Progress bar setting method and device based on bullet screen

Abstract

The present application discloses a method and device for setting a progress bar based on bullet screen, and the method includes: obtaining bullet screen information of a video within a preset time, and determining a first adjustment weight of a video progress bar according to the bullet screen information; performing a similarity comparison between the bullet screen information and text information in a preset text result set, determining text information similar to the bullet screen information, and determining the frequency of occurrence of the corresponding text information according to the number of occurrences of the bullet screen information within the preset time; calculating a second adjustment weight of the text information on the video progress bar according to the frequency of occurrence of each text information in the preset text result set and the emotional tendency result of each text information; obtaining the progress curve information of the video progress bar according to the first adjustment weight and the second adjustment weight, so as to set the video progress bar curve according to the progress curve information. By using the first adjustment weight and the second adjustment weight to determine the progress curve information, the video hotspot can be highlighted with high accuracy, and the user experience is also improved.

Description

Technical Field

[0001] The present application relates to the field of video playback technology, and in particular to a method and device for setting a progress bar based on bullet screen. Background Art

[0002] When a video is playing, in addition to displaying the video screen, a video progress bar is also displayed to help users understand the video's playback duration, the user's current viewing time, etc.

[0003] As an instant comment system that includes user opinions and emotions, barrage is widely used on major video platforms to enhance the interactivity and fun of watching videos. Unlike the traditional comment function for the entire video, barrage includes the time when the user posted and the user's emotion at that time, which can reflect the user's attention to the video at that time. If the user's attention to the video is reflected in the progress bar, it can help users quickly locate the hot moments in the video and improve the user's viewing experience. Therefore, a method for setting a progress bar based on barrage is needed. Summary of the invention

[0004] In view of the above problems, embodiments of the present application are proposed to provide a method and device for setting a progress bar based on bullet screen that overcomes the above problems or at least partially solves the above problems.

[0005] According to a first aspect of an embodiment of the present application, a method for setting a progress bar based on a bullet screen is provided, comprising:

[0006] Obtaining bullet screen information of the video within a preset time, and determining a first adjustment weight of the video progress bar according to the bullet screen information;

[0007] Compare the similarity between the bullet chat information and the text information in the preset text result set, determine the text information similar to the bullet chat information, and determine the appearance frequency of the corresponding text information according to the number of occurrences of the bullet chat information within the preset time;

[0008] According to the occurrence frequency of each text information in the preset text result set and the emotional tendency result of each text information, a second adjustment weight of the text information on the video progress bar is calculated;

[0009] According to the first adjustment weight and the second adjustment weight, progress curve information of the video progress bar is obtained, so as to set the video progress bar curve according to the progress curve information.

[0010] Optionally, before comparing the barrage information with the text information in the preset text result set for similarity, the method further includes:

[0011] Filter the barrage information.

[0012] Optionally, filtering the bullet comment information further includes:

[0013] Filtering the barrage text information that meets the preset removal conditions; the preset removal conditions include that the barrage text information contains digital information;

[0014] De-duplicate the bullet-screen text information to filter out duplicate bullet-screen text information.

[0015] Optionally, comparing the bullet chat information with text information in a preset text result set for similarity, and determining text information similar to the bullet chat information further includes:

[0016] Traverse the bullet message information and calculate the text similarity between each bullet message text information and the text information in the preset text result set;

[0017] Determine whether the text similarity is greater than a preset similarity threshold;

[0018] If yes, then determine the text information similar to the bullet screen text information;

[0019] If not, add the bullet text information to the preset text result set.

[0020] Optionally, determining the appearance frequency of the corresponding text information according to the number of appearances of the bullet screen information within a preset time further includes:

[0021] Counting the number of occurrences of the barrage information within a preset time, and counting the total number of barrage information that appear within the preset time;

[0022] The appearance frequency of the corresponding text information is calculated according to the number of occurrences of the barrage information and the total number of barrage information; the appearance frequency is specifically the ratio of the number of occurrences of the barrage information to the total number of barrage information.

[0023] Optionally, calculating the second adjustment weight of the text information on the video progress bar according to the occurrence frequency of each text information in the preset text result set and the emotional tendency result of each text information further includes:

[0024] Perform sentiment analysis on each text message in the preset text result set according to natural language analysis to obtain the sentiment trend result of each text message;

[0025] The second adjustment weight of the text information on the video progress bar is obtained by accumulating the sum of the products of the occurrence frequency of each text information in the preset text result set and the sentiment tendency result of each text information.

[0026] Optionally, performing sentiment analysis on each text information of the preset text result set according to natural language analysis to obtain the sentiment tendency result of each text information further includes:

[0027] Perform sentiment classification analysis and sentiment intensity analysis on each text information in the preset text result set according to natural language analysis to obtain sentiment classification results of each text information and sentiment intensity results of the text information;

[0028] The emotional tendency results of the text information are obtained based on the emotional classification results of the text information and the emotional intensity results of the text information.

[0029] Optionally, the sentiment classification results of the text information include positive, neutral, and negative; wherein different sentiment classification results correspond to different sentiment scores;

[0030] The emotional intensity result of the text information is obtained according to the language analysis of the text information to obtain the corresponding emotional intensity score;

[0031] The emotional tendency result of the text information obtained according to the emotional classification result of the text information and the emotional intensity result of the text information further includes:

[0032] Multiply the sentiment score by the sentiment intensity score to get the sentiment tendency of the text information.

[0033] Optionally, obtaining bullet screen information of the video within a preset time, and determining a first adjustment weight of the video progress bar according to the bullet screen information further includes:

[0034] Obtain the barrage information of the video within a preset time, count the number of barrages in the video, and obtain the density distribution information within the preset time;

[0035] According to the density distribution information within a preset time, a first adjustment weight of the video progress bar is determined; wherein the first adjustment weight is proportional to the density distribution information within the preset time.

[0036] Optionally, the method further comprises:

[0037] Obtaining the user's jump play operation information on the video progress; the jump play operation information includes the position information before the jump, the position information after the jump and / or the number of jumps;

[0038] According to the jump playback operation information, the first adjustment weight of the video progress bar before the jump and / or after the jump position information is adjusted; wherein, the first adjustment weight of the position information before the jump is reduced, and the first adjustment weight of the position information after the jump is increased; the first adjustment weight is proportional to the number of jumps.

[0039] Optionally, obtaining progress curve information of the video progress bar according to the first adjustment weight and the second adjustment weight, so as to set the video progress bar curve according to the progress curve information further includes:

[0040] Determining curvature information of a progress curve of the video progress bar according to a product of the first adjustment weight and the second adjustment weight;

[0041] Set the video progress bar curve according to the progress curve curvature information.

[0042] According to a second aspect of an embodiment of the present application, a progress bar setting device based on a bullet screen is provided, comprising:

[0043] A first weight module, adapted to obtain bullet screen information of a video within a preset time, and determine a first adjustment weight of the video progress bar according to the bullet screen information;

[0044] The second weight module is adapted to compare the similarity between the bullet-screen information and the text information in the preset text result set, determine the text information similar to the bullet-screen information, and determine the appearance frequency of the corresponding text information according to the number of appearances of the bullet-screen information in the preset time; and calculate the second adjustment weight of the text information on the video progress bar according to the appearance frequency of each text information in the preset text result set and the emotional tendency result of each text information;

[0045] The curve adjustment module is adapted to obtain the progress curve information of the video progress bar according to the first adjustment weight and the second adjustment weight, so as to set the video progress bar curve according to the progress curve information.

[0046] According to a third aspect of an embodiment of the present application, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0047] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the above-mentioned bullet-screen-based progress bar setting method.

[0048] According to a fourth aspect of an embodiment of the present application, a computer storage medium is provided, in which at least one executable instruction is stored, and the executable instruction enables a processor to perform operations corresponding to the above-mentioned method for setting a progress bar based on bullet screen.

[0049] According to the bullet-screen-based progress bar setting method and device provided in the present application, the first adjustment weight of the video progress bar is determined according to the bullet-screen information, and the second adjustment weight is determined according to the appearance frequency and emotional tendency results of the corresponding text information by comparing the similarity between the bullet-screen information and the text information in the preset text result set. The progress curve information of the video progress bar is determined using the first adjustment weight and the second adjustment weight, and the video progress bar is used to highlight the video hotspots, thereby improving the user experience and ensuring the accuracy of the progress curve information in the video progress bar.

[0050] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0052] Figure 1 A flowchart of a method for setting a progress bar based on bullet screen according to an embodiment of the present application is shown;

[0053] Figure 2 A schematic diagram of multiple bullet screen information is shown;

[0054] Figure 3 A flowchart of a method for setting a progress bar based on bullet screen according to another embodiment of the present application is shown;

[0055] Figure 4 A schematic diagram showing the density distribution of bullet message items is shown;

[0056] Figure 5 A schematic diagram of a video progress bar curve is shown;

[0057] Figure 6 A schematic diagram of the structure of a progress bar setting device based on bullet screen according to an embodiment of the present application is shown;

[0058] Figure 7 A schematic diagram of the structure of a computing device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0059] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0060] First, the terms involved in one or more embodiments of the present application are explained.

[0061] NLP sentiment analysis: NLP (Natural Language Processing) is a branch of artificial intelligence that uses deep learning or machine learning to analyze the structure and meaning of text. Sentiment analysis is a branch of text classification that analyzes subjective text with emotional connotations (commendatory, derogatory, positive, negative) to determine the text's views, preferences, and emotional tendencies;

[0062] Video on demand: Video on demand was developed in foreign countries in the 1990s, also known as "VOD (Video On Demand)", a video on demand system that plays programs according to the audience's requirements, and transmits the video content clicked or selected by the user to the requested user. Video on demand service is a new media method in recent years, and is the product of the integration of computer technology, network communication technology, multimedia technology, television technology and digital compression technology.

[0063] User seek operation: Selecting an appropriate time point in the video on the progress bar to jump to the playback is a common operation of the player.

[0064] Figure 1 A flowchart of a method for setting a progress bar based on bullet screen according to an embodiment of the present application is shown. Figure 1 As shown, the method comprises the following steps:

[0065] Step S101, obtaining the bullet screen information of the video within a preset time, and determining the first adjustment weight of the video progress bar according to the bullet screen information.

[0066] The barrage information sent by users when watching videos includes barrage text information, barrage time, etc. Barrage text information is the text information displayed in the video, such as Figure 2 As shown in the figure, "Group photo", "Long wait", "Famous scene", "Professional training", "Hold back tears", "111", etc. are all displayed barrage text information; the barrage time is the time point when the user sends the video corresponding to the barrage, so it can be displayed in the video at that time point. Most of the barrage information sent by users is related to the video content, such as the exciting plot, turning points, touching clips and other hot moments in the video, which will resonate with users and send barrage information.

[0067] The barrage information expresses the user's attention to the hot moments in the video, which includes the user's preferences and opinions on the video content. When there are hot moments in the video content, the barrage information will also increase accordingly. The barrage information corresponding to different moments is different, and the number of barrage information will also be different. The barrage information within the preset time in the video is obtained. The preset time can be multiple, such as different durations are obtained according to the length of the video, and the preset time corresponding to different videos is divided, such as dividing it every 6 seconds from the beginning of the video to obtain multiple preset times, etc., which are not limited here. By counting the barrage information within the preset time, the number and distribution density of barrage information in different preset times can be determined. According to the number and distribution density of barrage information in different preset times, the first adjustment weight of the video progress bar can be determined. For example, the more the number of barrage information in the preset time, the higher the first adjustment weight of the progress bar of this part of the video in the preset time; the higher the distribution density of the barrage information in the preset time, the higher the first adjustment weight of the progress bar of this part of the video in the preset time, etc. The specific value can be set according to the implementation situation, which is not limited here.

[0068] Step S102, compare the similarity between the bullet chat information and the text information in the preset text result set, determine the text information similar to the bullet chat information, and determine the appearance frequency of the corresponding text information according to the number of appearances of the bullet chat information within a preset time.

[0069] The first adjustment weight is mainly determined based on the number and distribution density of the barrage information. However, the first adjustment weight only indirectly reflects that there are more barrages being sent and more users participating. It cannot accurately determine whether the current moment of the video is a hot moment of the video. Whether the barrage information sent by the user is a favorite of the hot moment of the video or a complaint about the poor plot cannot be intuitively reflected based on the first adjustment weight alone, and further analysis is needed based on the barrage text information contained in the barrage information.

[0070] Specifically, different barrage messages express different emotions of users, such as positive emotions such as like, praise, happiness, etc.; neutral emotions without obvious emotional tendencies; negative emotions such as dislike, disgust, anger, etc. The sentiment analysis of barrage messages can be obtained through NLP sentiment analysis, such as splitting the barrage messages into phrases, and performing semantic analysis on the split phrases, etc., which are not limited here. Considering the similarities between the barrage messages sent by users, the barrage messages sent by users may have different texts but the same semantics and contain the same emotions. It takes a lot of time to perform NLP sentiment analysis on each barrage message. Based on the similarity, similar barrage messages can be sentimentally analyzed together. For similarity comparison, this embodiment pre-collects historical barrage information to construct a preset text result set. The text information contained in the preset text result set is obtained based on the historical barrage information. The barrage information is compared with the text information in the preset text result set for similarity, such as performing a similarity comparison between the barrage information and the text information based on natural language processing. If a preset similarity threshold is set, if the similarity is greater than the preset similarity threshold, it is determined that the barrage information is similar to the text information, that is, the text information similar to the barrage information is determined. Subsequently, the emotion of the barrage information can be determined based on the similar text information, thereby reducing the need to perform emotion analysis on multiple barrage information one by one.

[0071] After determining the text information similar to the bullet screen information, it is necessary to further count the number of occurrences of the bullet screen information within the preset time. The preset time is as described in step S101, such as dividing a preset time every 6 seconds, and counting the number of occurrences of the bullet screen information within the preset time. If there is one bullet screen information similar to the text information, the number of occurrences of the text information within the preset time is the number of occurrences of the bullet screen information within the preset time; if there are multiple bullet screen information similar to the text information, the number of occurrences of the text information within the preset time is the sum of the number of occurrences of the multiple bullet screen information within the preset time. After obtaining the number of occurrences of the text information within the preset time, the frequency of occurrence of the text information can be calculated based on the number of occurrences of the text information within the preset time and the total number of bullet screen information that appears within the preset time. For example, if the number of occurrences of the text information within the preset time is 10 times and the total number of bullet screen information that appears within the preset time is 20 times, the frequency of occurrence of the text information = the number of occurrences of the text information within the preset time / the total number of bullet screen information that appears within the preset time = 0.5. The above is an example, which is specifically set according to the implementation situation.

[0072] Step S103, calculating a second adjustment weight of the text information on the video progress bar according to the appearance frequency of each text information in the preset text result set and the emotional tendency result of each text information.

[0073] Each text information in the preset text result set can be subjected to sentiment analysis in advance, and the sentiment tendency results of each text information can be obtained and saved. When used, it can be calculated directly according to the saved sentiment tendency results. The sentiment tendency results can be represented by corresponding scores to facilitate the calculation of the second adjustment weight. For example, a positive sentiment tendency result uses a positive score to increase the second adjustment weight; a negative sentiment tendency result uses a negative score to reduce the second adjustment weight; a neutral sentiment tendency result uses a score of 0, which does not affect the second adjustment weight, etc. The above is an example. The corresponding sentiment tendency results are set according to the implementation situation, and there is no limitation here.

[0074] The second adjustment weight is determined according to the sentiment tendency result of the text information and the frequency of occurrence of the text information. The higher the sentiment tendency result score of the text information, the higher the frequency of occurrence of the text information, and the larger the corresponding second adjustment weight value, and vice versa. Specifically, the product of the frequency of occurrence of each text information in the preset text result set within the preset time and the sentiment tendency result is accumulated to obtain the second adjustment weight of the video progress bar within the preset time. When there are multiple preset times, the second adjustment weight of the video progress bar of each preset time is calculated respectively.

[0075] Step S104: obtaining progress curve information of the video progress bar according to the first adjustment weight and the second adjustment weight, so as to set the video progress bar curve according to the progress curve information.

[0076] After obtaining the first adjustment weight and the second adjustment weight, the progress curve information of the video progress bar can be determined by jointly calculating the first adjustment weight and the second adjustment weight. When the first adjustment weight and the second adjustment weight of the preset time are both large, that is, the number of barrage messages sent by the user at the preset time is large, and the positive emotions are large, the video is a hot moment at the preset time, and the corresponding curve information has a larger value here, and the video progress bar curve set according to the progress curve information has a higher curve height at the preset time. The user can know that this is the hot moment of the video according to the video progress bar curve, and the user can directly order this moment to improve the user's viewing experience.

[0077] According to the barrage-based progress bar setting method provided in the present application, the first adjustment weight of the video progress bar is determined according to the barrage information, and the second adjustment weight is determined according to the appearance frequency and emotional tendency results of the corresponding text information by comparing the similarity between the barrage information and the text information in the preset text result set. The progress curve information of the video progress bar is determined using the first adjustment weight and the second adjustment weight, and the video progress bar is used to highlight the video hotspots, thereby improving the user experience and ensuring the accuracy of the progress curve information in the video progress bar.

[0078] Figure 3A flowchart of a method for setting a progress bar based on bullet screen according to an embodiment of the present application is shown. Figure 3 As shown, the method comprises the following steps:

[0079] Step S301, obtaining the bullet screen information of the video within a preset time, and determining the first adjustment weight of the video progress bar according to the bullet screen information.

[0080] The barrage information includes barrage text information, barrage time, etc. According to the barrage time, the barrage information of the barrage time in the video within the preset time is obtained, the number of barrages within the preset time is counted, and the density distribution information within the preset time is further obtained. Figure 4 As shown, the horizontal axis is the time axis, in seconds, the time represented by the horizontal axis corresponds to the video duration, and the vertical axis is the number of bullet screen messages. The number of bullet screen messages (i.e., the number of bullet screen messages) is filled into the coordinate axis according to the time, and the result is Figure 4 The density distribution information of the bullet screen is shown.

[0081] According to the density distribution information within the preset time, the first adjustment weight of the video progress bar can be determined, wherein the first adjustment weight is proportional to the density distribution information within the preset time. It can be set as a preset coefficient, and the preset coefficient is multiplied by the density distribution information of the preset time to obtain the first adjustment weight, etc., which is not limited here.

[0082] In addition to considering the bullet screen information, the first adjustment weight is also determined according to the user's on-demand operation and seek operation on the video. Specifically, the jump play operation information of the user on the video progress is obtained, that is, the user's seek operation, and the jump play operation information includes the position information before the jump, the position information after the jump, the number of jumps, etc. If the user drags the progress bar to jump to a certain position information, it means that the user's attention to the position before the jump is low, and it also means that the user's attention to the position after the jump is high. If a certain position is sought by the user many times and the user repeatedly watches it, the more the number of jumps, the higher the user's attention to the position after the jump. According to the jump play operation information, the first adjustment weight of the video progress bar before the jump and after the jump position information is adjusted; wherein, for the position information before the jump, the first adjustment weight of the position information before the jump is reduced, and for the position after the jump, the first adjustment weight of the position information after the jump is increased, and the first adjustment weight is proportional to the number of jumps. The specific adjustment value can be set according to the implementation situation for the adjustment result, which is not limited here.

[0083] Step S302, filtering the barrage information.

[0084] Get the barrage information in the video within the preset time. Considering that there are a lot of repetitions in the barrage information sent by users, sometimes the barrage information is meaningless, such as Figure 2As shown, the barrage information contains repeated identical barrage text information such as "group photo", "Long wait", "Famous scene", "Professional training", "Hold back the tears", etc., and there is also meaningless barrage information such as "111". It is not necessary to calculate the emotions contained in the repeated barrage information one by one. For the meaningless barrage information, it does not contain emotions itself and does not need to be calculated. Therefore, before calculation, the barrage information can be filtered, such as filtering the barrage text information that meets the preset removal conditions. The preset removal conditions include that the barrage text information contains digital information, that is, the digital information contains various numbers. The barrage text information that meets the preset removal conditions is mostly meaningless barrage information, and there is no need to perform sentiment analysis. It can be filtered to reduce the calculation amount of the barrage information. Furthermore, for a large amount of repeated barrage information, the barrage text information can be deduplicated to filter and remove the repeated barrage text information. Only one calculation is required for the barrage text information, which greatly reduces the calculation amount. For example, for the same barrage text information such as "group photo", "Long wait", "Famous scene", "Professional training", "Hold back the tears", etc., only one similarity comparison is required, and there is no need to perform multiple comparisons.

[0085] Step S303, performing a similarity comparison between the bullet chat information and the text information in the preset text result set, determining the text information similar to the bullet chat information, and determining the appearance frequency of the corresponding text information according to the number of appearances of the bullet chat information within a preset time.

[0086] The filtered bullet-screen information is traversed, each bullet-screen information is traversed, and the text similarity between each bullet-screen text information and the text information in the preset text result set is calculated, such as the text similarity between each bullet-screen text information and the text information in the preset text result set is calculated by the NLP algorithm. It is determined whether the text similarity is greater than the preset similarity threshold. If so, the text information similar to the bullet-screen text information is determined. If not, it is determined that there is no similar text information in the preset text result set, and the bullet-screen text information is added to the preset text result set.

[0087] After determining the text information similar to the bullet-screen text information, the frequency of occurrence of the text information is determined based on the bullet-screen information. Here, based on the actual bullet-screen information, i.e., the unfiltered bullet-screen information, the number of unfiltered bullet-screen information that appear within the preset time is counted, and the total number of bullet-screen information that appears within the preset time is counted. Figure 2 For example, if the bullet message is "group photo", the number of its appearances is 22. The total number of bullet messages that appear within the preset time is Figure 2The total number of all barrage messages in the text result set is 60. The frequency of occurrence of the corresponding text message is calculated based on the number of barrage messages and the total number of barrage messages. The frequency of occurrence is the ratio of the number of barrage messages to the total number of barrage messages, such as frequency of occurrence = number of barrage messages / total number of barrage messages = 22 / 60 = 0.37. For each text message in the preset text result set, the frequency of occurrence of each text message is calculated. If there is no barrage message similar to the text message within the preset time, the frequency of occurrence of the text message is 0.

[0088] Step S304, calculating a second adjustment weight of the text information on the video progress bar according to the occurrence frequency of each text information in the preset text result set and the emotional tendency result of each text information.

[0089] According to natural language analysis NLP, sentiment tendency analysis is performed on each text information of the preset text result set to obtain the sentiment tendency results of each text information. Sentiment tendency analysis includes sentiment classification analysis and sentiment intensity analysis on each text information of the preset text result set to obtain the sentiment classification results of each text information and the sentiment intensity results of the text information. The sentiment classification results of the text information include positive, neutral, and negative, and different sentiment classification results correspond to different sentiment scores. As shown in Table 1 below, positive, neutral, and negative correspond to different categories of sentiment, and different sentiment tendency results correspond to different sentiment scores.

[0090] category illustrate Sentiment score like Expressing positive emotions 1 Happy Expressing positive emotions such as happiness and joy 1 disgust Expressing negative emotions such as dislike and disgust -1 sad Expressing unhappy and sad emotions -1 anger Expressing angry, irritated emotions -1 No emotions No obvious emotional tendency 0

[0091] Table 1

[0092] As shown in Table 1, the sentiment score of a positive sentiment tendency result can be 1, the sentiment score of a negative sentiment tendency result can be -1, and the sentiment score of a neutral sentiment tendency result can be 0. The above are examples, and different sentiment scores can be set according to the implementation situation, which is not limited here.

[0093] The emotional intensity result of the text information is obtained according to the language analysis of the text information to obtain the corresponding emotional intensity score. For example, if the text information of the bullet comment is "so cute", the emotional tendency result is positive, and the emotional intensity score is 0.99999. The setting of the emotional intensity score is set according to the implementation situation, and the value range can be set to 0-1.

[0094] The emotional tendency result of the text information can be obtained based on the emotional classification result of the text information and the emotional intensity result of the text information, such as multiplying the emotional score by the emotional intensity score to obtain the emotional tendency result of the text information. That is, the emotional tendency result of the text information = emotional score * emotional intensity score. The emotional tendency results of each text information in the above preset text result set can be pre-analyzed and stored, and the emotional tendency results can be directly obtained when used.

[0095] After obtaining the sentiment trend result of the text information, the second adjustment weight of the text information on the video progress bar can be obtained by accumulating the sum of the product of the occurrence frequency of each text information in the preset text result set and the sentiment trend result of each text information. Among them, n represents the total number of text information in the preset text result set, i represents the i-th text information in the preset text result set, Pi represents the occurrence frequency of the i-th text information in the preset text result set, and Xi represents the emotional tendency result of the i-th text information in the preset text result set.

[0096] Step S305: determine the curvature information of the progress curve of the video progress bar according to the product of the first adjustment weight and the second adjustment weight, and set the video progress bar curve according to the curvature information of the progress curve.

[0097] The first adjustment weight obtained represents the density distribution of barrage information within the preset time, the user seek intensity, etc. The higher the first adjustment weight, the more heated the user's discussion at that location, but the first adjustment weight cannot reflect whether the user's attention, discussion, etc. is a positive comment on the correct hot moment of the video, or the outbreak point of the user's negative emotions, or the focus point of no emotional tendency. Therefore, this embodiment also introduces a second adjustment weight, which represents the user's emotional tendency towards the video, and can clearly understand the user's positive comments, negative complaints, or no emotional output on the video.

[0098] According to the product of the first adjustment weight and the second adjustment weight, the curvature information of the progress curve of the video progress bar can be determined. Specifically, the progress curve curvature information = Ai + Ai*Ri, where Ai is the first adjustment weight and Ri is the second adjustment weight. The progress curve curvature information is mainly based on the user's attention and is adjusted according to the user's emotional inclination towards the video, that is, the first adjustment weight is mainly used, and the second adjustment weight is used to correct the first adjustment weight to obtain the final progress curve curvature information. The progress curve curvature information corresponds one-to-one to the preset time. The video progress bar curve can be set accordingly according to the progress curve curvature information of each preset time, such as Figure 5 As shown, a wave curve is displayed on the conventional video progress bar, and the wave curve is the video progress bar curve. The peak of the video progress bar curve is the hot moment in the video, where users pay more attention and have more positive comments. By correcting the first adjustment weight with the second adjustment weight, a more accurate hot moment of the video can be obtained.

[0099] This embodiment can be used in various video playback scenarios such as video, live playback, etc. Figure 5The video progress bar curve shown can utilize the amount of barrage information and the emotional tendency contained in the barrage information itself to make the video progress bar curve more accurately reflect the hot moments in the video or live broadcast, and also facilitate users to quickly locate, view hot moments or create based on hot moments.

[0100] According to the method for setting a progress bar based on bullet screen provided in the present application, the first adjustment weight of the video progress bar is determined according to the number and density distribution of bullet screen information, combined with the user's jump operation, etc., and the bullet screen information is filtered to remove useless and invalid bullet screen information, remove repeated bullet screen information, reduce the amount of calculation of the bullet screen information, and improve the processing effect. The filtered bullet screen information is compared with the text information in the preset text result set for similarity to determine similar text information. According to the number of occurrences of the bullet screen information in the preset time, the frequency of occurrence of each text information in the preset text result set is determined. The second adjustment weight is determined by accumulating the frequency of occurrence of each text information in the preset text result set within the preset time and the product of the emotional tendency result. The first adjustment weight and the second adjustment weight are used to determine the curvature information of the progress curve of the video progress bar, and the video progress bar curve is set based on the curvature information of the progress curve. The peak of the video progress bar curve can facilitate users to quickly locate the hot moments of the video, improve the user's experience of watching the video, and also ensure the accuracy of the matching of the progress curve information in the video progress bar with the heat moment.

[0101] Figure 6 FIG. 1 shows a schematic diagram of a structure of a progress bar setting device based on bullet screen provided by an embodiment of the present application. Figure 6 As shown, the device comprises:

[0102] The first weight module 610 is adapted to obtain the bullet screen information of the video within a preset time, and determine the first adjustment weight of the video progress bar according to the bullet screen information;

[0103] The second weight module 620 is adapted to compare the similarity between the bullet message information and the text information in the preset text result set, determine the text information similar to the bullet message information, and determine the appearance frequency of the corresponding text information according to the number of appearances of the bullet message information in the preset time; calculate the second adjustment weight of the text information on the video progress bar according to the appearance frequency of each text information in the preset text result set and the emotional tendency result of each text information;

[0104] The curve adjustment module 630 is adapted to obtain the progress curve information of the video progress bar according to the first adjustment weight and the second adjustment weight, so as to set the video progress bar curve according to the progress curve information.

[0105] Optionally, the device further comprises:

[0106] The filtering module 640 is adapted to filter the bullet screen information.

[0107] Optionally, the filtering module 640 is further adapted to:

[0108] Filtering the barrage text information that meets the preset removal conditions; the preset removal conditions include that the barrage text information contains digital information;

[0109] De-duplicate the bullet-screen text information to filter out duplicate bullet-screen text information.

[0110] Optionally, the second weight module 620 is further adapted to:

[0111] Traverse the bullet message information and calculate the text similarity between each bullet message text information and the text information in the preset text result set;

[0112] Determine whether the text similarity is greater than a preset similarity threshold;

[0113] If yes, then determine the text information similar to the bullet screen text information;

[0114] If not, add the bullet text information to the preset text result set.

[0115] Optionally, the second weight module 620 is further adapted to:

[0116] Counting the number of occurrences of the barrage information within a preset time, and counting the total number of barrage information that appear within the preset time;

[0117] The appearance frequency of the corresponding text information is calculated according to the number of occurrences of the barrage information and the total number of barrage information; the appearance frequency is specifically the ratio of the number of occurrences of the barrage information to the total number of barrage information.

[0118] Optionally, the second weight module 620 is further adapted to:

[0119] Perform sentiment analysis on each text message in the preset text result set according to natural language analysis to obtain the sentiment trend result of each text message;

[0120] The second adjustment weight of the text information on the video progress bar is obtained by accumulating the sum of the products of the occurrence frequency of each text information in the preset text result set and the sentiment tendency result of each text information.

[0121] Optionally, the second weight module 620 is further adapted to:

[0122] Perform sentiment classification analysis and sentiment intensity analysis on each text information in the preset text result set according to natural language analysis to obtain sentiment classification results of each text information and sentiment intensity results of the text information;

[0123] The emotional tendency results of the text information are obtained based on the emotional classification results of the text information and the emotional intensity results of the text information.

[0124] Optionally, the sentiment classification results of the text information include positive, neutral, and negative; wherein different sentiment classification results correspond to different sentiment scores;

[0125] The emotional intensity result of the text information is obtained according to the language analysis of the text information to obtain the corresponding emotional intensity score;

[0126] The second weight module 620 is further adapted to:

[0127] Multiply the sentiment score by the sentiment intensity score to get the sentiment tendency of the text information.

[0128] Optionally, the first weight module 610 is further adapted to:

[0129] Obtain the barrage information of the video within a preset time, count the number of barrages in the video, and obtain the density distribution information within the preset time;

[0130] According to the density distribution information within a preset time, a first adjustment weight of the video progress bar is determined; wherein the first adjustment weight is proportional to the density distribution information within the preset time.

[0131] Optionally, the device further comprises:

[0132] The jump module 650 is suitable for obtaining the user's jump playback operation information on the video progress; the jump playback operation information includes the pre-jump position information, the post-jump position information and / or the number of jumps; according to the jump playback operation information, the first adjustment weight of the video progress bar in the pre-jump position information and / or the post-jump position information is adjusted; wherein, the first adjustment weight of the pre-jump position information is reduced, and the first adjustment weight of the post-jump position information is increased; the first adjustment weight is proportional to the number of jumps.

[0133] Optionally, the curve adjustment module 630 is further adapted to:

[0134] Determining curvature information of a progress curve of the video progress bar according to a product of the first adjustment weight and the second adjustment weight;

[0135] Set the video progress bar curve according to the progress curve curvature information.

[0136] The description of each module above refers to the corresponding description in the method embodiment and will not be repeated here.

[0137] According to the barrage-based progress bar setting device provided in the present application, the first adjustment weight of the video progress bar is determined according to the barrage information, and the second adjustment weight is determined according to the appearance frequency and emotional tendency results of the corresponding text information by comparing the similarity between the barrage information and the text information in the preset text result set. The progress curve information of the video progress bar is determined using the first adjustment weight and the second adjustment weight, and the video progress bar is used to highlight the video hotspots, thereby improving the user experience and ensuring the accuracy of the progress curve information in the video progress bar.

[0138] The present application also provides a non-volatile computer storage medium, which stores at least one executable instruction, and the executable instruction can execute the bullet-screen-based progress bar setting method in any of the above method embodiments.

[0139] Figure 7 A schematic diagram of the structure of a computing device according to an embodiment of the present application is shown. The specific embodiment of the present application does not limit the specific implementation of the computing device.

[0140] like Figure 7 As shown, the computing device may include: a processor (processor) 702 , a communications interface (Communications Interface) 704 , a memory (memory) 706 , and a communication bus 708 .

[0141] in:

[0142] The processor 702 , the communication interface 704 , and the memory 706 communicate with each other via a communication bus 708 .

[0143] The communication interface 704 is used to communicate with other devices such as clients or other servers.

[0144] The processor 702 is used to execute the program 710, and specifically can execute the relevant steps in the above-mentioned embodiment of the progress bar setting method based on the bullet screen.

[0145] Specifically, the program 710 may include program codes, which include computer operation instructions.

[0146] The processor 702 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the present application. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0147] The memory 706 is used to store the program 710. The memory 706 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0148] Program 710 can be specifically used to enable processor 702 to execute the method for setting a progress bar based on bullet screen in any of the above-mentioned method embodiments. The specific implementation of each step in program 710 can refer to the corresponding descriptions in the corresponding steps and units in the above-mentioned progress bar setting embodiment based on bullet screen, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the aforementioned method embodiment, which will not be repeated here.

[0149] The algorithm or display provided here is not inherently related to any specific computer, virtual system or other device. Various general systems can also be used together with the teaching based on this. According to the above description, it is obvious to construct the structure required for this type of system. In addition, the application is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the application described here, and the above description of specific languages ​​is to disclose the preferred embodiment of the application.

[0150] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0151] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the claims below, the inventive aspects are less than all the features of the single embodiment disclosed above. Therefore, the claims following the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0152] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0153] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0154] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components of the present application. The present application can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing a part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0155] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be constructed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A method for setting a progress bar based on bullet screen, include: Obtaining bullet screen information of the video within a preset time, and determining a first adjustment weight of the video progress bar according to the bullet screen information; Compare the similarity between the bullet-chat information and the text information in the preset text result set, determine the text information similar to the bullet-chat information, and determine the appearance frequency of the corresponding text information according to the number of occurrences of the bullet-chat information in the preset time; Calculate the second adjustment weight of the text information on the video progress bar according to the appearance frequency of each text information in the preset text result set and the emotional tendency result of each text information; According to the first adjustment weight and the second adjustment weight, the first adjustment weight is corrected according to the second adjustment weight to obtain the curvature information of the progress curve; the curvature information of the progress curve corresponds one-to-one to the preset time, and the video progress bar curve is set according to the progress curve curvature information of each preset time.

2. The method according to claim 1, in, Before comparing the similarity between the bullet comment information and the text information in the preset text result set, the method further includes: The barrage information is filtered.

3. The method according to claim 2, in, The filtering process of the bullet screen information further includes: Filtering the bullet-screen text information that meets the preset removal condition; the preset removal condition includes that the bullet-screen text information contains digital information; De-duplicate the bullet-screen text information to filter out duplicate bullet-screen text information.

4. The method according to claim 1, in, The comparing the similarity between the bullet-chat information and the text information in the preset text result set to determine the text information similar to the bullet-chat information further comprises: Traversing the barrage information, calculating the text similarity between the barrage text information of the barrage information and the text information in the preset text result set; Determine whether the text similarity is greater than a preset similarity threshold; If yes, then determine the text information similar to the bullet screen text information; If not, then the bullet screen text information is added to the preset text result set.

5. The method according to claim 1, in, The step of determining the appearance frequency of the corresponding text information according to the number of occurrences of the bullet screen information within a preset time further includes: Counting the number of occurrences of the barrage information within a preset time, and counting the total number of barrage information that appear within the preset time; The appearance frequency of the corresponding text information is calculated according to the number of appearances of the barrage information and the total number of barrage information; the appearance frequency is specifically the ratio of the number of appearances of the barrage information to the total number of barrage information.

6. The method according to any one of claims 1 to 5, in, The calculating the second adjustment weight of the text information on the video progress bar according to the occurrence frequency of each text information in the preset text result set and the emotional tendency result of each text information further includes: Performing sentiment analysis on each text information in the preset text result set according to natural language analysis to obtain a sentiment tendency result of each text information; The sum of the products of the occurrence frequency of each text information in the preset text result set and the sentiment tendency results of each text information is accumulated to obtain the second adjustment weight of the text information on the video progress bar.

7. The method according to claim 6, in, The performing sentiment tendency analysis on each text information of the preset text result set according to the natural language analysis to obtain the sentiment tendency result of each text information further comprises: Performing sentiment classification analysis and sentiment intensity analysis on each text information in the preset text result set according to natural language analysis to obtain a sentiment classification result of each text information and a sentiment intensity result of the text information; The emotional tendency result of the text information is obtained according to the emotional classification result of the text information and the emotional intensity result of the text information.

8. The method according to claim 7, in, The sentiment classification of the text information includes positive, neutral, and negative; wherein different sentiment classification results correspond to different sentiment scores; The emotion intensity result of the text information is obtained by analyzing the language of the text information to obtain a corresponding emotion intensity score; The step of obtaining the emotional tendency result of the text information according to the emotional classification result of the text information and the emotional intensity result of the text information further comprises: The sentiment score is multiplied by the sentiment intensity score to obtain the sentiment tendency result of the text information.

9. The method according to any one of claims 1 to 8, in, The acquiring of bullet screen information of the video within a preset time, and determining the first adjustment weight of the video progress bar according to the bullet screen information further comprises: Obtain the barrage information of the video within a preset time, count the number of barrages in the video, and obtain the density distribution information within the preset time; According to the density distribution information within the preset time, a first adjustment weight of the video progress bar is determined; wherein the first adjustment weight is proportional to the density distribution information within the preset time.

10. The method according to any one of claims 1 to 9, in, The method further comprises: Obtaining the user's jump play operation information on the video progress; the jump play operation information includes the position information before the jump, the position information after the jump and / or the number of jumps; Adjust the first adjustment weight of the video progress bar before the jump position information and / or after the jump position information according to the jump playback operation information; wherein, the first adjustment weight of the position information before the jump is reduced, and the first adjustment weight of the position information after the jump is increased; the first adjustment weight is proportional to the number of jumps.

11. The method according to any one of claims 1 to 10, in, According to the first adjustment weight and the second adjustment weight, the first adjustment weight is corrected according to the second adjustment weight to obtain curvature information of the progress curve; The progress curve curvature information corresponds to the preset time one by one, and setting the video progress bar curve according to the progress curve curvature information of each preset time further includes: Determining curvature information of a progress curve of the video progress bar according to a product of the first adjustment weight and the second adjustment weight; The video progress bar curve is set according to the progress curve curvature information.

12. A progress bar setting device based on bullet screen, include: A first weight module, adapted to obtain bullet screen information of a video within a preset time, and determine a first adjustment weight of the video progress bar according to the bullet screen information; A second weight module is adapted to compare the similarity between the bullet chat information and the text information in the preset text result set, determine the text information similar to the bullet chat information, and determine the appearance frequency of the corresponding text information according to the number of occurrences of the bullet chat information within a preset time; Calculate the second adjustment weight of the text information on the video progress bar according to the appearance frequency of each text information in the preset text result set and the emotional tendency result of each text information; The curve adjustment module is suitable for correcting the first adjustment weight according to the second adjustment weight based on the first adjustment weight and the second adjustment weight to obtain the curvature information of the progress curve; the curvature information of the progress curve corresponds one-to-one to the preset time, and the video progress bar curve is set according to the progress curve curvature information of each preset time.

13. A computing device, include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the bullet-screen-based progress bar setting method as described in any one of claims 1-11.

14. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute operations corresponding to the method for setting a progress bar based on a bullet screen as described in any one of claims 1 to 11.

15. A computer program product, comprising at least one executable instruction, wherein the executable instruction enables a processor to execute operations corresponding to the method for setting a progress bar based on a bullet screen as described in any one of claims 1 to 11.

Images