Live script processing method, device, electronic device and storage medium

Abstract

The present disclosure provides a live broadcast script processing method, device, electronic device and storage medium, which relates to the field of computer technology, and specifically to the field of live broadcast technology. The specific implementation scheme is: obtaining the original live broadcast script; obtaining the interactive information generated when the original live broadcast script is executed; generating a real-time live broadcast script based on the interactive information, and fusing the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script; scoring the updated live broadcast script, and screening the live broadcast script according to the scoring results to obtain a screened live broadcast script. The present disclosure first generates a real-time live broadcast script based on the interactive information, and then fuses these real-time live broadcast scripts with the original live broadcast script to form an updated live broadcast script, and optimizes and screens the updated live broadcast script through a scoring mechanism, so that the efficiency and quality of live broadcast script generation can be improved, thereby significantly improving the interactivity, audience satisfaction and live broadcast effect of the live broadcast.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, specifically to the field of live broadcast technology, and more particularly to a live broadcast script processing method, device, electronic device, and storage medium. Background Art

[0002] Digital human broadcasters play a crucial role in the operation of digital human livestreaming studios. They simulate the presentation style of real-life broadcasters, introducing products and sharing information to viewers, aiming to attract viewers and boost sales. However, traditional methods for generating scripts for digital human broadcasts have significant limitations. Specifically, these scripts are often simply rewritten from livestream content. This approach is not only inefficient but also struggles to achieve the desired livestreaming results. This traditional script generation method struggles to quickly respond to market changes and the evolving needs of livestream viewers, placing digital human broadcast studios at a disadvantage in the fiercely competitive market. Therefore, improving the efficiency and effectiveness of digital human broadcast script generation has become a pressing technical challenge for digital human broadcast studios. Summary of the Invention

[0003] The present disclosure provides a live broadcast script processing method, device, electronic device and storage medium.

[0004] According to one aspect of the present disclosure, a method for processing a live broadcast script is provided, the method comprising:

[0005] Get the original live broadcast script;

[0006] Acquire interactive information generated when executing the original live broadcast script, the interactive information including user information and comment content corresponding to the user information;

[0007] Generate a real-time live broadcast script according to the interactive information, and merge the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script;

[0008] The updated live broadcast script is scored, and the live broadcast script is screened according to the scoring result to obtain the screened live broadcast script.

[0009] According to another aspect of the present disclosure, a live broadcast script processing device is provided, comprising:

[0010] The first acquisition module is used to obtain the original live broadcast script;

[0011] A second acquisition module is configured to acquire interactive information generated when the original live broadcast script is executed, wherein the interactive information includes user information and comment content corresponding to the user information;

[0012] A generating module, configured to generate a real-time live broadcast script according to the interactive information, and merge the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script;

[0013] The scoring module is used to score the updated live broadcast script and filter the live broadcast script according to the scoring result to obtain the filtered live broadcast script.

[0014] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any one of the methods described in the above technical solutions.

[0018] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods described above.

[0019] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements any one of the methods described above when executed by a processor.

[0020] The present disclosure provides a live broadcast script processing method, device, equipment and storage medium. The present disclosure obtains the original live broadcast script and analyzes the audience interaction information of the original live broadcast script in real time during the execution process, and intelligently generates a real-time live broadcast script that is closely related to the audience interaction. Then, these real-time generated live broadcast scripts are merged with the original live broadcast script to form an updated live broadcast script, and the updated live broadcast script is optimized and screened through a scoring mechanism. This live broadcast script generation method improves the generation efficiency and generation quality of the live broadcast script. Secondly, the live broadcast script is associated with the interactive information, which ensures the high quality of the live broadcast content and the high participation of the audience, and significantly improves the interactivity, audience satisfaction and live broadcast effect of the live broadcast.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0023] Figure 1 It is a schematic diagram of the steps of the live broadcast script processing method in an embodiment of the present disclosure;

[0024] Figure 2 is a flowchart of a live broadcast script processing method in an embodiment of the present disclosure;

[0025] Figure 3 A block diagram of the principle of a live script processing device in an embodiment of the present disclosure;

[0026] Figure 4 It is a block diagram of an electronic device used to implement the live broadcast script processing method of an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0028] This disclosure provides a live script processing method, see Figure 1 As shown, Figure 1 1 is a schematic diagram of the steps of a live script processing method in an embodiment of the present disclosure. The method can be applied to a server side, and the method includes:

[0029] Step S101, obtaining the original live broadcast script.

[0030] Specifically, obtaining the original live broadcast script means first collecting or creating the basic explanation text (i.e., the original live broadcast script) for live broadcast during the operation of the digital human live broadcast room. These live broadcast scripts usually contain the core information to be conveyed in the live broadcast and the preset interactive links. The original live broadcast script can be generated in advance through a well-trained large model, and its purpose is to provide a structured explanation framework for the digital human anchor. In this technical solution, this step is the starting point of the real-time script generation process, providing a basis for the subsequent dynamic adjustment of the live broadcast content according to audience feedback. By obtaining the original live broadcast script, the coherence and consistency of the live broadcast content can be ensured, while leaving enough flexibility to respond to the audience's real-time interaction, thereby enhancing the attractiveness of the live broadcast and the audience's participation.

[0031] Step S102: Obtain interactive information generated when the original live broadcast script is executed. The interactive information includes user information and comment content corresponding to the user information.

[0032] Specifically, after obtaining the original live broadcast script, it is executed. Next, interactive information posted by viewers in the live broadcast room is monitored and collected in real time. This interactive information includes not only audience feedback and questions, but also information about the users who posted these comments, such as usernames or user IDs. By capturing and analyzing the interactive information generated during the execution of the original live broadcast script, it is helpful to understand the audience's interests, concerns, or needs. This interactive information is then used to generate a more personalized and interactive real-time live broadcast script. This process enables instant interaction between live broadcast content and audience feedback, allowing the digital human anchor to more accurately respond to the audience's actual needs, thereby improving live broadcast engagement and audience satisfaction.

[0033] On the other hand, interactive information can also include comments in the form of text, voice, images, and videos. Comments in interactive information can be direct comments, replies to other comments, and comments on bullet screens. Interactive information can also include other data that reflects the real-time needs of live broadcast viewers, such as voting data in the live broadcast room.

[0034] By capturing the interactive information generated during the execution of the original live broadcast script, the live broadcast system can capture and analyze audience feedback in real time, thereby more accurately understanding their interests and needs. This real-time interactive analysis capability not only enhances the relevance and interactivity of live broadcast content, but also improves audience engagement and satisfaction, ultimately promoting more effective audience communication and higher-quality live broadcast viewing.

[0035] Step S103: Generate a real-time live broadcast script based on the interactive information, and merge the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script.

[0036] Specifically, after obtaining interactive information, it is first analyzed. This data is then used to generate real-time live broadcast scripts. These live broadcast scripts are tailored to audience feedback, designed to directly respond to audience questions or comments, enhancing the interactivity and relevance of the live broadcast. After generating the real-time live broadcast scripts, these real-time scripts are then combined with the pre-prepared original live broadcast script. Intelligent algorithms are used to optimize the sequence and structure of the content, ensuring a seamless integration of the two into a coherent, dynamically updated live broadcast script. This integration not only retains the core content and structure of the original live broadcast script, but also incorporates elements of audience feedback, making the live broadcast content more vivid and engaging, thereby increasing live broadcast participation and viewer satisfaction.

[0037] By generating a real-time live broadcast script based on interactive information and integrating it with the original live broadcast script to create an updated live broadcast script, dynamic adjustment and personalized optimization of live broadcast content are achieved. This allows live broadcasts to instantly respond to audience feedback and needs, enhancing interactivity and audience participation while ensuring the consistency and appeal of live content. This flexible content generation mechanism not only improves the real-time nature of live broadcasts and audience satisfaction, but also helps increase conversion rates and audience loyalty.

[0038] Step S104: score the updated live broadcast scripts, and filter the live broadcast scripts according to the score results to obtain filtered live broadcast scripts.

[0039] Specifically, after obtaining the updated live broadcast script, a quality control mechanism is introduced to screen the live broadcast. Specifically, the server will automatically score the live broadcast script that integrates real-time interactive information according to a series of preset standards (such as audience participation, interaction frequency, content relevance, etc.). This scoring process can be regarded as a quantitative assessment of the quality of the script. Subsequently, the server will screen the live broadcast script according to the score, retaining those scripts with higher scores and more likely to attract viewers. For good script content, for example, the explanation time of the good script can be extended, while those scripts with lower scores may be eliminated. This screening process aims to optimize the live broadcast content and ensure that the live broadcast can provide a high-quality, highly interactive viewing experience. In this way, the live broadcast script can continue to evolve to better meet the expectations of the audience and improve the overall effect of the live broadcast.

[0040] By implementing a scoring mechanism for updated live broadcast scripts and then filtering them based on the scoring results, this approach effectively improves the quality control of live broadcast content. It ensures that only scripts that can attract audience interest, promote interaction, and meet the live broadcast objectives are retained and displayed, thereby optimizing the audience viewing experience, increasing the appeal and participation of the live broadcast, and ultimately enhancing the influence and commercial value of the live broadcast.

[0041] The present disclosure provides a live broadcast script processing method, device, equipment and storage medium. The present disclosure obtains the original live broadcast script and analyzes the audience interaction information of the original live broadcast script in real time during the execution process, and intelligently generates a real-time live broadcast script that is closely related to the audience interaction. Then, these real-time generated live broadcast scripts are merged with the original live broadcast script to form an updated live broadcast script, and the updated live broadcast script is optimized and screened through a scoring mechanism. This live broadcast script generation method improves the generation efficiency and generation quality of the live broadcast script. Secondly, the live broadcast script is associated with the interactive information, which ensures the high quality of the live broadcast content and the high level of audience participation, and significantly improves the interactivity, audience satisfaction and live broadcast effect of the live broadcast.

[0042] In some optional embodiments, obtaining the original live broadcast script includes:

[0043] Get information about the product to be explained;

[0044] A pre-trained large model is used to generate an original live broadcast script corresponding to the product to be explained based on the information of the product to be explained, and the original live broadcast script is executed.

[0045] Specifically, when generating the original live broadcast script, information about the product to be explained is first collected, including its description, features, and advantages. Next, a pre-trained large model is used to automatically generate a preliminary live broadcast script based on this product information. This is the original live broadcast script. It should be noted that this pre-trained large model may be a deep learning algorithm that has been trained on large amounts of text data to understand and generate natural language. After the original live broadcast script is generated, the digital human anchor will execute the live broadcast based on this generated original live broadcast script, beginning to explain the product and interact with the audience. This process automates the generation of live broadcast content, improves the efficiency of live broadcast preparation, and ensures the consistency and accuracy of the live broadcast content and product information.

[0046] By capturing detailed information about the product being presented and automatically generating the corresponding original live broadcast script using a pre-trained large model, the live broadcast content can be rapidly prepared and standardized. This not only improves the efficiency of live broadcast script generation and reduces the need for manual editing, but also ensures the professionalism and accuracy of the live broadcast content. Furthermore, the use of pre-trained large models makes the live broadcast script more tailored to the product characteristics, increasing the appeal and persuasiveness of the live broadcast, thereby enhancing users' willingness to purchase and increasing the commercial value of the live broadcast.

[0047] In some optional embodiments, generating a real-time live broadcast script based on the interactive information includes:

[0048] Analyze the interactive information to obtain the importance of the interactive information;

[0049] Sort the interactive information according to its importance to obtain a list of responses to be received;

[0050] Based on the historical live broadcast script and the attribute information of the product to be explained, a real-time live broadcast script corresponding to the list to be responded to is generated.

[0051] Specifically, after obtaining interactive information, it is necessary to conduct an in-depth analysis of the interactive information and evaluate the importance of each comment. The importance of interactive information is usually determined based on factors such as the comment's content, sentiment, and user influence. Subsequently, these comments are sorted according to their importance to form a list of responses to be responded to, ensuring that those comments most likely to affect the live broadcast effect are responded to first. Next, referring to effective expression methods and strategies in historical live broadcast scripts, combined with specific attribute information of the product to be explained, such as characteristics and advantages, a real-time live broadcast script is intelligently generated. These live broadcast scripts directly respond to the audience's comments and questions, enhance the interactivity and targeted nature of the live broadcast, make the live broadcast content more vivid and closer to the audience's needs, and thus improve the user's viewing experience and engagement.

[0052] By analyzing interactive information to assess its importance and sorting comments by importance to create a response list, the livestream effectively enhances its interactivity and relevance. Then, by combining historical livestream scripts with product attribute information to generate real-time livestream scripts, the livestream ensures that the content addresses viewers' key concerns promptly and accurately, thereby enhancing their engagement and satisfaction. This intelligent content generation and response mechanism not only optimizes the livestream experience but also improves its efficiency and effectiveness, making it more engaging and persuasive.

[0053] In some optional embodiments, the real-time live broadcast script is merged with the original live broadcast script to obtain an updated live broadcast script, including:

[0054] If a return to original live broadcast script instruction is received, the real-time live broadcast script is inserted into the position where the original live broadcast script is interrupted, so as to connect the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script.

[0055] Specifically, the original live broadcast script refers to the pre-set live broadcast content framework, and the real-time live broadcast script is the script part that is dynamically generated based on real-time data such as audience comments. When a return to the original live broadcast script instruction is received, requiring a return to the original live broadcast script, a suitable breakpoint will be found, which is usually a logical breakpoint or natural pause in the original script. Then, the real-time live broadcast script is inserted into this position to ensure a smooth connection between the new and old content, thereby forming an updated live broadcast script. This process involves real-time monitoring and intelligent editing of the live broadcast process. The purpose is to maintain the continuity of the live broadcast while also being able to adjust the live broadcast content in a timely manner according to the audience's feedback to improve the interactivity of the live broadcast and the audience's viewing experience.

[0056] In this way, by intelligently inserting the live broadcast script into the appropriate location of the original live broadcast script upon receiving the instruction to return to the original live broadcast script, the live broadcast content is seamlessly connected and dynamically updated. This flexible script management mechanism not only ensures the consistency and fluency of the live broadcast content, but also allows the live broadcast to be adjusted promptly based on real-time feedback, thereby significantly improving the interactivity and audience participation of the live broadcast, making the live broadcast more vivid and engaging, and enhancing the appeal and influence of the live broadcast content.

[0057] In some optional embodiments, the updated live broadcast script is scored, and the live broadcast script is filtered according to the scoring result to obtain the filtered live broadcast script, including:

[0058] Obtain the live broadcast data corresponding to the updated live broadcast script;

[0059] Scoring the updated live broadcast script according to the live broadcast data to obtain a scoring result;

[0060] The live broadcast scripts are screened according to the scoring results to obtain screened live broadcast scripts.

[0061] Specifically, "live broadcast data" refers to various types of information collected during the execution of the live broadcast script, such as the total number of times viewers watch the live broadcast room, the number of product card exposures, product card clicks, the number of orders, the average viewing time per person, the number of comments, the number of likes, the number of favorites, and other key indicators. First, the server will collect these live broadcast data corresponding to the updated live broadcast script. Then, using this data, the live broadcast script is scored. The scoring may be based on a preset algorithm, taking into account factors such as audience participation and feedback enthusiasm to obtain a scoring result. Finally, based on these scoring results, the live broadcast scripts with better performance are screened out, and the parts with poor performance are eliminated to obtain the screened live broadcast scripts. This process realizes the continuous monitoring and improvement of the quality of live broadcast content, ensuring that the live broadcast can continue to attract audiences and achieve the expected business goals.

[0062] This approach enables a quantitative assessment of live broadcast script effectiveness by capturing live broadcast data related to updated live broadcast scripts and scoring them based on this data. This scoring process helps identify which scripts are most effective in attracting and retaining viewers' attention, allowing for precise selection of scripts based on the scoring results and optimizing live broadcast content. This approach not only improves the relevance and appeal of live broadcast content but also enhances audience engagement and overall performance through data-driven decision support, ultimately improving the viewing experience and commercial success of live broadcasts.

[0063] In some optional embodiments, the live broadcast data includes: product click-through rate, average viewing time per person, number of product exposure click orders, and number of interactions;

[0064] The updated live broadcast script is scored according to the live broadcast data to obtain the scoring results, including:

[0065] Set the first, second, third, and fourth weight coefficients corresponding to the product click-through rate, average viewing time per person, number of product card exposure click orders, and number of interactions, respectively;

[0066] Calculate the product of the first weight coefficient and the product click rate to obtain a first calculation result;

[0067] Calculate the product of the second weight coefficient and the average viewing time per person to obtain a second calculation result;

[0068] Calculate the product of the third weight coefficient and the number of product exposure click orders to obtain a third calculation result;

[0069] Calculate the product of the fourth weight coefficient and the number of interactions to obtain a fourth calculation result;

[0070] The first calculation result, the second calculation result, the third calculation result and the fourth calculation result are accumulated to obtain a scoring result.

[0071] Specifically, a product's click-through rate (CTR) is a metric that measures a product's ability to attract users. It's typically defined as the ratio of the number of times a product is clicked to the number of times it's displayed within a certain period of time. A higher CTR indicates a product is more likely to attract user attention.

[0072] Average viewing time per user: This metric reflects the average length of time users spend watching content in a livestream. It is expressed as the sum of all users' viewing time divided by the number of viewing users. A longer average viewing time generally indicates greater user interest in the livestream content.

[0073] Product Exposure-Click Orders: This refers to the number of orders resulting from users clicking on a product after seeing it and ultimately completing a purchase. This metric is directly linked to the product's conversion rate, specifically the conversion rate from potential customers to actual purchasers.

[0074] Interactions: This refers to the total number of times users interact with the live content during the live broadcast, typically including comments, likes, shares, and gift giving. A high number of interactions generally indicates high user engagement and a lively atmosphere.

[0075] The scoring process describes a comprehensive scoring system for evaluating the effectiveness of live streaming scripts: the score = first weight factor * product click-through rate + second weight factor * average viewing time + third weight factor * product exposure, click-through, and order number + fourth weight factor * number of interactions. In this system, the first through fourth weight factors are pre-set values, which can be tuned based on historical or empirical data. They correspond to different live streaming performance metrics: product click-through rate, average viewing time, product card exposure, click-through, and order number, and number of interactions. These weight factors reflect the importance of each metric in the scoring system. The server first multiplies each metric by its corresponding weight factor, resulting in four different calculation results. This process considers the relative importance of each metric to the success of the live streaming. These four results are then summed to produce a comprehensive score that comprehensively reflects the live streaming script's performance in promoting user engagement and purchasing behavior. This approach allows the effectiveness of the live streaming script to be quantified and optimized accordingly to improve conversion rates and user engagement.

[0076] By assigning corresponding weights to key livestream metrics like product click-through rate, average viewing time per person, product card impression click-through orders, and number of interactions, and calculating the product of these metrics with the weights, and then summing these results to create a comprehensive score, we achieve a multi-dimensional quantitative assessment of the effectiveness of livestream scripts. This approach not only comprehensively reflects the impact of livestream scripts on viewer behavior but also provides an objective scoring mechanism to measure and optimize the performance of livestream content, thereby helping to increase audience engagement and conversion efficiency, and thus enhance the commercial value of livestreams.

[0077] In some optional embodiments, the live broadcast script is screened according to the scoring result to obtain the screened live broadcast script, including:

[0078] According to the scoring results, live broadcast scripts with scores greater than a preset threshold are screened out from the updated live broadcast scripts to obtain screened live broadcast scripts.

[0079] Specifically, the "scoring result" refers to a numerical value obtained through the comprehensive scoring mechanism mentioned above, which reflects the overall performance of the live broadcast script in promoting user participation and purchasing behavior. The "preset threshold" is a scoring standard set in advance by the system to distinguish between valid and invalid live broadcast scripts. Based on this scoring result, the server will automatically filter out those live broadcast scripts whose scores exceed the preset threshold, which means that only those scripts that perform well and can effectively attract viewers will be retained. This process realizes the automated screening of live broadcast scripts, ensures the quality and effectiveness of live broadcast content, and improves the audience participation and conversion rate of live broadcasts. Among them, the screened live broadcast scripts are a collection of live broadcast scripts that meet specific standards after this quality control process. They are the content to be used in the next live broadcast activities.

[0080] By selecting live broadcast scripts with scores exceeding a preset threshold based on the scoring results, strict quality control of live broadcast content is achieved. This ensures that only highly performant and engaging scripts are used in the actual live broadcast, thereby improving audience engagement and interaction. This approach not only optimizes live broadcast content but also helps improve the overall viewing experience and commercial effectiveness of live broadcasts, allowing live broadcasts to more accurately meet audience expectations and needs.

[0081] In order to understand the technical solution of this application as a whole, see Figure 2 , Figure 2The flowchart is a flow chart of a live broadcast script processing method in an embodiment of the present disclosure. Specifically, the flowchart illustrates an intelligent live broadcast interactive processing system. First, the live broadcast is performed using the original live broadcast script, corresponding to the real-time explanation content within the live broadcast room. Next, the real-time dynamics within the live broadcast room are monitored, including new comments and the number of viewers. If there are new comments, the comment information is captured, that is, the user information and comment content in the comment area within the recent period are obtained. The comment information is aggregated according to priority, that is, a list of comments that need to be responded to is identified. Next, a response method is selected, that is, the response priority is determined based on the urgency and relevance of the comments. Specifically, the value of the comment information itself (whether it is prevalent / influences other users to purchase) is used to decide whether to quickly reply to all questions or only reply to the most relevant selling points. Finally, a reply script is generated. Specifically, based on the previous explanation, considering the appropriate reply position, the explanation content with the reply script is re-planned (history) + reply position + reply script + continued explanation. That is, based on the historical explanation and real-time data, the reply script is generated and inserted into the live broadcast script, while emphasizing the core selling points of the product to attract viewers and promote purchases. The entire process involves real-time evaluation and weighting of multiple tasks to ensure the consistency and interactivity of the livestream content, ultimately achieving dynamic optimization of the livestream explanations. If there are no new comments, the livestream continues according to the original script. If the number of viewers in the livestream exceeds the set number, the inventory control task flow is activated. If the number of viewers does not exceed the set number, the peer-to-peer interaction task flow is activated.

[0082] The following describes an embodiment of the device of the present application, which can be used to execute the live script processing method in the above embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the live script processing method in the above embodiment of the present application.

[0083] The present disclosure also provides a live script processing device 300, such as Figure 3 Shown, including:

[0084] The first acquisition module 301 is used to obtain the original live broadcast script;

[0085] The second acquisition module 302 is used to acquire interactive information generated when the original live broadcast script is executed, where the interactive information includes user information and comment content corresponding to the user information;

[0086] A generating module 303 is configured to generate a real-time live broadcast script based on the interactive information, and merge the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script;

[0087] The scoring module 304 is used to score the updated live broadcast scripts and filter the live broadcast scripts according to the scoring results to obtain filtered live broadcast scripts.

[0088] In some optional embodiments, the first obtaining module 301 obtains the original live broadcast script, including:

[0089] Get information about the product to be explained;

[0090] A pre-trained large model is used to generate an original live broadcast script corresponding to the product to be explained based on the information of the product to be explained, and the original live broadcast script is executed.

[0091] In some optional embodiments, the generating module 303 generates a real-time live broadcast script according to the interactive information, including:

[0092] Analyze the interactive information to obtain the importance of the interactive information;

[0093] Sort the interactive information according to its importance to obtain a list of responses to be received;

[0094] Based on the historical live broadcast script and the attribute information of the product to be explained, a real-time live broadcast script corresponding to the list to be responded to is generated.

[0095] In some optional embodiments, the generation module 303 merges the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script, including:

[0096] If a return to original live broadcast script instruction is received, the real-time live broadcast script is inserted into the position where the original live broadcast script is interrupted, so as to connect the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script.

[0097] In some optional embodiments, the scoring module 304 scores the updated live broadcast script and filters the live broadcast script according to the scoring result to obtain the filtered live broadcast script, including:

[0098] Obtain the live broadcast data corresponding to the updated live broadcast script;

[0099] Scoring the updated live broadcast script according to the live broadcast data to obtain a scoring result;

[0100] The live broadcast scripts are screened according to the scoring results to obtain screened live broadcast scripts.

[0101] In some optional embodiments, the live broadcast data includes: product click-through rate, average viewing time per person, number of product exposure click orders, and number of interactions;

[0102] The scoring module 304 scores the updated live broadcast script according to the live broadcast data to obtain a scoring result, including:

[0103] Set the first, second, third, and fourth weight coefficients corresponding to the product click-through rate, average viewing time per person, number of product card exposure click orders, and number of interactions, respectively;

[0104] Calculate the product of the first weight coefficient and the product click rate to obtain a first calculation result;

[0105] Calculate the product of the second weight coefficient and the average viewing time per person to obtain a second calculation result;

[0106] Calculate the product of the third weight coefficient and the number of product exposure click orders to obtain a third calculation result;

[0107] Calculate the product of the fourth weight coefficient and the number of interactions to obtain a fourth calculation result;

[0108] The first calculation result, the second calculation result, the third calculation result and the fourth calculation result are accumulated to obtain a scoring result.

[0109] In some optional embodiments, the scoring module 304 filters the live broadcast script according to the scoring result to obtain the filtered live broadcast script, including:

[0110] According to the scoring results, live broadcast scripts with scores greater than a preset threshold are screened out from the updated live broadcast scripts to obtain screened live broadcast scripts.

[0111] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0112] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0113] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0114] like Figure 4As shown, electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. Various programs and data required for the operation of device 400 can also be stored in RAM 403. Computing unit 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to bus 404.

[0115] Various components in device 400 are connected to I / O interface 405, including an input unit 406, such as a keyboard, mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a magnetic disk, optical disk, etc.; and a communication unit 409, such as a network card, modem, wireless communication transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0116] The computing unit 401 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as the live script processing method. For example, in some embodiments, the live script processing method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the applet distribution described above can be performed. Alternatively, in other embodiments, the computing unit 401 can be configured to execute the live script processing method by any other appropriate means (e.g., by means of firmware).

[0117] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0118] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0119] 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.

[0120] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0121] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0122] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0123] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0124] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for processing a live broadcast script, the method comprising: Get the original live broadcast script; Acquire interactive information generated when executing the original live broadcast script, the interactive information including user information and comment content corresponding to the user information; Generate a real-time live broadcast script according to the interactive information, and merge the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script; Obtaining live broadcast data corresponding to the updated live broadcast script, the live broadcast data including: product click-through rate, average viewing time per person, number of product exposure click orders, and number of interactions; Setting a first weight coefficient, a second weight coefficient, a third weight coefficient, and a fourth weight coefficient corresponding to the product click-through rate, average viewing time per person, number of product exposure click orders, and number of interactions, respectively; Calculating the product of the first weight coefficient and the product click rate to obtain a first calculation result; Calculating the product of the second weight coefficient and the average viewing time per person to obtain a second calculation result; Calculating the product of the third weight coefficient and the number of product exposure click orders to obtain a third calculation result; Calculating a product of the fourth weight coefficient and the number of interactions to obtain a fourth calculation result; Accumulate the first calculation result, the second calculation result, the third calculation result, and the fourth calculation result to obtain a scoring result; The live broadcast scripts are screened according to the scoring results to obtain screened live broadcast scripts.

2. The method according to claim 1, wherein The obtaining of the original live broadcast script includes: Get information about the product to be explained; A pre-trained large model is used to generate an original live broadcast script corresponding to the product to be explained based on the information of the product to be explained, and the original live broadcast script is executed.

3. The method according to claim 1, wherein Generating a real-time live broadcast script according to the interactive information includes: Analyzing the interactive information to obtain the importance of the interactive information; Sorting the interactive information according to the importance of the interactive information to obtain a list to be responded to; According to the historical live broadcast script and the attribute information of the product to be explained, a real-time live broadcast script corresponding to the list to be responded to is generated.

4. The method according to claim 1, wherein The step of fusing the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script includes: If a return to original live broadcast script instruction is received, the real-time live broadcast script is inserted into the position where the original live broadcast script is interrupted, so as to connect the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script.

5. The method according to claim 1, wherein The live broadcast script is screened according to the scoring result to obtain the screened live broadcast script, including: According to the scoring result, live broadcast scripts having scores greater than a preset threshold are screened out from the updated live broadcast scripts to obtain screened live broadcast scripts.

6. A live script processing device, comprising: The first acquisition module is used to obtain the original live broadcast script; A second acquisition module is configured to acquire interactive information generated when the original live broadcast script is executed, wherein the interactive information includes user information and comment content corresponding to the user information; A generating module, configured to generate a real-time live broadcast script according to the interactive information, and merge the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script; A scoring module is used to obtain live broadcast data corresponding to the updated live broadcast script, the live broadcast data including: product click-through rate, average viewing time per person, number of product exposure click orders, and number of interactions; set a first weight coefficient, a second weight coefficient, a third weight coefficient, and a fourth weight coefficient corresponding to the product click-through rate, average viewing time per person, number of product exposure click orders, and number of interactions, respectively; calculate the product of the first weight coefficient and the product click-through rate to obtain a first calculation result; calculate the product of the second weight coefficient and the average viewing time per person to obtain a second calculation result; calculate the product of the third weight coefficient and the number of product exposure click orders to obtain a third calculation result; calculate the product of the fourth weight coefficient and the number of interactions to obtain a fourth calculation result; accumulate the first calculation result, the second calculation result, the third calculation result, and the fourth calculation result to obtain a scoring result; filter the live broadcast script according to the scoring result to obtain a filtered live broadcast script.

7. The device according to claim 6, wherein The first acquisition module acquires the original live broadcast script, including: Get information about the product to be explained; A pre-trained large model is used to generate an original live broadcast script corresponding to the product to be explained based on the information of the product to be explained, and the original live broadcast script is executed.

8. The device according to claim 6, wherein The generating module generates a real-time live broadcast script according to the interactive information, including: Analyzing the interactive information to obtain the importance of the interactive information; Sorting the interactive information according to the importance of the interactive information to obtain a list to be responded to; According to the historical live broadcast script and the attribute information of the product to be explained, a real-time live broadcast script corresponding to the list to be responded to is generated.

9. The device according to claim 6, wherein The generating module merges the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script, including: If a return to original live broadcast script instruction is received, the real-time live broadcast script is inserted into the position where the original live broadcast script is interrupted, so as to connect the real-time live broadcast script with the original live broadcast script to obtain an updated live broadcast script.

10. The device according to claim 6, wherein The scoring module screens the live broadcast script according to the scoring result to obtain the screened live broadcast script, including: According to the scoring result, live broadcast scripts having scores greater than a preset threshold are screened out from the updated live broadcast scripts to obtain screened live broadcast scripts.

11. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.

13. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images