Bullet screen style configuration method and device

Abstract

The embodiment of the invention provides a bullet screen style configuration method and related equipment / products, and belongs to the technical field of bullet screens. The method comprises the following steps: receiving a bullet screen style configuration request of a target object for a target video sent by a client; obtaining a plurality of pre-configured bullet screen style templates, and determining a matching degree score of each bullet screen style template based on the target video; determining a related object according to the target object; determining a bullet screen style template selected by the related object from a plurality of bullet screen style templates in the related video, and taking the selected bullet screen style template as a candidate set; and based on the candidate set and the matching degree score of each bullet screen style template, determining a target bullet screen style template, and pushing the target bullet screen style template to the client. According to the technical scheme provided by the embodiment of the invention, the bullet screen style template meeting the personalized requirements and the current video playing scene can be accurately pushed to the bullet screen initiator, so that the configuration efficiency of the bullet screen style is improved, and the bullet screen interaction effect and satisfaction are enhanced.

Description

Technical Field

[0001] Embodiments of the present application relate to the technical field of bullet screen technology, and in particular, to a method, device, computer device, computer-readable storage medium, and computer program product for configuring bullet screen styles. Background Art

[0002] With the development of the Internet, more and more users watch videos through the network and send bullet screens to interact with the host or other viewers and participate in content creation. The bullet screen can be directly superimposed on the video screen and presented in a specific visual style.

[0003] However, the existing bullet screen style configuration schemes only provide limited general templates, which require users to browse and try one by one, time-consuming and laborious, and the finally selected template may be difficult to achieve the ideal display effect, affecting the bullet screen interaction experience.

[0004] It should be noted that the above content is not necessarily prior art and is not used to limit the patent protection scope of the present application. Summary of the Invention

[0005] Embodiments of the present application provide a method, device, computer device, computer-readable storage medium, and computer program product for configuring bullet screen styles to solve or alleviate one or more of the above technical problems.

[0006] One aspect of embodiments of the present application provides a method for configuring a bullet screen style, the method including: Receiving a bullet screen style configuration request sent by a client for a target object for a target video; Obtaining a plurality of pre-configured bullet screen style templates and determining a matching degree score for each bullet screen style template based on the target video; Determining a related object according to the target object, where the similarity between the related object and the target object is greater than a first preset threshold; Determining a bullet screen style template selected from the plurality of bullet screen style templates by the related object in a related video, and using the selected bullet screen style template as a candidate set; wherein, the similarity between the related video and the target video is greater than a second preset threshold; Based on the candidate set and the matching degree score of each bullet screen style template, determining a target bullet screen style template from the plurality of bullet screen style templates and pushing the target bullet screen style template to the client, where the client is used to: perform bullet screen style configuration according to the target bullet screen style template.

[0007] Optionally, determining the matching degree score for each bullet screen style template based on the target video includes: Obtaining the description information of the target video; Determine the content theme of the target video based on the described information; Determine the matching degree score of each bullet screen style template according to the content theme of the target video.

[0008] Optionally, determine relevant objects according to the target object, including: Obtain the bullet screen preference and video preference of the target object; Determine the relevant object based on the bullet screen preference and video preference of the target object; wherein, the similarity between the relevant object and the target object in the bullet screen preference and the video preference is greater than the second preset threshold.

[0009] Optionally, the bullet screen style template includes multiple display style elements, and each display style element has multiple parameters; correspondingly, obtaining the bullet screen preference and video preference of the target object includes: Obtain the historical bullet screen style data of the target object provided by the client; Determine the bullet screen preference of the target object based on the historical bullet screen style data, and the bullet screen preference includes the preference parameters corresponding to each display style element; and Obtain the historical video type data of the target object; Determine the video preference of the target object based on the historical video type data, and the video preference includes the preference degree for different video types.

[0010] Optionally, the bullet screen style templates in the candidate set are associated with similarity scores, and the similarity scores are determined based on the similarity between the relevant object and the target object and / or the similarity between the relevant video and the target video; Correspondingly, based on the candidate set and the matching degree score of each bullet screen style template, determine the target bullet screen style template from the multiple bullet screen style templates, including: Determine the weights of the similarity score and the matching degree score respectively; Determine the comprehensive score of each bullet screen style template based on the similarity score of the bullet screen style template in the candidate set, the matching degree score of each bullet screen style template, and their respective weights; Determine the target bullet screen style template from the multiple bullet screen style templates according to the comprehensive score of each bullet screen style template.

[0011] Optionally, perform bullet screen style configuration based on the target bullet screen style template, including: Display a bullet screen style configuration interface associated with the target video, and the bullet screen style configuration interface is used to display the target bullet screen style template; In response to selecting the target bullet screen style template, generate a preview bullet screen based on the target bullet screen style template and display the preview bullet screen on the target video.

[0012] Optionally, the bullet screen style configuration interface further includes a feedback control for the target bullet screen style template; correspondingly, performing bullet screen style configuration based on the target bullet screen style template further includes: In response to selecting the feedback control, generate feedback data for the target bullet screen style template; Send the feedback data to the server, and the server is used to: adjust the target bullet screen style template based on the feedback data.

[0013] Another aspect of the embodiments of the present application provides a bullet screen style configuration device, and the device includes: A receiving module, configured to receive a bullet screen style configuration request sent by a client for a target video by a target object; An obtaining module, configured to obtain a plurality of pre-configured bullet screen style templates and determine a matching degree score of each bullet screen style template based on the target video; A first determining module, configured to determine a related object according to the target object, and the similarity between the related object and the target object is greater than a first preset threshold; A second determining module, configured to determine a bullet screen style template selected from the plurality of bullet screen style templates by the related object in a related video, and use the selected bullet screen style template as a candidate set; wherein, the similarity between the related video and the target video is greater than a second preset threshold; A third determining module, configured to determine a target bullet screen style template from the plurality of bullet screen style templates based on the candidate set and the matching degree score of each bullet screen style template, and push the target bullet screen style template to the client, and the client is used to: perform bullet screen style configuration according to the target bullet screen style template.

[0014] Another aspect of the embodiments of the present application provides a computer device, including: At least one processor; and A memory communicatively connected to the at least one processor; Wherein: the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0015] Another aspect of the embodiments of the present application provides a computer-readable storage medium, and computer instructions are stored in the computer-readable storage medium, and when the computer instructions are executed by a processor, the method as described above is implemented.

[0016] Another aspect of the embodiments of the present application provides a computer program product, including a computer program, which implements the method described above when executed by a processor.

[0017] The embodiments of the present application adopting the above technical solutions may include the following advantages: The barrage style configuration request is initiated by the target object when watching the target video and sent from the client to the server. After receiving the barrage style configuration request, the server obtains multiple pre-configured barrage style templates and determines the matching degree scores of each barrage style template based on the target video. At the same time, relevant objects with high similarity are determined according to the target object, and it is determined which barrage style templates the relevant objects will select from the multiple barrage style templates in the context of similar target videos (related videos). The selected barrage style templates are determined as the preliminary candidate set. Based on the candidate set and the matching degree scores of each barrage style template, the target barrage style template to be pushed to the client is determined from the multiple barrage style templates. It can be seen that the embodiments of the present application can accurately push the barrage style template that meets the personalized needs of the barrage initiator and the current video playback scene to improve the configuration efficiency of the barrage style, enhance the barrage interaction effect, and improve the satisfaction with the barrage function. Description of the Drawings

[0018] The drawings exemplarily show the embodiments and form a part of the specification, and are used together with the written description of the specification to explain the exemplary implementation manners of the embodiments. The shown embodiments are only for illustrative purposes and do not limit the scope of the claims. In all the drawings, the same reference numerals refer to similar but not necessarily the same elements.

[0019] Figure 1 Schematically shows the operating environment diagram of the barrage style configuration method according to Embodiment 1 of the present application; Figure 2 Schematically shows the flowchart of the barrage style configuration method according to Embodiment 1 of the present application; Figure 3 Schematically shows Figure 2 The sub-step flowchart of step S202 in; Figure 4 Schematically shows Figure 2 The sub-step flowchart of step S204 in; Figure 5 Schematically shows Figure 4 The sub-step flowchart of step S400 in; Figure 6 Schematically shows Figure 2 The sub-step flowchart of step S208 in; Figure 7Schematically shows a flowchart of sub-steps of step S1000 according to Embodiment 1 of the present application; Figure 8 Schematically shows a flowchart of sub-steps of step S1000 according to Embodiment 1 of the present application; Figure 9 、 Figure 10 、 Figure 11 and Figure 12 are application example diagrams of the bullet screen style configuration method according to Embodiment 1 of the present application; Figure 13 Schematically shows a block diagram of the bullet screen style configuration device according to Embodiment 2 of the present application; and Figure 14 Schematically shows a schematic diagram of the hardware architecture of the computer device according to Embodiment 3 of the present application. Detailed implementation manners

[0020] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0021] It should be noted that the descriptions involving "first", "second", etc. in the embodiments of the present application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between various embodiments may be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present application.

[0022] In the description of the present application, it should be understood that the numerical labels before the steps do not identify the order of execution of the steps, but are only used to facilitate the description of the present application and distinguish each step, and thus cannot be understood as a limitation to the present application.

[0023] First, provide the term explanations involved in the present application: Intelligent recommendation algorithm: An algorithm based on computer algorithms and data analysis technologies that can automatically screen and push content or options that meet the user's potential needs to the user according to various information such as the user's specific behaviors, preferences, and relevant environmental factors. In the embodiments of the present application, the intelligent recommendation algorithm is used to recommend appropriate bullet screen style templates to the bullet screen initiator.

[0024] Secondly, to facilitate the understanding of the technical solutions provided by the embodiments of the present application by those skilled in the art, the related technologies are described below: With the development of the mobile Internet, video applications are becoming increasingly popular on mobile devices. Among them, bullet screens, as a characteristic function that can enhance user interaction and sense of participation, are deeply loved by users.

[0025] However, the applicant has learned that the related bullet screen style configuration solutions still have the following defects: (1) Most mobile video players only provide a limited number of general templates. Users can only browse and try them one by one, and it is difficult to quickly find a bullet screen style template that fits their own ideas and the current video viewing situation.

[0026] (2) Although some applications provide a certain degree of classification and screening functions, they lack in-depth exploration of users' personalized needs. As a result, users need to spend a lot of time and effort when configuring the bullet screen style, and the templates finally selected often do not necessarily achieve the ideal display effect, affecting the user experience in the bullet screen interaction session and reducing the enthusiasm of users to participate in bullet screen interaction.

[0027] Therefore, the embodiments of the present application provide a technical solution for bullet screen style configuration. In this technical solution: (1) Collect multi-dimensional data such as the historical bullet screen style data of bullet screen initiators, historical video types viewed, and the content theme of the currently playing video (target video), and update the collected data in real time or at regular intervals to ensure the timeliness and accuracy of the data, providing reliable basic data support for subsequent precise recommendations; (2) Based on the collected multi-dimensional data, design a unique intelligent recommendation algorithm, such as a hybrid mode that combines collaborative filtering algorithm and content theme analysis algorithm. Among them, the collaborative filtering algorithm finds the bullet screen style templates that the bullet screen initiator may be interested in by analyzing the bullet screen style templates selected by other users with similar bullet screen preferences and video preferences in a situation similar to the current video viewing situation. The content theme analysis algorithm deeply analyzes the matching degree between the content theme of the currently playing video (target video) and different bullet screen style templates in terms of visual presentation. Finally, the bullet screen style templates for pushing are determined by integrating the results of the two algorithms. This intelligent recommendation algorithm can be adaptively adjusted according to the actual application scenario, continuously optimizing the accuracy and rationality of the recommendation results; (3) Visualize and display the recommended bullet screen style templates through an intuitive and convenient bullet screen style configuration interface, and at the same time, the template features can be marked to facilitate users to quickly understand. Interactive functions can also be provided to try the bullet screen style templates with one key or give feedback. These feedbacks can be used to adjust the intelligent recommendation algorithm and further optimize the subsequent recommended content. See the following for details.

[0028] Finally, for the convenience of understanding, an exemplary operating environment is provided below.

[0029] As Figure 1 shown, the operating environment diagram includes: service platform (server) 2, and clients (4A, 4B, …, 4N).

[0030] The service platform 2 can connect to the clients (4A, 4B, …, 4N) via a network.

[0031] The service platform 2 can be a single server, a server cluster, or a cloud computing service center.

[0032] The service platform 2 can provide video services, bullet screen services, etc. to the clients.

[0033] The service platform 2 can be located in a data center such as a single location, or distributed in different geographical locations (e.g., in multiple locations). The service platform 2 can provide services via a network. The network includes various network devices such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and / or the like. The network can include physical links such as coaxial cable links, twisted pair cable links, fiber optic links, and combinations thereof, or wireless links such as cellular links, satellite links, Wi-Fi links, etc.

[0034] The clients (4A, 4B, …, 4N) can be configured to access the content and services of the service platform 2. The clients (4A, 4B, …, 4N) can include electronic devices with or external to a display panel, such as mobile devices, tablet devices, laptop computers, workstations, virtual reality devices, gaming devices, digital streaming devices, vehicle terminals, smart TVs, set-top boxes, etc., and can also include virtualized computing instances. The virtualized computing instances can include virtual machines, such as emulations of computer systems, operating systems, servers, etc. The computing device can load the virtual machine based on a virtual image and / or other data defining specific software (e.g., operating system, dedicated application, server) for emulation. As the demand for different types of processing services changes, different virtual machines can be loaded and / or terminated on one or more computing devices.

[0035] The clients (4A, 4B, …, 4N) can be associated with one or more users. A single user can also use one or more of the clients (4A, 4B, …, 4N) to access the service platform 2. The clients (4A, 4B, …, 4N) can travel to various locations and use different networks to access the service platform 2.

[0036] The client (4A, 4B, …, 4N) may include an interface. The interface may include a touchpad, a touch screen, a mouse, a keyboard, or other sensing elements. For example, the input element may be configured to receive user instructions, and the user instructions may cause the client (4A, 4B, …, 4N) to perform various operations, such as selecting a barrage style template, selecting a barrage style configuration control, inputting barrage text, and selecting a feedback control, etc.

[0037] It should be noted that the above devices are exemplary, and in different scenarios or according to different requirements, the number and types of devices are adjustable.

[0038] Taking server 2 as the execution subject below, the technical solutions of this application will be introduced through multiple embodiments. It should be noted that these embodiments can be implemented in various different forms and should not be construed as being limited only to the embodiments described herein.

[0039] Embodiment 1 Figure 2 A flowchart of a barrage style configuration method according to Embodiment 1 of this application is schematically shown.

[0040] As Figure 2 shown, the barrage style configuration method may include steps S200~S208, where: Step S200, receiving a barrage style configuration request for a target video sent by a client.

[0041] Step S202, obtaining a plurality of pre-configured barrage style templates, and determining a matching degree score for each barrage style template based on the target video.

[0042] Step S204, determining a related object according to the target object, where the similarity between the related object and the target object is greater than a first preset threshold.

[0043] Step S206, determining the barrage style template selected from the plurality of barrage style templates by the related object in a related video, and using the selected barrage style template as a candidate set. Wherein, the similarity between the related video and the target video is greater than a second preset threshold.

[0044] Step S208, determining a target barrage style template from the plurality of barrage style templates based on the candidate set and the matching degree score of each barrage style template, and pushing the target barrage style template to the client. The client is used to: perform barrage style configuration according to the target barrage style template.

[0045] In the bullet screen style configuration method provided in this embodiment, the bullet screen style configuration request is initiated by a target object while watching a target video and sent from the client to the server. After receiving the bullet screen style configuration request, the server obtains multiple pre-configured bullet screen style templates and determines the matching degree scores of each bullet screen style template based on the target video. At the same time, relevant objects with high similarity are determined according to the target object, and it is determined which bullet screen style templates the relevant objects will select from the multiple bullet screen style templates in the context of a similar target video (relevant video). The selected bullet screen style templates are determined as the preliminary candidate set. Based on the candidate set and the matching degree scores of each bullet screen style template, the target bullet screen style template to be pushed to the client is determined from the multiple bullet screen style templates. It can be seen that the embodiment of the present application can accurately push the bullet screen style template that meets the personalized needs of the bullet screen initiator and the current video playback scenario to improve the configuration efficiency of the bullet screen style, enhance the bullet screen interaction effect, and improve the satisfaction of the bullet screen function.

[0046] The following combines Figure 2 to elaborate in detail on each step in steps S200 to S208 and other optional steps.

[0047] Step S200 , receive the bullet screen style configuration request sent by the client for the target video by the target object.

[0048] The target object can be the bullet screen initiator, and the target video can be the video that the bullet screen initiator is currently watching. Exemplarily, the bullet screen initiator can watch a video through a player in a video application on the client. The player can provide a bullet screen style configuration control, and the bullet screen initiator can start the bullet screen style configuration function by performing operations such as clicking, double-clicking, long-pressing, swiping, dragging, and gestures on the bullet screen style configuration control, and generate a bullet screen style configuration request accordingly. The client can send the bullet screen style configuration request to the server in real time.

[0049] Step S202 , obtain multiple pre-configured bullet screen style templates, and determine the matching degree score of each bullet screen style template based on the target video.

[0050] After receiving the barrage style configuration request sent by the client, the server can obtain multiple pre-configured barrage style templates. Among them, the barrage style templates can include display style elements such as the font, color, size, dynamic special effects, and background pattern of the barrage text, which are used to standardize the presentation form of the sent barrage, so that the barrage shows a specific visual style on the video screen. Determine the matching degree between each barrage style template and the target video to obtain a matching degree score. The matching degree score can be used to measure the adaptability of the barrage style template to the current video playing scenario. Subsequently, template recommendation can be based on the matching degree score to improve the accuracy of the recommendation. Exemplarily, based on multi-dimensional features such as the content features of the target video (such as: video type, video theme, video mood), picture features (such as: color style, degree of dynamic change, visual complexity), audio features (such as: background music rhythm, dialogue intonation, key sound events), and text features (such as: subtitles, stickers), calculate the matching degree score between the target video and the barrage style template, thereby improving the recommendation accuracy, reducing errors, and enhancing the generalization ability of the recommendation algorithm. The following provides an exemplary solution.

[0051] In an alternative embodiment, as Figure 3 described, step S202 may include: Step S300, obtain the description information of the target video.

[0052] Step S302, based on the description information, determine the content theme of the target video.

[0053] Step S304, according to the content theme of the target video, determine the matching degree score of each barrage style template.

[0054] Exemplarily, the server can interact with the background database of the video platform to obtain the description information of the currently playing video (target video). Among them, the description information can include the video title, video tags, and content summary of the video. Through techniques such as keyword recognition, pre-trained large language models, natural language processing, or others, the content theme of the target video can be extracted from the description information. The content theme can be used to determine the main content direction of the target video. For example: If the video title includes the keyword "science fiction movie", the content theme "science fiction" can be identified. Using the content theme analysis algorithm, calculate the matching degree for all available barrage style templates according to the content theme of the target video. For example: For a target video with a science fiction theme, those templates with a technological sense of special effects and a cool color scheme can obtain a higher matching degree score.

[0055] In this embodiment, by extracting the content theme of the target video and calculating the matching degree scores of each barrage style template, it can be used for subsequent recommendation of barrage style templates that conform to the current video playing scenario, improving the recommendation accuracy in different scenarios.

[0056] Step S204 Determine relevant objects according to the target object, and the similarity between the relevant object and the target object is greater than a first preset threshold.

[0057] The relevant object can be a user who has a high similarity with the target object in multiple aspects, such as: barrage usage preferences, video viewing preferences, social relationships (such as mutual attention, common friends, common concerns), age, gender, region, language, device, network conditions, etc. The relevant object can be used to quantify the personalized needs of users and improve the recommendation accuracy of barrage style templates. The following provides an exemplary solution.

[0058] In an alternative embodiment, as Figure 4 shown, step S204 may include: Step S400, obtain the barrage preference and video preference of the target object.

[0059] Step S402, determine the relevant object based on the barrage preference and video preference of the target object; wherein, the similarity between the relevant object and the target object in the barrage preference and the video preference is greater than the second preset threshold.

[0060] Exemplarily, based on the historical behavior data of the target object, such as the sent barrages, watched videos, etc., the barrage preference and video preference of the target object can be determined. It should be noted that the data involved in the embodiments of the present application are all obtained on the premise of compliance and with the consent of the user, and have been desensitized and privacy protected. According to the preset collaborative filtering algorithm, other user groups with high similarity in barrage preference and video preference with the barrage initiator can be found, and these users are used as relevant objects.

[0061] In this embodiment, based on the barrage preference and video preference of the target video, the collaborative filtering algorithm is used to match user groups with high similarity, accurately identify relevant objects, and subsequently improve the recommendation accuracy and personalization degree of barrage style templates.

[0062] In an alternative embodiment, the barrage style template may include multiple display style elements, such as font, color, size, dynamic special effects, background pattern, etc. Each display style element may include multiple parameters. For example, the color may include red, yellow, blue, green, pink. The font may include regular script, Song typeface, boldface, etc. Correspondingly, as Figure 5 shown, step S400 may include: Step S500, obtain the historical barrage style data of the target object provided by the client.

[0063] Step S502: Determine the barrage preference of the target object based on the historical barrage style data, where the barrage preference includes preference parameters corresponding to each display style element.

[0064] Step S504: Obtain the historical video type data of the target object.

[0065] Step S506: Determine the video preference of the target object based on the historical video type data, where the video preference includes the preference degrees for different video types.

[0066] Exemplarily, after receiving a barrage style configuration request sent by a client, the server can extract historical barrage style data from the local history of the client, that is, relevant data used in past barrages. For example: query the parameters selected for each display style element (such as: font, color, special effects) when the target object sent barrages before, and count the frequency of occurrence of each parameter, thereby determining the barrage preference of the target object. Among them, the barrage preference can include preference parameters corresponding to each display style element. For example, color: blue; font: boldface; special effect: fireworks, etc. The server can also interact with the background database of the video platform to obtain the historical video type data of the target object, that is, type statistics data of past watched videos. Based on the historical video type data, it can be analyzed which video types the target object watches more frequently, which video types are watched less frequently, etc., so as to determine the video preference of the target object. Among them, the video preference can include the preference degrees for different video types, or the video type with the highest preference degree.

[0067] In this embodiment, by collecting and analyzing multi-dimensional data of the target object, the barrage preference and video preference of the target object can be determined, which are subsequently used to implement personalized recommendations and further optimize the accuracy of barrage style configuration.

[0068] Step S206 , determine the barrage style template selected by the relevant object from the multiple barrage style templates in the relevant video, and use the selected barrage style template as a candidate set; where the similarity between the relevant video and the target video is greater than a second preset threshold.

[0069] The relevant video can be a video that has a high similarity with the target video in many aspects. For example: video title, video tags, video content summary, video type, video content, video release time, etc. Obtain the barrage style templates selected by users (relevant objects) similar to the target object in a playback scenario similar to the target video (relevant video), and use these templates as a preliminary candidate set.

[0070] In this embodiment, by selecting a bullet screen style template based on similar users in a similar video playback scenario to construct a candidate set, the pertinence and adaptability of recommendations can be effectively improved.

[0071] Step S208 , based on the matching degree scores between the candidate set and each bullet screen style template, determine the target bullet screen style template from the multiple bullet screen style templates, and push the target bullet screen style template to the client. The client is used for: Step S1000, perform bullet screen style configuration according to the target bullet screen style template.

[0072] Exemplarily, corresponding weights can be assigned to the collaborative filtering results (candidate set) and the content theme analysis results (matching degree scores of each bullet screen style template), where the weights can be dynamically adjusted according to the actual application effects and verification situations of the bullet screen style configuration. According to the assigned weights, combining the collaborative filtering results and the content theme analysis results, sort the available bullet screen style templates to determine the final recommendation list, and the recommendation list can include one or more target bullet screen style templates. The target bullet screen style template can be used to configure a bullet screen whose visual style simultaneously adapts to the personalized needs of the target object and the current video playback scenario, improving the bullet screen interaction effect. After determining the target bullet screen style template, the server can push the target bullet screen style template to the client so that the target object can perform bullet screen style configuration based on the target bullet screen style template through the client. The following provides an exemplary solution.

[0073] In an alternative embodiment, the bullet screen style templates in the candidate set can be associated with similarity scores, where the similarity scores can be determined based on the similarity between the relevant object and the target object and / or the similarity between the relevant video and the target video. Correspondingly, as Figure 6 shown, Step S208 can include: Step S600, determine the respective weights of the similarity scores and the matching degree scores.

[0074] Step S602, based on the similarity scores of the bullet screen style templates in the candidate set, the matching degree scores of each bullet screen style template, and their respective weights, determine the comprehensive score of each bullet screen style template.

[0075] Step S604, according to the comprehensive scores of each bullet screen style template, determine the target bullet screen style template from the multiple bullet screen style templates.

[0076] Exemplarily, different weights can be assigned to the similarity score and the matching score according to the actual situation, such as: similarity score × 0.4, matching score × 0.6, etc. By performing weighted summation based on the similarity score, the matching score, and their respective weights, the comprehensive score of each bullet screen style template can be obtained. Among them, for the bullet screen style templates not in the candidate set, the similarity score can be set to zero. Sorting the comprehensive scores of multiple bullet screen style templates can select the top N bullet screen style templates with the highest comprehensive scores as the target bullet screen style templates for recommendation.

[0077] In this embodiment, by weighted fusion of the similarity score and the matching score and screening high-score templates for recommendation, it can simultaneously adapt to the personalized needs of users and the current video playback scenario, improving the recommendation accuracy and personalization level.

[0078] In an alternative embodiment, as Figure 7 described, step S1000 may include: Step S700, displaying a bullet screen style configuration interface associated with the target video, where the bullet screen style configuration interface is used to display the target bullet screen style template.

[0079] Step S702, in response to selecting the target bullet screen style template, generating a preview bullet screen based on the target bullet screen style template and displaying the preview bullet screen on the target video.

[0080] Exemplarily, the bullet screen style configuration interface can be displayed in the player (overlayed on the target video screen), and of course, it can also be displayed in an area outside the player. The bullet screen style configuration interface is used to display the target bullet screen style template, for example: visualizing and displaying it in the form of thumbnails. In some embodiments, the target bullet screen style template can also be displayed in association with prompt information, and the prompt information can be used to mark the main features of the template, such as: a cool special effect style, suitable for game videos, etc. The bullet screen style configuration interface can also provide interaction controls for the target bullet screen style template. In response to the target object selecting the target bullet screen style template through the interaction controls, it can be tried out with one key and the simulated bullet screen sending effect can be viewed, that is, generating a preview bullet screen and displaying it on the target video.

[0081] In this embodiment, providing a visual bullet screen configuration style interface and an interactive preview function enables users to efficiently and conveniently select a suitable bullet screen style template, improving the convenience and experience of bullet screen style configuration.

[0082] In an alternative embodiment, the bullet screen style configuration interface may further include a feedback control for the target bullet screen style template. Correspondingly, as Figure 8 shown, step S1000 may further include: Step S800: Generate feedback data for the target bullet screen style template in response to the selection of the feedback control.

[0083] Step S802: Send the feedback data to the server, which is used to adjust the target bullet screen style template based on the feedback data.

[0084] Exemplarily, the feedback control may include a first option (for marking like), a second option (for marking dislike), and a text input box (for receiving the user's evaluation of the target bullet screen style template, such as the color is too bright or the font is not beautiful). In response to the selection of the feedback control, feedback data for the target bullet screen style template can be generated. The client can send the feedback data to the server, and the server can adjust weights, recommendation algorithms, data sources, etc. according to this feedback data, re-determine the target bullet screen style template for recommendation, and further optimize the subsequent recommended content.

[0085] In this embodiment, a user feedback mechanism is introduced to dynamically optimize the bullet screen style template recommendation algorithm, further improving the personalization level, accuracy, and user satisfaction of the recommendation.

[0086] To make the present application easier to understand, the following provides Figures 9 - 12 an exemplary application.

[0087] S1: Collect data from data sources such as the user's (bullet screen initiator, target object) local history records and the video platform database through a multi-dimensional data collection module. The collected data will be sorted and stored in a dedicated data warehouse for subsequent algorithm calls.

[0088] Among them, font preferences, color preferences, and other preferences can be collected from the user's local history records to obtain bullet screen preferences. Video preferences and description information (including content themes) of the target video (the currently playing video) can be collected from the video platform database. The data is summarized and integrated and provided to the intelligent recommendation algorithm module.

[0089] S2: Receive the collected data through the intelligent recommendation algorithm module: Through the collaborative filtering algorithm module, calculate the user similarity based on the barrage preferences and video preferences to determine relevant objects. And based on the barrage style templates selected by the relevant objects in the playing scenarios of similar target videos, filter them out and determine them as the preliminary candidate set (i.e., the collaborative filtering result); Through the content feature (theme) analysis algorithm module, extract and quantify the features of the description information to obtain the content theme of the target video. Based on the content theme, calculate the matching degree of the available barrage style templates to obtain the matching degree score (i.e., the content feature analysis result). Integrate the collaborative filtering result and the content feature analysis result, and sort them to generate a recommendation list. The recommendation list includes one or more target barrage style templates. Push the recommendation list to the client.

[0090] Among them, the client can display a barrage style configuration interface, and the barrage style configuration interface can include a recommended template thumbnail display area, a trial button, a feedback input box, a submit feedback button, etc. The barrage initiator selects the trial button to simulate the display effect of the barrage on the video playback screen. The barrage initiator inputs feedback and selects the submit feedback button to generate feedback data. The client can send the feedback data to the server, and the server can receive the feedback data and optimize and adjust the intelligent recommendation algorithm module and the multi-dimensional data collection module based on the feedback data.

[0091] In this exemplary application, (1) Collect multi-dimensional data such as the historical barrage style data of the barrage initiator, the historical video types watched, and the content theme of the currently played video (target video), and update the collected data in real time or regularly to ensure the timeliness and accuracy of the data, providing reliable basic data support for subsequent accurate recommendations; (2) Design a unique intelligent recommendation algorithm based on the collected multi-dimensional data, such as adopting a hybrid mode of the collaborative filtering algorithm combined with the content theme analysis algorithm. Among them, the collaborative filtering algorithm finds the templates that the barrage initiator may be interested in by analyzing the barrage style templates selected by other users with similar barrage preferences and video preferences in similar current viewing video scenarios. The content theme analysis algorithm deeply analyzes the matching degree between the content theme of the currently played video (target video) and different barrage style templates in visual presentation. Finally, determine the barrage style templates for pushing by integrating the results of the two algorithms. This intelligent recommendation algorithm can be adaptively adjusted according to the actual application scenario, continuously optimizing the accuracy and rationality of the recommendation results. (3) Visualize and display the recommended barrage style templates through an intuitive and convenient barrage style configuration interface, and at the same time, the template features can be marked to facilitate users to quickly understand. Interactive functions can also be provided to try the barrage style templates with one key or give feedback. These feedbacks can be used to adjust the intelligent recommendation algorithm and further optimize the subsequent recommended content.

[0092] Embodiment 2 Figure 13 Schematically shown is a block diagram of a bullet screen style configuration device according to Embodiment 2 of the present application. The device can be divided into one or more program modules. One or more program modules are stored in a storage medium and executed by one or more processors to complete the embodiments of the present application. The program modules referred to in the embodiments of the present application refer to a series of computer program instruction segments that can complete specific functions. The following description will specifically introduce the functions of each program module in this embodiment. As Figure 13 shown, the device 1000 may include: a receiving module 1100, an obtaining module 1200, a first determination module 1300, a second determination module 1400, and a third determination module 1500, where: The receiving module 1100 is configured to receive a bullet screen style configuration request sent by a client for a target object with respect to a target video; The obtaining module 1200 is configured to obtain a plurality of pre-configured bullet screen style templates, and determine a matching degree score for each bullet screen style template based on the target video; The first determination module 1300 is configured to determine a related object according to the target object, where the similarity between the related object and the target object is greater than a first preset threshold; The second determination module 1400 is configured to determine a bullet screen style template selected from the plurality of bullet screen style templates by the related object in a related video, and use the selected bullet screen style template as a candidate set; where the similarity between the related video and the target video is greater than a second preset threshold; The third determination module 1500 is configured to determine a target bullet screen style template from the plurality of bullet screen style templates based on the candidate set and the matching degree score of each bullet screen style template, and push the target bullet screen style template to the client, and the client is configured to: perform bullet screen style configuration according to the target bullet screen style template.

[0093] As an optional embodiment, determining a matching degree score for each bullet screen style template based on the target video includes: Obtaining description information of the target video; Based on the description information, determining a content theme of the target video; According to the content theme of the target video, determining a matching degree score for each bullet screen style template.

[0094] As an optional embodiment, determining a related object according to the target object includes: Obtaining the bullet screen preference and video preference of the target object; Determine the relevant object based on the barrage preference and video preference of the target object; wherein, the similarity between the relevant object and the target object in terms of the barrage preference and the video preference is greater than the second preset threshold.

[0095] As an optional embodiment, the barrage style template includes a plurality of display style elements, and each display style element has a plurality of parameters; correspondingly, obtaining the barrage preference and video preference of the target object includes: Obtain the historical barrage style data of the target object provided by the client; Based on the historical barrage style data, determine the barrage preference of the target object, where the barrage preference includes the preference parameters corresponding to each display style element; and Obtain the historical video type data of the target object; Based on the historical video type data, determine the video preference of the target object, where the video preference includes the preference degrees for different video types.

[0096] As an optional embodiment, the barrage style templates in the candidate set are associated with similarity scores, and the similarity scores are determined based on the similarity between the relevant object and the target object and / or the similarity between the relevant video and the target video; Correspondingly, based on the matching degree scores of the candidate set and each barrage style template, determining the target barrage style template from the multiple barrage style templates includes: Determine the weights of the similarity scores and the matching degree scores respectively; Based on the similarity scores of the barrage style templates in the candidate set, the matching degree scores of each barrage style template, and their respective weights, determine the comprehensive scores of each barrage style template; According to the comprehensive scores of each barrage style template, determine the target barrage style template from the multiple barrage style templates.

[0097] As an optional embodiment, performing barrage style configuration based on the target barrage style template includes: Display a barrage style configuration interface associated with the target video, and the barrage style configuration interface is used to display the target barrage style template; In response to selecting the target barrage style template, generate a preview barrage based on the target barrage style template and display the preview barrage on the target video.

[0098] As an optional embodiment, the barrage style configuration interface further includes a feedback control for the target barrage style template; correspondingly, performing barrage style configuration based on the target barrage style template further includes: In response to selecting the feedback control, feedback data for the target bullet screen style template is generated; The feedback data is sent to the server, which is used to: adjust the target bullet screen style template based on the feedback data.

[0099] Embodiment III Figure 14 The hardware architecture diagram of a computer device 10000 suitable for implementing the bullet screen style configuration method according to Embodiment III of the present application is schematically shown. In some embodiments, the computer device 10000 may be a terminal device such as a smart phone, a wearable device, a tablet computer, a personal computer, a vehicle-mounted terminal, a game console, a virtual device, a workbench, a digital assistant, a set-top box, a robot, etc. In other embodiments, the computer device 10000 may be a rack-mounted server, a blade server, a tower server or a cabinet server (including an independent server or a server cluster composed of multiple servers). As Figure 14 shown, the computer device 10000 includes, but is not limited to: a memory 10010, a processor 10020, and a network interface 10030 that can communicate with each other through a system bus. Among them: The memory 10010 includes at least one type of computer-readable storage medium. The readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 10010 may be an internal storage module of the computer device 10000, such as the hard disk or memory of the computer device 10000. In other embodiments, the memory 10010 may also be an external storage device of the computer device 10000, such as a plug-in hard disk equipped on the computer device 10000, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Of course, the memory 10010 may also include both the internal storage module and the external storage device of the computer device 10000. In this embodiment, the memory 10010 is generally used to store the operating system and various application software installed on the computer device 10000, such as the program code of the bullet screen style configuration method. In addition, the memory 10010 may also be used to temporarily store various data that have been output or will be output.

[0100] In some embodiments, the processor 10020 may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other chips. The processor 10020 is generally used to control the overall operation of the computer device 10000, such as performing control and processing related to data interaction or communication with the computer device 10000. In this embodiment, the processor 10020 is used to run the program code stored in the memory 10010 or process data.

[0101] The network interface 10030 may include a wireless network interface or a wired network interface. The network interface 10030 is generally used to establish a communication link between the computer device 10000 and other computer devices. For example, the network interface 10030 is used to connect the computer device 10000 to an external terminal through a network, and establish a data transmission channel and a communication link between the computer device 10000 and the external terminal. The network can be an enterprise internal network (Intranet), the Internet, the Global System of Mobile communication (abbreviated as GSM), Wideband Code Division Multiple Access (abbreviated as WCDMA), 4G network, 5G network, Bluetooth, Wi-Fi and other wireless or wired networks.

[0102] It should be noted that Figure 14 Only the computer device with components 10010 - 10030 is shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0103] In this embodiment, the bullet screen style configuration method stored in the memory 10010 can also be divided into one or more program modules and executed by one or more processors (such as the processor 10020) to complete the embodiments of the present application.

[0104] Embodiment 4 The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the bullet screen style configuration method in the embodiments are implemented.

[0105] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the computer-readable storage medium may be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device. Of course, the computer-readable storage medium may also include both the internal storage unit and the external storage device of the computer device. In this embodiment, the computer-readable storage medium is generally used to store the operating system and various application software installed on the computer device, such as the program code of the bullet screen style configuration method in the embodiment. In addition, the computer-readable storage medium can also be used to temporarily store various data that have been output or will be output.

[0106] Embodiment 5 The embodiment of the present application also provides a computer program product, including a computer program, which implements the method in the above embodiment when executed by a processor.

[0107] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the embodiments of the present application can be implemented by a general computer device. They can be concentrated on a single computer device or distributed on a network composed of multiple computer devices. Optionally, they can be implemented by program codes executable by the computer device. Thus, they can be stored in a storage device and executed by the computer device. And in some cases, the steps shown or described can be executed in a different order from here, or they can be separately made into individual integrated circuit modules, or multiple modules or steps among them can be made into a single integrated circuit module to implement. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0108] It should be noted that the above are only the preferred embodiments of the present application, and do not limit the patent protection scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for configuring a bullet screen style, characterized in that, For a server, the method includes: Receiving a barrage style configuration request for a target video sent by a client; Obtaining a plurality of pre-configured barrage style templates, and determining a matching degree score for each barrage style template based on the target video; Determining a related object according to the target object, where the similarity between the related object and the target object is greater than a first preset threshold; Determining the barrage style template selected from the plurality of barrage style templates by the related object in a related video, and using the selected barrage style template as a candidate set; wherein, the similarity between the related video and the target video is greater than a second preset threshold; Based on the candidate set and the matching degree scores of each barrage style template, determining a target barrage style template from the plurality of barrage style templates, and pushing the target barrage style template to the client, where the client is configured to: perform barrage style configuration according to the target barrage style template.

2. The method according to claim 1, wherein Determining the matching degree score for each barrage style template based on the target video includes: Obtaining description information of the target video; Based on the description information, determining the content theme of the target video; According to the content theme of the target video, determining the matching degree score for each barrage style template.

3. The method according to claim 1, wherein Determining a related object according to the target object includes: Obtaining the barrage preference and video preference of the target object; Based on the barrage preference and video preference of the target object, determining the related object; wherein, the similarity between the related object and the target object in terms of the barrage preference and the video preference is greater than the second preset threshold.

4. The method according to claim 1, characterized in that The barrage style template includes a plurality of display style elements, and each display style element has a plurality of parameters; correspondingly, obtaining the barrage preference and video preference of the target object includes: Obtaining the historical barrage style data of the target object provided by the client; Based on the historical barrage style data, determining the barrage preference of the target object, where the barrage preference includes the preference parameters corresponding to each display style element; and Obtaining the historical video type data of the target object; Based on the historical video type data, determining the video preference of the target object, where the video preference includes the preference degree for different video types.

5. The method according to claim 1, wherein The barrage style template of the candidate set is associated with a similarity score, and the similarity score is determined based on the similarity between the related object and the target object and / or the similarity between the related video and the target video; Correspondingly, based on the candidate set and the matching degree scores of each barrage style template, determining a target barrage style template from the plurality of barrage style templates includes: Determining the respective weights of the similarity score and the matching degree score; Based on the similarity score of the barrage style template of the candidate set, the matching degree score of each barrage style template, and their respective weights, determining the comprehensive score of each barrage style template; According to the comprehensive score of each barrage style template, determining the target barrage style template from the plurality of barrage style templates.

6. The method according to claim 1, wherein Performing barrage style configuration based on the target barrage style template includes: Display a bullet screen style configuration interface associated with the target video, where the bullet screen style configuration interface is used to display the target bullet screen style template; In response to selecting the target bullet screen style template, generate a preview bullet screen based on the target bullet screen style template and display the preview bullet screen on the target video.

7. The method according to claim 6, characterized in that, The bullet screen style configuration interface further includes a feedback control for the target bullet screen style template; correspondingly, performing bullet screen style configuration based on the target bullet screen style template further includes: In response to selecting the feedback control, generate feedback data for the target bullet screen style template; Send the feedback data to the server, where the server is configured to: adjust the target bullet screen style template based on the feedback data.

8. A bullet screen style configuration device, characterized in that, For a server, the apparatus includes: A receiving module, configured to receive a bullet screen style configuration request sent by a client for a target object with respect to a target video; An obtaining module, configured to obtain a plurality of pre-configured bullet screen style templates and determine a matching degree score for each bullet screen style template based on the target video; A first determining module, configured to determine a related object according to the target object, where the similarity between the related object and the target object is greater than a first preset threshold; A second determining module, configured to determine a bullet screen style template selected from the plurality of bullet screen style templates by the related object in a related video and use the selected bullet screen style template as a candidate set; wherein, the similarity between the related video and the target video is greater than a second preset threshold; A third determining module, configured to determine a target bullet screen style template from the plurality of bullet screen style templates based on the candidate set and the matching degree score of each bullet screen style template, and push the target bullet screen style template to the client, where the client is configured to: perform bullet screen style configuration according to the target bullet screen style template.

9. A computer device, characterized in that, Includes: At least one processor; And A memory communicatively connected to the at least one processor; wherein: The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the method according to claims 1 to 7 are implemented.

Images