Emotion distribution display method and device of video

Abstract

The embodiment of the invention provides a video emotion distribution display method and device, and relates to the technical field of computers. The method comprises the following steps: acquiring sentiment analysis data of a plurality of bullet screens corresponding to a target video, wherein the sentiment analysis data comprises sentiment tags of the bullet screens and creation time of the bullet screens; determining emotion distribution data of the target video according to the emotion analysis data of each bullet screen; and pushing the emotion distribution data to a user side, so that the user side displays the emotion distribution data. According to the technical scheme provided by the embodiment of the invention, the user can intuitively know the overall atmosphere and emotion trend of the story content of the target video currently watched by the user.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of computer technology, and in particular, to a method and device for displaying the emotional distribution of a video, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the rapid development of video technology, more and more users can watch various video programs through the network. During the process of watching video programs, users can interact with the host or other users by sending bullet screens. The bullet screen refers to comments, messages or interactive content that appears in the form of sliding, scrolling or popping up in media such as videos or live broadcasts.

[0003] However, this form of bullet screen interaction lacks a deep combination with video content and cannot help users quickly understand the overall atmosphere and emotional trend of the video content.

[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 and device for displaying the emotional distribution of a video, a computer device, a computer-readable storage medium, and a computer program product to solve or alleviate one or more of the above technical problems.

[0006] One aspect of the embodiments of the present application provides a method for displaying the emotional distribution of a video for a server, and the method includes: Obtaining emotional analysis data of a plurality of bullet screens corresponding to a target video, where the emotional analysis data includes the emotional label of the bullet screen and the creation time of the bullet screen; Determining the emotional distribution data of the target video according to the emotional analysis data of each bullet screen; Pushing the emotional distribution data to the user side so that the user side displays the emotional distribution data.

[0007] Optionally, determining the emotional distribution data of the target video according to the emotional analysis data of each bullet screen includes: Counting the proportion of emotional labels of various categories according to the emotional analysis data of each bullet screen to obtain the emotional distribution data of the target video in the user dimension; Counting the proportion of emotional labels of various categories in time periods according to the emotional analysis data of each bullet screen to obtain the emotional distribution data of the target video in the time dimension.

[0008] Optionally, the emotional analysis data further includes the emotional label score of the bullet screen; Correspondingly, based on the sentiment analysis data of each of the bullet screens, the proportion of various types of sentiment tags is counted, and the sentiment distribution data of the target video in the user dimension includes: Count the total value of the first sentiment tag scores for various types of sentiment tags respectively; Based on the total value of the first sentiment tag scores of various types of sentiment tags and the total value of the second sentiment tag scores of all types of sentiment tags, determine the proportion of various types of sentiment tags; Take the proportion of various types of sentiment tags as the sentiment distribution data of the target video in the user dimension; Correspondingly, based on the sentiment analysis data of each of the bullet screens, the proportion of various types of sentiment tags is counted by time period, and the sentiment distribution data of the target video in the time dimension includes: Count the total value of the third sentiment tag scores of various types of sentiment tags in each time period respectively; Based on the total value of the third sentiment tag scores of various types of sentiment tags in each time period and the total value of the fourth sentiment tag scores of all types of sentiment tags in each time period, determine the proportion of various types of sentiment tags in each time period; Take the proportion of various types of sentiment tags in all time periods as the sentiment distribution data of the target video in the time dimension.

[0009] Optionally, the sentiment analysis data further includes a bullet screen weight value; Correspondingly, the total value of the first sentiment tag scores of various types of sentiment tags is obtained in the following manner: Calculate the sentiment score of each bullet screen based on the sentiment tag score and the bullet screen weight value of each bullet screen; Count the total first sentiment score corresponding to various types of sentiment tags, and take the total first sentiment score as the total value of the first sentiment tag scores; Correspondingly, the total value of the third sentiment tag scores of various types of sentiment tags in each time period is obtained in the following manner: Calculate the sentiment score of each bullet screen based on the sentiment tag score and the bullet screen weight value of each bullet screen; Count the total second sentiment score corresponding to various types of sentiment tags in each time period, and take the total second sentiment score as the total value of the third sentiment tag scores.

[0010] Optionally, the sentiment analysis data is obtained by the following method: Input the bullet screen into a pre-trained sentiment analysis model, and output the sentiment tags of the bullet screen through the sentiment analysis model; Generate the sentiment analysis data based on the sentiment tags of the bullet comments and the attribute data of the bullet comments.

[0011] Another aspect of the embodiments of the present application provides a method for displaying the sentiment distribution of a video, which is used for a user terminal. The method includes: Obtain the sentiment distribution data of the target video; In response to a display instruction for the sentiment distribution data, display the sentiment distribution data.

[0012] Optionally, in response to a display instruction for the sentiment distribution data, displaying the sentiment distribution data includes: In response to a display instruction for the sentiment distribution data, display the sentiment distribution data in a curve graph or a bar graph.

[0013] Another aspect of the embodiments of the present application provides a device for displaying the sentiment distribution of a video, which is used for a server. The device includes: An acquisition module, configured to acquire sentiment analysis data of a plurality of bullet comments corresponding to a target video, where the sentiment analysis data includes sentiment tags of the bullet comments and creation times of the bullet comments; A determination module, configured to determine the sentiment distribution data of the target video according to the sentiment analysis data of each of the bullet comments; A push module, configured to push the sentiment distribution data to a user terminal so that the user terminal displays the sentiment distribution data.

[0014] Another aspect of the embodiments of the present application provides a device for displaying the sentiment distribution of a video, which is used for a user terminal. The device includes: An acquisition module, configured to acquire the sentiment distribution data of the target video; A display module, configured to display the sentiment distribution data in response to a display instruction for the sentiment distribution data.

[0015] 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.

[0016] Another aspect of the embodiments of the present application provides a computer-readable storage medium, where 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.

[0017] Another aspect of the embodiments of the present application provides a computer program product, including a computer program, which when executed by a processor implements the method described above.

[0018] The embodiments of the present application adopting the above technical solutions may include the following advantages: First, after obtaining the sentiment analysis data of multiple bullet screens corresponding to the target video, the server will determine the sentiment distribution data of the target video according to the sentiment analysis data of each bullet screen, so as to obtain the overall atmosphere and sentiment trend of the plot content of the target video. Finally, the sentiment distribution data is pushed to the user side for the user side to display the sentiment distribution data. Thus, the user can intuitively understand the overall atmosphere and sentiment trend of the plot content of the target video currently being watched, improving the user's viewing experience. BRIEF DESCRIPTION OF THE DRAWINGS The drawings exemplarily show embodiments and form a part of the specification, and are used together with the written description of the specification to explain the exemplary 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 identical elements.

[0019] Figure 1 Schematically shows an operating environment diagram of a method for displaying sentiment distribution of a video according to Embodiment 1 of the present application; Figure 2 Schematically shows a flowchart of a method for displaying sentiment distribution of a video according to Embodiment 1 of the present application; Figure 3 Schematically shows Figure 2 a sub-step flowchart of step S202 in; Figure 4 Schematically shows a refined flowchart of obtaining sentiment analysis data; Figure 5 Schematically shows a flowchart of a method for displaying sentiment distribution of a video according to Embodiment 2 of the present application; Figure 6 Schematically shows a schematic diagram of sentiment distribution data display; Figure 7 Schematically shows a schematic diagram of sentiment distribution data display; Figure 8 Schematically shows a block diagram of a device for displaying sentiment distribution of a video according to Embodiment 3 of the present application; Figure 9 Schematically shows a block diagram of a device for displaying sentiment distribution of a video according to Embodiment 4 of the present application; and Figure 10 Schematically shows a schematic diagram of the hardware architecture of a computer device according to Embodiment 5 of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] To make the objectives, technical solutions and advantages of this application clearer and more understandable, the following further elaborates on this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts belong to the scope of protection of this application.

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

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

[0023] First, the following provides the glossary explanations related to this application: Danmaku: It refers to content such as text, emoticons, pictures, animations, etc. that pop up and move in a predetermined direction when watching a video through the network. There is no fixed term for danmaku in English yet, and it is usually called: comment, danmaku, barrage, bullet screen, bullet-screen comment, etc. Danmaku allows viewers to post comments or feelings. However, different from ordinary video sharing websites that only display special comment areas under the player, it will appear on the video screen in real time in the form of scrolling subtitles to ensure that all viewers can notice.

[0024] Exemplarily, the data structure of danmaku can be as follows: { The time of emission in the video, in seconds; The type of danmaku; The size of the danmaku text; The color of the danmaku text; The date of creation of the danmaku; The class name of the danmaku; The content of the danmaku (such as text, pictures, controls); Whether the danmaku has a border; The color of the danmaku border; The line style between bullet comments; }

[0025] Natural language processing technology: An important branch in the fields of artificial intelligence and computer science, aiming to enable computers to understand, interpret, and generate human language. Natural language processing technology includes two aspects: natural language understanding (NLU) and natural language generation (NLG). Natural language understanding means that a computer can understand the meaning in human language, including aspects such as grammar, semantics, and context. Natural language generation means that a computer can generate human language text that conforms to grammar and semantic norms based on certain semantic information.

[0026] Large Language Model (LLM model): A natural language processing technology based on deep learning, trained through large-scale datasets, capable of generating natural language text or understanding the meaning of language text.

[0027] Secondly, to facilitate the understanding of the technical solutions provided in the embodiments of the present application by those skilled in the art, the related technologies are described below: With the rapid development of video technology, more and more users can watch various video programs through the network. During the process of watching video programs, users can interact with the host or other users by sending bullet comments. The bullet comments refer to comments, messages, or interactive content that appear in forms such as sliding, scrolling, or popping up in media such as videos or live broadcasts.

[0028] However, this form of bullet comment interaction lacks a deep combination with video content and cannot help users quickly understand the overall atmosphere and emotional trend of the video content.

[0029] Therefore, the embodiments of the present application provide a technical solution for displaying the emotional distribution of videos. In this technical solution, the following effects can be achieved: By determining the emotional distribution data of the target video based on the emotional analysis data of each bullet comment, the overall atmosphere and emotional trend of the plot content of the target video can be obtained, enabling users to intuitively understand the overall atmosphere and emotional trend of the plot content of the target video they are currently watching, and improving the user's viewing experience. See the following for details.

[0030] Finally, for ease of understanding, an exemplary operating environment is provided below.

[0031] As Figure 1 shown, the operating environment diagram includes: a service platform 2 and a user terminal.

[0032] The service platform 2 can be connected to the user terminals (4A, 4B,..., 4N) through the network.

[0033] The service platform 2 can provide various contents and bullet screen services, etc. for the user terminals. For example, videos and bullet screens are sent to the user terminals via the network. The network includes various network devices, such as routers, switches, multiplexers, hubs, bridges, repeaters, firewalls, proxy devices, and / or similar devices. The network can include physical links, such as coaxial cable links, twisted pair cable links, fiber optic links, and combinations thereof, etc. The network can include wireless links, such as cellular links, satellite links, Wi-Fi links, etc.

[0034] Among them, the service platform 2 can be a single server, a server cluster, or a cloud computing service center for providing various services. For example: The service platform 2 can provide content services. Among them, the content services can be configured to provide contents such as videos, audios, text data, and combinations thereof. The content can include content streams (e.g., video streams, audio streams, information streams), content files (e.g., video files, audio files, text files), and / or other data.

[0035] The service platform 2 can be configured to receive multiple messages. The multiple messages can include multiple bullet screens associated with the content.

[0036] The service platform 2 can provide bullet screen services, which can be configured to allow users to comment on and / or share comments (i.e., bullet screens) associated with the content. The bullet screens and the content are presented on the same screen. The bullet screens can be displayed in an overlay above the content and can have animation effects. For example, the bullet screens can scroll (e.g., from right to left, from left to right, from top to bottom,...), and the animation effect can be implemented based on the transition property of CSS3.

[0037] The user terminals (4A, 4B,... 4N) can be configured to access the contents and services of the service platform 2. The user terminals (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 user terminals, smart TVs, set-top boxes, etc., and can also include virtualized computing examples. The virtualized computing examples can include virtual machines, such as emulations of computer systems, operating systems, servers, etc.

[0038] The user terminals (4A, 4B,... 4N) can include multiple user terminal programs, such as video APPs, live broadcast APPs, or mini-programs with built-in bullet screen systems, etc. In the embodiments of the present application, through the user terminal programs, contents such as videos provided by the service platform 2 can be presented, and the bullet screen contents can be presented in a specific manner through the bullet screen system.

[0039] The client (4A, 4B, …… 4N) may include an interface, which may include a touchpad, a touch screen, a mouse, a keyboard, or other sensing elements. For example, the input element may be configured to accept user instructions, and the user instructions may cause the client (4A, 4B, …… 4N) to perform various operations, such as inputting bullet comments, etc.

[0040] 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. It should be known that these embodiments can be implemented in various different forms and should not be construed as being limited only to the embodiments described herein.

[0041] The following takes the service platform 2 or the client as the execution subject and introduces the technical solutions of the present application through multiple embodiments. It should be known that these embodiments can be implemented in various different forms and should not be construed as being limited only to the embodiments described herein.

[0042] Embodiment 1 This method embodiment can be executed in a server.

[0043] Figure 2 Schematically shows a flowchart of a method for displaying the emotional distribution of a video according to Embodiment 1 of the present application.

[0044] As Figure 2 shown, the method for displaying the emotional distribution of the video may include steps S200 to S204, where: Step S200, obtaining emotional analysis data of multiple bullet comments corresponding to a target video, where the emotional analysis data includes the emotional tags of the bullet comments and the creation time of the bullet comments.

[0045] Step S202, determining the emotional distribution data of the target video according to the emotional analysis data of each of the bullet comments.

[0046] Step S204, pushing the emotional distribution data to the client so that the client can display the emotional distribution data.

[0047] For the method for displaying the emotional distribution of a video provided in this embodiment, first, after obtaining the emotional analysis data of multiple bullet comments corresponding to a target video, the server will determine the emotional distribution data of the target video according to the emotional analysis data of each of the bullet comments, so as to obtain the overall atmosphere and emotional trend of the plot content of the target video. Finally, the emotional distribution data is pushed to the client so that the client can display the emotional distribution data. Thus, the user can intuitively understand the overall atmosphere and emotional trend of the plot content of the target video currently being watched, improving the user's viewing experience.

[0048] The following combines Figure 2, elaborate on each step in steps S200 - S204 and other optional steps in detail.

[0049] Step S200 , obtain the sentiment analysis data of multiple bullet screens corresponding to the target video, where the sentiment analysis data includes the sentiment label of the bullet screen and the creation time of the bullet screen.

[0050] The target video can be associated with a bullet screen pool, which is used to store all the bullet screens sent by users when watching the target video. The multiple bullet screens corresponding to the target video obtained can be all the bullet screens in the bullet screen pool, or the bullet screens screened according to preset criteria. Among them, the screening criteria can include user level, bullet screen type, blocked words, release time, etc.

[0051] The bullet screens can include: text bullet screens, picture bullet screens, emoticon bullet screens, animation bullet screens, etc.

[0052] Among them, the sentiment label is used to reflect the label information of the emotional state when the user sends the bullet screen, and it is used as the basis for determining the emotional distribution data of the target video in subsequent steps. The sentiment label can be divided into "happy", "sad", "angry", "surprised", etc.

[0053] In one example, a sentiment classification model can be used to perform sentiment analysis on the bullet screen content of the bullet screen to obtain the sentiment label corresponding to the bullet screen content. The sentiment classification model can be obtained by training the corresponding deep learning model through deep learning.

[0054] In another example, sentiment analysis can also be performed on the bullet screen content of the bullet screen by a method based on a sentiment dictionary to obtain the sentiment label corresponding to the bullet screen content.

[0055] In another example, natural language processing technology can also be used to perform real-time analysis by combining the bullet screen content of the bullet screen and the content context of the target video currently being watched by the user to obtain the sentiment label corresponding to the bullet screen content.

[0056] In an optional implementation manner, before performing sentiment analysis on the bullet screen content, the bullet screen content can be preprocessed to facilitate subsequent sentiment analysis. Among them, the preprocessing includes removing useless symbols, stop words, and noise data, etc.

[0057] Step S202 , determine the emotional distribution data of the target video according to the sentiment analysis data of each bullet screen.

[0058] The emotional distribution data is used to reflect the overall atmosphere of the target video and the overall emotional trend of the video content.

[0059] In an optional embodiment, refer to Figure 3, step S202 may include: Step S300, according to the sentiment analysis data of each of the bullet screens, count the proportion of various types of sentiment tags to obtain the sentiment distribution data of the target video in the user dimension.

[0060] Step S302, according to the sentiment analysis data of each of the bullet screens, count the proportion of various types of sentiment tags by time period to obtain the sentiment distribution data of the target video in the time dimension.

[0061] In one example, according to the sentiment analysis data of each bullet screen, the number of sentiment tags of different types can be counted, and the proportion of various types of sentiment tags can be calculated. For example, the target video is associated with a total of 100 bullet screens, among which 70 bullet screens have a sentiment tag of "happy", 20 bullet screens have a sentiment tag of "sad", and 10 bullet screens have a sentiment tag of "surprised". After obtaining the proportion of various types of sentiment tags based on the above bullet screens, these proportions can be used as the sentiment distribution data of the target video in the user dimension.

[0062] In another example, since each bullet screen has a creation time, when counting the number of sentiment tags of different types according to the sentiment analysis data of each bullet screen, the proportion of various types of sentiment tags in each time period can also be counted. For example, the target video is 10 minutes in total, and the 10-minute target video is divided into 10 time periods, each time period containing 1 minute of video. The target video is associated with a total of 100 bullet screens, among which 70 bullet screens have a sentiment tag of "happy", 20 bullet screens have a sentiment tag of "sad", and 10 bullet screens have a sentiment tag of "surprised". Further, assume that according to the creation time of the bullet screens, 70 bullet screens with a sentiment tag of "happy" are distributed in the 1st time period, the 2nd time period, and the 7th time period in sequence; 20 bullet screens with a sentiment tag of "sad" are distributed in the 1st time period and the 5th time period in sequence according to the creation time of the bullet screens. 100 bullet screens with a sentiment tag of "surprised" are distributed in the 8th time period and the 9th time period in sequence according to the creation time of the bullet screens. After obtaining the proportion of various types of sentiment tags in each time period based on the above bullet screens, these proportions can be used as the sentiment distribution data of the target video in the time dimension.

[0063] In this embodiment, by statistically obtaining the sentiment distribution data of the target video in the user dimension and the sentiment distribution data of the target video in the time dimension, it is convenient for users to quickly understand the overall sentiment trend and overall atmosphere of the video content.

[0064] In an alternative embodiment, the sentiment analysis data further includes the sentiment label scores of the bullet comments, and the sentiment label scores are used to represent the degree to which the bullet comments have sentiment labels of this type. For example, if the sentiment label score of the sentiment label "happy" is 0.7, it indicates that the emotion of the user when sending this bullet comment is not only "happy", but also other "non-happy" emotions.

[0065] Correspondingly, according to the sentiment analysis data of each bullet comment, the proportion of various types of sentiment labels is statistically calculated, and the sentiment distribution data of the target video in the user dimension includes: respectively statistically calculating the total value of the first sentiment label scores of various types of sentiment labels; determining the proportion of various types of sentiment labels based on the total value of the first sentiment label scores of various types of sentiment labels and the total value of the second sentiment label scores of all types of sentiment labels; and taking the proportion of various types of sentiment labels as the sentiment distribution data of the target video in the user dimension.

[0066] In one example, the total value of the first sentiment label scores of different types of sentiment labels can be statistically calculated according to the sentiment label scores and sentiment labels of each bullet comment, and the proportion of various types of sentiment labels can be calculated. For example, the target video is associated with a total of 100 bullet comments, among which 70 bullet comments have the sentiment label "happy", and the total value of the first sentiment label scores of these 70 bullet comments is 50. 20 bullet comments have the sentiment label "sad", and the total value of the first sentiment label scores of these 20 bullet comments is 16. 10 bullet comments have the sentiment label "surprised", and the total value of the first sentiment label scores of these 10 bullet comments is 7. After obtaining the total values of the first sentiment label scores of the above three types of sentiment labels, the proportions of the three types of sentiment labels can be calculated to be 50 / 73, 16 / 73, and 7 / 73 in sequence. After obtaining these 3 proportion values, these proportions can be used as the sentiment distribution data of the target video in the user dimension.

[0067] In one example, according to the sentiment label score, sentiment label, and creation time of each bullet comment, the total value of the third sentiment label score for each time period of different categories of sentiment labels can be statistically calculated by time period, and the proportion of various categories of sentiment labels in each time period can be calculated. For example, the target video is associated with a total of 100 bullet comments, and the target video is divided into 10 time periods. Among them, the sentiment label of 70 bullet comments is "happy", and these 70 bullet comments are distributed in the 1st time period, the 2nd time period, and the 7th time period in sequence. The total values of the third sentiment label scores corresponding to these 3 time periods are 20, 20, and 10 respectively. The sentiment label of 20 bullet comments is "sad", and these 20 bullet comments are distributed in the 1st time period and the 5th time period in sequence. The total values of the third sentiment label scores corresponding to these 2 time periods are 10 and 6 respectively. The sentiment label of 10 bullet comments is "surprised", and these 10 bullet comments are distributed in the 8th time period and the 9th time period in sequence. The total values of the third sentiment label scores corresponding to these 2 time periods are 5 and 2 respectively. After obtaining the total values of the third sentiment label scores of the above three categories of sentiment labels in each time period, the proportions of the three categories of sentiment labels in each time period can be calculated respectively. After obtaining the proportions of these three categories of sentiment labels in each time period, these proportions can be used as the sentiment distribution data of the target video in the time dimension.

[0068] In this embodiment, by statistically calculating the sentiment distribution data based on the sentiment label and the corresponding sentiment label score, more accurate sentiment distribution data can be obtained.

[0069] In an optional embodiment, the sentiment analysis data further includes a bullet comment weight value. The bullet comment weight value is used to reflect the importance of the bullet comment.

[0070] Correspondingly, the total value of the first sentiment label score of various categories of sentiment labels is obtained in the following manner: the sentiment score of each bullet comment is calculated based on the sentiment label score and the bullet comment weight value of each bullet comment; the total first sentiment score corresponding to various categories of sentiment labels is statistically calculated, and the total first sentiment score is used as the total value of the first sentiment label score.

[0071] Correspondingly, the total value of the third sentiment label score of various categories of sentiment labels in each of the time periods is obtained in the following manner: the sentiment score of each bullet comment is calculated based on the sentiment label score and the bullet comment weight value of each bullet comment; the total second sentiment score corresponding to various categories of sentiment labels in each of the time periods is statistically calculated, and the total second sentiment score is used as the total value of the third sentiment label score.

[0072] In this embodiment, by statistically calculating the sentiment distribution data based on the sentiment label, the corresponding sentiment label score, and the bullet comment weight value, more accurate sentiment distribution data can be obtained.

[0073] Step S204 Push the emotion distribution data to the user terminal so that the user terminal can display the emotion distribution data.

[0074] In this embodiment, after obtaining the emotion distribution data, the server will promptly push the emotion distribution data to the user terminal so that the user terminal can display the emotion distribution data, facilitating the user to intuitively understand the overall atmosphere and emotional trend of the plot content of the target video they are currently watching.

[0075] In an alternative embodiment, refer to Figure 4 , the emotion analysis data is obtained through the following method: Step S400, input the bullet comments into a pre-trained emotion analysis model, and output the emotion labels of the bullet comments through the emotion analysis model.

[0076] Step S402, generate the emotion analysis data based on the emotion labels of the bullet comments and the attribute data of the bullet comments.

[0077] The attribute data of the bullet comments may include data such as the creation time of the bullet comments and the ID of the bullet comments.

[0078] In this embodiment, the emotion analysis model is used to perform emotion analysis on the bullet comments, so that the emotion labels of the bullet comments can be accurately output.

[0079] Embodiment Two This method embodiment can be executed in the user terminal. Figure 5 Schematically shows a flowchart of a method for displaying the emotion distribution of a video according to Embodiment Two of the present application. As Figure 5 shown, the method for displaying the emotion distribution of the video may include steps S500 to S502, where: S500, obtain the emotion distribution data of the target video.

[0080] In this embodiment, after obtaining the emotion distribution data, the emotion distribution data can be immediately sent to the user terminal. It can also be sent to the user terminal when receiving a request from the user terminal for obtaining the emotion distribution data. Among them, the generation method of the emotion distribution data has been described in detail in Embodiment One and will not be elaborated in this embodiment.

[0081] S502, in response to a display instruction for the emotion distribution data, display the emotion distribution data.

[0082] The display instruction can be generated after the user clicks on an emotion distribution data display control.

[0083] In this embodiment, by responding to a display instruction for the emotion distribution data, the emotion distribution data is displayed, enabling the user to intuitively understand the overall atmosphere and emotional trend of the plot content of the target video currently being watched, thus enhancing the user's viewing experience.

[0084] In an alternative embodiment, responding to a display instruction for the emotion distribution data and displaying the emotion distribution data includes: responding to the display instruction for the emotion distribution data and displaying the emotion distribution data in the form of a line graph or a bar graph.

[0085] As an example, referring to Figure 6 and Figure 7 as shown, after the user triggers the display instruction for the emotion distribution data, the emotion distribution data can be intuitively displayed in the form of a line graph or a bar graph.

[0086] Embodiment III Figure 8 Schematically shows a block diagram of an emotion distribution display device for a video according to Embodiment III of the present application, for a server. 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 8 shown, the emotion distribution display device 800 for the video may include: an acquisition module 810, an analysis module 820, a determination module 820, and a push module 830, where: The acquisition module 810 is configured to acquire emotion analysis data of a plurality of bullet screens corresponding to a target video, where the emotion analysis data includes an emotion label of the bullet screen and a creation time of the bullet screen; The determination module 820 is configured to determine the emotion distribution data of the target video according to the emotion analysis data of each of the bullet screens; The push module 830 is configured to push the emotion distribution data to the user terminal so that the user terminal displays the emotion distribution data.

[0087] As an alternative embodiment, determining the emotion distribution data of the target video according to the emotion analysis data of each of the bullet screens includes: According to the emotion analysis data of each of the bullet screens, counting the proportion of various types of emotion labels to obtain the emotion distribution data of the target video in the user dimension; According to the emotion analysis data of each of the bullet screens, counting the proportion of various types of emotion labels by time period to obtain the emotion distribution data of the target video in the time dimension.

[0088] As an optional embodiment, the sentiment analysis data further includes the sentiment label scores of the bullet comments; Correspondingly, according to the sentiment analysis data of each of the bullet comments, the proportion of various types of sentiment labels is statistically analyzed, and the sentiment distribution data of the target video in the user dimension includes: Statistically analyze the total value of the first sentiment label scores of various types of sentiment labels respectively; Based on the total value of the first sentiment label scores of various types of sentiment labels and the total value of the second sentiment label scores of all types of sentiment labels, determine the proportion of various types of sentiment labels; Take the proportion of various types of sentiment labels as the sentiment distribution data of the target video in the user dimension; Correspondingly, according to the sentiment analysis data of each of the bullet comments, the proportion of various types of sentiment labels is statistically analyzed by time period, and the sentiment distribution data of the target video in the time dimension includes: Statistically analyze the total value of the third sentiment label scores of various types of sentiment labels in each time period respectively; Based on the total value of the third sentiment label scores of various types of sentiment labels in each time period and the total value of the fourth sentiment label scores of all types of sentiment labels in each time period, determine the proportion of various types of sentiment labels in each time period; Take the proportion of various types of sentiment labels in all time periods as the sentiment distribution data of the target video in the time dimension.

[0089] As an optional embodiment, the sentiment analysis data further includes the bullet comment weight value; Correspondingly, the total value of the first sentiment label scores of various types of sentiment labels is obtained in the following manner: Calculate the sentiment scores of each bullet comment based on the sentiment label scores and bullet comment weight values of each bullet comment; Statistically analyze the total first sentiment scores corresponding to various types of sentiment labels, and take the total first sentiment scores as the total value of the first sentiment label scores; Correspondingly, the total value of the third sentiment label scores of various types of sentiment labels in each time period is obtained in the following manner: Calculate the sentiment scores of each bullet comment based on the sentiment label scores and bullet comment weight values of each bullet comment; Statistically analyze the total second sentiment scores corresponding to various types of sentiment labels in each time period, and take the total second sentiment scores as the total value of the third sentiment label scores.

[0090] As an optional embodiment, the sentiment analysis data is obtained by the following method: Input the barrage into a pre-trained sentiment analysis model, and output the sentiment label of the barrage through the sentiment analysis model; Generate the sentiment analysis data based on the sentiment label of the barrage and the attribute data of the barrage.

[0091] Embodiment 4 Figure 9 Schematically shows a block diagram of a sentiment distribution display device for a video according to Embodiment 4 of the present application, for a user terminal. 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 9 shown, the sentiment distribution display device 900 for the video may include: an acquisition module 910 and a display module 920, where: The acquisition module 910 is used to acquire the sentiment distribution data of the target video; The display module 920 is used to display the sentiment distribution data in response to a display instruction for the sentiment distribution data.

[0092] As an optional embodiment, displaying the sentiment distribution data in response to a display instruction for the sentiment distribution data includes: In response to a display instruction for the sentiment distribution data, display the sentiment distribution data in a line graph or a bar graph.

[0093] Embodiment 5 Figure 10 Schematically shows a hardware architecture diagram of a computer device 1000 suitable for implementing the method for displaying the sentiment distribution of a video according to Embodiment 5 of the present application. In some embodiments, the computer device 1000 may be 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, and other terminal devices. In other embodiments, the computer device 1000 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server or a server cluster composed of multiple servers), etc. As Figure 10 shown, the computer device 1000 includes but is not limited to: a memory 1010, a processor 1020, and a network interface 1030 that can communicate with each other through a system bus. Among them: The memory 1010 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 1010 may be an internal storage module of the computer device 1000, such as the hard disk or memory of the computer device 1000. In other embodiments, the memory 1010 may also be an external storage device of the computer device 1000, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the computer device 1000. Of course, the memory 1010 may also include both the internal storage module and the external storage device of the computer device 1000. In this embodiment, the memory 1010 is generally used to store the operating system and various application software installed on the computer device 1000, such as the program code of the method for displaying the emotional distribution of videos. In addition, the memory 1010 can also be used to temporarily store various types of data that have been output or will be output.

[0094] In some embodiments, the processor 1020 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other chip. The processor 1020 is generally used to control the overall operation of the computer device 1000, such as performing control and processing related to data interaction or communication with the computer device 1000. In this embodiment, the processor 1020 is used to run the program code stored in the memory 1010 or process data.

[0095] The network interface 1030 may include a wireless network interface or a wired network interface, which is generally used to establish a communication link between the computer device 1000 and other computer devices. For example, the network interface 1030 is used to connect the computer device 1000 to an external terminal via a network, and establish a data transmission channel and a communication link between the computer device 1000 and the external terminal. The network may be a wireless or wired network such as an enterprise intranet (Intranet), the Internet, Global System of Mobile communication (GSM for short), Wideband Code Division Multiple Access (WCDMA for short), 4G network, 5G network, Bluetooth, Wi-Fi, etc.

[0096] It should be noted that Figure 10 Only the computer device with components 1010 - 1030 is shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components may be alternatively implemented.

[0097] In this embodiment, the method for displaying the emotional distribution of the video stored in the memory 1010 may also be divided into one or more program modules and executed by one or more processors (such as the processor 1020) to complete the embodiments of the present application.

[0098] Embodiment Six The embodiment of the present application further provides 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 method for displaying the emotional distribution of the video in the embodiment are implemented.

[0099] 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, Smart Media Card (SMC), Secure Digital (SD) card, 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 method for displaying the emotional distribution of videos in the embodiment. In addition, the computer-readable storage medium may also be used to temporarily store various data that have been output or will be output.

[0100] Embodiment VII The embodiment of the present application also provides a computer program product, including a computer program, which when executed by a processor implements the method in the above embodiment.

[0101] 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, so that 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.

[0102] 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 displaying the emotional distribution of a video, characterized in that: For a server, the method comprises: Acquire sentiment analysis data of multiple bullet comments corresponding to the target video, wherein the sentiment analysis data includes sentiment tags of the bullet comments and creation time of the bullet comments; Determine the emotion distribution data of the target video according to the emotion analysis data of each barrage; The emotion distribution data is pushed to a user terminal so that the user terminal displays the emotion distribution data.

2. The method according to claim 1, characterized in that Determining the emotion distribution data of the target video according to the emotion analysis data of each of the bullet comments includes: According to the sentiment analysis data of each barrage, the proportion of various categories of sentiment tags is counted to obtain the sentiment distribution data of the target video in the user dimension; According to the sentiment analysis data of each barrage, the proportion of various categories of sentiment tags is counted by time period to obtain the sentiment distribution data of the target video in the time dimension.

3. The method according to claim 1, characterized in that: The sentiment analysis data also includes the sentiment tag score of the barrage; Correspondingly, according to the sentiment analysis data of each barrage, the proportion of various categories of sentiment tags is counted to obtain the sentiment distribution data of the target video in the user dimension, including: Count the total scores of the first emotion labels of various categories respectively; Determine the proportion of various categories of emotion tags based on the total value of the first emotion tag scores of various categories of emotion tags and the total value of the second emotion tag scores of all categories of emotion tags; The proportion of the emotion tags of various categories is used as the emotion distribution data of the target video in the user dimension; Correspondingly, according to the sentiment analysis data of each barrage, the proportion of various categories of sentiment tags is counted by time period, and the sentiment distribution data of the target video in the time dimension is obtained, including: Counting the total scores of the third emotion tags of various categories in each time period respectively; Determine the proportion of various categories of emotion tags in each of the time periods based on the total value of the third emotion tag scores of various categories of emotion tags in each of the time periods and the total value of the fourth emotion tag scores of all categories of emotion tags in each of the time periods; The proportion of various categories of emotional tags in all time periods is used as the emotional distribution data of the target video in the time dimension.

4. The method according to claim 3, characterized in that: The sentiment analysis data also includes a barrage weight value; Correspondingly, the total score of the first emotion label of each category of emotion labels is obtained as follows: The emotional score of each barrage is calculated based on the emotional label score and the weight value of each barrage; Counting the first total emotion scores corresponding to the emotion tags of various categories, and taking the first total emotion scores as the total score of the first emotion tag scores; Correspondingly, the total value of the third emotion label score of the emotion labels of various categories in each time period is obtained by the following method: The emotional score of each barrage is calculated based on the emotional label score and the weight value of each barrage; The second total emotion scores corresponding to the emotion tags of various categories in each time period are counted, and the second total emotion scores are used as the third emotion tag score total value.

5. The method according to any one of claims 1 to 4, characterized in that: The sentiment analysis data is obtained in the following way: Input the barrage into a pre-trained sentiment analysis model, and output the sentiment label of the barrage through the sentiment analysis model; The sentiment analysis data is generated based on the sentiment tag of the barrage and the attribute data of the barrage.

6. A method for displaying the emotional distribution of a video, characterized in that: For a user terminal, the method includes: Obtain the emotional distribution data of the target video; In response to a display instruction for the emotion distribution data, the emotion distribution data is displayed.

7. The method according to claim 7, characterized in that: In response to a display instruction for the emotion distribution data, displaying the emotion distribution data comprises: In response to a display instruction for the emotion distribution data, the emotion distribution data is displayed in a curve graph or a bar graph.

8. A device for displaying the emotional distribution of a video, characterized in that: For a server, the device comprises: An acquisition module is used to acquire sentiment analysis data of multiple bullet comments corresponding to a target video, wherein the sentiment analysis data includes sentiment tags of the bullet comments and creation time of the bullet comments; A determination module, used to determine the emotion distribution data of the target video according to the emotion analysis data of each barrage; The push module is used to push the emotion distribution data to the user terminal so that the user terminal displays the emotion distribution data.

9. A device for displaying the emotional distribution of a video, characterized in that: For a user terminal, the device comprises: An acquisition module is used to obtain the emotion distribution data of the target video; The display module is used to display the emotion distribution data in response to a display instruction for the emotion distribution data.

10. A computer device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

11. 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.

12. 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 any one of claims 1 to 7 are implemented.

Images