtaining associated data of the at least one live broadcast content, wherein the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content; and determining the associated data of the at least one live broadcast content as the live broadcast data.

[0160] According to one or more embodiments of the present disclosure, the live broadcast data is input into a preset language model, and live broadcast auxiliary operations are performed based on the data processing results output by the language model, including: inputting the live broadcast data into a preset language model; obtaining the auxiliary broadcast copy generated by the language model based on the live broadcast data, the auxiliary broadcast copy being question content generated based on the associated data of the at least one live broadcast content; when it is determined that the time for the anchor user to stop speaking exceeds a preset time threshold, controlling a preset virtual assistant to simulate the body movements when reading the auxiliary broadcast copy and playing the voice content corresponding to the auxiliary broadcast copy.

[0161] According to one or more embodiments of the present disclosure, the control of the preset virtual assistant to simulate the body movements when reading the assistant copy and play the voice content corresponding to the assistant copy includes: converting the assistant copy into the voice content through a preset text-to-speech algorithm; driving the virtual assistant to simulate the body movements when reading the assistant copy based on the voice content, rendering the virtual assistant into a two-dimensional image, and combining the two-dimensional image with the video frame of the current live broadcast; and simultaneously playing the current live broadcast and the voice content through video audio and picture synchronization technology.

[0162] According to one or more embodiments of the present disclosure, the target auxiliary function includes a prompting function, and the obtaining of live broadcast data matching the at least one target auxiliary function includes: determining at least one live broadcast content corresponding to the current live broadcast; obtaining associated data of the at least one live broadcast content, and determining the associated data of the at least one live broadcast content as the live broadcast data, wherein the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content.

[0163] According to one or more embodiments of the present disclosure, the live broadcast auxiliary operation based on the data processing result output by the language model includes: obtaining the live broadcast copy output by the language model; controlling a preset prompting device to display the live broadcast copy, so that the user can view the live broadcast copy on the prompting device.

[0164] According to one or more embodiments of the present disclosure, the target auxiliary function includes a customer service auxiliary function, and the obtaining of live broadcast data matching the at least one target auxiliary function includes: filtering at least one target comment content associated with at least one live broadcast content corresponding to the current live broadcast from at least one comment associated with the current live broadcast according to preset filtering conditions; and determining the at least one comment content as the live broadcast data.

[0165] According to one or more embodiments of the present disclosure, the live broadcast auxiliary operation based on the data processing results output by the language model includes: obtaining the reply text output by the language model for each comment content; and displaying the reply text in the display area associated with the comment content for each comment content.

[0166] In a second aspect, according to one or more embodiments of the present disclosure, a live broadcast auxiliary device is provided, comprising:

[0167] an acquisition module, configured to acquire a live broadcast assistance request, and display a preset function list based on the live broadcast assistance request, wherein the function list includes at least one live broadcast assistance function;

[0168] A determination module, configured to determine at least one target auxiliary function selected by the anchor user in response to a selection operation by the anchor user in the function list;

[0169] a processing module, configured to obtain live broadcast data matching the at least one target auxiliary function, wherein the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and associated data of live broadcast content;

[0170] The auxiliary module is used to input the live broadcast data into a preset language model and perform live broadcast auxiliary operations based on the data processing results output by the language model.

[0171] According to one or more embodiments of the present disclosure, the target assistance function includes a virtual assistant function, and the processing module is used to: determine at least one live broadcast content corresponding to the current live broadcast, and obtain associated data of the at least one live broadcast content, wherein the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content; obtain the live voice data of the anchor user during the live broadcast, and convert the live voice data into text content based on a preset voice recognition algorithm, wherein the live voice data includes the question content raised by the anchor user based on the live broadcast content; determine the associated data of the at least one live broadcast content and the text content corresponding to the live voice data as the live data.

[0172] According to one or more embodiments of the present disclosure, the auxiliary module is used to: obtain the auxiliary copy generated by the language model based on the live broadcast data, wherein the auxiliary copy is the reply content generated based on the question content; control the preset virtual assistant to simulate the body movements when reading the auxiliary copy and play the voice content corresponding to the auxiliary copy.

[0173] According to one or more embodiments of the present disclosure, the target auxiliary function includes a virtual assisting function, and the processing module is used to: determine at least one live broadcast content corresponding to the current live broadcast, and obtain associated data of the at least one live broadcast content, wherein the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content; and determine the associated data of the at least one live broadcast content as the live broadcast data.

[0174] According to one or more embodiments of the present disclosure, the auxiliary module is used to: input the live broadcast data into a preset language model; obtain the auxiliary broadcast copy generated by the language model based on the live broadcast data, wherein the auxiliary broadcast copy is question content generated based on the associated data of the at least one live broadcast content; when it is determined that the time for the host user to stop speaking exceeds a preset time threshold, control the preset virtual assistant to simulate the body movements when reading the auxiliary broadcast copy and play the voice content corresponding to the auxiliary broadcast copy.

[0175] According to one or more embodiments of the present disclosure, the auxiliary module is controlled to simulate the reading of the auxiliary module, and is used to: convert the auxiliary text into the voice content through a preset text-to-speech algorithm; drive the virtual assistant to simulate the body movements when reading the auxiliary text based on the voice content, render the virtual assistant into a two-dimensional image, and combine the two-dimensional image with the video frame of the current live broadcast; and simultaneously play the current live broadcast and the voice content through video audio and video synchronization technology.

[0176] According to one or more embodiments of the present disclosure, the target auxiliary function includes a prompting function, and the processing module is used to: determine at least one live broadcast content corresponding to the current live broadcast; obtain associated data of the at least one live broadcast content, and determine the associated data of the at least one live broadcast content as the live broadcast data, wherein the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content.

[0177] According to one or more embodiments of the present disclosure, the auxiliary module is used to: obtain the live broadcast copy output by the language model; control a preset prompting device to display the live broadcast copy, so that the user can view the live broadcast copy on the prompting device.

[0178] According to one or more embodiments of the present disclosure, the target assistance function includes a customer service assistance function, and the processing module is used to: filter at least one target comment content associated with at least one live broadcast content corresponding to the current live broadcast from at least one comment associated with the current live broadcast according to preset filtering conditions; and determine the at least one comment content as the live broadcast data.

[0179] According to one or more embodiments of the present disclosure, the auxiliary module is used to: obtain the reply text output by the language model for each comment content; and display the reply text in a display area associated with the comment content for each comment content.

[0180] In a third aspect, according to one or more embodiments of the present disclosure, there is provided an electronic device, comprising: at least one processor and a memory;

[0181] The memory stores computer-executable instructions;

[0182] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the live broadcast assistance method described in the first aspect and various possible designs of the first aspect.

[0183] In a fourth aspect, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer execution instructions. When the processor executes the computer execution instructions, the live broadcast assistance method described in the first aspect and various possible designs of the first aspect is implemented.

[0184] In a fifth aspect, according to one or more embodiments of the present disclosure, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the live broadcast assistance method as described in the first aspect and various possible designs of the first aspect.

[0185] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0186] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0187] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A live broadcast assisting method, comprising: Acquire a live broadcast assistance request, and display a preset function list based on the live broadcast assistance request, wherein the function list includes at least one live broadcast assistance function; In response to a selection operation of the anchor user in the function list, determining at least one target auxiliary function selected by the anchor user; Acquire live broadcast data matching the at least one target auxiliary function, wherein the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and associated data of live broadcast content; The live broadcast data is input into a preset language model, and live broadcast auxiliary operations are performed based on the data processing results output by the language model.

2. The method according to claim 1, wherein: The target auxiliary function includes a virtual broadcast assisting function, and the acquiring of live broadcast data matching the at least one target auxiliary function includes: Determine at least one live broadcast content corresponding to the live broadcast, and obtain associated data of the at least one live broadcast content, wherein the associated data includes one or more of attribute information, description information, and virtual resource information of the live broadcast content; Acquire live voice data of the anchor user during the live broadcast process, and convert the live voice data into text content based on a preset voice recognition algorithm, wherein the live voice data includes question content raised by the anchor user based on the live broadcast content; The associated data of the at least one live broadcast content and the text content corresponding to the live broadcast voice data are determined as the live broadcast data.

3. The method according to claim 2, wherein: The live broadcast auxiliary operation is performed based on the data processing result output by the language model, including: Obtaining a broadcast assistance copy generated by the language model based on the live broadcast data, wherein the broadcast assistance copy is a reply content generated based on the question content; The preset virtual assistant is controlled to simulate the body movements when reading the assistant copy and play the voice content corresponding to the assistant copy.

4. The method according to claim 1, wherein: The target auxiliary function includes a virtual broadcast assisting function, and the acquiring of live broadcast data matching the at least one target auxiliary function includes: Determine at least one live broadcast content corresponding to the live broadcast, and obtain associated data of the at least one live broadcast content, wherein the associated data includes one or more of attribute information, description information, and virtual resource information of the live broadcast content; The associated data of the at least one live broadcast content is determined as the live broadcast data.

5. The method according to claim 4, wherein: The step of inputting the live broadcast data into a preset language model and performing a live broadcast auxiliary operation based on a data processing result output by the language model includes: Inputting the live broadcast data into the preset language model; Acquire a broadcast assistance copy generated by the language model based on the live broadcast data, wherein the broadcast assistance copy is question content generated based on associated data of the at least one live broadcast content; When it is determined that the time for which the host user stops speaking exceeds a preset time threshold, the preset virtual assistant is controlled to simulate the body movements when reading the assistant copy and play the voice content corresponding to the assistant copy.

6. The method according to claim 3 or 5, wherein: The controlling of the preset virtual assistant to simulate the body movements when reading the assistant copy and playing the voice content corresponding to the assistant copy includes: Converting the auxiliary broadcast copy into the voice content through a preset text-to-speech algorithm; Based on the voice content, the virtual assistant is driven to simulate the body movements when reading the assistant copy, the virtual assistant is rendered into a two-dimensional image, and the two-dimensional image is combined with the current live video frame; The current live broadcast and the voice content are played simultaneously through video, audio and picture synchronization technology.

7. The method according to claim 1, wherein: The target auxiliary function includes a prompting function, and the acquiring of live broadcast data matching the at least one target auxiliary function includes: Determine at least one live broadcast content corresponding to the live broadcast; The associated data of the at least one live broadcast content is obtained, and the associated data of the at least one live broadcast content is determined as the live broadcast data, wherein the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content.

8. The method according to claim 7, wherein: The live broadcast auxiliary operation is performed based on the data processing result output by the language model, including: Obtaining the live broadcast copy output by the language model; Control a preset prompting device to display the live broadcast copy, so that the user can view the live broadcast copy on the prompting device.

9. The method according to claim 1, wherein: The target auxiliary function includes a customer service auxiliary function, and the acquiring of live broadcast data matching the at least one target auxiliary function includes: Filtering at least one target comment content associated with at least one live broadcast content corresponding to the current live broadcast from at least one comment associated with the current live broadcast according to a preset filtering condition; The at least one comment content is determined as the live broadcast data.

10. The method according to claim 9, wherein: The live broadcast auxiliary operation is performed based on the data processing result output by the language model, including: Obtaining the reply text output by the language model for each comment content; For each comment content, the reply text is displayed in a display area associated with the comment content.

11. A live broadcast auxiliary device, comprising: an acquisition module, configured to acquire a live broadcast assistance request, and display a preset function list based on the live broadcast assistance request, wherein the function list includes at least one live broadcast assistance function; A determination module, configured to determine at least one target auxiliary function selected by the anchor user in response to a selection operation of the anchor user in the function list; A processing module is configured to obtain live broadcast data matching the at least one target auxiliary function, wherein the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and associated data of live broadcast content; The auxiliary module is configured to input the live broadcast data into a preset language model and perform live broadcast auxiliary operations based on the data processing results output by the language model.

12. An electronic device comprising a processor and a memory, in, The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the live broadcast assistance method as described in any one of claims 1 to 10.

13. A computer-readable storage medium storing computer-executable instructions, wherein: When the processor executes the computer-executable instructions, the live broadcast assistance method as described in any one of claims 1 to 10 is implemented.

14. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method for live broadcast assistance as described in any one of claims 1 to 10 is implemented.

Images