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

Abstract

The embodiment of the invention provides a live broadcast auxiliary method, device and equipment, a computer readable storage medium and a product, and the method comprises the steps: obtaining a live broadcast auxiliary request, displaying a preset function list based on the live broadcast auxiliary request, and enabling the function list to comprise at least one live broadcast auxiliary 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; live broadcast data matched with the at least one target auxiliary function is acquired, and the live broadcast data comprises at least one of live broadcast voice data, live broadcast comment data and associated data of live broadcast content; and inputting the live broadcast data into a preset language model, and performing live broadcast auxiliary operation based on a data processing result output by the language model. Therefore, the auxiliary live broadcast function can be individually provided for the anchor user based on the selection operation of the anchor user, the anchor user does not need to organize a language by himself to perform live broadcast operation, and the live broadcast effect and the live broadcast efficiency can be improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of Internet technologies, and in particular, to a live broadcast assistance method, apparatus, device, computer-readable storage medium, and product. Background Art

[0002] With the continuous development of Internet technologies, webcasting has gradually entered the lives of users. More and more users conduct interactive operations such as dialogue interviews and product demonstrations with audiences through webcasting. Webcasting is also increasingly applied in the e-commerce field. Anchor users can introduce products through webcasting so that audiences can have a more detailed understanding of the products.

[0003] However, during webcasting, due to the weak writing and expression abilities of some anchor users, the atmosphere in the live broadcast room is relatively dull, resulting in poor live broadcast effects. Therefore, how to assist anchor users in live broadcasting to improve the live broadcast effects has become an urgent problem to be solved. Summary of the Invention

[0004] Embodiments of the present disclosure provide a live broadcast assistance method, apparatus, device, computer-readable storage medium, and product for solving the technical problem of poor live broadcast effects.

[0005] In a first aspect, embodiments of the present disclosure provide a live broadcast assistance method, including:

[0006] Obtaining a live broadcast assistance request, and displaying a preset function list based on the live broadcast assistance request, where the function list includes at least one live broadcast assistance function;

[0007] Responding to a selection operation of an anchor user in the function list, and determining at least one target assistance function selected by the anchor user;

[0008] Obtaining live broadcast data matching the at least one target assistance function, where the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and associated data of live broadcast content;

[0009] 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.

[0010] In a second aspect, embodiments of the present disclosure provide a live broadcast assistance apparatus, including:

[0011] An obtaining module, configured to obtain a live broadcast assistance request, and display a preset function list based on the live broadcast assistance request, where the function list includes at least one live broadcast assistance function;

[0012] A determination module, configured to determine at least one target auxiliary function selected by the host user in response to a selection operation of the host user in the function list;

[0013] A processing module, configured to obtain live data matching the at least one target auxiliary function, where the live data includes at least one of live voice data, live comment data, and associated data of live content;

[0014] An auxiliary module, configured to input the live data into a preset language model and perform a live auxiliary operation based on a data processing result output by the language model.

[0015] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0016] The memory stores computer-executable instructions;

[0017] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the live auxiliary method described in the first aspect and various possible designs of the first aspect above.

[0018] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored. When the processor executes the computer-executable instructions, the live auxiliary method described in the first aspect and various possible designs of the first aspect above is implemented.

[0019] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, where when the computer program is executed by a processor, the live auxiliary method described in the first aspect and various possible designs of the first aspect above is implemented.

[0020] The live auxiliary method, device, device, computer-readable storage medium, and product provided in this embodiment, after obtaining a live auxiliary request, display a preset function list, and display at least one live auxiliary function in the function list. Perform an operation of obtaining live data based on at least one target auxiliary function selected by the host user, so that the obtained live data can be input into a preset language model, which can process the live data to obtain a data processing result, and the data result can be used to assist the live broadcast. Thus, it is possible to provide an auxiliary live broadcast function for the host user personalized based on the selection operation of the host user, without the host user having to organize language by himself for the live broadcast operation, which can improve the live broadcast effect and live broadcast efficiency. Description of the Drawings

[0021] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0022] Figure 1 Schematic diagram of the system architecture on which the present disclosure is based;

[0023] Figure 2 Schematic flowchart of the live broadcast assistance method provided by an embodiment of the present disclosure;

[0024] Figure 3 Schematic flowchart of the live broadcast assistance method provided by another embodiment of the present disclosure;

[0025] Figure 4 Schematic flowchart of the live broadcast assistance method provided by another embodiment of the present disclosure;

[0026] Figure 5 Schematic flowchart of the live broadcast assistance method provided by another embodiment of the present disclosure;

[0027] Figure 6 Schematic flowchart of the live broadcast assistance method provided by another embodiment of the present disclosure;

[0028] Figure 7 Schematic diagram of the structure of the live broadcast assistance device provided by an embodiment of the present disclosure;

[0029] Figure 8 Schematic diagram of the structure of the electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some, but not all, of the embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present disclosure.

[0031] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the users and the users' authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0032] For example, when a user's active request is received, a prompt message is sent to the user to clearly prompt the user that the operation requested by the user will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, an application, a server, or a storage medium that performs the operations of the present disclosure's technical solution based on the prompt message.

[0033] As an optional but non-limiting implementation manner, the manner of sending a prompt message to the user in response to receiving the user's active request may be, for example, a pop-up window manner, and the prompt message may be presented in text in the pop-up window. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0034] It can be understood that the above notification and user authorization process is only illustrative and does not limit the implementation manner of the present disclosure. Other manners that comply with relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0035] In order to solve the technical problem of poor live broadcast effects caused by the weak expression ability of the host user, 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 to any live broadcast scenario.

[0037] In current network live broadcasts, generally, the host user needs to organize language by himself / herself to introduce products and interact with the audience. For host users with poor language expression ability, poor communication with the audience may lead to poor live broadcast effects and low popularity of the live broadcast room.

[0038] In the process of solving the above technical problems, the inventors found through research that in order to improve the live broadcast effect, multiple auxiliary live broadcast functions can be preset. Among them, each auxiliary live broadcast function can process the live broadcast data generated during the live broadcast through a preset language model to generate a data processing result for assisting the live broadcast. The host can directly perform live broadcast operations based on the data processing result, avoiding organizing language by himself / herself for the live broadcast. Among them, the language model can be pre-trained through big data, and it can flexibly generate a logically coherent and clearly expressed data processing result based on the live broadcast data. Furthermore, assisting the live broadcast based on the data processing result can obtain a relatively high-quality live broadcast effect.

[0039] The inventor further studies and finds that in order to enable the host user to conduct live broadcasts more flexibly, a function list can be displayed based on the auxiliary live broadcast request triggered by the user, and the multiple auxiliary live broadcast functions can be displayed in the function list for the user to select. Furthermore, auxiliary live broadcast operations can be performed based on at least one target auxiliary live broadcast function selected by the user.

[0040] Figure 1 Schematic diagram of the system architecture on which the present disclosure is based, as Figure 1 shown, the system architecture on which the present disclosure is based at least includes a terminal device 11 for performing live broadcast operations and a server 12, wherein a trained language model is pre-set in the server 12.

[0041] Based on the above system architecture, in response to the live broadcast assistance request triggered by the host user on the terminal device 11, a function list can be displayed on the terminal device 11 for the user to select. After the user determines at least one target auxiliary function, the live broadcast data generated by the host user during the live broadcast can be obtained. The live broadcast data is sent to the server 12, and data processing is performed based on the pre-set language model in the server 12 to obtain a data processing result. Furthermore, auxiliary live broadcast can be performed based on the data processing result.

[0042] Figure 2 Schematic diagram of the process of the live broadcast assistance method provided by an embodiment of the present disclosure, as Figure 2 shown, the method includes:

[0043] Step 201, obtain a live broadcast assistance request, and display a pre-set function list based on the live broadcast assistance request, where the function list includes at least one live broadcast assistance function.

[0044] The execution subject of this embodiment is a live broadcast assistance device. The live broadcast assistance device can be coupled to a terminal device for live broadcast. Thus, live broadcast assistance operations can be performed based on at least one target auxiliary function selected by the host user based on a pre-set language model. Among them, the language model can be coupled to the terminal device. Or, the language model can be coupled to a server communicatively connected to the terminal device.

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

[0046] Correspondingly, the live broadcast assistance device can obtain the live broadcast assistance request. In order to reduce the difficulty of the host user's live broadcast, at least one live broadcast assistance function can be provided in advance. Among them, the live broadcast assistance functions include but are not limited to virtual co-host functions, teleprompter functions, and intelligent customer service functions.

[0047] After receiving the live broadcast assistance request, a preset function list can be displayed, and at least one live broadcast assistance function is displayed in the function list. Thus, the user can perform a selection operation on the live broadcast assistance function according to actual needs.

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

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

[0050] Among them, the live broadcast assistance function can be implemented independently or in combination. For example, after the host user selects the virtual co-host function and the teleprompter function, the virtual co-host can ask questions to the host user so that the host user can answer the questions of the virtual co-host. When the host user cannot answer the question, the teleprompter function can display the answer information of the question on a preset teleprompter device so that the host user can perform live broadcast operations based on the answer information displayed on the teleprompter device.

[0051] Step 203: Obtain live broadcast data matching the at least one target assistance function, where 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.

[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 the at least one target assistance function can be obtained, where 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. 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 comment text published 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 promotion information, etc.

[0054] Step 204: Input the live broadcast data into a preset language model, and perform a live broadcast assistance operation based on the data processing result output by the language model.

[0055] In this embodiment, a language model can be pre-set. The language model can be a deep learning model pre-trained with a large amount of text data, which can generate natural language text or understand the meaning of language text. The language model can handle a variety of natural language tasks, such as text classification, question answering, dialogue, etc.

[0056] Therefore, after the live broadcast data is acquired, 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 method, 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 train the language model in a targeted manner to obtain the language models corresponding to the different auxiliary live broadcast functions. In the auxiliary live broadcast process, different language models can be used for data processing for different functions. The present disclosure does not limit this.

[0058] The live broadcast assistance method provided in this embodiment displays a preset function list after obtaining a live broadcast assistance request, and displays at least one live broadcast assistance function in the function list. The live broadcast data acquisition operation is performed based on at least one target auxiliary function selected by the anchor user, so that the acquired live broadcast data can be input into a preset language model, and the language model can perform data processing on the live broadcast data to obtain a data processing result, and the data result can be used to assist the live broadcast. Therefore, the anchor user can be provided with an auxiliary live broadcast function based on the selection operation of the anchor user in a personalized manner, without the anchor user having to organize language to perform live broadcast operations by himself, which can improve the live broadcast effect and efficiency.

[0059] Optionally, the target auxiliary function may be a virtual assistant broadcasting function. Under the virtual assistant broadcasting function, a virtual assistant broadcasting with a virtual three-dimensional image may be pre-set, and the virtual assistant broadcasting may read the data processing result output by the language model to achieve interaction with the anchor user and improve the fun of the live broadcasting 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 questions based on the questions raised by the virtual assistant.

[0061] Alternatively, under the virtual assistant function, the anchor 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 anchor user based on the data processing results output by the language model.

[0062] Figure 3 A flowchart of a live broadcast auxiliary method provided by another embodiment of the present disclosure is provided. Based on any of the above embodiments, Figure 3As shown, the target auxiliary function can be a virtual co-host function. The virtual co-host can ask questions about at least one live content corresponding to the live broadcast. Step 203 includes:

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

[0064] Step 302, obtain the live voice data of the host user during the live broadcast, and convert the live voice data into text content based on a preset speech recognition algorithm. The live voice data includes the question content proposed by the host user based on the live content.

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

[0066] In this embodiment, under the virtual co-host function, the virtual co-host can ask questions about at least one live content corresponding to the live broadcast, so that the host user can answer the questions proposed by the virtual co-host.

[0067] In order to enable the virtual co-host to answer the questions of the host user, it is possible to determine at least one live content corresponding to the current live broadcast and obtain the associated data of the at least one live content, where the associated data includes one or more of the attribute information, description information, and virtual resource information of the live content. Obtain the live voice data of the host user during the live broadcast, and convert the live voice data into text content based on a preset speech recognition algorithm. The live voice data includes the question content proposed by the host user based on the live content. Determine the associated data of the at least one live content and the text content corresponding to the live voice data as the live data.

[0068] Optionally, during the process of obtaining the live language data, the voice issued by the host user can be recognized, and the question voice associated with the live content can be extracted as the live language data. Any method can be used to implement the recognition of the question voice, and the present disclosure does not limit this. For example, keywords associated with the live content can be recognized, and the tone of the host user can be recognized, and the voice data including the keywords and having an interrogative tone can be extracted.

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

[0070] Obtain the co-host copywriting generated by the language model based on the live data, where the co-host copywriting is a reply content generated based on the question content.

[0071] Control the body movements of the preset virtual co-host when simulating reading the co-host copywriting and play the voice content corresponding to the co-host copywriting.

[0072] In this embodiment, after obtaining the live broadcast data, the live broadcast data can be input into a preset language model. The language model can answer the questions of the host user, generate a co-host copywriting corresponding to the question content, and the co-host copywriting is the answer content generated based on the question content.

[0073] In order to simulate the live broadcast effect of the interaction between the virtual co-host and the host user, the body movements of the preset virtual co-host when simulating reading the co-host copywriting can be controlled and the voice content corresponding to the co-host copywriting can be played.

[0074] The live broadcast assistance method provided in this embodiment provides a virtual co-host function for users, so that users can perform a two-person live broadcast operation based on this virtual co-host function, and then can perform interactive operations with the virtual co-host, better display the live broadcast content, and improve the live broadcast effect.

[0075] Figure 4 It is a schematic flowchart of the live broadcast assistance method provided in another embodiment of the present disclosure. On the basis of any of the above embodiments, as Figure 4 shown, the target assistance function can be a virtual co-host function. The virtual co-host can answer the questions raised by the host user based on the data processing result output by the language model. Step 203 includes:

[0076] Step 401, determine at least one live broadcast content corresponding to this live broadcast, and obtain the associated data of the at least one live broadcast content, where the associated data includes one or more of the 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 co-host function, the host user can ask questions about at least one live broadcast content corresponding to the live broadcast, so that the virtual co-host can answer the questions raised by the host user based on the data processing result output by the language model.

[0079] In order to enable the language model to ask questions related to the live broadcast content, at least one live broadcast content corresponding to this live broadcast can be determined, and the associated data of the at least one live broadcast content can be obtained, where the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content. Determine the associated data of the at least one live broadcast content as the live broadcast data.

[0080] For example, the live content can be product content. The associated data can be content such as product introduction information, product attribute information, and preferential information associated with the product.

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

[0082] Input the live data into a preset language model.

[0083] Obtain the co-host copywriting generated by the language model based on the live data, where the co-host copywriting is question content generated based on the associated data of the at least one live content.

[0084] When it is determined that the time when the host user stops speaking exceeds a preset time threshold, control the preset virtual co-host to simulate the body movements when reading the co-host copywriting and play the voice content corresponding to the co-host copywriting.

[0085] In this embodiment, in order to prevent the virtual co-host's questions from interrupting the host user's speech, when it is determined that the time when the host user stops speaking exceeds a preset time threshold, control the virtual co-host to simulate reading the co-host copywriting generated based on the live data, so as to achieve an interactive operation with the host user.

[0086] The language model can be a deep learning model pre-trained with a large amount of text data, which can generate natural language text or understand the meaning of language text. The language model can handle various natural language tasks, such as text classification, question answering, dialogue, etc. Thus, after inputting the live data into the language model, the language model can output the co-host copywriting, which is question content generated based on the associated data of the at least one live content.

[0087] In order to simulate the live effect of the interaction between the virtual co-host and the host user, when it is determined that the time when the host user stops speaking exceeds a preset time threshold, the preset virtual co-host can be controlled to simulate the body movements when reading the co-host copywriting and play the voice content corresponding to the co-host copywriting. Thus, after the virtual co-host asks a question, the host user can answer the question.

[0088] As an implementable manner, the live broadcast data may 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 host user may set the associated data before starting the live broadcast, or the host user may change the associated data according to the real-time situation of the live broadcast content during the live broadcast. Therefore, the live broadcast data may be input into the language model before the host user starts the live broadcast, or the updated live broadcast data may be input into the language model during the live broadcast, or the live broadcast data may be input into the language model after detecting that the host 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 enables the user to perform a dual live broadcast operation with the virtual co-host based on the virtual co-host function, and then enables the user to interact with the virtual co-host, better display the live broadcast content, and improve the live broadcast effect.

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

[0091] Converting the co-host copy into the voice content through a preset text-to-speech algorithm.

[0092] Driving the virtual co-host to simulate the body movements when reading the co-host copy aloud based on the voice content, rendering the virtual co-host as a two-dimensional image, and combining the two-dimensional image with the video frame of the current live broadcast.

[0093] Simultaneously playing the current live broadcast and the voice content through video audio-visual synchronization technology.

[0094] In this embodiment, after obtaining the co-host copy output by the language model, the co-host copy may be converted into voice content through a preset text-to-speech algorithm. Any text-to-speech algorithm may be used to implement the conversion operation of the co-host copy, and the present disclosure does not limit this.

[0095] Further, after obtaining the language content, the body movements when the virtual co-host simulates reading the co-host copy aloud may be driven based on the voice content. The body movements include but are not limited to lip movements, hand movements, body movements, etc.

[0096] Further, in order to achieve the effect of interaction between the virtual co-host and the host user, the three-dimensional virtual co-host may be rendered as multiple frames of two-dimensional images, and each frame of two-dimensional image is combined with the video frame of the current live broadcast in chronological order.

[0097] To ensure that the current live stream and voice content are in sync in terms of audio and video, the current live stream and voice content can also be played simultaneously through video and audio synchronization technology.

[0098] The live broadcast assistance method provided in this embodiment can simulate the live broadcast effect of the virtual co-host interacting with the host by displaying the image of the virtual co-host during the live broadcast and playing the voice content generated based on the co-host's copywriting, making the live broadcast process no longer monotonous and boring, and being able to better introduce the live broadcast content and improve the live broadcast effect.

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

[0100] Figure 5 As a schematic flowchart of the live broadcast assistance method provided in another embodiment of the present disclosure, based on any of the above embodiments, the target assistance function may include a teleprompter function. As Figure 5 shown, step 203 includes:

[0101] Step 501, determine at least one live broadcast content corresponding to this live broadcast.

[0102] Step 502, obtain the 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, where the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content.

[0103] In this embodiment, for some host users with poor language expression ability, when facing the camera, they may not know where to start, how to continue speaking continuously, or how to impress the audience. To solve the above problems, a teleprompter function can be provided.

[0104] When the target assistance function is the teleprompter function, at least one live broadcast content corresponding to this live broadcast can be determined. Obtain the 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, where the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content. For example, the live broadcast content can be product content. The associated data can be content such as product introduction information, product attribute information, and preferential information associated with the product.

[0105] The language model can be a pre-trained language model. After inputting the associated data, the language model can generate a live copywriting that is logically coherent, information-rich, and freshly expressed and associated with the product based on the input product information.

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

[0107] Obtain the live copywriting output by the language model.

[0108] Control a preset teleprompter device to display the live copywriting so that the user can view the live copywriting on the teleprompter 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 the language model. The language model can generate a live copywriting that is logically coherent, information-rich, and freshly expressed based on the obtained associated data of at least one live content.

[0110] Further, a teleprompter device can be preset in advance. After obtaining the live copywriting output by the language model, the teleprompter device can be controlled to display the live copywriting. Thus, the host user can perform a better live operation based on the live copywriting displayed on the teleprompter device.

[0111] The live assistance method provided in this embodiment performs a teleprompter operation based on the live content during the live broadcast, so that the host user does not need to organize the language by himself for the live operation, and the host user can perform the live operation more smoothly based on the teleprompter content.

[0112] Optionally, the target assistance function can include a customer service assistance function. During each live broadcast, repeatedly answering similar questions in the comment area seriously disrupts the merchant's live broadcast rhythm and reduces the merchant's live broadcast efficiency. Therefore, the customer assistance function can extract the comment information associated with the current live broadcast in the comment area and reply to the comment information based on the data processing result output by the language model, thereby improving the live broadcast effect.

[0113] Figure 6 It is a schematic flowchart of the live assistance method provided in another embodiment of the present disclosure. Based on any of the above embodiments, the target assistance function can include a customer service assistance function. As Figure 6 shown, step 203 includes:

[0114] Step 601: Screen at least one target comment content associated with at least one live content corresponding to the current live broadcast from at least one comment associated with the current live broadcast according to a preset screening 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 comment information according to actual needs. Among them, some comment information may be comments related to the live content corresponding to the live broadcast, and some comment information may be comments unrelated to the live content, such as social interactions, expressions, etc. For example, the host user can introduce a certain product during the live broadcast, and the viewers can post comments on the product, such as what materials the product is made of? How long is the product's shelf life, etc. Or, the viewers can also post comments on other content, such as posting expressions, or praising the host user's comments.

[0117] During the live broadcast of the host user, if the host frequently replies to repeated comment content, it may lead to a poor live broadcast effect. If the host user does not reply to the questions raised by the viewers, it may lead to a poor viewing experience for the viewers and cause the loss of viewers.

[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 reply to the content related to the live content in the comment area.

[0119] Optionally, at least one target comment content associated with at least one live content corresponding to the current live broadcast can be screened from at least one comment associated with the current live broadcast according to a preset screening condition. Among them, the preset screening condition can be to extract comment information at preset time intervals, or the screening condition can be to extract comments at preset comment quantity intervals, or the screening condition can be to identify comments based on a preset keyword recognition model and extract comments with preset keywords associated with the live content, etc. The host user can set the screening condition according to actual needs, and the present disclosure does not limit this.

[0120] After obtaining at least one target comment content associated with at least one live content corresponding to the current live broadcast, at least one comment content can 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, display the reply text in the display area associated with the comment content.

[0124] In this embodiment, after obtaining at least one target comment content, at least one comment content can be input into a preset language model. The preset language model can output a reply text for the comment content.

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

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

[0127] The live broadcast assistance method provided in this embodiment automatically replies by screening the comment content associated with the live broadcast content in the comments and based on the data processing results output by the language model. Thus, 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 The structural schematic diagram of the live broadcast assistance device provided in an embodiment of the present disclosure is as Figure 7 shown. The device includes: an acquisition module 71, a determination module 72, a processing module 73, and an assistance module 74. Among them, the acquisition module 71 is used to acquire a live broadcast assistance request and display a preset function list based on the live broadcast assistance request. The function list includes at least one live broadcast assistance function. The determination module 72 is used to determine at least one target assistance function selected by the host user in response to a selection operation of the host user in the function list. The processing module 73 is used to acquire live broadcast data matching the at least one target assistance function, where 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. The assistance module 74 is used to input the live broadcast data into a preset language model and perform a live broadcast assistance operation based on the data processing results output by the language model.

[0129] Furthermore, based on any of the above embodiments, the target assistance function includes a virtual host function. The processing module is used to: determine at least one live broadcast content corresponding to the current live broadcast and acquire the associated data of the at least one live broadcast content, where the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content. Acquire the live broadcast voice data of the host user during the live broadcast and convert the live broadcast voice data into text content based on a preset speech recognition algorithm. The live broadcast voice data includes the question content proposed by the host 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 broadcast voice data as the live broadcast data.

[0130] Further, based on any of the above embodiments, the auxiliary module is configured to: obtain the assistant copywriting generated by the language model based on the live data, where the assistant copywriting is a reply content generated based on the question content. Control a preset virtual assistant to simulate the body movements when reading the assistant copywriting aloud and play the voice content corresponding to the assistant copywriting.

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

[0132] Further, based on any of the above embodiments, the auxiliary module is configured to: input the live data into a preset language model. Obtain the assistant copywriting generated by the language model based on the live data, where the assistant copywriting is a question content generated based on the associated data of the at least one live content. When it is determined that the time when the host user stops speaking exceeds a preset time threshold, control a preset virtual assistant to simulate the body movements when reading the assistant copywriting aloud and play the voice content corresponding to the assistant copywriting.

[0133] Further, based on any of the above embodiments, the module for controlling the preset virtual assistant to simulate reading aloud is configured to: convert the assistant copywriting into the voice content through a preset text-to-speech algorithm. Drive the virtual assistant to simulate the body movements when reading the assistant copywriting aloud based on the voice content, render the virtual assistant as a two-dimensional image, and combine the two-dimensional image with the video frame of the current live broadcast. Simultaneously play the current live broadcast and the voice content through video audio-visual synchronization technology.

[0134] Further, based on any of the above embodiments, the target auxiliary function includes a teleprompter function, and the processing module is configured to: determine at least one live content corresponding to the current live broadcast. Obtain the 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, where the associated data includes one or more of the attribute information, description information, and virtual resource information of the live content.

[0135] Further, based on any of the above embodiments, the auxiliary module is configured to: obtain the live copywriting output by the language model. Control a preset teleprompter device to display the live copywriting so that the user can view the live copywriting on the teleprompter device.

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

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

[0138] The device provided in this embodiment can be used to execute the technical solutions of the above method embodiments, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

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

[0140] To implement the above embodiments, the present disclosure embodiments also provide a computer program product, including a computer program, and when the computer program is executed by a processor, the live broadcast assistance method as described in any of the above embodiments is implemented.

[0141] To implement the above embodiments, the present disclosure embodiments also provide 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] Figure 8 FIG. is a schematic structural diagram of the electronic device provided in the embodiments of the present disclosure. The electronic device 800 may be a terminal device or a server. Among them, 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 for short), tablet computers (PADs for short), portable multimedia players (PMPs for short), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs and desktop computers. Figure 8The electronic device shown is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present disclosure.

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

[0146] Generally, 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 wiredly to exchange data. Although Figure 8 the electronic device 800 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. More or fewer devices may be implemented or had alternatively.

[0147] Specifically, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from the network through 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 functions defined in the methods of the embodiments of the present disclosure are executed.

[0148] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can 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 can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0149] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; or it can exist separately without being assembled into the electronic device.

[0150] The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device is caused to execute the method shown in the above-mentioned embodiments.

[0151] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed 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 the case of 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., through the Internet using an Internet service provider).

[0152] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0153] The units described in the embodiments of the present disclosure may be implemented in software or in hardware. Among them, the name of the unit does not constitute a limitation on the unit itself in some cases. For example, the first acquisition unit may also be described as "the 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, without limitation, exemplary types of hardware logic components that may be used include: Field Programmable Gate Arrays (FPGA), Application Specific Integrated Circuits (ASIC), Application Specific Standard Products (ASSP), Systems on Chip (SOC), Complex Programmable Logic Devices (CPLD), and so on.

[0155] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, 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 the machine-readable storage medium would 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 fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0156] In a first aspect, according to one or more embodiments of the present disclosure, there is provided a live broadcast assistance method, including: obtaining a live broadcast assistance request, displaying a preset function list based on the live broadcast assistance request, where the function list includes at least one live broadcast assistance function; in response to a selection operation of a host user in the function list, determining at least one target assistance function selected by the host user; obtaining live broadcast data matching the at least one target assistance function, where 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 assistance function includes a virtual co-host function. The obtaining of the live broadcast data matching the at least one target assistance 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, where the associated data includes one or more of attribute information, description information, and virtual resource information of the live broadcast content; obtaining the live broadcast voice data of the host user during the live broadcast, and converting the live broadcast voice data into text content based on a preset speech recognition algorithm, where the live broadcast voice data includes question content raised by the host user based on the live broadcast content; determining 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.

[0158] According to one or more embodiments of the present disclosure, the live broadcast assistance operation based on the data processing result output by the language model includes: obtaining the assistant broadcast copywriting generated by the language model based on the live broadcast data, where the assistant broadcast copywriting is the reply content generated based on the problem content; controlling the preset virtual assistant to simulate the body movements when reading the assistant broadcast copywriting aloud and playing the voice content corresponding to the assistant broadcast copywriting.

[0159] According to one or more embodiments of the present disclosure, the target assistance function includes a virtual assistant function. The obtaining of the live broadcast data matching the at least one target assistance function includes: determining at least one live broadcast content corresponding to the current live broadcast, and obtaining the associated data of the at least one live broadcast content, where the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content; 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 inputting of the live broadcast data into a preset language model and the live broadcast assistance operation based on the data processing result output by the language model includes: inputting the live broadcast data into a preset language model; obtaining the assistant broadcast copywriting generated by the language model based on the live broadcast data, where the assistant broadcast copywriting is the problem content generated based on the associated data of the at least one live broadcast content; when it is determined that the time when the host user stops speaking exceeds a preset time threshold, controlling the preset virtual assistant to simulate the body movements when reading the assistant broadcast copywriting aloud and playing the voice content corresponding to the assistant broadcast copywriting.

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

[0162] According to one or more embodiments of the present disclosure, the target assistance function includes a teleprompter function. The obtaining of the live broadcast data matching the at least one target assistance function includes: determining at least one live broadcast content corresponding to the current live broadcast; obtaining the 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, where 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 assistance operation based on the data processing result output by the language model includes: obtaining the live broadcast copywriting output by the language model; controlling a preset teleprompter device to display the live broadcast copywriting, so that the user can view the live broadcast copywriting on the teleprompter device.

[0164] According to one or more embodiments of the present disclosure, the target assistance function includes a customer service assistance function. The obtaining of the live broadcast data matching the at least one target assistance function includes: screening 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 screening condition; 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 assistance operation based on the data processing result output by the language model includes: obtaining the reply text output by the language model for each comment content; for each comment content, displaying the reply text in the display area associated with the comment content.

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

[0167] An obtaining module, configured to obtain a live broadcast assistance request, and display a preset function list based on the live broadcast assistance request, where the function list includes at least one live broadcast assistance function;

[0168] A determining module, configured to determine at least one target assistance function selected by the host user in response to a selection operation of the host user in the function list;

[0169] A processing module, configured to obtain live broadcast data matching the at least one target assistance function, where 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] An assistance module, configured to input the live broadcast data into a preset language model, and perform a live broadcast assistance operation based on the data processing result output by the language model.

[0171] According to one or more embodiments of the present disclosure, the target auxiliary function includes a virtual co-hosting function. The processing module is configured to: determine at least one live content corresponding to the current live broadcast, and obtain associated data of the at least one live content, where the associated data includes one or more of attribute information, description information, and virtual resource information of the live content; obtain the live voice data of the host user during the live broadcast, and convert the live voice data into text content based on a preset speech recognition algorithm, where the live voice data includes question content proposed by the host user based on the live content; determine the associated data of the at least one live 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 configured to: obtain the co-hosting copywriting generated by the language model based on the live data, where the co-hosting copywriting is a reply content generated based on the question content; control the body movements of a preset virtual co-host when simulating the reading of the co-hosting copywriting and play the voice content corresponding to the co-hosting copywriting.

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

[0174] According to one or more embodiments of the present disclosure, the auxiliary module is configured to: input the live data into a preset language model; obtain the co-hosting copywriting generated by the language model based on the live data, where the co-hosting copywriting is question content generated based on the associated data of the at least one live content; when it is determined that the time when the host user stops speaking exceeds a preset time threshold, control the body movements of a preset virtual co-host when simulating the reading of the co-hosting copywriting and play the voice content corresponding to the co-hosting copywriting.

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

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

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

[0178] According to one or more embodiments of the present disclosure, the target auxiliary function includes a customer service auxiliary function, and the processing module is configured to: screen at least one target comment content associated with at least one live content corresponding to the current live broadcast from at least one comment associated with the current live broadcast according to a preset screening condition; 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 configured to: obtain the reply text output by the language model for each comment content; display the reply text in the display area associated with each comment content.

[0180] In a third aspect, according to one or more embodiments of the present disclosure, there is provided an electronic device, including: 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 as described in the first aspect and various possible designs of the first aspect above.

[0183] In a fourth aspect, according to one or more embodiments of the present disclosure, there is provided a computer-readable storage medium, in which computer-executable instructions are stored, and when the processor executes the computer-executable instructions, the live broadcast assistance method as described in the first aspect and various possible designs of the first aspect above is implemented.

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

[0185] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0186] In addition, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, the various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[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. On the contrary, the specific features and acts described above are merely example forms for implementing the claims.

Claims

1. A live broadcast assistance method, characterized in that, it includes: Obtain a live broadcast assistance request, and display a preset function list based on the live broadcast assistance request. At least one live broadcast assistance function is included in the function list; In response to the selection operation of the host user in the function list, determine at least one target assistance function selected by the host user; Obtain live broadcast data matching the at least one target assistance function, where the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and associated data of live broadcast content; 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.

2. The method according to claim 1, characterized in that, The target assistance function includes a virtual assistant function. The obtaining of the live broadcast data matching the at least one target assistance function includes: Determine at least one live broadcast content corresponding to this live broadcast, and obtain the associated data of the at least one live broadcast content, where 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 broadcast voice data of the host user during the live broadcast, and convert the live broadcast voice data into text content based on a preset speech recognition algorithm. The live broadcast voice data includes question content proposed by the host 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 broadcast voice data as the live broadcast data.

3. The method according to claim 2, characterized in that, The performing of the live broadcast assistance operation based on the data processing results output by the language model includes: Obtain the assistant copywriting generated by the language model based on the live broadcast data. The assistant copywriting is a reply content generated based on the question content; Control the preset virtual assistant to simulate the body movements when reading the assistant copywriting aloud and play the voice content corresponding to the assistant copywriting.

4. The method according to claim 1, characterized in that, The target assistance function includes a virtual assistant function. The obtaining of the live broadcast data matching the at least one target assistance function includes: Determine at least one live broadcast content corresponding to this live broadcast, and obtain the associated data of the at least one live broadcast content, where the associated data includes one or more of the attribute information, description information, and virtual resource information of the live broadcast content; Determine the associated data of the at least one live broadcast content as the live broadcast data.

5. The method according to claim 4, characterized in that, The inputting of the live broadcast data into a preset language model and performing live broadcast assistance operations based on the data processing results output by the language model includes: Input the live broadcast data into a preset language model; Obtain the assistant copywriting generated by the language model based on the live broadcast data. The assistant copywriting is question content generated based on the associated data of the at least one live broadcast content. When it is determined that the time when the host user stops speaking exceeds a preset time threshold, control a preset virtual co-host to simulate the body movements during the recitation of the co-host copywriting and play the voice content corresponding to the co-host copywriting.

6. The method according to claim 3 or 5, wherein, the controlling the preset virtual co-host to simulate the body movements during the recitation of the co-host copywriting and play the voice content corresponding to the co-host copywriting includes: converting the co-host copywriting into the voice content through a preset text-to-speech algorithm; driving the virtual co-host to simulate the body movements during the recitation of the co-host copywriting based on the voice content, rendering the virtual co-host as a two-dimensional image, and combining the two-dimensional image with the video frame of the current live broadcast; simultaneously playing the current live broadcast and the voice content through video and audio synchronization technology.

7. The method according to claim 1, wherein, the target auxiliary function includes a teleprompter function, and the obtaining the 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 the 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.

8. The method according to claim 7, wherein, the performing the live broadcast assistance operation based on the data processing result output by the language model includes: obtaining the live broadcast copywriting output by the language model; controlling a preset teleprompter device to display the live broadcast copywriting so that the user can view the live broadcast copywriting on the teleprompter device.

9. The method according to claim 1, wherein, the target auxiliary function includes a customer service auxiliary function, and the obtaining the live broadcast data matching the at least one target auxiliary function includes: screening 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 screening condition; determining the at least one comment content as the live broadcast data.

10. The method according to claim 9, wherein, the performing the live broadcast assistance operation based on the data processing result output by the language model includes: obtaining the reply text output by the language model for each comment content; displaying the reply text in the display area associated with each comment content.

11. A live broadcast assistance device, wherein, comprising: an obtaining module, configured to obtain a live broadcast assistance request, and display a preset function list based on the live broadcast assistance request, where the function list includes at least one live broadcast assistance function; a determining module, configured to determine at least one target auxiliary function selected by the host user in response to a selection operation of the host user in the function list; a processing module, configured to obtain live broadcast data matching the at least one target auxiliary function, where the live broadcast data includes at least one of live broadcast voice data, live broadcast comment data, and associated data of live broadcast content; An auxiliary module for inputting the live data into a preset language model and performing live assistance operations based on the data processing results output by the language model.

12. An electronic device, characterized in that, it includes: a processor and a memory; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the processor executes the live assistance method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, the computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the live assistance method according to any one of claims 1 to 10 is implemented.

14. A computer program product, including a computer program, characterized in that, when the computer program is executed by a processor, the live assistance method according to any one of claims 1 to 10 is implemented.

Images