Information display method and device, computer equipment and storage medium

Abstract

The present disclosure provides a method and apparatus, a computer device, and a storage medium for displaying information, the method including the steps of: obtaining a plurality of search terms related to a target video, the plurality of search terms including a first search term for initiating a search after viewing the target video, and a second search term for initiating a search after viewing the target video and comments corresponding to the target video; displaying video search terms in association with the playback page of the target video, the video search terms being determined based on the first search terms and related to video features of the target video; and displaying general search terms on the comment page of the target video, the general search terms being determined based on the first search terms and the second search terms and related to video features and / or comment features of the comments.

Description

[Technical Field]

[0001] [CROSS-REFERENCE TO RELATED APPLICATIONS] This application claims priority from Chinese Patent Application No. 202310315733.3 filed on March 28, 2023, and the entire contents of the above Chinese patent application are incorporated herein by reference.

[0002] [Technical field] The present disclosure relates to information display methods and apparatus, computer devices and storage media. [Background technology]

[0003] On video playback platforms, users can view comments below a video after watching it. After viewing this information, users may develop an expanded search need for parts of their interest. In such cases, search information is displayed in relevant positions in the video and comments. However, because comments generally contain extensive discussion content that is not included in the video, search terms displayed in relation to the video may be unrelated to the video but related to the comments. In such cases, after watching the video, users may select the search content and not perform an expanded search, which wastes the displayed information and degrades the user experience. Summary of the Invention

[0004] Embodiments of the present disclosure provide at least an information display method and apparatus, a computer device, and a storage medium.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for displaying information, the method including the steps of: obtaining a plurality of search terms related to a target video, the plurality of search terms including a first search term to be searched after viewing the target video, and a second search term to be searched after viewing the target video and comments corresponding to the target video; displaying video search terms in association with a playback page of the target video, the video search terms being determined based on the first search terms and related to video features of the target video; and displaying general search terms on a comment page of the target video, the general search terms being determined based on the first search terms and the second search terms and related to the video features and / or comment features of the comments.

[0006] In one optional embodiment, the method further includes a step of determining target search terms based on rating information corresponding to each search term, where the target search terms include video search terms and comment search terms, and the rating information of the search terms is determined based on at least one of information including the number of historical searches for the search terms in the target video, consumption results corresponding to search results related to the search terms, and behavior information of related searches that occur after the search results are displayed.

[0007] In one optional embodiment, content attribute features that satisfy predetermined consumption conditions within a current period are determined, and the predetermined consumption conditions include at least one of a condition that the number of searches corresponding to search terms that match the content attribute features exceeds a predetermined number of searches, and a condition that the consumption amount corresponding to multimedia content that matches the content attribute features exceeds a predetermined consumption amount, and in response to any one of a plurality of search terms being related to the content attribute features, the target search term is dynamically determined by updating the target search term to the search term.

[0008] In one optional embodiment, the method further includes a step of determining the correlation between each search term and the video features and / or comment features by inputting the target video and the search term as input data into a pre-trained correlation detection model and having the correlation detection model output the correlation between the search term and the video features of the target video and / or comment features of the comments, wherein the correlation detection model includes a first detection model and a second detection model, the first detection model is used to detect the correlation between the search term and the video features, and the second detection model is used to detect the correlation between the search term and the video features and / or the comment features.

[0009] In one optional embodiment, the step of displaying general search terms on the comment page of the target video includes the steps of: displaying at least one comment content and a general search term related to the at least one comment content on the comment page in response to a comment viewing operation; and displaying updated comment content and a general search term related to the updated comment content in response to a slide operation on the comment page.

[0010] In one optional embodiment, the step of displaying video search terms in association with the playback page of the target video includes updating and displaying video search terms associated with the currently played video segment on the playback page, wherein the target video includes a plurality of video segments each including at least one video frame, and each video segment is associated with a corresponding video search term.

[0011] In one optional embodiment, the video features of the target video include video features in at least one video dimension of the target video, and the video dimensions include at least one of a video description dimension corresponding to descriptive information of the target video, a video content dimension corresponding to screen content shown in the target video, and a viewing behavior dimension corresponding to the user's viewing behavior in the target video.

[0012] In a second aspect, an embodiment of the present disclosure further provides an information display device, the device including: an acquisition module for acquiring a plurality of search terms related to a target video, the plurality of search terms including a first search term to start searching after viewing the target video and a second search term to start searching after viewing the target video and comments corresponding to the target video; a first display module for displaying video search terms in association with the playback page of the target video, the video search terms being determined based on the first search terms and related to video features of the target video; and a second display module for displaying general search terms on the comment page of the target video, the general search terms being determined based on the first search terms and the second search terms and related to the video features and / or comment features of the comments.

[0013] In one optional embodiment, the device further includes a processing module for determining target search terms based on rating information corresponding to each search term, where the target search terms include video search terms and comment search terms, and the rating information of the search terms is determined based on at least one of the following information: the number of historical searches for the search terms in the target video, consumption results corresponding to search results related to the search terms, and behavioral information of related searches occurring after displaying the search results.

[0014] In one optional embodiment, content attribute features that satisfy predetermined consumption conditions within a current period are determined, and the predetermined consumption conditions include at least one of a condition that the number of searches corresponding to search terms that match the content attribute features exceeds a predetermined number of searches, and a condition that the consumption amount corresponding to multimedia content that matches the content attribute features exceeds a predetermined consumption amount, and in response to any search term among a plurality of search terms being related to the content attribute features, the target search term is dynamically determined by updating the target search term.

[0015] In one optional embodiment, the correlation between each search term and the video features and / or comment features is determined by inputting the target video and the search term as input data into a pre-trained correlation detection model and causing the correlation detection model to output correlations between the search term and the video features of the target video and / or comment features of the comments, and the correlation detection model includes a first detection model and a second detection model, wherein the first detection model is used to detect correlations between the search term and the video features, and the second detection model is used to detect correlations between the search term and the video features and / or the comment features.

[0016] In one optional embodiment, the second display module is used to, when displaying general search terms on the comment page of the target video, display at least one comment content and general search terms related to the at least one comment content on the comment page in response to a comment viewing operation, and to display updated comment content and general search terms related to the updated comment content in response to a slide operation on the comment page.

[0017] In one optional embodiment, when displaying video search terms in association with the playback page of the target video, the first display module is used to update and display video search terms associated with the currently played video segment on the playback page, wherein the target video includes multiple video segments each including at least one video frame, and each video segment is associated with a corresponding video search term.

[0018] In one optional embodiment, the video features of the target video include video features in at least one video dimension of the target video, and the video dimensions include at least one of a video description dimension corresponding to descriptive information of the target video, a video content dimension corresponding to screen content shown in the target video, and a viewing behavior dimension corresponding to the user's viewing behavior in the target video.

[0019] In a third aspect, an optional embodiment of the present disclosure further provides a computing device, the computing device including a processor and a memory, the memory storing machine-readable instructions executable by the processor, the processor being adapted to execute the machine-readable instructions stored in the memory, the machine-readable instructions, when executed by the processor, performing the steps of the first aspect above or any one of the possible embodiments of the first aspect.

[0020] In a fourth aspect, an optional embodiment of the present disclosure further provides a computer-readable storage medium having stored thereon a computer program that, when executed, performs the steps of the first aspect or any one of the optional embodiments of the first aspect.

[0021] In order to make the above objects, features and advantages of the present disclosure more clearly comprehensible, preferred embodiments will be described in detail below in conjunction with the drawings. [Brief explanation of the drawings]

[0022] In order to more clearly explain the technical solutions of the embodiments of the present disclosure, the drawings that need to be used in the embodiments will be briefly described below. The drawings herein are incorporated into and constitute a part of this specification, and these drawings show embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure. It can be understood that the following drawings only show some embodiments of the present disclosure, and therefore should not be considered as limiting the scope, and those skilled in the art can also obtain other related drawings based on these drawings without paying creative labor.

[0023] [Figure 1] 1 is a flowchart of an information display method provided in an embodiment of the present disclosure. [Figure 2]FIG. 1 is a schematic diagram displaying target search terms provided in an embodiment of the present disclosure. [Figure 3] 1 is a schematic diagram showing different video search terms when playing target videos provided in an embodiment of the present disclosure; [Figure 4] FIG. 1 is a schematic diagram of a comment page provided in an embodiment of the present disclosure, displaying comment content and general search terms. [Figure 5] 1 is a flowchart illustrating a specific implementation of an information display method provided in an embodiment of the present disclosure. [Figure 6] 1 is a schematic diagram of an information display device provided in an embodiment of the present disclosure. [Figure 7] FIG. 1 is a schematic diagram of a computer device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. The components of the embodiments of the present disclosure generally described and illustrated herein can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present disclosure is not intended to limit the scope of the present disclosure for which protection is sought, but only represents selected embodiments of the present disclosure. All other embodiments obtained based on the embodiments of the present disclosure without the need for creative efforts by those skilled in the art fall within the scope of protection of the present disclosure.

[0025] Research has shown that on video viewing platforms, users can obtain information by viewing videos and the comments below them, but their information needs are not limited to this. As users view videos and comments, they also have extended search needs (more detailed search needs) for parts of their interest. In some cases, users' consumption order is to watch a video and then view comments, and the comments may contain extended discussion content about the video. When displaying extended search terms, the search terms displayed in connection with a video may be unrelated to the video but related to the comments. In this case, users will not select the search content to perform an extended search after watching the video, which wastes the displayed information and degrades the user experience.

[0026] Based on the above research, the present disclosure provides a method for displaying information, which first obtains multiple search terms related to a target video, the multiple search terms including a first search term to be searched after viewing the target video and a second search term to be searched after viewing the target video and comments. When displaying the search terms in association with the playback page of the target video, video search terms related to the video features of the target video are selected from the first search terms and displayed. When displaying the search terms in association with the comment page of the target video, comprehensive search terms related to the video features and / or comment features of the comments are displayed from the first search terms and the second search terms. In this way, when displaying search terms in association with the target video and comments, the content range (content range) currently being viewed by the user is fully taken into consideration, and the selection also takes into account the relevance of the search terms to the target video or comments through the video features and / or comment features. After a user views some content, the platform can provide search terms related to the content the user viewed, thereby meeting the user's extensive search needs for content of interest and reducing the waste of displayed information.

[0027] The deficiencies in the above solutions are all the result of the inventor's practice and thorough research. Therefore, the process of discovering the above problems and the solutions to the above problems in the following disclosure are both contributions made by the inventor to the present disclosure during the disclosure process.

[0028] It should be noted that in the following drawings, like numerals and letters represent like items, so once an item is defined in a drawing, it does not need to be further defined and interpreted in the next drawing.

[0029] To facilitate understanding of the present embodiment, the method for displaying information disclosed in the embodiments of the present disclosure will first be described in detail. The execution entity of the method for displaying information provided in the embodiments of the present disclosure is generally a computer device having a certain degree of computing power, and the computer device may be, for example, a terminal device, a server, or other processing device, and the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a mobile phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, an in-vehicle device, a wearable device, etc. In some possible embodiments, the method for displaying information can be realized by a processor calling computer-readable instructions stored in a memory.

[0030] The following describes a method for displaying information provided by an embodiment of the present disclosure. The method for displaying information provided in the embodiment of the present disclosure can be specifically applied to video playback platforms, such as short video playback platforms and shopping platforms that allow users to play videos. These platforms provide a function for viewing comments below videos in addition to the function for playing videos. The comments below videos may be information posted by users who watch the videos, and generally include comments related to the content of the video, but may also include comments that go beyond the content of the video itself.

[0031] For example, a target video played on the platform records the daily life of User A, and since User A resembles a certain celebrity A, the comments under the target video may contain multiple comments centered on the similarities between User A and celebrity A, so "celebrity A" may be displayed as a search term. When displaying the search term, it may be displayed in relation to the target video or in relation to the comments.

[0032] In one case, since the order in which users view a target video and comments is generally to watch the target video first and then the comments, when the search term "celebrity A" is displayed in association with the target video, "celebrity A" is actually only associated with the comments and not the content contained in the target video itself, so users who only watch the target video will not search for it as content of interest, and the displayed information will be wasted. Using the information display method in the embodiments of the present disclosure, the search terms to be displayed in association with the target video and comments can be determined based on the user's information acquisition habits for the target video and comments and the relevance of the search terms to the corresponding features of the target video and comments. In this way, after the user has viewed some content, the platform can provide search terms related to the content the user has viewed, thereby meeting the user's demand for extensive search for content of interest.

[0033] As shown in FIG. 1, FIG. 1 is a flowchart of a method for displaying information provided by an embodiment of the present disclosure, the method including steps S101 to S103: S101: Obtaining a plurality of search terms related to a target video, the plurality of search terms including a first search term that starts a search after viewing the target video, and a second search term that starts a search after viewing the target video and comments corresponding to the target video.

[0034] S102: Displaying a video search term associated with the playback page of the target video, the video search term being determined based on the first search term and related to video features of the target video.

[0035] S103: Displaying a general search term on the comment page of the target video, the general search term being determined based on the first search term and the second search term and related to the video features and / or comment features of the comments.

[0036] Next, the above steps S101 to S103 will be described in detail.

[0037] Regarding the above S101, the target video will be described first. In the embodiments of the present disclosure, the target video is different for different scenes. For example, in the short video platform described above, the target video may be any short video played by users on the platform; or in the shopping platform described above, the target video may be a product introduction video introducing products or a live video, which is specifically determined according to the actual application scenario.

[0038] A plurality of search terms related to the target video can also be acquired. The search terms described herein include search terms that initiate a search after viewing specific content. Specifically, the plurality of search terms can include a first search term and a second search term. The first search term is displayed in association with the target video, so a search term initiated by a user viewing only the video is selected as the first search term when acquired. Regarding the second search term, the second search term is displayed in association with comment information corresponding to the target video, so a search term initiated by a user viewing the target video and comments is selected as the second search term.

[0039] Here, for example, the target video may be, for example, User A's daily life, specifically including User A's work and study routines. When determining the first search term, for a user who only watches the target video, the only information acquired from the target video is User A's work and study routines. Therefore, after watching the target video, the user may initiate a search for a term related to the video content, such as "report work summary" or "foreign language learning." Alternatively, the user may initiate a search for a term less related to the content of the target video, such as another associated search term, such as "time planning management." These search terms may be search terms that one or more users initiate after watching the target video, and are referred to as first search terms in the embodiments of the present disclosure.

[0040] After viewing a target video, users typically also view comments corresponding to the target video. Comments are typically discussion-style information posted by other users about the target video, and therefore may contain more diverse and expansive information than the content itself contained in the target video. In one possible scenario, the comments include information about the video. In this case, the search term initiated by a user after viewing the comments may include a search term such as "foreign language learning." Continuing with the example above, another possible scenario is that the comments may contain multiple pieces of information centered on the similarity between User A and Celebrity A. After viewing the comments, a user may also search for Celebrity A, for example, searching for "Celebrity A" or "Photo of Celebrity A." In both of the above scenarios, the search term initiated by the search may be a secondary search term.

[0041] Regarding S102 and S103 above, the first and second search terms determined in the above steps can be used to determine video search terms to be associated with the target video and displayed, and general search terms to be associated with the comments and displayed.

[0042] Here, the video search term is determined based on the first search term and is related to the video features of the target video, and the overall search term is determined based on the first search term and the second search term and is related to the video features and / or comment features of the comments.

[0043] Next, a method for determining video search terms and general search terms will be described. The video search terms and general search terms are determined from search terms such as corresponding first search terms or first search terms and second search terms, respectively, and are related to feature information such as video features or video features and / or comment features of comments. Therefore, in the embodiments of the present disclosure, both video search terms and general search terms are used as target search terms, that is, the target search terms include video search terms and general search terms, and a method for determining target search terms will be described.

[0044] In a specific embodiment, target search terms can be determined based on evaluation information corresponding to each search term, where the target search terms include video search terms and comment search terms, and the evaluation information for the search terms is determined based on at least one of the following information: the number of historical searches for the search terms in the target video, consumption results corresponding to search results related to the search terms, and behavioral information of related searches occurring after the search results are displayed.

[0045] Here, due to limitations on the display area when displaying target search terms, only a limited number of target search terms can be displayed. For example, one or two search terms are displayed in association with a target video or comment. Therefore, it is necessary to filter and determine the target search terms for display from among the determined multiple search terms. In this case, it is possible to determine whether any search term is more suitable for display as a target search term based on evaluation information.

[0046] Here, when determining whether a search term is suitable for display as a target search term, multiple dimensions can be considered. For example, whether the search term has been searched multiple times in the target video can prove that the search term has a normal demand for extended search after a user watches the target video. Therefore, by displaying the search term, a user can quickly and easily obtain information about the search term by triggering the search term.

[0047] In addition, it is possible to consider whether the search results related to the search term match the user's extended search intent, thereby verifying the search efficiency of the search term. For example, in the above example, the information obtained by the user system from the target search term is the specific appearance of Celebrity A, but the search results for the search term "photos of Celebrity A" include all photos that directly display Celebrity A's appearance, and the search results for the search term "Celebrity A" may include information such as musical works and news articles related to that person, but such information such as musical works and news articles cannot directly allow the user to understand the specific appearance of that person. Therefore, compared with the latter search term, the related search results for the former search term are more in line with the extended search demand for the target video, and are therefore more suitable for display as the target search term.

[0048] In addition, behavioral information of related searches that occur after displaying search results related to a search term can be taken into account, thereby determining whether the search results are effectively consumed and therefore inferring whether the search term is suitable for display as a target search term. For example, after displaying related search results for a given search term under a target video, a user may continue to perform related searches. Specifically, the user may replace the search term with another search term having the same meaning as the search term, or perform further searches. Following the above example, for example, such behavioral information of related searches may specifically replace "photo of celebrity A" with "frontal photo of celebrity A" or further search for "photo of celebrity A when he was young." Such behavioral information of further searches after searching the target video can reflect whether the selected search term produces effective and sufficient search results and can therefore also be used to determine whether the search term is suitable as a target search term.

[0049] In one possible situation, this reflects the fact that the search terms acquired in relation to the target video constantly change over time, as well as the changes in the content in which users have specific interests in the target video at different times. For example, if the content corresponding to the target video includes a representative of Company A giving an opening speech at University B, when the video is played for users, during the job-hunting season, more users will have expanded search demand for Company A in the video, such as obtaining an introductory video for the company. When the video is played for users, during the college entrance season, more users will have expanded search demand for University B in the video, such as obtaining recommended videos for each major at University B.

[0050] In a specific embodiment, a content attribute feature that satisfies a predetermined consumption condition within a current period can be determined, the predetermined consumption condition including at least one of a condition that the number of searches corresponding to the search term that matches the content attribute feature exceeds a predetermined number of searches and a condition that the consumption amount corresponding to the multimedia content that matches the content attribute feature exceeds a predetermined consumption amount, and in response to any one of a plurality of search terms being related to the content attribute feature, the search term is updated to the target search term.

[0051] Here, when determining the current period, it can be set to, for example, three days or five days before the time the target video is currently being displayed. Regarding the preset consumption conditions, for example, if the number of searches corresponding to a search term related to specific content, such as a certain event or person, during the current period exceeds a preset number of searches, the content attribute feature corresponding to this specific content may be considered to satisfy the preset consumption conditions. Furthermore, if the consumption amount of a certain multimedia content exceeds a preset consumption amount and specific topic content is displayed, the content attribute features displayed under these topic content belong to the content attribute features that satisfy the preset consumption conditions. For example, in the above example, if a certain period is job hunting season and the number of searches for a search term related to "job hunting" exceeds a preset search count threshold, the content attribute feature of "job hunting" may be considered to satisfy the preset consumption conditions.

[0052] When determining the content attribute feature, it may be determined whether or not a search term related to the content attribute feature is included among the acquired multiple search terms, and the search term may be updated to the target search term. For example, in the above example, when the target video is played in the first quarter, the content attribute feature tends to be biased toward "job hunting," so the target search term may be updated to "company introduction by company A." When the target video is played in the second quarter, the content attribute feature tends to be biased toward "advancement to higher education," so the target search term may be updated to "recommended major for university B."

[0053] In another embodiment of the present disclosure, regardless of which of the above methods for determining target search terms is considered, each target search term must be associated with its corresponding feature, i.e., video search terms must be associated with video features of the target video, and general search terms must be associated with video features and / or comment features of the comments of the target video. Therefore, the correlation between each search term and the video features and / or comment features must be determined.

[0054] Here, we first explain the video features and comment features, and then explain how to determine the correlation.

[0055] First, the video features of the target video will be described. The video features of the target video include video features of the target video in at least one video dimension, and the video dimension includes at least one of a video description dimension corresponding to description information of the target video, a video content dimension corresponding to screen content displayed in the target video, and a viewing behavior dimension corresponding to a user's viewing behavior in the target video.

[0056] The following describes video features in multiple video dimensions. Video features in the video description dimension are specifically used to describe the topic content primarily expressed by a video, and can be acquired based on the description information of the target video. The description information can be determined from directly obtainable information, such as the search information, video title, video topic tag, author name, and background music name of the target video, or can be recognized from the video using methods such as optical character recognition and speech-to-text conversion.

[0057] Video features in the video content dimension are specifically used to represent features associated with specific content within a video, such as the multimodal features of a recognized image, the name of a movie or TV show shown on the screen, or the actors appearing in the video.

[0058] The video features corresponding to the viewing behavior dimension are specifically determined by the user's viewing behavior for the target video. For example, after watching the target video, the search terms most frequently searched by the user and the search counts corresponding to these search terms are obtained, and the video features of the target video in the viewing behavior dimension are determined based on the obtained information.

[0059] Specifically, the comment characteristics of a comment can be determined based on the comment content of multiple comments under the target video, and interactive information such as the number of comments, likes, and forwards for each comment content, thereby obtaining typical content characteristics of the comments.

[0060] Next, a specific method for determining the correlation between each search term and the video features and / or comment features will be described. In the embodiment of the present disclosure, since both the video features and the comment features can include multi-dimensional features, a highly efficient model recognition method is specifically selected to detect the correlation.

[0061] In a specific embodiment, the target video and the search term are input as input data into a pre-trained correlation detection model, and the correlation detection model is made to output a correlation between the search term and the video features of the target video and / or the comment features of the comments, and the correlation detection model includes a first detection model and a second detection model, wherein the first detection model is used to detect a correlation between the search term and the video features, and the second detection model is used to detect a correlation between the search term and the video features and / or the comment features.

[0062] That is, the correlation detection model includes multiple branch networks, where the first detection model is used to detect correlations between search terms and video features, and the second detection model is used to detect correlations between search terms and video features and / or comment features. To enable the first detection model and the second detection model to perform correlation detection, the correlation detection model extracts video features of the target video and comment features of the comments using a feature extraction model configured before the first detection model and the second detection model, thereby obtaining the video features of the target video and the comment features of the comments. The correlation detection model described here may specifically be called an attribution model, and is configured as a neural network model based on the BERT end-to-end language representation model. The output result may be a score, where a higher score indicates a greater correlation between the input search term and the target video.

[0063] In one possible situation, for multiple available search terms, a correlation detection model can be used to score the correlation between the target video and the search terms, and the scoring results can be sorted based on the correlation scoring. If the number of target search terms that can be displayed is limited, multiple search terms can be selected and displayed through the sorted results.

[0064] In this way, by using any of the above target search term selection methods or a combination of at least one of the above selection methods, it is possible to determine the video search terms to be displayed in association with the playback page of the target video and the general search terms to be displayed on the comment page of the target video. When displaying the video search terms and the general search terms, for example, refer to FIG. 2, which is a schematic diagram displaying the target search terms provided by an embodiment of the present disclosure. FIG. 2(a) shows the playback page of the target video and the video search terms displayed in association with it, and FIG. 2(b) shows the comment page of the target video and the general search terms displayed. Furthermore, in the comments of FIG. 2(b), characters related to the general search terms can be highlighted, and an icon indicating their searchability can be displayed. For example, in the comments of User B and User C, the same "Celebrity A" as the general search term can be bolded, allowing direct search in response to the user's trigger operation.

[0065] Here, with regard to the playback page displaying the target video, since the target video may contain a large amount of video content, for example, the target video may include multiple content-related videos, each of which may display different information, such as video segments introducing multiple products individually. In this case, during the process of playing the target video, related search terms can be subdivided under each video segment, and thus, as the target video is played, search terms corresponding to the content in which the user is interested can be displayed under the current video segment.

[0066] In a specific embodiment, on the playback page, video search terms related to the currently played video segment can be updated and displayed on the playback page, and the target video includes multiple video segments each including at least one video frame, and each video segment is associated with a corresponding video search term.

[0067] For example, the target video may include three video segments, each introducing three different styles of clothing: work attire, shopping attire, and everyday attire. Therefore, the video search terms associated with the three video segments may be, specifically, "how to choose a suit for work," "shoes suitable for shopping," and "everyday accessories." Therefore, when the target video is played, the video search terms may be displayed in association with the playback of different video segments. For example, as shown in FIG. 3, FIG. 3 is a schematic diagram illustrating the display of different video search terms when a target video provided by an embodiment of the present disclosure is played. In FIG. 3(a), the video search term "how to choose a suit for work" is displayed below the target video in association with the playback of a video segment introducing work attire. In FIG. 3(b), the video segment introducing shopping attire is played, and the video search term below the target video is updated to "shoes suitable for shopping."

[0068] In addition, when a user slides through multiple comments under a target video, different comment contents can be displayed for that user on the comment page. In addition, when there are many comments under a target video, there is a possibility that there are many corresponding discussion directions, so when the comment contents are constantly updated and displayed on the comment page, general search terms related to the displayed comment contents can also be displayed.

[0069] In a specific implementation, in response to a comment viewing operation, at least one comment content and a general search term related to the at least one comment content can be displayed on a comment page, and in response to a slide operation on the comment page, updated comment content can be displayed and general search terms related to the updated comment content can be displayed.

[0070] For example, in the example corresponding to Figure 3 above, the comments may include information about work, shopping, everyday fashion, etc., so when displaying general search terms, the comment content to be displayed to the user through the current comment page can be determined, and then related general search terms can be displayed.

[0071] A specific example is shown in FIG. 4, which is a schematic diagram of displaying comment content and general search terms on a comment page provided by an embodiment of the present disclosure. Since the comment content shown in FIG. 4(a) is solely related to workplace fashion, the general search term "how to choose a work suit" can be displayed. In an embodiment of the present disclosure, the general search terms associated with the comments may be related to the video features of the target video, so the video search terms associated with the target video can be used as the general search terms. Meanwhile, the comment content displayed in FIG. 4(b) includes comments related to shopping and everyday fashion, but the comments related to shopping fashion are displayed first. Therefore, general search terms related to shopping fashion, such as "favorite shopping bag," can be updated and displayed. Alternatively, general search terms with many related comments can be selected and displayed. For example, if there are three comments in FIG. 4(b), both of which are related to shopping fashion, "favorite shopping bag" can be selected and displayed.

[0072] This makes it possible to display video search terms on the playback page and general search terms on the comment page.

[0073] In another embodiment of the present disclosure, a specific embodiment of displaying video search terms for a target video and displaying general search terms for comments under the target video is also provided. For example, as shown in Figure 5, which is a flowchart of a specific implementation of the information display method provided by the embodiment of the present disclosure, S501: A target video is determined.

[0074] S502: Determine a first search term for the target video and a second search term for the comments below the target video.

[0075] Here, the steps may specifically include the following steps:

[0076] S5021: Obtain the search terms generated by searching the target video.

[0077] S5022: Using a video correlation attribution model, a first search term related to the video characteristics of the target video is determined from among the multiple search terms.

[0078] S5023: Using the comprehensive correlation attribution model, a second search term is determined from among the multiple search terms that is related to the video features of the target video and / or the comment features of the comments below the target video.

[0079] Here, the video correlation attribution model is the first detection model described in the above example, and the overall correlation attribution model is the second detection model described in the above example. The video correlation attribution model and the overall correlation attribution model can be used to determine the correlation between the search term and the video features and / or comment features, thereby enabling initial recall of the search term (the search term can be initially recalled) based on a preset correlation threshold.

[0080] Here, when determining the correlation using a model, it can be done by offline processing.

[0081] S503: The first search term and the second search term are sorted, and a video search term and a general search term are determined based on the sorting result.

[0082] Here, when sorting, sorting and filtering can be performed based on the correlation between the corresponding features described in the above examples, whether they are related to content attribute features that meet the pre-set consumption conditions in the current period, the played video segments, the displayed comment information, etc., thereby obtaining video search terms and overall search terms.

[0083] Here, sorting and determining video search terms and general search terms can also be done offline.

[0084] S504: The video search term is displayed in association with the playback page of the target video, and the general search term is displayed on the comment page of the target video.

[0085] For the specific implementation of the above steps, please refer to the explanations of the corresponding parts in the above embodiments, and the explanations will be omitted here.

[0086] Those skilled in the art can understand that in the above method of the specific embodiment, the order of making each step does not mean that a strict execution order constitutes any limitation on the implementation process, and the specific execution order of each step should be determined by its function and possible inherent logic.

[0087] Based on the same inventive concept, an embodiment of the present disclosure also provides an information display device corresponding to the information display method, and the principle by which the device in the embodiment of the present disclosure solves the problem is similar to that of the above-mentioned information display method in the embodiment of the present disclosure, so the implementation of the device can refer to the implementation of the method, and the overlapping points will no longer be described.

[0088] As shown in FIG. 6, a schematic diagram of an apparatus for displaying information provided by an embodiment of the present disclosure includes an acquisition module 61, a first display module 62, and a second display module 63.

[0089] The acquisition module 61 is used to acquire multiple search terms related to the target video, and the multiple search terms include a first search term that starts a search after viewing the target video, and a second search term that starts a search after viewing the target video and comments corresponding to the target video.

[0090] The first display module 62 is used to display video search terms in association with the playback page of the target video, and the video search terms are determined based on the first search terms and are related to the video features of the target video.

[0091] The second display module 63 is used to display general search terms on the comment page of the target video, and the general search terms are determined based on the first search terms and the second search terms and are related to the video features and / or comment features of the comments.

[0092] In one optional embodiment, the device further includes a processing module 64 used to determine target search terms based on rating information corresponding to each search term, where the target search terms include video search terms and comment search terms, and the rating information of the search terms is determined based on at least one of the following information: the number of historical searches for the search terms in the target video, consumption results corresponding to search results related to the search terms, and behavior information of related searches occurring after the search results are displayed.

[0093] In one optional embodiment, content attribute features that satisfy predetermined consumption conditions within a current period are determined, and the predetermined consumption conditions include at least one of a condition that the number of searches corresponding to search terms that match the content attribute features exceeds a predetermined number of searches, and a condition that the consumption amount corresponding to multimedia content that matches the content attribute features exceeds a predetermined consumption amount, and in response to any one of a plurality of search terms being related to the content attribute features, the target search term is dynamically determined by updating the target search term to the search term.

[0094] In one optional embodiment, the correlation between each search term and the video features and / or comment features is determined by inputting the target video and the search term as input data into a pre-trained correlation detection model and causing the correlation detection model to output correlations between the search term and the video features of the target video and / or comment features of the comments, and the correlation detection model includes a first detection model and a second detection model, wherein the first detection model is used to detect correlations between the search term and the video features, and the second detection model is used to detect correlations between the search term and the video features and / or the comment features.

[0095] In one optional embodiment, the second display module 63 is used to display at least one comment content and a general search term related to the at least one comment content on the comment page in response to a comment viewing operation when displaying general search terms on the comment page of the target video, and to display updated comment content and a general search term related to the updated comment content in response to a slide operation on the comment page.

[0096] In one optional embodiment, when displaying video search terms in association with the playback page of the target video, the first display module 62 is used to update and display video search terms associated with the currently played video segment on the playback page, where the target video includes multiple video segments each including at least one video frame, and each video segment is associated with a corresponding video search term.

[0097] In one optional embodiment, the video features of the target video include video features in at least one video dimension of the target video, and the video dimensions include at least one of a video description dimension corresponding to descriptive information of the target video, a video content dimension corresponding to screen content shown in the target video, and a viewing behavior dimension corresponding to the user's viewing behavior in the target video.

[0098] For the description of the processing flow of each module in the device and the interaction flow between each module, please refer to the relevant description in the above method embodiment, and will not be described in detail here.

[0099] The embodiments of the present disclosure further provide a computer device, as shown in FIG. 7, which is a schematic block diagram of the computer device provided by the embodiments of the present disclosure, and the computer device includes: The present invention includes a processor 10 and a memory 20, wherein the memory 20 stores machine-readable instructions executable by the processor 10, the processor 10 is used to execute the machine-readable instructions stored in the memory 20, and when the machine-readable instructions are executed by the processor 10, the processor 10: The method performs the following steps: a step of obtaining multiple search terms related to the target video, the multiple search terms including a first search term that starts a search after viewing the target video, and a second search term that starts a search after viewing the target video and comments corresponding to the target video; a step of displaying video search terms in association with the playback page of the target video, the video search terms being determined based on the first search terms and related to video features of the target video; and a step of displaying general search terms on the comment page of the target video, the general search terms being determined based on the first search terms and the second search terms and related to the video features and / or comment features of the comments.

[0100] The memory 20 includes a memory 210 and an external memory 220. The memory 210 is also called an internal storage device and is used to temporarily store calculation data in the processor 10 and data to be exchanged with the external memory 220 such as a hard disk. The processor 10 exchanges data with the external memory 220 via the memory 210.

[0101] The specific execution procedures of the above-mentioned instructions may refer to the steps of the information display method described in the embodiments of the present disclosure, and will not be further described here.

[0102] An embodiment of the present disclosure further provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the method steps of displaying information described in the above method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0103] An embodiment of the present disclosure also provides a computer program product carrying program code including instructions for executing the steps of the information display method described in the above method embodiment, which may specifically refer to the above method embodiment and will not be described herein.

[0104] Here, the computer program product can be specifically realized by hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied as a computer storage medium, and in another alternative embodiment, the computer program product is specifically embodied as a software product such as a software development kit (SDK).

[0105] As will be apparent to those skilled in the art, for ease of explanation and brevity, the specific operation processes of the systems and devices described above may refer to the corresponding processes in the method embodiments and will not be described again here. It should be understood that in some embodiments provided by the present disclosure, the disclosed systems, devices, and methods can be realized in other manners. The device embodiments mentioned above are merely exemplary. For example, the division of the units is merely a logical function division. In actual implementation, other division methods may be used. For example, multiple units or components may be combined or integrated into other systems, or some features may be omitted or not implemented. Furthermore, the couplings or direct couplings or communication connections between devices shown or discussed may be indirect couplings or communication connections via several communication interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0106] The units shown as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units, and some or all of the units may be selected according to actual needs to achieve the objectives of the technical solution of this embodiment.

[0107] Each functional unit in each embodiment of the present disclosure may be integrated into a single processing unit, each unit may exist physically alone, or two or more units may be integrated into a single unit.

[0108] When the functions are realized in the form of a software functional unit and sold or used as an independent product, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on this understanding, an essential contributing part of the technical solution of the present disclosure or a part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium containing several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to execute all or some of the steps of the method described in each embodiment of the present disclosure. The storage medium includes various media capable of storing program code, such as a USB memory, a removable hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0109] Finally, it should be explained that the above-described examples are merely specific embodiments of the present disclosure, and are used to explain the technical solutions of the present disclosure, but do not limit it, and the scope of protection of the present disclosure is not limited thereto. However, although the present disclosure has been described in detail with reference to the above examples, those skilled in the art should understand that, within the technical scope disclosed in the present disclosure, those skilled in the art can still modify or easily think of changes to the technical solutions described in the above examples, or equivalently replace some of the technical features. These modifications, changes, or substitutions should all be included in the scope of protection of the present disclosure, as long as the essence of the corresponding technical solutions does not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure. Therefore, the scope of protection of the present disclosure should be governed by the claims.

Claims

1. 1. A method of displaying information, the method comprising: A step of obtaining a plurality of search terms related to the target video, the plurality of search terms including a first search term to be searched after viewing the target video, and a second search term to be searched after viewing the target video and comments corresponding to the target video; Displaying a video search term in association with the playback page of the target video, the video search term being determined based on the first search term and related to video features of the target video; and displaying a general search term on the comment page of the target video, the general search term being determined based on the first search term and the second search term and related to the video features and / or comment features of the comments. method.

2. The method further includes determining target search terms based on evaluation information corresponding to each search term, wherein the target search terms include video search terms and comment search terms; The method of claim 1, wherein the evaluation information of the search term is determined based on at least one of the following information: the number of historical searches for the search term in the target video, consumption results corresponding to search results related to the search term, and behavioral information of related searches that occur after displaying the search results.

3. Determine content attribute features that satisfy a predetermined consumption condition within a current period, the predetermined consumption condition including at least one of a condition that the number of searches corresponding to a search term that matches the content attribute features exceeds a predetermined number of searches, and a condition that the consumption amount corresponding to multimedia content that matches the content attribute features exceeds a predetermined consumption amount; The method of claim 2, wherein the target search term is dynamically determined by updating the target search term to the search term in response to any one of the plurality of search terms being related to the content attribute feature.

4. The method further includes a step of determining a correlation between each search term and the video features and / or comment features by inputting the target video and the search terms as input data into a pre-trained correlation detection model and causing the correlation detection model to output correlations between the search terms and the video features of the target video and / or the comment features of the comments; The method of claim 1 or 2, wherein the correlation detection model includes a first detection model and a second detection model, the first detection model is used to detect correlations between the search terms and the video features, and the second detection model is used to detect correlations between the search terms and the video features and / or the comment features.

5. The step of displaying the general search term on the comment page of the target video includes: In response to a comment viewing operation, displaying at least one comment content and a general search term related to the at least one comment content on the comment page; and displaying updated comment content and general search terms related to the updated comment content in response to a slide operation on the comment page.

6. The step of displaying a video search term in association with the playback page of the target video includes: The method of claim 1, further comprising: updating and displaying, on the playback page, video search terms associated with the currently played video segment; the target video including a plurality of video segments each including at least one video frame; and each video segment being associated with a corresponding video search term.

7. the motion characteristics of the target motion include motion characteristics in at least one motion dimension of the target motion; The method described in claim 1, wherein the video dimensions include at least one of a video description dimension corresponding to descriptive information of the target video, a video content dimension corresponding to screen content shown in the target video, and a viewing behavior dimension corresponding to the user's viewing behavior for the target video.

8. 1. A device for displaying information, the device comprising: an acquisition module configured to acquire a plurality of search terms related to a target video, the plurality of search terms including a first search term to be searched after viewing the target video, and a second search term to be searched after viewing the target video and comments corresponding to the target video; A first display module configured to display a video search term in association with the playback page of the target video, the video search term being determined based on the first search term and related to the video features of the target video; a second display module configured to display a general search term on a comment page of the target video, the general search term being determined based on the first search term and the second search term, and related to the video features and / or comment features of the comments; Device.

9. A computing device, the computing device including a processor and a memory; The memory stores machine-readable instructions executable by the processor, the processor being used to execute the machine-readable instructions stored in the memory, and when the machine-readable instructions are executed by the processor, the processor performs the method of any one of claims 1 to 7. Computer equipment.

10. 10. A computer-readable storage medium having a computer program stored thereon, the computer program being adapted, when executed by a computing device, to cause the computing device to perform the method of any one of claims 1 to 7.

Images