Video watching point generation method and device, equipment and storage medium

Abstract

The invention provides a video watching point generation method and device, equipment and a storage medium, and the method comprises the steps: determining bullet screen theme information, the bullet screen theme information comprises a bullet screen subject term and a time period corresponding to the bullet screen subject term, and the bullet screen subject term is a phrase determined based on a plurality of bullet screen texts with an association relationship; taking the plot abstract with the intersection between the time period corresponding to the plot abstract and the time period corresponding to the bullet screen subject term as a target plot abstract; determining a standard role name in the bullet screen subject term based on a character name in the bullet screen subject term; acquiring role information corresponding to the standard role name from a role information base based on the standard role name; and generating watching point information of the video clip based on the bullet screen subject term, the target plot abstract and role information corresponding to the standard role name. The step of manually analyzing the bullet screen content is avoided, the plot watching point generation efficiency is improved, the influence of human subjective factors on video watching points is avoided, and the plot watching point quality is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for generating video highlights. Background Art

[0002] With the continuous development of Internet technology, video websites have become an important platform for mass leisure and entertainment. For example, users can play videos by visiting video websites, video applications, etc.

[0003] In the related technology, when watching a film or TV series, the staff needs to manually summarize the barrage content based on their own understanding of the barrage content to obtain the highlights of the video.

[0004] However, manually watching TV series and barrage takes a long time and requires a lot of manpower and time, resulting in low efficiency in generating video highlights. Summary of the invention

[0005] In order to solve the above technical problems, the present application provides a method, device, equipment and storage medium for generating video highlights, which avoids the step of manually analyzing the content of the barrage, improves the efficiency of generating plot highlights, avoids the influence of human subjective factors on the video highlights, and improves the quality of the plot highlights.

[0006] In a first aspect, the present application provides a method for generating highlights of a video, the method comprising: determining bullet screen theme information, the bullet screen theme information comprising bullet screen theme words and time periods corresponding to the bullet screen theme words, the bullet screen theme words being phrases determined based on multiple bullet screen texts having an associated relationship, the time periods corresponding to the bullet screen theme words being time periods in which multiple bullet screen texts appear in an initial video, and the initial video being the video watched when the user inputs the bullet screen text; taking a plot summary in which a time period corresponding to a plot summary and a time period corresponding to a bullet screen theme word intersect as a target plot summary, the time period corresponding to the plot summary being a time period in which a video clip corresponding to the plot summary appears in the initial video; determining a standard character name in the bullet screen theme words based on the character name in the bullet screen theme words, the character name being a name that identifies a specific character that appears in the bullet screen theme words, the character name being a name that identifies a character displayed in the initial video, and the standard character name being a character name that conforms to a preset naming rule; obtaining character information of the standard character name from a character information library based on the standard character name, wherein the character information library includes multiple character information, and the character information being descriptive information related to the character in the initial video; generating highlight information of the video clip based on the bullet screen theme words, the target plot summary, and the character information of the standard character name.

[0007] In a second aspect, the present application provides a device for generating highlights of a video, the device comprising: a theme information determination module for determining bullet screen theme information, the bullet screen theme information comprising bullet screen theme words and time periods corresponding to the bullet screen theme words, the bullet screen theme words being phrases determined based on a plurality of associated bullet screen texts, the time periods corresponding to the bullet screen theme words being time periods in which the plurality of bullet screen texts appear in an initial video, the initial video being the video watched when the user inputs the bullet screen text; a target plot summary acquisition module for taking a plot summary in which the time period corresponding to the plot summary and the time period corresponding to the bullet screen theme words intersect as a target plot summary, the time period corresponding to the plot summary being the time period of the video clip corresponding to the plot summary in the initial video; the target A character name extraction module is used to determine the standard character name in the barrage keywords based on the character name in the barrage keywords, where the character name refers to the name that identifies a specific character that appears in the barrage keywords, the character name refers to the name that identifies the character shown in the initial video, and the standard character name refers to the character name that conforms to the preset naming rules; a character information acquisition module is used to obtain the character information of the standard character name from the character information library based on the standard character name, wherein the character information library includes multiple character information, and the character information refers to the descriptive information related to the character in the initial video; a highlight information generation module is used to generate the highlight information of the video clip based on the barrage keywords, the target plot summary and the character information of the standard character name.

[0008] In a third aspect, the present application provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by one or more processors, the one or more processors implement the video highlight generation method as described in the first aspect above.

[0009] In a fourth aspect, the present application provides a storage medium, which may be a computer-readable storage medium, storing a computer program thereon, which, when executed by a processor, implements the video highlight generation method as described in the first aspect above.

[0010] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, a method for generating video highlights as described in any one of the first aspects above is implemented.

[0011] Compared with the prior art, the technical solution provided by the embodiments of the present application has the following advantages:

[0012] The embodiment of the present application provides a method, device, equipment and storage medium for generating highlights of a video, the method comprising: determining bullet screen theme information, the bullet screen theme information comprising bullet screen theme words and time periods corresponding to the bullet screen theme words, the bullet screen theme words being phrases determined based on multiple bullet screen texts having an associated relationship, the time periods corresponding to the bullet screen theme words being time periods in which multiple bullet screen texts appear in an initial video, the initial video being the video being watched when the user inputs the bullet screen text; taking a plot summary in which a time period corresponding to a plot summary and a time period corresponding to a bullet screen theme word intersect as a target plot summary, the time period corresponding to the plot summary being the time period in which the video clip corresponding to the plot summary appears in the initial video; time period in the video; based on the character names in the barrage keywords, determine the standard role names in the barrage keywords, where the character name refers to the name that identifies a specific character that appears in the barrage keywords, the role name refers to the name that identifies the role shown in the initial video, and the standard role name refers to the role name that conforms to the preset naming rules; based on the standard role name, obtain the role information of the standard role name from the role information library, wherein the role information library includes multiple role information, and the role information refers to the description information related to the role in the initial video; generate the highlight information of the video clip based on the barrage keywords, the target plot summary and the role information of the standard role name.

[0013] In the embodiment of the present application, starting from the bullet screen, the plot summary and the character information in the video are analyzed to generate the final video highlights. Since the bullet screen theme is obtained by analyzing the bullet screen text input by the user, the generated video highlights are more in line with the interests of the public, and the quality of the plot highlights is improved. In the process of generating the video highlights, the character information is introduced, so that the final video highlights are more accurate, further improving the quality of the video highlights. In addition, this process avoids the step of manually analyzing the content of the bullet screen, improves the efficiency of generating the plot highlights, and avoids the influence of human subjective factors on the plot highlights, further improving the quality of the plot highlights. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0016] Figure 1 A schematic diagram of a flow chart of a method for generating video highlights provided in an embodiment of the present application;

[0017] Figure 2 A schematic diagram of a flow chart of an optimized video highlight generation method provided in an embodiment of the present application;

[0018] Figure 3 A flowchart of a method for determining a standard role name provided in an embodiment of the present application;

[0019] Figure 4 A schematic diagram of the structure of a video highlight generation device provided in an embodiment of the present application;

[0020] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.

[0023] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0024] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0025] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0026] The video highlight generation method provided by the present application is described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0027] Figure 1This is a flow chart of a method for generating video highlights in an embodiment of the present application. This embodiment is applicable to the case of mining video highlights. The method can be executed by a video highlight generation device. The video highlight generation device can be implemented in software and / or hardware. The video highlight generation device can be configured in an electronic device. The electronic device can be any one of a smart phone, a laptop computer, a desktop computer, a portable computer, a server, etc.

[0028] like Figure 1 As shown, the video highlight generation method provided in the embodiment of the present application mainly includes steps S101-S105.

[0029] S101. Determine the barrage theme information, which includes barrage theme words and time periods corresponding to the barrage theme words. The barrage theme words are phrases determined based on multiple barrage texts with associated relationships. The time period corresponding to the barrage theme words is the time period when multiple barrage texts appear in the initial video. The initial video is the video watched by the user when entering the barrage text.

[0030] Among them, barrage is an effect in which the real-time comments sent by users float across the screen in the form of subtitles during video playback. Barrage text refers to the comment content sent by users in the form of barrage. In other words, barrage text can refer to the real-time comment content sent by users, and the comment content can be composed of text and / or special symbols. Furthermore, when users send voice barrage while watching videos, the barrage text is obtained after audio recognition of the voice in the language barrage.

[0031] The barrage keywords are phrases determined based on multiple barrage texts with associated relationships. Among them, the barrage texts with associated relationships can be understood as the themes or topics discussed by multiple barrage texts are the same or similar. In other words, the barrage keywords are the common content or subject content of the barrage texts within a period of time. The barrage keywords are usually obtained by semantically analyzing multiple barrage texts using a pre-set algorithm. Specifically, a certain number of barrage texts or a period of time are collected, and the latent Dirichlet allocation algorithm (LDA) or the latent semantic analysis algorithm (LSA) can be used to perform semantic analysis on the collected barrage texts to obtain the barrage keywords.

[0032] The initial video is the video that the user is watching when inputting the barrage text. The initial video may refer to an episode of a TV series, a movie, a clip of a TV series or a movie, etc. During the playback of the initial video, multiple barrage texts sent by the user are received, and semantic analysis is performed on the multiple barrage texts to obtain one or more barrage theme words.

[0033] In an initial video, as the plot develops, different bullet screen keywords may exist at different plot stages. Therefore, there may be multiple bullet screen keywords in an initial video. For each bullet screen keyword, the video highlight generation method provided in the embodiment of the present application can be used to generate its corresponding video highlight.

[0034] Since the barrage theme words are obtained by aggregating multiple barrage texts, and since multiple barrage texts may be sent by one or more viewers at different time points, resulting in different sending time points for multiple barrage texts, when multiple viewers send barrage texts with the same topic or discussion point in the same initial video, multiple barrage texts form a barrage theme word. The time period in which multiple barrage texts of the barrage theme word appear in the initial video obtained by semantic analysis is the time period corresponding to the barrage theme word. The time period corresponding to the barrage theme word can be the time interval between the earliest sending time point and the latest sending time point of the multiple barrage texts that form the barrage theme word.

[0035] Exemplarily, the barrage keyword is obtained by semantic analysis of barrage text 1, barrage text 2, ..., barrage text N, and the subject or topic discussed by barrage text 1, barrage text 2, ..., barrage text N is the same. The i-th barrage text among the N barrage texts is sent the earliest, when the initial video is played to 10:35, and the j-th barrage text among the N barrage texts is sent the latest, when the initial video is played to 15:48. If the other barrage texts among the N barrage texts are all sent within the time interval [10:35, 15:48], then the time period corresponding to the barrage keyword is [10:35, 15:48].

[0036] S102, taking a plot summary whose time period corresponding to the plot summary and the time period corresponding to the bullet screen keyword intersect as a target plot summary, wherein the time period corresponding to the plot summary is the time period of the video clip corresponding to the plot summary in the initial video.

[0037] A plot summary refers to a text summary that summarizes the plot of a film or TV work. The plot summary in the embodiment of the present application may include a minute-level plot summary. Among them, a minute-level plot summary is a detailed description of the content of the episode in chronological order, usually accurate to what key events or dialogues occurred every minute. The minute-level plot summary is mainly used to help people quickly understand or review the main plot of a movie, TV series or video.

[0038] In practical applications, a plot summary usually refers to a minute-level plot summary of a TV series or a movie. The above target plot summary can be understood as a plot summary related to the bullet screen theme words. In other words, the plot described in the target plot summary is the same or similar to the theme content represented by the bullet screen theme words, or the theme content represented by the bullet screen theme words is part of the plot content in the target plot summary.

[0039] Since each important plot or dialogue in the minute-level plot summary is recorded and the exact time of appearance of each plot or dialogue in the original video is marked (for example, "5th minute", "23rd minute 45 seconds"), it can help quickly locate a specific scene. The time period corresponding to the target plot summary is the time period when the important plot or dialogue included in the target plot summary appears in the original video.

[0040] In one possible implementation, a minute-level plot summary of the initial video is obtained, and a minute-level plot summary whose time period overlaps with the time period corresponding to the bullet-screen theme word is used as the target plot summary. In other words, the time period corresponding to the bullet-screen theme word overlaps with the time period corresponding to the target plot summary.

[0041] In a possible implementation, a plot summary in which a time period corresponding to the plot summary and a time period corresponding to the barrage theme word intersect is used as a target plot summary, including: obtaining the start time point and the end time point of the time period corresponding to the plot summary; obtaining the start time point and the end time point of the time period corresponding to the barrage theme word; taking the minimum value between the end time point of the plot summary and the end time point of the barrage theme word as the first time point; taking the maximum value between the start time point of the plot summary and the start time point of the barrage theme word as the second time point; if the difference between the first time point and the second time point is greater than a set time threshold, taking the plot summary as the target plot summary.

[0042] The plot summary of the initial video can be processed in segments to obtain multiple plot summaries. The above segmentation method can be segmented according to set time intervals, and accordingly, each plot summary is the plot summary of the video clip corresponding to each time interval. For example: an initial video is 45 minutes, and it can be divided into 9 time intervals according to 5 minutes, and each time interval corresponds to a plot summary. The above segmentation method can also be divided according to the scene conversion situation in the initial video. If a transition occurs in the initial video, the plot summary is segmented at the transition time point, and the plot summary before the transition is used as one plot summary, and the plot summary after the transition is used as another plot summary. It should be noted that the embodiment of the present application only briefly introduces the division method of the plot summary, and is not limited.

[0043] As can be seen from the above, each plot summary is obtained by dividing the overall plot summary of the initial video, so each plot summary has its corresponding time period. The time period is the time period when the corresponding video clip of each plot summary appears in the initial video.

[0044] As shown in Table 2, the time period corresponding to the first plot summary is The time period corresponding to the second plot summary is

[0045] Table 2

[0046]

[0047] If the time period corresponding to the bullet screen keyword is The time period corresponding to the bullet screen keywords The time periods corresponding to each plot summary For comparison, if the time period corresponding to the bullet screen keyword Time period corresponding to the plot summary If there is an intersection, the plot summary is used as the target plot summary.

[0048] Furthermore, if the time periods corresponding to multiple plot summaries overlap with the time period corresponding to the bullet screen keyword, the multiple plot summaries are merged in chronological order and used as the target plot summary.

[0049] In a possible implementation, taking one of the plot summaries as an example, a method for determining whether the plot summary is a target plot summary is introduced. Each plot summary can be determined by the following method to determine whether the plot summary is a target plot summary.

[0050] Get the start time point in the time period corresponding to the bullet screen keyword The starting time point in the time period corresponding to the plot summary The starting time point in the time period corresponding to the bullet screen keyword The starting time point in the time period corresponding to the plot summary The maximum value among is taken as the second time point.

[0051] Get the end time point in the time period corresponding to the bullet screen keyword The end time point in the time period corresponding to the plot summary The end time point in the time period corresponding to the bullet screen keyword will be taken The end time point in the time period corresponding to the plot summary Compare the sizes and select the minimum value from the two end time points as the first time point.

[0052] Then, the first time point is subtracted from the second time point to obtain the difference between the two. If the difference is greater than 0, it indicates that the time period corresponding to the plot summary and the time period corresponding to the barrage theme word have an intersection. If the difference is less than or equal to 0, it indicates that the time period corresponding to the plot summary and the time period corresponding to the barrage theme word do not have an intersection.

[0053] Specifically, formula (1) can be used to determine whether the time period corresponding to a plot summary and the time period corresponding to the bullet screen keyword have an intersection.

[0054]

[0055] in, Indicates the end time point of the time period corresponding to the bullet screen keyword. Indicates the end time point of the time period corresponding to a plot summary. Indicates the start time of the time period corresponding to the bullet screen keyword. Indicates the starting time point of the time period corresponding to a plot summary. Represents the minimum value of two end time points, Indicates the maximum value between two start time points.

[0056] If the above formula (1) is greater than 0, that is, the smaller end time point minus the larger start time point is greater than 0, then the time period corresponding to the bullet screen theme word and the time period corresponding to the plot summary partially overlap. If the above formula (1) is less than or equal to 0, that is, the smaller end time point minus the larger start time point is less than or equal to 0, it means that the time period corresponding to the plot summary starts after the time period corresponding to the bullet screen theme word ends, or the time period corresponding to the plot summary ends before the time period corresponding to the bullet screen theme word starts, then the time period corresponding to the bullet screen theme word and the time period corresponding to the plot summary do not overlap.

[0057] In this embodiment, whether the time period corresponding to the barrage theme word and the time period corresponding to the plot summary intersect is determined to determine whether the plot summary is a plot summary related to the barrage theme word, thereby providing a method for determining a target plot summary, making the obtained target plot summary more accurate, thereby improving the accuracy of the video highlights.

[0058] S103. Based on the character names in the barrage keywords, determine the standard role names in the barrage keywords. The character name refers to the name that appears in the barrage keywords to identify a specific person. The role name refers to the name that identifies the character shown in the initial video. The standard role name refers to the role name that conforms to the preset naming rules.

[0059] Among them, the character name refers to the name used to identify a specific person that appears in the barrage keywords. The character name can be a standard name or a non-standard name. A standard name refers to a name that conforms to the set specifications and format naming rules. Specifically, a standard name refers to a name that conforms to the naming rules of surname plus given name. For example, "Zhang San" is a standard name, with the surname "Zhang" and the given name "San". A non-standard name means that the character name is not a standard name, and can also be understood as other ways of addressing besides the standard name.

[0060] The character name refers to the name that identifies the character shown in the initial video. For example, the name of the male protagonist and the name of the female protagonist in a drama are both character names. Character names can include non-standard character names and standard character names. For example, non-standard character names can include the user's nickname for an actor, the user's nickname for a character, the identity of the character in the drama, etc. For example, if the virtual character is a princess of a dynasty, the user also calls the virtual character by her identity "Princess".

[0061] Furthermore, the standard name also includes a standard actor name, which refers to an actor name that complies with the set specification and format naming rules, and the actor name refers to the name of the performer who plays the role. For example, the standard actor name is "Zhang San", and the standard character name of the virtual character he plays in the initial video is "Zhao Wu".

[0062] The character name is extracted from the bullet-chat keywords, and the character name is matched in the standard character name library. If a standard character name can be matched, the character name is determined to be a standard character name, and the character name is directly used as the standard character name in the bullet-chat keywords. The standard character name library includes the standard character names of all characters in the initial video.

[0063] The character name is extracted from the bullet-screen keywords. If the character name is not a standard role name, a match is performed in the standard actor name library based on the character name. If a standard actor name can be matched, the standard role name corresponding to the standard actor name is queried in the actor role relationship based on the standard actor name, and the queried standard role name is used as the standard role name in the bullet-screen keywords. The standard actor name library includes the standard actor names of all the roles in the initial video. The actor role relationship refers to the correspondence between a virtual character and the performer who plays the virtual character, and the correspondence includes the correspondence between the standard role name and the standard role name. The above correspondence can be stored in the form of a list or in the form of data, which is not limited in this embodiment.

[0064] In an embodiment of the present application, when a standard actor name is extracted from the barrage keywords, the actor-role relationship is queried to determine the standard role name corresponding to the standard actor name, so as to obtain the role information of the standard role name, thereby improving the accuracy of the highlight information.

[0065] In the case where the character name is a non-standard name, the standard character names of all characters are extracted from the target plot summary, and semantic analysis is performed on the non-standard name and the target plot summary to obtain the standard character name corresponding to the character name.

[0066] In the case where the character name is a non-standard name, since the reasons for the user to use the non-standard name are very personalized, it is impossible to obtain the standard character name by processing the barrage theme words or character names alone. In this case, the standard character name in the barrage theme words is determined based on the target plot summary, which improves the accuracy of the highlight information.

[0067] S104. Based on the standard role name, obtain role information of the standard role name from a role information library, wherein the role information library includes a plurality of role information, and the role information refers to description information related to the role in the initial video.

[0068] Character information can also be called character introduction information, which can be understood as the descriptive information about the name, background, personality, characteristics, abilities, etc. of any virtual character in the initial video. Character information can help the big model better understand the character.

[0069] In another possible implementation, since the role information stored in the role information database is recorded as standard role names, after extracting the standard role names in the barrage keywords, a query is performed in the role information database based on the standard role names. If a standard role name consistent with the standard role name can be found, the role information corresponding to the standard role name is read from the role information database.

[0070] S105, generating highlight information of the video clip based on the bullet screen keywords, the target plot summary and the character information of the standard character name.

[0071] The highlight information of a video clip refers to the information corresponding to the clip that the audience may be interested in. The highlight information includes the reason why the user sends a barrage comment and / or a plot phrase. The plot phrase refers to a concise and powerful expression that summarizes or emphasizes the key points or turning points in the plot.

[0072] In one possible implementation, the character information of the barrage keywords, target plot summary, and standard character name is input into the text generation model, so that the text generation model outputs the reason why the user sends the barrage comment and the plot phrase corresponding to the barrage keyword.

[0073] In a possible implementation, a preset prompt word is obtained. The prompt word is mainly used to obtain keywords or phrases provided for specific information or answers when interacting with the text generation model. The prompt word can help the text generation model understand the user's needs and generate relevant answers or content.

[0074] Specifically, in the process of inputting the character information corresponding to the bullet-screen theme words, target plot summary, and standard character name into the text generation model, the prompt words corresponding to the bullet-screen theme words may be: "The audience sent a bullet screen when watching a certain plot: []" The prompt words corresponding to the target plot summary may be: "The plot is as follows: []". The prompt words corresponding to the character information may be: "Related character introduction: []".

[0075] For example, when the bullet screen keyword is "aaa", the target plot summary is "bbbbb", and the character information network is "Zhang San is ccccc, Li Si is ddddd". Among them, "ccccc" is Zhang San's character information, and "ddddd" is Li Si's character information.

[0076] Then the data input into the text generation model is "The audience sent a barrage while watching a certain plot: [aaa]; the plot is as follows: [bbbbb]; "The relevant character introductions are: [Zhang San is ccccc, Li Si is ddddd]"; please analyze the reasons why the audience sent the barrage and summarize the plot phrases related to the barrage based on the given plot and dialogue." The text generation model analyzes and processes the input data and can output the reasons why users send barrage comments and the brief plot phrases corresponding to the barrage keywords.

[0077] In one possible implementation, highlight information of a video clip is generated based on barrage keywords, target plot summaries, and character information of standard character names, including: obtaining pre-set prompt words, the prompt words are used to indicate the type of plot highlights output by the text generation big model; generating input information from the prompt words, barrage keywords, target plot summaries, and character information of standard character names, and inputting the input information into the generation big model; receiving the highlight information of the video clip outputted from the generation big model, the type of the highlight information being consistent with the type indicated by the prompt words.

[0078] Among them, the prompt word is used to indicate the type of the highlight information output by the text generation model. This type mainly refers to the tendency of the plot phrase. For example, the types indicated by the prompt word may include: "exciting plot", "emotional resonance", "social issues", "educational value", "visual effects", etc. For example: "Phrase type: [happy]" and so on.

[0079] In an embodiment of the present application, the prompt words, barrage keywords, target plot summary, and character information of the target object are simultaneously input into the text generation model to instruct the text generation model to mine the highlight information in the barrage keywords.

[0080] For example, the prompt word is happy in emotional resonance, and the data input into the text generation model is "the audience sent a barrage when watching a certain plot: [aaa]; the plot is as follows: [bbbbb]; "the relevant character introductions are: [Zhang San is ccccc, Li Si is ddddd]"; phrase type: [happy]; please analyze the reasons why the audience sent the barrage and summarize the plot related to the barrage based on the given plot and dialogue. "The text generation model analyzes the reasons why users have emotional resonance based on the input data and generates relevant plot phrases.

[0081] For example, the first prompt word is XXXX in the social topic, and the data input into the big model is "the audience sent a barrage while watching a certain plot: [aaa]; the plot is as follows: [bbbbb]; the lines and dialogues of the characters are as follows: [Zhang San: "*******", Li Si: "*******"]; "The relevant character introductions are: [Zhang San is ccccc, Li Si is ddddd]: "Phrase type: [XXXX]"; please analyze the reasons why the audience sent the barrage and summarize the plot phrases related to the barrage based on the given plot and dialogue". The text generation big model analyzes the reasons why the audience raised the topic based on the input data and generates relevant plot phrases.

[0082] On the basis of the above embodiment, the data input into the text generation big model also includes step prompt words, which are used to indicate the steps of the big model analyzing the character information of the barrage keywords, target plot summaries, and standard character names.

[0083] For example: the step prompts may include: "step1: extract characters from the barrage keywords; step2: extract characters from the plot summary step3: if there are characters in the barrage keywords that do not appear in the plot, please try to determine their identities based on the character introduction information and replace them in the barrage keywords and give the replaced barrage keywords. step4: analyze the reasons for the barrage keywords obtained in step 3. step5: if there is a plot related to the barrage keywords, please extract the plot phrases related to the barrage from the plot summary and the dialogue content. The answer is given in json format, with the key being the reason for the barrage, the relevant plot and the summary of the relevant plot. If the barrage is not based on the plot, please answer: {"barrage reason":"none","relevant plot":"none"}".

[0084] The embodiment of the present application provides a method for generating highlights of a video, the method comprising: determining bullet screen theme information, the bullet screen theme information comprising bullet screen theme words and time periods corresponding to the bullet screen theme words, the bullet screen theme words being phrases determined based on a plurality of bullet screen texts having an associated relationship, the time periods corresponding to the bullet screen theme words being time periods in which the plurality of bullet screen texts appear in an initial video, and the initial video being the video watched when the user inputs the bullet screen text; taking a plot summary in which a time period corresponding to a plot summary and a time period corresponding to a bullet screen theme word have an intersection as a target plot summary, the time period corresponding to the plot summary being a time period in which a video clip corresponding to the plot summary appears in the initial video; determining a standard role name in the bullet screen theme words based on a character name in the bullet screen theme words, the character name being a name that identifies a specific character that appears in the bullet screen theme words, the role name being a name that identifies a character displayed in the initial video, and the standard role name being a role name that conforms to a preset naming rule; acquiring role information of the standard role name from a role information library based on the standard role name, wherein the role information library includes a plurality of role information, and the role information being description information related to the character in the initial video; generating highlight information of the video clip based on the bullet screen theme words, the target plot summary, and the role information of the standard role name.

[0085] In the embodiment of the present application, starting from the bullet screen, the plot summary and the character information in the video are analyzed to generate the final video highlights. Since the bullet screen theme is obtained by analyzing the bullet screen text input by the user, the generated video highlights are more in line with the interests of the public, and the quality of the plot highlights is improved. In the process of generating the video highlights, the character information is introduced, so that the final video highlights are more accurate, further improving the quality of the video highlights. In addition, this process avoids the step of manually analyzing the content of the bullet screen, improves the efficiency of generating the plot highlights, and avoids the influence of human subjective factors on the plot highlights, further improving the quality of the plot highlights.

[0086] On the basis of the above embodiments, the embodiments of the present application further optimize the method for generating video highlights, such as Figure 2 As shown, the optimized video highlight generation method provided in the embodiment of the present application mainly includes the following steps S201 to S206.

[0087] S201. Determine the barrage theme information, which includes barrage theme words and time periods corresponding to the barrage theme words. The barrage theme words are phrases determined based on multiple barrage texts with associated relationships. The time period corresponding to the barrage theme words is the time period when multiple barrage texts appear in the initial video. The initial video is the video watched when the user enters the barrage text.

[0088] S202, taking the plot summary whose time period corresponding to the plot summary and the time period corresponding to the bullet screen keyword intersect as the target plot summary, and the time period corresponding to the plot summary is the time period of the video clip corresponding to the plot summary in the initial video.

[0089] S203. Based on the character names in the barrage keywords, determine the standard role names in the barrage keywords. The character name refers to the name that appears in the barrage keywords to identify a specific person. The role name refers to the name that identifies the character shown in the initial video. The standard role name refers to the role name that conforms to the preset naming rules.

[0090] S204. Based on the standard role name, obtain role information of the standard role name from a role information library, wherein the role information library includes a plurality of role information, and the role information refers to description information related to the role in the initial video.

[0091] The execution process of steps S201-S204 provided in the embodiment of the present application is the same as that of steps S101-S104 provided in the above embodiment. For details, please refer to the description in the above embodiment, which will not be repeated in the embodiment of the present application.

[0092] S205. The conversation content whose time period corresponding to the conversation content and the time period corresponding to the bullet screen keyword intersect is taken as the target conversation content. The time period corresponding to the conversation content is the time period of the video clip corresponding to the conversation content in the initial video.

[0093] The dialogue content refers to the speech content of each character in the initial video. After the dialogue content included in the initial video is segmented, multiple dialogue contents are obtained. The target dialogue content can be understood as the intersection of the time period corresponding to it and the time period corresponding to the barrage theme word. In other words, the target dialogue content refers to the dialogue content of the characters in the video clip within the time period corresponding to the barrage theme word. Among them, the dialogue content includes the speaking role and the dialogue content. For example: the dialogue content is "Zhang San: "*******"; Li Si: "*******"".

[0094] The segmentation method of the dialogue content is the same as the segmentation method of the plot summary. For details, please refer to the description in the above embodiment, and will not be repeated in the embodiments of this application.

[0095] As can be seen from the above, each conversation content is divided by the overall conversation content corresponding to the initial video, so each conversation content has its corresponding time period. The time period corresponding to the conversation content is the time period of the video clip corresponding to the conversation content in the initial video.

[0096] As shown in Table 3, the time period corresponding to conversation content 1 is The time period corresponding to conversation content 2 is

[0097] Table 3

[0098]

[0099] If the time period corresponding to the bullet screen keyword is Then the time period corresponding to the bullet screen keyword The time period corresponding to each conversation content For comparison, if the time period corresponding to the bullet screen keyword The time period corresponding to the conversation content If there is an intersection, the conversation content is used as the target conversation content.

[0100] Furthermore, if the time periods corresponding to multiple conversation contents overlap with the time period corresponding to the bullet screen keyword, the multiple conversation contents are merged in chronological order and used as the target conversation content.

[0101] Taking one of the conversation contents as an example, a method for determining whether the conversation content is the target conversation content is introduced. The following method can be used to determine whether each conversation content is the target conversation content.

[0102] The conversation content in which the time period corresponding to the conversation content and the time period corresponding to the barrage theme word intersect is taken as the target conversation content, including: obtaining the start time point and the end time point of the time period corresponding to the conversation content; obtaining the start time point and the end time point of the time period corresponding to the barrage theme word; taking the minimum value between the end time point of the conversation content and the end time point of the barrage theme word as the third time point; taking the maximum value between the start time point of the conversation content and the start time point of the barrage theme word as the fourth time point; if the difference between the third time point and the fourth time point is greater than the set time threshold, taking the conversation content as the target conversation content.

[0103] Get the start time point in the time period corresponding to the bullet screen keyword And the start time point in the time period corresponding to the conversation content The maximum value is selected from the two starting time points as the fourth time point.

[0104] Get the end time point in the time period corresponding to the bullet screen keyword And the end time point in the time period corresponding to the conversation content Select the minimum value from the two end time points as the third time point.

[0105] Then, the third time point is subtracted from the fourth time point to obtain the difference between the two. If the difference is greater than 0, it indicates that the time period corresponding to the target content and the time period corresponding to the barrage theme word have an intersection. If the difference is less than or equal to 0, it indicates that the time period corresponding to the target content and the time period corresponding to the barrage theme word do not have an intersection.

[0106] Specifically, formula (2) can be used to determine whether a time period corresponding to a certain target content and a time period corresponding to a bullet screen keyword have an intersection.

[0107]

[0108] in, Indicates the end time point of the time period corresponding to the bullet screen keyword. Indicates the end time point of the time period corresponding to a certain target content. The start time of the time period corresponding to the bullet screen keyword. Indicates the start time of the time period corresponding to a certain target content. Represents the minimum value of two end time points, Indicates the maximum value between two start time points.

[0109] If the above formula (2) is greater than 0, that is, the smaller end time point minus the larger start time point is greater than 0, then the time period corresponding to the bullet screen theme word and the time period corresponding to the target content partially overlap. If the above formula (1) is less than or equal to 0, that is, the smaller end time point minus the larger start time point is less than or equal to 0, it means that the time period corresponding to the target content starts after the time period corresponding to the bullet screen theme word ends, or the time period corresponding to the target content ends before the time period corresponding to the bullet screen theme word starts, then the time period corresponding to the bullet screen theme word and the time period corresponding to the target content do not overlap.

[0110] S206, generating highlight information of the video clip based on the bullet screen keywords, the target plot summary, the character information of the standard character name, and the target dialogue content.

[0111] In one possible implementation, the barrage keywords, target plot summary, character information of the standard character name, and target dialogue content are input into a text generation model, so that the text generation model outputs the reason why the user sends the barrage comment and the plot phrase corresponding to the barrage keyword.

[0112] Specifically, in the process of inputting the barrage theme words, target plot summary, character information of standard character names, and target dialogue content into the text generation model, the prompt words corresponding to the barrage theme words can be: "The audience sent a barrage while watching a certain plot: []" The prompt words corresponding to the target plot summary can be: "The plot is as follows: []". The prompt words corresponding to the character information can be: "Related character introduction: []; the dialogue content is "Zhang San: "*******", Li Si: "*******"".

[0113] S206 provided in the embodiment of the present application is similar to S105 provided in the above embodiment, except that relevant information about the conversation content is added to the prompt words and the data input into the text generation model. Other processing methods are the same, and specific details may be referred to the description in the above embodiment.

[0114] In the embodiment of the present application, starting from the bullet screen, the character information in the plot summary and the dialogue content video is analyzed to generate the final video highlights. Since the bullet screen theme is obtained by analyzing the bullet screen text input by the user, the generated video highlights are more in line with the interests of the public, and the quality of the plot highlights is improved. In the process of generating the video highlights, the character information is introduced, so that the final video highlights are more accurate, and the quality of the video highlights is further improved. In the process of generating the video highlights, the dialogue content is introduced, so that the final video highlights are more accurate, and the quality of the video highlights is further improved.

[0115] On the basis of the above embodiment, the embodiment of the present application optimizes the step of "determining the standard character name in the barrage theme words based on the character name in the barrage theme words" in the above embodiment, such as Figure 3 As shown, the optimized standard role name determination method provided in the embodiment of the present application mainly includes the following steps S301 to S306.

[0116] S301, extracting the character names from the bullet screen keywords.

[0117] Use natural language processing (NLP) tools to extract character names from barrage keywords, or use trained deep learning models or machine learning models to extract character names from barrage keywords.

[0118] S302, determine whether the character name is a standard name, if so, execute S303, if not, execute S306. A standard name refers to a name that complies with a preset naming rule.

[0119] A large number of standard name samples are used to train the entity naming judgment model. The character names in the barrage keywords are input into the entity naming judgment model, and the entity naming judgment model is used to determine whether the character name is a standard name.

[0120] S303, determine whether the character name is a standard role name, if so, execute S304, if not, execute S305.

[0121] A standard character name library is pre-built, and the character name extracted from the bullet comment keywords is searched in the standard character name library. If a standard character name that is consistent with the character name is found, it indicates that the character name is a standard character name. If a standard character name that is consistent with the character name is not found, it indicates that the character name is not a standard character name, and further identification of the target character name is required.

[0122] S304, using the character name as the standard role name in the bullet screen keywords.

[0123] If a standard role name that is consistent with the character name can be searched in the standard role name library, it means that the character name is a standard role name, and the character name is directly used as the standard role name in the barrage theme words.

[0124] S305: Determine whether the character name is a standard actor name, if yes, execute S306.

[0125] A standard actor name library is pre-constructed, and a search is performed in the standard actor name library based on the character name. If a standard actor name consistent with the character name can be found, and if a standard name consistent with the character name cannot be found in the standard actor name library, it indicates that the character name is a standard actor name, and S306 is executed.

[0126] If a standard actor name that is consistent with a character name cannot be found in the standard actor name database, it indicates that the character name is neither a standard actor name nor a standard role name.

[0127] S306. Searching for a standard role name corresponding to a standard actor name in the actor-role relationship; and using the searched standard role name as the standard role name in the bullet comment keyword.

[0128] Based on the standard actor name, the actor role relationship is searched, and the searched standard role name is used as the standard role name in the bullet screen theme. For example, the standard actor name extracted from the bullet screen theme is "Zhang San", and by searching in the actor role relationship, the standard role name played by "Zhang San" is "Zhao Wu".

[0129] S307, extracting the standard character names included in the target plot summary; obtaining the role information of the standard character names included in the target plot summary from the role information library; performing semantic analysis on the character names and the role information to determine the standard character names corresponding to the character names.

[0130] If the character name is not a standard name, since the reasons for users to use non-standard names are very personalized, at this time, it is impossible to obtain the standard character name by simply processing the bullet screen theme words or character names. At this time, the target plot summary and character information are used to assist in determining the standard character name.

[0131] In one implementation, for each standard character name extracted from the target plot summary, the character information corresponding to each standard character name is obtained. Semantic analysis is performed on the character name and each piece of character information to determine the standard character name corresponding to the character name.

[0132] If the character name is a non-standard name, for example: the character name is "the eldest princess". Then semantic analysis is performed on each piece of character information to determine which piece of character information describes "the eldest princess", and then the standard character name of the character information is used as the standard character name in the bullet screen theme words.

[0133] Based on the above embodiments, in the case where the character name is a standard actor name or the character name is not a standard name, the character name in the bullet screen theme words is replaced with the standard character name corresponding to the character name to obtain a new bullet screen theme word; based on the bullet screen theme word, the target plot summary, and the character information of the standard character name, the highlight information of the video segment is generated, including: generating the highlight information of the video segment based on the new bullet screen theme word, the target plot summary, and the character information of the standard character name.

[0134] Furthermore, in the case where the character name is a standard actor name, the character name is replaced with the standard character name to obtain a new bullet screen theme word.

[0135] For example: the bullet screen theme word is "Zhang San returns on horseback", the standard actor name extracted from the bullet screen theme word is "Zhang San", and by querying in the actor-role relationship, the standard character name played by "Zhang San" is obtained as "Zhao Wu". Then the standard character name "Zhao Wu" is used to replace the standard actor name "Zhang San" in the bullet screen theme word to form a new bullet screen theme word. The new bullet screen theme word is "Zhao Wu returns on horseback".

[0136] Since in the actual application process, the plot summary and dialogue information content usually use standard character names, then the standard actor name in the bullet screen theme word is replaced with the standard character name to obtain a new bullet screen topic to assist the text generation large model in understanding the bullet screen theme word and improve the accuracy of the highlight information.

[0137] Furthermore, in the case where the character name is a non-standard name, the character name is replaced with the standard character name corresponding to the character name to obtain a new bullet screen theme word.

[0138] For example, if the bullet screen theme is "General Zhao returns on horseback", the non-standard name extracted from the bullet screen theme is "General Zhao". By searching in the actor-role relationship, the standard role name played by "General Zhao" is "Zhao Wu". Then the non-standard name "General Zhao" in the bullet screen theme is replaced with the standard role name "Zhao Wu" to form a new bullet screen theme. The new bullet screen theme is "Zhao Wu returns on horseback".

[0139] In actual applications, plot information and dialogue information usually use standard character names to describe characters. In this embodiment, standard character names are used to replace non-standard names to obtain new barrage topics, so as to assist the large model in understanding the barrage keywords and improve the accuracy of the highlight information.

[0140] Figure 4 Schematic diagram of the structure of a video highlight generating device in an embodiment of the present application. Figure 4 As shown, the video highlight generating device 30 provided in the embodiment of the present application mainly includes: a theme information determining module 41, a target plot summary acquiring module 42, a target character name extracting module 43, a character information acquiring module 44 and a highlight information generating module 45.

[0141] Among them, the theme information determination module 41 is used to determine the bullet screen theme information, the bullet screen theme information includes the bullet screen theme words and the time period corresponding to the bullet screen theme words, the bullet screen theme words are phrases determined based on multiple bullet screen texts with an associated relationship, the time period corresponding to the bullet screen theme words is the time period when the multiple bullet screen texts appear in the initial video, and the initial video is the video watched when the user inputs the bullet screen text; the target plot summary acquisition module 42 is used to take the plot summary where the time period corresponding to the plot summary and the time period corresponding to the bullet screen theme words intersect as the target plot summary, and the time period corresponding to the plot summary is the time period of the video clip corresponding to the plot summary in the initial video; the target character name extraction module 43 is used Based on the character names in the barrage keywords, the standard character names in the barrage keywords are determined, where the character name refers to the name that identifies a specific character that appears in the barrage keywords, the character name refers to the name that identifies the character shown in the initial video, and the standard character name refers to the character name that conforms to the preset naming rules; a character information acquisition module 44 is used to obtain character information of the standard character name from a character information library based on the standard character name, wherein the character information library includes multiple character information, and the character information refers to descriptive information related to the character in the initial video; a highlight information generation module 45 is used to generate highlight information of a video clip based on the barrage keywords, the target plot summary, and the character information of the standard character name.

[0142] The embodiment of the present application provides a device for generating highlights of a video, which is used to execute the following process: determining bullet screen theme information, the bullet screen theme information includes bullet screen theme words and time periods corresponding to the bullet screen theme words, the bullet screen theme words are phrases determined based on multiple bullet screen texts with associated relationships, the time periods corresponding to the bullet screen theme words are time periods when multiple bullet screen texts appear in an initial video, and the initial video is the video watched when the user inputs the bullet screen text; taking a plot summary in which the time period corresponding to the plot summary and the time period corresponding to the bullet screen theme words intersect as the target plot summary, and the time period corresponding to the plot summary is the time period when the video clip corresponding to the plot summary appears in the initial video time period in the bullet screen; based on the character names in the bullet screen keywords, determine the standard role names in the bullet screen keywords, where the character name refers to the name that identifies a specific character that appears in the bullet screen keywords, the role name refers to the name that identifies the role shown in the initial video, and the standard role name refers to the role name that conforms to the preset naming rules; based on the standard role name, obtain role information of the standard role name from the role information library, wherein the role information library includes multiple role information, and the role information refers to the descriptive information related to the role in the initial video; generate the highlight information of the video clip based on the bullet screen keywords, the target plot summary and the role information of the standard role name.

[0143] In the embodiment of the present application, starting from the bullet screen, the plot summary and the character information in the video are analyzed to generate the final video highlights. Since the bullet screen theme is obtained by analyzing the bullet screen text input by the user, the generated video highlights are more in line with the interests of the public, and the quality of the plot highlights is improved. In the process of generating the video highlights, the character information is introduced, so that the final video highlights are more accurate, further improving the quality of the video highlights. In addition, this process avoids the step of manually analyzing the content of the bullet screen, improves the efficiency of generating the plot highlights, and avoids the influence of human subjective factors on the plot highlights, further improving the quality of the plot highlights.

[0144] In a possible implementation, the target plot summary acquisition module 42 is specifically used to obtain the start time point and the end time point of the time period corresponding to the plot summary; obtain the start time point and the end time point of the time period corresponding to the barrage theme word; take the minimum value between the end time point of the plot summary and the end time point of the barrage theme word as the first time point; take the maximum value between the start time point of the plot summary and the start time point of the barrage theme word as the second time point; if the difference between the first time point and the second time point is greater than the set time threshold, the plot summary is taken as the target plot summary.

[0145] In one possible implementation, the device also includes: a target dialogue content acquisition module, which is used to take the dialogue content whose time period corresponding to the dialogue content intersects with the time period corresponding to the barrage theme word as the target dialogue content, and the time period corresponding to the dialogue content is the time period of the video clip corresponding to the dialogue content in the initial video; a highlight information generation module 45, which is specifically used to generate highlight information of the video clip based on the barrage theme words, the target plot summary, the character information of the standard character name and the target dialogue content.

[0146] In one possible implementation, the target conversation content acquisition module is specifically used to obtain the start time point and end time point of the time period corresponding to the conversation content; obtain the start time point and end time point of the time period corresponding to the barrage theme word; take the minimum value between the end time point of the conversation content and the end time point of the barrage theme word as the third time point; take the maximum value between the start time point of the conversation content and the start time point of the barrage theme word as the fourth time point; if the difference between the third time point and the fourth time point is greater than the set time threshold, the conversation content is taken as the target conversation content.

[0147] In one possible implementation, the target character name extraction module 43 is specifically used to extract the character name in the barrage keywords; determine whether the character name is a standard name, where a standard name refers to a name that conforms to the set specifications and format naming rules; if the character name is a standard name, determine whether the character name is a standard character name; if the character name is a standard character name, use the character name as the standard character name in the barrage keywords.

[0148] In one possible implementation, the target character name extraction module 43 is specifically used to determine whether the character name is a standard actor name if it is not a standard character name. A standard actor name refers to an actor name that conforms to the naming rules of the set specifications and formats. The actor name refers to the name of the performer who plays the role; if the character name is a standard actor name, the standard role name corresponding to the standard actor name is queried in the actor-role relationship; and the queried standard role name is used as the standard role name in the barrage keyword.

[0149] In one possible implementation, the target character name extraction module 43 is specifically used to extract the standard character name included in the target plot summary if the character name is not a standard name; obtain the character information of the standard character name included in the target plot summary from the character information library; perform semantic analysis on the character name and character information to determine the standard character name corresponding to the character name.

[0150] A possible implementation method also includes: a name replacement module, which is used to replace the character name in the barrage theme words with the standard role name corresponding to the character name when the character name is a standard actor name or the character name is not a standard name, so as to obtain a new barrage theme word; a highlight information generation module 45, which is specifically used to generate highlight information of the video clip based on the new barrage theme word, the target plot summary and the role information of the standard role name.

[0151] In a possible implementation, the highlight information generation module 45 is specifically used to obtain a preset prompt word, which is used to indicate the type of plot highlights output by the text generation model; generate input information from the prompt word, the bullet screen theme word, the target plot summary, and the character information of the standard character name, and input the input information into the generation model; receive the highlight information of the video clip output from the generation model, and the type of the highlight information is consistent with the type indicated by the prompt word. The video highlight generation device provided in the embodiment of the present application can execute the video highlight generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0152] Figure 5 is a schematic diagram of the structure of an electronic device provided in this embodiment. The electronic device may include a video highlight generating device, such as Figure 5 As shown, the electronic device 500 includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of the processor 510 in the electronic device can be one or more. Figure 5 A processor 510 is taken as an example; the processor 510, the memory 520, the input device 530 and the output device 540 in the electronic device can be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0153] The memory 520 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the video highlights generation method in the embodiment of the present invention. The processor 510 executes various functional applications and data processing of the electronic device by running the software programs, instructions and modules stored in the memory 520, that is, the video highlights generation method provided in the embodiment of the present invention is implemented.

[0154] The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 520 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 520 may further include a memory remotely arranged relative to the processor 510, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0155] The input device 530 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device, and may include a keyboard, a mouse, etc. The output device 540 may include a display device such as a display screen.

[0156] This embodiment also provides a storage medium containing computer executable instructions. When the computer executable instructions are executed by a computer processor, they are used to implement the video highlight generation method provided in the embodiment of the present invention.

[0157] Of course, the storage medium containing computer executable instructions provided in an embodiment of the present invention is not limited to the above method operations, and the computer executable instructions can also execute related operations in the video highlight generation method provided in any embodiment of the present invention.

[0158] Through the above description of the implementation mode, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation mode. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0159] It is worth noting that in the embodiment of the above-mentioned video highlight generating device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0160] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0161] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating video highlights, characterized in that: The method comprises: Determine barrage theme information, the barrage theme information includes barrage theme words and time periods corresponding to the barrage theme words, the barrage theme words are phrases determined based on multiple barrage texts with associated relationships, the time periods corresponding to the barrage theme words are time periods in which the multiple barrage texts appear in an initial video, and the initial video is a video watched when the user inputs the barrage texts; The plot summary whose time period corresponding to the plot summary and the time period corresponding to the barrage keyword intersect is used as the target plot summary, and the time period corresponding to the plot summary is the time period of the video clip corresponding to the plot summary in the initial video; Based on the character names in the barrage theme words, determine the standard character names in the barrage theme words, wherein the character name refers to a name that appears in the barrage theme words to identify a specific character, the character name refers to a name that identifies the character shown in the initial video, and the standard character name refers to a character name that conforms to a preset naming rule; Based on the standard role name, obtaining role information of the standard role name from a role information library, wherein the role information library includes a plurality of role information, and the role information refers to description information related to the role in the initial video; The highlight information of the video clip is generated based on the barrage theme words, the target plot summary and the character information of the standard character name.

2. The method according to claim 1, characterized in that The plot summary whose time period corresponding to the plot summary and the time period corresponding to the barrage theme word intersect is used as the target plot summary, including: Obtaining the start time point and the end time point of the time period corresponding to the plot summary; Obtain the start time point and end time point of the time period corresponding to the bullet screen keyword; The minimum value between the ending time point of the plot summary and the ending time point of the bullet screen theme word is taken as the first time point; The maximum value between the starting time point of the plot summary and the starting time point of the bullet screen keyword is taken as the second time point; If the difference between the first time point and the second time point is greater than a set time threshold, the plot summary is used as a target plot summary.

3. The method according to claim 1 or 2, characterized in that: Also includes: The conversation content whose time period corresponding to the conversation content and the time period corresponding to the barrage keyword intersect is used as the target conversation content, and the time period corresponding to the conversation content is the time period of the video clip corresponding to the conversation content in the initial video; The generating of the highlight information of the video clip based on the bullet screen theme words, the target plot summary and the character information of the standard character name includes: Based on the barrage keywords, the target plot summary, the character information of the standard character name, and the target dialogue content, the highlight information of the video clip is generated.

4. The method according to claim 3, characterized in that The conversation content whose time period corresponding to the conversation content and the time period corresponding to the barrage keyword intersect is used as the target conversation content, including: Obtaining the start time point and the end time point of the time period corresponding to the conversation content; Obtain the start time point and end time point of the time period corresponding to the bullet screen keyword; The minimum value between the end time point of the conversation content and the end time point of the bullet screen keyword is used as the third time point; The maximum value between the start time point of the conversation content and the start time point of the bullet screen keyword is taken as the fourth time point; If the difference between the third time point and the fourth time point is greater than a set time threshold, the conversation content is used as the target conversation content.

5. The method according to claim 1, characterized in that Based on the character names in the barrage theme words, determining the standard character names in the barrage theme words includes: Extracting the character names from the bullet screen keywords; Determine whether the character name is a standard name, where the standard name refers to a name that complies with a preset naming rule; If the character name is a standard name, determining whether the character name is a standard character name; If the character name is a standard character name, the character name is used as the standard character name in the barrage theme words.

6. The method according to claim 5, characterized in that Also includes: If the character name is not a standard role name, determining whether the character name is a standard actor name, wherein the standard actor name refers to an actor name that complies with a preset naming rule, and the actor name refers to the name of the performer who plays the role; If the character name is a standard actor name, query the actor-role relationship for a standard role name corresponding to the standard actor name; The queried standard role name is used as the standard role name in the barrage keyword.

7. The method according to claim 5, characterized in that Also includes: If the character name is not a standard name, extracting a standard character name included in the target plot summary; Acquire character information of standard character names included in the target plot summary from the character information database; Semantic analysis is performed on the character name and the role information to determine a standard role name corresponding to the character name.

8. The method according to claim 5 or 6, characterized in that: Also includes: In the case where the character name is a standard actor name or the character name is not a standard name, the character name in the barrage theme word is replaced with a standard role name corresponding to the character name to obtain a new barrage theme word; Generating the highlight information of the video clip based on the bullet screen theme word, the target plot summary and the character information of the standard character name includes: The highlight information of the video clip is generated based on the new barrage theme word, the target plot summary and the character information of the standard character name.

9. The method according to claim 1, characterized in that: Generating the highlight information of the video clip based on the bullet screen theme word, the target plot summary and the character information of the standard character name includes: Obtaining a preset prompt word, where the prompt word is used to indicate the type of plot highlights output by the text generation model; Generating input information from the prompt word, the bullet screen theme word, the target plot summary and the character information of the standard character name, and inputting the input information into the generative large model; The highlight information of the video clip outputted from the generative large model is received, wherein the type of the highlight information is consistent with the type indicated by the prompt word.

10. A video highlight generating device, characterized in that: The device comprises: A topic information determination module, used to determine the topic information of the bullet screen, wherein the topic information of the bullet screen includes a topic word of the bullet screen and a time period corresponding to the topic word of the bullet screen, wherein the topic word of the bullet screen is a phrase determined based on a plurality of bullet screen texts having an associated relationship, and the time period corresponding to the topic word of the bullet screen is a time period in which the plurality of bullet screen texts appear in an initial video, and the initial video is a video watched when the user inputs the bullet screen text; A target plot summary acquisition module is used to take a plot summary whose time period corresponding to the plot summary and the time period corresponding to the barrage keyword intersect as a target plot summary, wherein the time period corresponding to the plot summary is the time period of the video clip corresponding to the plot summary in the initial video; A target character name extraction module is used to determine a standard character name in the barrage theme words based on the character name in the barrage theme words, wherein the character name refers to a name that identifies a specific character that appears in the barrage theme words, the character name refers to a name that identifies the character shown in the initial video, and the standard character name refers to a character name that conforms to a preset naming rule; A role information acquisition module, used for acquiring role information of the standard role name from a role information library based on the standard role name, wherein the role information library includes a plurality of role information, and the role information refers to description information related to the role in the initial video; A highlight information generating module is used to generate highlight information of the video clip based on the barrage theme words, the target plot summary and the character information of the standard character name.

11. An electronic device, characterized in that: The device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the video highlight generation method as described in any one of claims 1-9.

12. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the video highlight generation method as described in any one of claims 1 to 9 is implemented.

Images