CN114003741A - Text display method and device, electronic equipment and storage medium - Google Patents

Abstract

The disclosure relates to a text display method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a first to-be-displayed text set corresponding to a target multimedia, and determining a pivot text in the acquired first to-be-displayed text set; the plot position of the drama text is behind the display position; the plot position is a position corresponding to plot information contained in the perspective text in the target multimedia; the display position is the position where the perspective text is displayed in the target multimedia; and deleting the pivot text in the first text set to be displayed to obtain a second text set to be displayed under the condition that the target account requesting to acquire the target multimedia does not meet the preset acquisition requirement, and sending the obtained second text set to be displayed to the target account. According to the method, whether the pivot text is sent or not is determined according to the specific condition of the account, so that the use experience of the account can be improved.

Description

Text display method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer application technologies, and in particular, to a text display method and apparatus, an electronic device, and a storage medium.

Background

With the popularization of the internet, the account can acquire rich multimedia resources from the internet. Such as a television show, a novel, a caricature, etc.

When the account acquires the multimedia resource, the corresponding text to be displayed can be acquired. Such as a drama episode profile, a barrage, an account review, etc. The texts to be presented can be presented together with the multimedia resources. For example, the account can watch the barrage at the same time when watching the video, and the account can watch the chapter comments during watching the novel.

However, the text to be presented may contain scenario information in the multimedia resource, which may cause the account to be played through acquiring the text to be presented containing subsequent scenario information in advance, resulting in poor use experience.

Disclosure of Invention

The disclosure provides a text display method, a text display device, an electronic device and a storage medium, which are used for at least solving the problem of poor account experience caused by the penetration of a text to be displayed in the related art. The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided a text presentation method, including:

acquiring a first to-be-displayed text set corresponding to a target multimedia, and determining a pivot text in the acquired first to-be-displayed text set; the plot position of the drama text is behind the display position; the plot position is a position corresponding to plot information contained in the perspective text in the target multimedia; the display position is the position where the perspective text is displayed in the target multimedia;

and deleting the pivot text in the first text set to be displayed to obtain a second text set to be displayed under the condition that the target account requesting to acquire the target multimedia does not meet the preset acquisition requirement, and sending the obtained second text set to be displayed to the target account.

Optionally, the sending the obtained second set of texts to be displayed to the target account includes:

and under the condition that the target account refuses to acquire the pivot text, sending the obtained second text set to be displayed to the target account.

Optionally, the method of determining the pivot text comprises one or more of:

determining the text to be displayed with the pivot identification in the acquired first text set to be displayed as a pivot text; the pivot identification is added aiming at a text to be displayed specified by the operation of a preset account; the preset account operation is used for designating a pivot text;

determining the corresponding position of the contained preset pivot key word in the target multimedia aiming at the text to be displayed containing any preset pivot key word in the acquired first text set to be displayed; if the determined position is behind the display position of the aimed text to be displayed, determining the aimed text to be displayed as a pivot text;

and determining the text to be displayed, which has the coincidence degree with any determined pivot text and is larger than the preset coincidence degree, as the pivot text in the acquired first text set to be displayed.

Optionally, the determining of the pivot text in the acquired first set of texts to be displayed includes:

determining a text recognition model corresponding to the target multimedia at present; the model is used for identifying the corresponding pivot text of the target multimedia;

inputting the text characteristics and the display position of the text to be displayed in the acquired first text set to be displayed into the model, and determining the pivot text according to the output of the model.

Optionally, the determining a text recognition model currently corresponding to the target multimedia includes:

acquiring a training sample according to a pivot text currently corresponding to the target multimedia; the sample features of the training sample comprise text features and a display position of the perspective text;

and training to obtain a text recognition model corresponding to the target multimedia currently according to the obtained training sample.

Optionally, the method of obtaining training samples comprises one or more of:

taking the text feature and the display position of the pivot text corresponding to the target multimedia as sample features, and adding a label for representing the pivot text to obtain a training sample;

generating a newly added text with the coincidence degree of any pivot text currently corresponding to the target multimedia being greater than a preset coincidence degree, taking the text characteristics of the newly added text and the display position of the pivot text as sample characteristics, and adding a label for representing the pivot text to obtain a training sample;

and determining a text to be displayed, which has the coincidence degree greater than the preset coincidence degree, of any pivot text corresponding to the target multimedia from the text to be displayed currently corresponding to the target multimedia, taking the text characteristics of the determined text to be displayed and the display position of the pivot text as sample characteristics, and adding a label for representing the pivot text to obtain a training sample.

Optionally, the preset obtaining requirement is used for characterizing that the target account has obtained the main scenario content of the target multimedia.

Optionally, the main storyline content comprises one or more of:

presetting the content of a position in the target multimedia;

the content with the proportion larger than the preset proportion in the target multimedia;

the content with the account interest degree larger than the preset interest degree in the target multimedia;

and the target multimedia has content with preset main scenario marks.

According to a second aspect of the embodiments of the present disclosure, there is provided a text presentation apparatus, including:

an acquisition unit configured to perform: acquiring a first to-be-displayed text set corresponding to a target multimedia, and determining a pivot text in the acquired first to-be-displayed text set; the plot position of the drama text is behind the display position; the plot position is a position corresponding to plot information contained in the perspective text in the target multimedia; the display position is the position where the perspective text is displayed in the target multimedia;

a transmitting unit configured to perform: and deleting the pivot text in the first text set to be displayed to obtain a second text set to be displayed under the condition that the target account requesting to acquire the target multimedia does not meet the preset acquisition requirement, and sending the obtained second text set to be displayed to the target account.

Optionally, the sending unit includes:

a rejection subunit configured to perform: and under the condition that the target account refuses to acquire the pivot text, sending the obtained second text set to be displayed to the target account.

Optionally, the obtaining unit includes:

a pivot text determination subunit configured to perform one or more of the following methods of determining pivot text:

determining the text to be displayed with the pivot identification in the acquired first text set to be displayed as a pivot text; the pivot identification is added aiming at a text to be displayed specified by the operation of a preset account; the preset account operation is used for designating a pivot text;

determining the corresponding position of the contained preset pivot key word in the target multimedia aiming at the text to be displayed containing any preset pivot key word in the acquired first text set to be displayed; if the determined position is behind the display position of the aimed text to be displayed, determining the aimed text to be displayed as a pivot text;

and determining the text to be displayed, which has the coincidence degree with any determined pivot text and is larger than the preset coincidence degree, as the pivot text in the acquired first text set to be displayed.

Optionally, the obtaining unit includes:

a model determination subunit configured to perform: determining a text recognition model corresponding to the target multimedia at present; the model is used for identifying the corresponding pivot text of the target multimedia; inputting the text characteristics and the display position of the text to be displayed in the acquired first text set to be displayed into the model, and determining the pivot text according to the output of the model.

Optionally, the obtaining unit includes:

a model training subunit configured to perform: acquiring a training sample according to a pivot text currently corresponding to the target multimedia; the sample features of the training sample comprise text features and a display position of the perspective text; and training to obtain a text recognition model corresponding to the target multimedia currently according to the obtained training sample.

Optionally, the model training subunit includes:

a sample acquisition subunit configured to perform one or more of the following methods of acquiring training samples:

taking the text feature and the display position of the pivot text corresponding to the target multimedia as sample features, and adding a label for representing the pivot text to obtain a training sample;

generating a newly added text with the coincidence degree of any pivot text currently corresponding to the target multimedia being greater than a preset coincidence degree, taking the text characteristics of the newly added text and the display position of the pivot text as sample characteristics, and adding a label for representing the pivot text to obtain a training sample;

and determining a text to be displayed, which has the coincidence degree greater than the preset coincidence degree, of any pivot text corresponding to the target multimedia from the text to be displayed currently corresponding to the target multimedia, taking the text characteristics of the determined text to be displayed and the display position of the pivot text as sample characteristics, and adding a label for representing the pivot text to obtain a training sample.

Optionally, the preset obtaining requirement is used for characterizing that the target account has obtained the main scenario content of the target multimedia.

Optionally, the main scenario content includes:

presetting the content of a position in the target multimedia; and/or

The content with the proportion larger than the preset proportion in the target multimedia; and/or

The content with the account interest degree larger than the preset interest degree in the target multimedia; and/or

Content having a primary storyline indicia in the target multimedia.

According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the text presentation method described above.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein instructions of the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the above text presentation method.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising computer programs/instructions which, when executed by a processor, implement the above text presentation method.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

and determining whether the pivot text can be acquired according to the condition that whether the target account meets the preset acquisition requirement, so that the target account is prevented from being pivoted due to the acquisition of the pivot text under the condition that the target account does not meet the preset acquisition requirement, and the use experience is improved.

Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

FIG. 1 is a flow diagram illustrating a method of text presentation in accordance with an exemplary embodiment;

FIG. 2 is a flow diagram illustrating a method of video barrage presentation in accordance with an exemplary embodiment;

FIG. 3 is a block diagram illustrating a text presentation device according to an exemplary embodiment;

FIG. 4 is a schematic block diagram illustrating an electronic device in accordance with an exemplary embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

With the popularization of the internet, the account can acquire rich multimedia resources from the internet. Such as a television show, a novel, a caricature, etc. The forms of these multimedia assets may include: video, pictures, text, etc.

In order to improve account experience and meet account requirements, when an account acquires multimedia resources, a corresponding text to be displayed can be acquired. Such as a synopsis of a television drama, a video barrage, a review of a caricature, etc. The texts to be presented can be presented together with the multimedia resources. For example, the account can watch the barrage at the same time when watching the video, and the account can watch the chapter comments during watching the novel.

To facilitate understanding, in a particular embodiment, when an account clicks open a web page to view a video, the web page may typically include video-related text that may be presented in the web page along with the video. For example, a barrage of a video, an account review, a video summary, a video author introduction, an account rating for a video, and so forth.

For convenience of description, the related text that can be presented together with the multimedia resource is referred to as the text to be presented corresponding to the multimedia.

The text to be displayed may include text uploaded by the multimedia service party, such as a movie name, movie related staff, a movie introduction, and the like; text edited and uploaded by the account may also be included, such as video barrage, comic reviews, novel reviews, movie reviews, and the like.

However, the text to be presented may contain scenario information in the multimedia resource, which may cause the account to be played through acquiring the text to be presented containing subsequent scenario information in advance, resulting in poor use experience.

In order to solve the technical problem, the present disclosure provides a text display method.

First, for a text to be presented corresponding to multimedia, a pivot text therein needs to be determined, and for convenience of description, the text that causes the account to be pivoted is referred to as the pivot text. Whether the drama text can be acquired or not can be determined respectively for different accounts.

Specifically, for an account which does not know the multimedia scenario, it is determined that the account cannot acquire the pivot text, so that the account can be prevented from acquiring the pivot text when acquiring the multimedia, specifically, the pivot text can be deleted from the text to be displayed, and then the deleted text to be displayed is sent to the account, so that the account can be prevented from being pivoted, and the use experience of the account can be improved.

Of course, since some accounts that do not know the multimedia scenario may not be really watching the scenario, it may be further determined that the account cannot acquire the scenario text if the account that does not know the multimedia scenario determines to reject the scenario according to the actual requirements of such accounts.

In addition, the drama text may also include a text for improving account experience and meeting account requirements, for example, highlight rating related to the drama, highlight account comment for parsing the drama, highlight barrage for canon the drama, and the like, and for an account for knowing the multimedia drama, the drama is known by the account and cannot be dramatized by acquiring the drama text, so that in order to improve the experience of the account, it may be determined that the account can acquire the drama text, and the account can also acquire the drama text when acquiring the multimedia, thereby meeting the account requirements.

The method can respectively determine whether the pivot text can be acquired according to the conditions and requirements of different accounts, so that the situation that the account which does not know the scenario is pivoted can be avoided, the account which knows the scenario can acquire the pivot text, and the use experience of the account can be improved.

Fig. 1 is a flowchart illustrating a text presentation method according to an exemplary embodiment, and as shown in fig. 1, the text presentation method may be applied to an electronic device of a service party, for example, a server of a multimedia platform.

Optionally, the service party may store a corresponding relationship between the multimedia and the text to be presented, and specifically, may receive the text to be presented uploaded by the account for the multimedia and store the received text to be presented in the text to be presented corresponding to the multimedia.

The method may include the following steps.

S101: and acquiring a first text set to be displayed corresponding to the target multimedia, and determining the pivot text in the acquired first text set to be displayed.

Optionally, the storyline location of the pivot text is behind the presentation location; the scenario position is a position corresponding to scenario information contained in the perspective text in the target multimedia; the presentation position is a position where the drama text is presented in the target multimedia.

For the story location, optionally, for the novel, the story location of a certain story text may be a location of the story information contained in the story text in the novel, and specifically may be at a certain chapter of the novel.

For a video, the scenario position of a certain drama text may be a time or a time period of scenario information contained in the drama text during the playing of the video.

For the display position, optionally, if the pivot text can be directly displayed in the multimedia, the display position of the pivot text may be directly determined, for example, a video bullet screen is displayed during the video playing process, and the bullet screen itself is displayed in the video, so that the time of the video playing when the bullet screen is displayed may be determined as the display position of the bullet screen.

Or, the comic comment may be displayed during the comic viewing process, and may be specifically displayed at the end of each chapter of the comic, so that the display position of the comic comment (specifically, the displayed comic chapter) may be determined as the display position of the comment.

If the drama text is not directly displayed in the multimedia, for example, the video comment is usually displayed below the webpage where the video is located, and the webpage can be pulled down by the account at any time to be displayed, so that it is necessary to additionally determine a position in the multimedia as the display position of the drama text.

Alternatively, for a pivot text that is not directly presented in the multimedia, a preset presentation position in the multimedia may be determined as a presentation position of the pivot text. Specifically, the preset display position may be dynamically determined, and may be determined as the preset display position when the pivot text is displayed.

For example, when the account pull-down network views a video comment, the current video playing time may be determined as a preset display position in real time, and the preset display position is used as a display position corresponding to the viewed video comment.

S102: and deleting the pivot text in the first text set to be displayed to obtain a second text set to be displayed under the condition that the target account requesting to obtain the target multimedia does not meet the preset obtaining requirement, and sending the obtained second text set to be displayed to the target account.

In an alternative embodiment, the target multimedia may be any multimedia, and for convenience of description, the multimedia targeted by the method flow is referred to as the target multimedia. It will be appreciated that the pivot text may also be determined based on the same method flow for other multimedia.

Alternatively, the target account may be any account requesting to acquire the target multimedia, and for convenience of description, the account targeted by the method flow is referred to as the target account. It is understood that, for other accounts requesting to acquire the target multimedia, it may also be determined whether the other accounts can acquire the corresponding drama text of the target multimedia based on the same method flow.

The method can determine whether the target account can acquire the pivot text according to the condition whether the target account meets the preset acquisition requirement, so that the target account is prevented from being pivoted due to the acquisition of the pivot text under the condition that the target account does not meet the preset acquisition requirement, and the use experience is improved.

In addition, the target account can be determined to be capable of acquiring the pivot text under the condition that the target account is determined to meet the preset acquisition requirement, and further, the use experience can be improved due to the fact that more texts to be displayed are acquired.

In an optional embodiment, when the target account specifically requests to acquire the target multimedia, it is not necessary to acquire a text to be displayed corresponding to the target multimedia, for example, a bullet screen and comments are shielded when a comic is viewed; the text to be displayed corresponding to the target multimedia may also need to be acquired, for example, when watching a video, the comment area is clicked to view the account comment.

When the target account needs to acquire the text to be displayed corresponding to the target multimedia, the one or more texts to be displayed corresponding to the target multimedia can be automatically acquired while the target multimedia is acquired, and the one or more texts to be displayed of the target multimedia can also be requested to be acquired.

For example, after the target account clicks on a video webpage, account comments of the video may be automatically obtained. And the target account can determine whether to acquire the video bullet screen by setting a bullet screen option. Specifically, "close barrage" may be set, and then the target account may not acquire the barrage of the video, and "open barrage" may also be set, and then the target account may send a request to acquire the barrage of the video for display.

In an optional embodiment, the obtaining authority of the target account for the pivot text may be determined first according to whether the target account meets the preset obtaining requirement. And then specifically acquiring a text to be displayed corresponding to the target multimedia, and determining the text to be displayed which can be sent to the target account according to the determined text acquisition permission.

Optionally, all or part of the text to be displayed corresponding to the target multimedia can be sent to the target account under the condition that the target account is determined to have the right of acquiring the pivot text; and under the condition that the target account does not have the permission of acquiring the pivot text, transmitting all or none of the texts to be displayed except the pivot text in the texts to be displayed corresponding to the target multimedia to the target account.

Specifically, it may be that the text to be presented is sent to the client or device that logs in to the target account.

Optionally, in response to a request for obtaining a text to be shown corresponding to a target multimedia by a target account, sending all or part of the text to be shown corresponding to the target multimedia to the target account under the condition that the target account is determined to have the right of obtaining the pivot text; and under the condition that the target account does not have the permission of acquiring the pivot text, transmitting all or part of the texts to be displayed except the pivot text in the texts to be displayed corresponding to the target multimedia to the target account.

In this embodiment, the text to be displayed, which can be sent to the target account, can be determined according to the obtaining permission of the pivot text, and then the corresponding text to be displayed can be obtained to meet the account requirement on the premise of avoiding the pivot of the target account. The account with the permission to acquire the pivot text can acquire more texts to be displayed in quantity and variety, and the account without the permission to acquire the pivot text can avoid being pivoted by the pivot text.

First, the following explains the relationship between S101 and S102.

In an alternative embodiment, S101 may be performed in advance, and determine the corresponding drama text of the target multimedia in advance. Then, for any account, a request for obtaining the target multimedia may be directly executed to step S102, and it is determined whether the account can obtain a predetermined pivot text corresponding to the target multimedia. In this embodiment, the execution efficiency of the process of the method can be improved.

Correspondingly, optionally, the corresponding pivot text may also be determined in advance for a plurality of multimedia, so that subsequent requests for acquiring any multimedia can be directly executed S102, and the execution efficiency of text display is improved.

In another alternative embodiment, S101 may also be performed in real time. Specifically, after a request for acquiring the target multimedia from any account is received, the corresponding pivot text is determined for the target multimedia.

The present embodiment does not limit the execution timing of S101 and S102. Optionally, after receiving a request for acquiring a target multimedia from any account, S101 may be executed in parallel with S102, or S101 may be executed first and then S102 may be executed.

In the embodiment, the accuracy of identifying the pivot text can be improved by determining the pivot text corresponding to the target multimedia in real time.

Second, the following explains S101 in detail.

1. For the text to be presented corresponding to the target multimedia, in an alternative embodiment, the text to be presented corresponding to the target multimedia may include a text related to the target multimedia. For example, text such as barrage and account comments for the target multimedia.

The method can include the text uploaded by the account aiming at the target multimedia editing, and can also include the text uploaded by the business party aiming at the target multimedia editing.

The method flow does not limit the specific way of obtaining the text to be displayed corresponding to the target multimedia. As an exemplary illustration, it can be obtained at least by the following 2 ways.

1) The text to be displayed corresponding to the target multimedia is stored in advance, and the text to be displayed corresponding to the target multimedia can be directly acquired from the storage area.

2) The method comprises the steps of acquiring a text uploaded by any account aiming at a target multimedia in real time, and determining the text to be displayed corresponding to the target multimedia.

Therefore, optionally, the obtaining of the text to be presented corresponding to the target multimedia may include: and acquiring a text uploaded by any account aiming at the target multimedia, and determining the text to be displayed corresponding to the target multimedia.

In an alternative example, a request for an account to upload text may be received, which may be used to upload text for a target multimedia. The uploaded text can include comments, barrage, ratings, etc. text of the account for the target multimedia.

Optionally, after determining the text uploaded by any account for the target multimedia as the text to be displayed corresponding to the target multimedia, the determined text to be displayed may be stored in the storage area, so as to subsequently obtain the text to be displayed corresponding to the target multimedia from the storage area.

In the embodiment, the text uploaded by the account aiming at the target multimedia can be determined as the text to be displayed corresponding to the target multimedia, the text to be displayed corresponding to the target multimedia can be newly added in real time, the pivot text in the pivot text can be conveniently determined in real time, the account is prevented from being pivoted by the newly added text to be displayed, and the use experience is improved.

2. For the drama text, the drama text may contain scenario information. In an alternative embodiment, the storyline location of the drama text is behind the presentation location, thereby resulting in a drama. The scenario position is a position corresponding to scenario information contained in the perspective text in the target multimedia; the presentation position is a position where the drama text is presented in the target multimedia.

Since the scenario position of the pivot text is behind the display position, if the pivot text is also acquired for the account for acquiring the target multimedia for the first time, the subsequent scenario of the target multimedia is likely to be known in advance due to the pivot text, so that the target multimedia is pivoted, and the use experience is reduced.

In a specific example, for an account for acquiring a movie video for the first time, since an "open barrage" is set, a barrage corresponding to the movie video may also be acquired. If there is a drama text in the barrage, for example, "this chief angle died last", "this person wearing glasses is a murder", etc., containing the drama information, the account is likely to be dramatized by looking up the barrage of the movie video in advance, resulting in a degraded movie viewing experience.

Since the pivot text is determined from the text to be presented corresponding to the target multimedia, the determined pivot text may also correspond to the target multimedia.

To facilitate further understanding of the drama text, three examples of the drama text are given below.

Example of pivot text one: a pivot text common to multiple multimedia.

In scenarios provided by different multimedia, it is often possible to include communicated scenario information. The drama text containing the through scenario information can be generally determined to be the drama text containing the scenario information of the multimedia aiming at different multimedia.

For example, "this movie ending is a good ending" contains the plot information of the movie itself for all movies with good ending; "the protagonist of this caricature is the strongest at last" the caricature with the strongest protagonist of all protagonists contains the scenario information of the caricature itself, "the person in this novel goes away" contains the scenario information of the novel itself for all novel with dead characters.

Example two of pivot text: a pivot text that is more unique to a single multimedia.

In the scenarios provided by different multimedia, scenario information unique to each multimedia can be included. The unique scenario information may be generated for a unique setting or may be generated based on a unique scenario development. The drama text containing the more unique drama information of a single multimedia can be generally determined to be the drama text containing the drama information of the multimedia per se, and is more targeted.

For example, in a movie, where the term "original force" appears, the text containing the plot information related to the "original force" may be determined as the drama text. The "inheritance of origin only", "the origin can be mutated", "the principal and the inverse have the origin", etc. can be determined as the pivot text.

When the texts appear in the texts to be displayed corresponding to other multimedia, the texts can be determined as drama texts because of the fact that the texts contain the plot information. These texts are more likely to actually appear in the movie-corresponding text to be presented.

Example three of pivot text: and the text with higher coincidence degree with a certain perspective text.

Different accounts may edit different similar text when editing text for the same plot information. Of course, different similar texts may also contain different storyline information.

If the coincidence degree of a text to be presented and a pivot text is high, the text to be presented is likely to contain the scenario information in the pivot text, and therefore, the text to be presented can also be determined as the pivot text.

For example, four texts such as "the character comes to an end soon", "the character comes to an end", "the character does not come to an end soon". In the case where "this character is soon died" is determined as the pivot text, the other three texts have a high degree of overlap with this pivot text, and may also be determined as the pivot text.

In an alternative embodiment, since the pivot text may be uploaded by the account editing, the account may realize that the text to be presented uploaded by the account contains scenario information, which relates to the pivot, and may reduce the use experience of other accounts. In this case, the account may still choose to upload the drama text, or may not upload the drama text in order to avoid drama.

Optionally, an operation interface may be provided for the account, so that the account can mark the text to be displayed, which is considered by the account to contain the scenario information, through a preset account operation, thereby facilitating the business party to determine the scenario text according to the mark.

According to the embodiment, the uploaded text to be displayed can be subjected to the pivot text marking through the account, so that the account operation is facilitated, the situation that the text to be displayed is not uploaded because the account realizes the pivot is avoided, and the use experience is improved.

In a specific example, an option "relating to drama perspective" may be provided beside text editing performed on the account, and if the option is checked, the currently edited text to be presented may be marked as drama perspective text, and if the option is not checked, the currently edited text to be presented may not be marked and is directly uploaded.

In an alternative embodiment, the text to be presented uploaded by the service party may also include a pivot text. For example, the official introduction of a movie may contain scenario information, and the editing recommendation of a novel may also contain scenario information.

Therefore, the pivot text can be determined for all the texts to be displayed corresponding to the target multimedia.

It should be noted that, in an alternative embodiment, the determined drama text may be further reviewed by a reviewer of the service party, and the text that is erroneously determined to be the drama text may be determined to be the non-drama text again. Specifically, the pivot mark may be deleted. The embodiment can improve the identification accuracy of the pivot text.

3. The following is a detailed explanation of the operation of determining the pivot text.

The method for determining the pivot text is not particularly limited in the process of the method, and as an exemplary illustration, the pivot text may be determined in the following four ways. The four modes can be used separately for determining the pivot text or used together for determining the pivot text.

1) And determining according to the identification. The identifier may be added to the pivot text actively when the account uploads the text to be displayed, may be added to the pivot text in the acquired text to be displayed by the account, or may be added to the pivot text obtained by auditing by the service staff of the service party. In other words, the text may be the pivot text of the account feedback, or the pivot text that is audited by the service party.

2) And determining according to the keywords. The preset scenario information may be embodied by a part of keywords, such as "character", "ending", "climax part", "hero", and the like.

3) And calculating the contact ratio according to the determined perspective text. Specifically, for the determined pivot text, the text with a higher overlap ratio with any determined pivot text in the text to be displayed is determined as the pivot text.

4) Determined according to a text recognition model. Specifically, a text recognition model is trained in advance, and is used for determining a pivot text from a text to be displayed corresponding to the target multimedia.

Correspondingly, the method for determining the pivot text can comprise one or more of the following methods.

Determining the text to be displayed with the pivot identification in the acquired first text set to be displayed as a pivot text; the pivot identification is added aiming at a text to be displayed specified by the preset account operation; the preset account operation is used for specifying the pivot text.

Determining the corresponding position of the contained preset pivot key word in the target multimedia aiming at the text to be displayed containing any preset pivot key word in the acquired first text set to be displayed; and determining the targeted text to be presented as the drama text if the determined position is behind the presentation position of the targeted text to be presented.

And determining the text to be displayed, which has the coincidence degree with any determined pivot text and is larger than the preset coincidence degree, as the pivot text in the acquired first text set to be displayed.

Determining a text recognition model corresponding to the target multimedia at present; the text recognition model is used for recognizing the corresponding pivot text of the target multimedia; inputting the text characteristics and the display position of the text to be displayed in the acquired first text set to be displayed into a text recognition model, and determining the pivot text according to the output of the text recognition model.

In an alternative embodiment, the text to be presented with the pivot identifier in the acquired first set of texts to be presented may be determined as the pivot text.

Optionally, the pivot identifier is added to the text to be displayed specified by the preset account operation; the preset account operation is used for designating the pivot text.

The preset account operation may be performed by the account for the drama text in the acquired first set of texts to be displayed. In the process of specifically acquiring the text to be displayed, the account can automatically determine the pivot text in the text to be displayed, execute the preset account operation, add the pivot identification aiming at the text specified by the preset account operation, and mark the pivot text. Namely, the account feeds back the text to be displayed, and the pivot text in the account is determined.

For example, when the account is played by a certain bullet screen for the first time of watching a movie, a preset account operation may be performed on the bullet screen, and the preset account operation is marked as a drama text. The preset account operation may specifically include: right clicking the bullet screen to call out the menu item, and clicking 'zoom in is related' in the menu item.

The preset account operation may also be performed by an auditor of the business party on the obtained pivot text in the first text set to be displayed. In the process of specifically acquiring the text to be displayed, the auditor can determine the pivot text through auditing, execute a preset account operation, add a pivot identification to the text specified by the preset account operation, and mark the pivot text.

For example, when an auditor audits comic reviews, and finds that one review relates to a plot discussion, a preset account operation may be performed on the review, and the review is marked as a drama text.

The preset account operation can also be executed by the account aiming at the text to be displayed to be uploaded. When the account uploads the text to be displayed aiming at the multimedia, the fact that the text to be displayed to be uploaded relates to the pivot can be realized, therefore, the preset account operation can be executed aiming at the text to be displayed to be uploaded, the pivot mark is added aiming at the text specified by the preset account operation, and the pivot text is marked, so that the text to be displayed relating to the pivot can be conveniently uploaded by the account.

For example, when an account wishes to upload a highlight rating related to a pivot for a movie, the account may mark the pending upload rating as pivot text by checking the "pivot" option.

In another optional embodiment, for a text to be presented, which contains any preset pivot keyword, in the acquired first text set to be presented, a corresponding position of the contained preset pivot keyword in the target multimedia may be determined; and determining the targeted text to be presented as the drama text if the determined position is behind the presentation position of the targeted text to be presented.

The corresponding position of the preset drama-through keyword contained in the text to be displayed in the target multimedia can be the drama position of the text to be displayed.

Alternatively, the preset perspective keywords may include keywords commonly used in the scenario, such as "hero", "character", "ending", "climax part", and the like.

The preset drama keywords may also include keywords unique to the scenario of the multimedia, such as a name of a hero, unique settings, a key location, and the like.

In another alternative embodiment, a text to be presented, which has a higher degree of overlap with any determined pivot text than a preset degree of overlap, in the acquired first text set to be presented may be determined as a pivot text.

The determined pivot text may include previously determined pivot text, pivot text corresponding to other multimedia, or pivot text determined by other methods, such as the above-mentioned keywords, pivot identifier, and the like.

Since the text similar to any determined drama text will generally contain the drama information, the text similar to any determined drama text may also be determined as the drama text. Whether the texts are similar or not can be determined by calculating the overlap ratio between the texts.

The embodiment does not limit the method for calculating the degree of overlap, and alternatively, the ratio of the number of identical characters between texts to the total number of characters may be determined as the degree of overlap.

Therefore, the text overlap ratio between any text to be displayed and any determined pivot text can be determined in the acquired text to be displayed, whether the text overlap ratio is greater than the preset overlap ratio or not is judged, and whether the text is the pivot text or not is further determined.

In this embodiment, the pivot text can be quickly and accurately determined by presetting the operation identifier, presetting the pivot keyword and the text overlap ratio, the execution efficiency of the text display method is improved, and the subsequent operation can be conveniently executed for the determined pivot text.

In another alternative embodiment, a text recognition model corresponding to the target multimedia currently can be determined; the text recognition model can be used for recognizing the corresponding pivot text of the target multimedia; inputting the text characteristics and the display position of the text to be displayed in the acquired first text set to be displayed into a text recognition model, and determining the pivot text according to the output of the text recognition model.

Alternatively, the text recognition model may be pre-trained based on both dramatic and non-dramatic text. The pivot text therein may be determined by other methods or pre-stored.

Alternatively, the text recognition model may be constructed based on natural language processing algorithms, and further trained based on samples of both dramatic and non-dramatic text. Of course, the text recognition model may be constructed by other algorithms, such as deep learning, neural networks, and the like.

Alternatively, the output of the text recognition model may be the probability that the text to be presented is the pivot text, so that the text to be presented with the output probability greater than the preset probability may be determined as the pivot text.

In the embodiment, the pivot text can be accurately and comprehensively determined through the pre-trained text recognition model, so that the accuracy and recall rate of pivot text recognition are improved, and the use experience is improved.

4. The following is a detailed explanation of the text recognition model used in determining the pivot text.

In an alternative embodiment, different multimedia may correspond to the same text recognition model, and for different multimedia, the same text recognition model may be used to determine the pivot text.

Because the text containing any scenario information can be determined as the pivot text corresponding to each multimedia, the pivot text containing any multimedia scenario information can be synthesized, the text recognition model can be trained to obtain the same text recognition model, and the pivot text recognition can be performed on each multimedia.

In this embodiment, the use of the same text recognition model may save computational resources without having to train the text recognition model separately for each multimedia.

In another alternative embodiment, different multimedia may correspond to different text recognition models. For different multimedia, the pivot text may be determined using corresponding different text recognition models.

For a single multimedia, the occurrence frequency of the drama text containing the self-related scenario information of the multimedia is high, and the occurrence frequency of the drama text containing other multimedia-related scenario information is low. Different multimedia, the pivot text that needs to be identified in focus may not be the same.

In order to more accurately identify the dramatic text corresponding to the multimedia, different text identification models can be obtained by training different training sets for different multimedia.

In an alternative embodiment, the text to be presented corresponding to the multimedia may be updated, for example, an account uploads a new text to be presented for the multimedia. Correspondingly, the corresponding pivot text of the multimedia can be updated.

In order to more accurately identify the pivot text corresponding to the multimedia, a new pivot text can be obtained to retrain the text identification model corresponding to the multimedia.

Optionally, in a case where different multimedia corresponds to the same text recognition model, a new pivot text may be obtained, so as to obtain a new training sample, which is used together for retraining the same text recognition model, so as to obtain the same retrained text recognition model.

Alternatively, in case different multimedia correspond to the same text recognition model, a new drama text may be obtained for each multimedia, resulting in a new training sample. In other words, different multimedia may correspond to different new training samples. Therefore, different new training samples can be used for training the same text recognition model again aiming at different multimedia, and different retrained text recognition models can be obtained.

Alternatively, in the case where different multimedia correspond to different text recognition models, a new drama text may be acquired for each multimedia, resulting in a new training sample. In other words, different multimedia may correspond to different new training samples. Therefore, different new training samples can be used for training different text recognition models for different multimedia, and different retrained text recognition models can be obtained.

The method flow does not limit the specific method for training the text recognition model for a single multimedia, and as an exemplary illustration, a specific method for training the text recognition model is provided below.

Optionally, the training method of the text recognition model may include: acquiring a training sample according to a perspective text currently corresponding to a target multimedia; the sample features of the training sample comprise text features and display positions of the perspective text; and training to obtain a text recognition model corresponding to the target multimedia currently according to the obtained training sample.

The method comprises the steps of judging whether a text to be displayed belongs to a pivot text or not, wherein the judgment is carried out according to the display position and the plot position of the text to be displayed, and if the plot position of the text to be displayed is behind the display position, the text to be displayed is the pivot text.

Optionally, the display position may be determined directly for the text to be displayed, and the scenario position may be characterized by a text feature. Thus, the sample features of the training sample may include text features and presentation positions of the pivot text.

Specifically, the text feature of the text to be displayed can represent the plot information contained in the text to be displayed, so that the plot position of the plot information contained in the text to be displayed in the target multimedia can be represented.

For example, the text feature of the text to be presented may be "hero win", and may be used to represent the position of the hero win scenario in the target multimedia, specifically, the 90 th minute in the video playing process. If the display position of the text to be displayed is after 90 minutes, determining that the text to be displayed is non-pivot text; if the display position of the text to be displayed is before 90 minutes, the text to be displayed can be determined to be the pivot text.

In addition, the text to be displayed corresponding to the target multimedia can be updated in real time, for example, for the same video, the corresponding barrage may be increased every day, so that when the text recognition model corresponding to the target multimedia is determined, the text recognition model can be trained in real time according to the current pivot text, the training effect of the text recognition model is improved through the latest pivot text, and the accuracy of pivot text recognition is improved.

The following explains the detailed description of the currently corresponding pivot text of the target multimedia.

When an initial text recognition model is trained, a dramatic text needs to be used for training, and therefore, the dramatic text needs to be acquired in advance before training. In particular, the drama text currently determined by the target multimedia.

Optionally, the currently determined pivot text of the target multimedia may include: the title text with the title may be a title text audited and determined by service personnel from a text to be displayed corresponding to the target multimedia, an account mark, or a feedback title text, etc.; the method also can comprise the pivot text containing any preset key words; the drama text determined by other multimedia may be determined, and the drama text determined by other multimedia may be determined as the drama text corresponding to the target multimedia because the drama text includes the scenario information.

Further, the number of currently determined pivot texts of the target multimedia may be smaller, and therefore, optionally, expansion may be performed based on the currently determined pivot texts, resulting in more training samples.

Optionally, since the text similar to the pivot text may include the scenario information in the pivot text, the text similar to the pivot text may be generated or determined, and directly determined as the pivot text, so as to obtain the corresponding training sample.

It should be noted that similar text may be generated or determined for text features, but the presentation position typically needs to be consistent with the original pivot text.

Thus, optionally, the method of obtaining training samples comprises one or more of the following.

And taking the text feature and the display position of the pivot text corresponding to the target multimedia as sample features, and adding a label for representing the pivot text to obtain a training sample.

And generating a newly added text with the coincidence degree of any pivot text currently corresponding to the target multimedia being greater than the preset coincidence degree, taking the text characteristics of the newly added text and the display position of the pivot text as sample characteristics, and adding a label for representing the pivot text to obtain a training sample.

Determining a text to be displayed, corresponding to the target multimedia, of which the coincidence degree of any pivot text is greater than the preset coincidence degree, from the text to be displayed, corresponding to the target multimedia, taking the text characteristics of the determined text to be displayed and the display position of the pivot text as sample characteristics, and adding a label for representing the pivot text to obtain a training sample.

By the method, the number of the pivot texts corresponding to the target multimedia can be expanded, and the number of the samples marked with the pivot text labels in the training samples can be expanded, so that the training effect of the text recognition model can be improved, and the accuracy of the text recognition model for recognizing the pivot texts can be improved.

As an exemplary illustration, a plurality of newly added texts may be generated by adding a preset word, deleting the preset word, and/or modifying the preset word for a currently determined pivot text, and one or more newly added texts with an overlap ratio of any pivot text corresponding to a target multimedia greater than the preset overlap ratio may be determined from the newly added texts, and the newly added texts are considered to include any scenario information, so that the newly added texts may be determined as pivot texts and used as training samples for training a text recognition model.

In a specific example, for the currently determined pivot text "pivot dead", a plurality of similar texts may be generated, specifically preset words may be added or deleted or modified, and these preset words may be used for adjective or embellishment. E.g., fast, not, soon, strongly, long, etc. Similar text may be generated based on these preset words, e.g., "hero dies soon," "hero dies strongly," "hero dies soon," etc. The generated similar texts have high overlap with the perspective text "the main character dies" and can be determined as the perspective text and used as a training sample for training the text recognition model.

The method for determining the text contact ratio is not limited in this embodiment, and as an exemplary illustration, the ratio between the number of the same characters between two texts and the total number of characters of the two texts may be determined as the contact ratio.

In another specific example, for a currently determined perspective text "the pivot is dead", a degree of overlap between the perspective text and "the pivot is fast dead" in the text to be presented may be calculated, specifically, a ratio between the number 4 of the same characters and the total number 10 of the characters is 0.4, which is greater than a preset degree of overlap 0.3, and therefore, the text to be presented "the pivot is fast dead" may be determined as the perspective text, which is used as a training sample for training the text recognition model.

In this embodiment, the training samples may be obtained according to the pivot text, and the number of the pivot text may be expanded by generating similar text or determining similar text, that is, the number of the training samples is expanded, so that the training effect of the text recognition model may be improved.

In an alternative embodiment, the text recognition model currently corresponding to the target multimedia may be updated.

The text to be presented corresponding to the target multimedia can be updated, and specifically, the text to be presented uploaded by the receiving account for the target multimedia can be received, so that a new drama text may exist therein. For example, the account is newly marked or fed back with the drama text, the auditor audits the determined new drama text, and so on. In addition, as multimedia is added, the multimedia may also correspond to new drama text.

In order to facilitate adaptation to a constantly changing situation, a new pivot text is accurately recognized, and optionally, the newly determined pivot text may be utilized to retrain the text recognition model and update the current corresponding text recognition model.

Optionally, after detecting that the training sample set is updated, the current text recognition model may be retrained by using the updated training sample set, and the retrained text recognition model may be determined as the current text recognition model.

Wherein the set of training samples may be used to train the text recognition model, which may include training samples labeled as dramatic and non-dramatic text.

In this embodiment, after the training sample set is updated, the current text recognition model can be retrained, so that a new pivot text can be conveniently and accurately recognized, and the use experience is improved.

Optionally, the training sample set updating may include: acquiring a new pivot text corresponding to a target multimedia; and acquiring a new training sample according to the new enhanced perspective text, and adding the new training sample into the training sample set.

Aiming at the target multimedia, a new text to be displayed sent by an account can be received as time goes on, and a pivot text determined in other modes can be added, so that the training sample set can be updated and used for retraining the text recognition model.

In this embodiment, the training sample set can be updated by using the newly added pivot text, so as to help update the training text recognition model, conveniently and accurately recognize the new pivot text, and improve the use experience.

Optionally, a new training sample is obtained specifically according to the new enhanced pivot text, and the training effect of the text recognition model can be improved by expanding the number of the training samples.

Specifically, the text features in the newly added pivot text can be used as sample features, and labels used for representing the pivot text are added to obtain training samples; and/or generating a newly added text with the coincidence degree with any newly added pivot text being greater than the preset coincidence degree, taking the text characteristics in the newly added text as sample characteristics, and adding a label for representing the pivot text to obtain a training sample; and/or determining a text to be displayed, corresponding to the target multimedia, of which the coincidence degree is greater than the preset coincidence degree from the text to be displayed, corresponding to the target multimedia, taking the text features in the determined text to be displayed as sample features, and adding a label for representing the pivot text to obtain a training sample.

For a detailed explanation of the method for generating the new text and the method for determining the degree of overlap, see above.

In this embodiment, in the process of retraining the text recognition model, the training samples may be obtained according to the new pivot text, and the number of pivot texts may be expanded by generating similar texts or determining similar texts, that is, the number of training samples is expanded, so that the training effect of the retrained text recognition model may be improved.

Third, the following explains S102 in detail.

In the above explanation for S101, the drama text corresponding to the target multimedia is determined, and in order to improve the use experience of the accounts with different requirements, the account that knows the target multimedia scenario and the account that does not know the target multimedia scenario may be distinguished, so that it may be determined that the accounts can obtain the drama text. The distinction can be made specifically by presetting the acquisition requirements.

The method comprises the steps that account for knowing a target multimedia scenario is obviously not subjected to full play using experience caused by full play texts, so that full play texts can be obtained, more texts to be displayed are provided, and the using experience is improved; for the account which does not know the target multimedia scenario, the use experience of the drama is caused by the drama text, so that the situation that the drama text cannot be obtained can be limited, the situation that the drama text is drama after being obtained is avoided, and the use experience is improved.

Thus, optionally, the preset acquisition requirement may be used to distinguish between an account that knows the target multimedia scenario and an account that does not know the target multimedia scenario.

Optionally, the preset obtaining requirement may be used to characterize the account to obtain the target multimedia. In other words, the account for acquiring the target multimedia for the first time may be determined as an account not knowing the scenario of the target multimedia, and the account for acquiring the target multimedia for a plurality of times may be determined as an account for understanding the scenario of the target multimedia.

For example, for an account that acquires a cartoon for the second time, the account may be considered to have known a cartoon scenario, so that the acquisition of a pivot text may be allowed, and the use experience of the account may be improved; for an account which acquires a movie for the first time, the account can be considered not to know the scenario of the movie, and the account can be limited not to acquire a pivot text, so that the account is prevented from being pivoted, and the use experience is improved.

However, in practical situations, there may be a situation where the account acquires part of the content of the target multimedia, so that the scenario of the target multimedia is not known, for example, the account only sees the first half of a movie, or only sees the first chapter of a novel, in which case the account may still have the possibility of acquiring the drama text to be dramatized.

In one specific example, the account has previously acquired the movie, but for time reasons only the first half of the movie is seen, and the scenario of the second half is not understood. Therefore, if the account acquires the movie for the second time, if the pivot text is acquired, the rear half of the scenario may be pivoted, reducing the use experience.

Therefore, it may be specifically determined whether the account knows the scenario of the multimedia by whether the account acquires the main scenario content of the target multimedia. The main scenario content may include a main scenario of the target multimedia, so that the account of the main content of the target multimedia is obtained to know the scenario of the target multimedia.

Optionally, the preset obtaining requirement may be used to characterize an account to obtain the main scenario content of the target multimedia.

Correspondingly, whether the target account meets the preset acquisition requirement is specifically determined, and the determination can be performed by judging whether the target account acquires the main scenario content of the target multimedia.

Under the condition that the target account acquires the main scenario content of the target multimedia, the target account can be determined to meet the preset acquisition requirement, and the scenario of the target multimedia can be known.

Under the condition that the target account does not acquire the main scenario content of the target multimedia, the target account can be determined not to meet the preset acquisition requirement, and the scenario of the target multimedia is not known.

In a specific example, in the case that the target account acquires the main scenario content of the target multimedia, a preset acquisition flag may be added to the target account, so that whether the target account meets the preset acquisition requirement may be determined according to the preset acquisition flag.

For example, when any account plays a movie/tv show/comedy last episode to the end of the episode, the status of the account that the video is completely played is recorded, and the account that recorded the status can be regarded as a "multiple video watching user" of the movie/tv show/comedy, so as to meet the preset acquisition requirement, and can be regarded as knowing the video scenario and allowing to acquire the pivot text.

In this embodiment, the account that knows the target multimedia scenario and the account that does not know the target multimedia scenario can be quickly and accurately distinguished by presetting the acquisition requirement, so that the execution efficiency of the text display method is improved, and whether the target account can acquire the pivot text or not can be conveniently and subsequently determined.

Alternatively, the main scenario content may contain most of the scenario information of the target multimedia. Therefore, if the account acquires the main scenario content of the target multimedia, most of the scenario information contained in the main scenario content is already acquired by the account, and cannot be played by acquiring the play text.

Alternatively, the main scenario content may specifically be the entire content of the target multimedia. Obviously, in the case that the account acquires all the content of the target multimedia, it can be determined that the account knows the scenario of the target multimedia.

Optionally, the main scenario content is specifically determined, and the specific content in the target multimedia needs to be determined as the main scenario content.

For example, for a movie, all video content before the trailer may be determined as main scenario content; for a cartoon, all pictures before the tail page can be determined as main scenario contents; for a novel, partial chapters may be determined as the main storyline content.

Optionally, the main scenario content of the target multimedia may include: presetting the content of a position in the target multimedia; and/or the content with the ratio larger than the preset ratio in the target multimedia; and/or the content with the account interest degree larger than the preset interest degree in the target multimedia; and/or content having pre-dominant storyline tags in the targeted multimedia.

In an alternative embodiment, the main scenario content may be content at a preset position in the target multimedia. Since the accounts are usually obtained in sequence when the multimedia is obtained, if the accounts obtain the content at the preset position in the target multimedia, the accounts are likely to obtain the content before the preset position in the target multimedia, and thus the scenario in the target multimedia is likely to be obtained.

Alternatively, the preset position may be fixed, and the preset positions of different multimedia may be the same. For example, the preset positions of different movies are all the trailer positions. The preset positions of the different novels are all the tail positions. For example, an account is acquired when a movie is acquired, typically in chronological order within the movie. If the account acquires the content of the trailer in the movie, the account is likely to acquire all the content before the trailer in the movie, so that the scenario of the movie is acquired.

Alternatively, the preset position may not be fixed, and the preset positions of different multimedia may be different. For example, the preset position of movie one is 5 seconds before the end, and the preset position of movie two is 10 seconds before the end.

In another alternative embodiment, the main scenario content may be a content with a ratio greater than a preset ratio in the target multimedia. If the account has captured most of the content in the target multimedia, the account is likely to capture the scenario in the target multimedia. The preset proportions of different multimedia can be the same or different.

For example, when an account captures a cartoon, if 99% of the content has already been captured, the account is likely to capture a scenario in the cartoon.

In another alternative embodiment, the main scenario content may be content with an account interest level greater than a preset interest level in the target multimedia. Since the account is in the process of acquiring multimedia, the interest level of key scenarios in the multimedia is usually large, such as key turns in movies, highlights in cartoons, and the like. Therefore, if the account acquires the content of which the account interest degree is greater than the preset interest degree in the target multimedia, the account is likely to acquire the scenario in the target multimedia.

For example, when the account acquires a novel, if all the content with a high interest level of the account is acquired, the account is likely to acquire a scenario in the novel.

Wherein, optionally, the interest degree can be reflected by account comments, the number of barrage, and the like. For example, for a key scenario in a movie, there may be a large number of barrages, and then it may be determined that video segments with the number of barrages larger than a preset number of barrages are main scenario content; for the comments of each chapter of the novel, if the number of the comments of a certain chapter is larger than the preset number of the comments, the chapter can be determined as the main storyline content.

In another alternative embodiment, the main scenario content may be content having a main scenario label in the target multimedia. In the target multimedia, the auditor can mark the content containing the main scenario or the key scenario, particularly can add the main scenario mark, thereby being convenient to determine the main scenario content according to the main scenario mark,

for example, a business party auditor can mark important scenarios in a movie; the important pictures in the cartoon can be marked; important story paragraphs in a novel may also be marked.

According to the embodiment, the main scenario content can be quickly and accurately determined through the preset position, the preset proportion, the interest degree and the main scenario mark, so that whether the account acquires the main scenario content or not is conveniently judged, whether the main scenario content meets the preset acquisition requirement or not is judged, and the execution efficiency of the method is improved.

In an optional embodiment, it is specifically determined whether the target account meets the preset acquisition requirement, and the determination may be performed in advance or in real time.

Optionally, when storing any multimedia, the service party may determine the main scenario content therein, and of course, the main scenario content may be updated. And then, for any multimedia acquisition operation of any account, whether the account meets the preset acquisition requirement for the multimedia can be judged in advance. Specifically, the determination may be performed by determining in advance whether the account acquires the main scenario content in the multimedia.

If the account acquires the main scenario content in the multimedia, it can be determined that the account meets the preset acquisition requirement for the multimedia. The account may be specifically marked.

In the embodiment, whether the multimedia by the account meets the preset acquisition requirement or not can be determined in advance, so that the situation that the target account can acquire the pivot text can be conveniently and quickly determined subsequently.

Optionally, for the target account requesting to acquire the target multimedia, it may be determined in real time whether the target account acquires the main scenario content of the target multimedia, so as to determine whether the target account meets a preset acquisition requirement.

Under the condition that the target account meets the preset acquisition requirement, the target account can be determined to be capable of acquiring the pivot text corresponding to the target multimedia.

Optionally, the drama text corresponding to the target multimedia may be directly sent to the target account, or the text to be presented including the drama text corresponding to the target multimedia may be sent to the target account when the target account needs to acquire the text to be presented corresponding to the target multimedia.

Under the condition that the target account is determined not to meet the preset obtaining requirement, the target account can be determined not to obtain the pivot text corresponding to the target multimedia, and therefore the target account can be prevented from obtaining the pivot text corresponding to the target multimedia. Even if the target account needs to acquire the text to be shown corresponding to the target multimedia, only the text to be shown except the pivot text corresponding to the target multimedia is sent to the target account.

In this embodiment, more texts to be displayed in quantity and variety can be provided for the target account meeting the preset acquisition requirement, so that the use experience is improved. The target account which does not meet the preset acquisition requirement can be prevented from being played due to the acquisition of the play text, so that the use experience is improved.

In an alternative embodiment, since the account partially not knowing the multimedia scenario may not actually be in mind, it may be further determined that the account cannot acquire the scenario text based on the actual requirements of such an account without knowing the account of the multimedia scenario to determine that the scenario is rejected.

Optionally, sending the obtained second set of texts to be presented to the target account may include: and under the condition that the target account refuses to acquire the pivot text, sending the obtained second text set to be displayed to the target account.

The embodiment does not limit how the target account is determined to refuse to obtain the pivot text.

Optionally, the determining that the target account refuses to acquire the drama text may be determining that the target account sets "avoid drama" or "mask drama text". It is also possible that the target account sends a request for characterizing the rejection of the acquisition of the pivot text.

Correspondingly, in the case that the target account is determined not to refuse to acquire the pivot text, the first text set to be displayed may be sent to the target account.

Optionally, all or part of the text to be presented in the first set of text to be presented may be sent to the target account.

According to the embodiment, the specific requirement of the target account which does not meet the preset acquisition requirement is determined, and the situation that the target account refuses to acquire the pivot text is determined, so that the pivot text is prevented from being sent to the target account, the use requirement of the account can be better met, and the use experience is improved.

The method flow can determine whether the pivot text can be acquired according to the requirement of the target account, so that the target account can be prevented from being pivoted due to the acquisition of the pivot text under the condition that the target account is determined not to know the target multimedia scenario, and the use experience is improved; and under the condition that the target account is determined to know the target multimedia scenario, the target account which knows the scenario can acquire the pivot text, so that the use experience can be improved because more texts to be displayed are acquired.

In addition, since the method flow can be automatically executed, and participation of the target account is not required, whether the drama text is sent or not can be determined under the condition that the target account is unaware, so that the use experience of the target account is improved.

And for the target account obtained for many times, more kinds and numbers of texts can be provided, and the use experience is improved.

Moreover, the function of shielding the perspective text can also take effect simultaneously with the function of shielding other texts to be displayed, and cannot influence each other.

For the convenience of understanding, the present disclosure also provides an application example. Specifically, in the scene of the video barrage, the perspective barrage is identified.

When the account plays a video, a barrage is usually required to be opened to be watched together with the video content. Wherein, the barrage with the video scenario leakage information can be a perspective barrage.

If the account is used for watching the video for the first time, the video is easy to be played due to the fact that the user watches the full play bullet screen, and the watching experience is reduced.

If the account is used for watching the video for the second time, even watching the video for multiple times, the video cannot be played due to the fact that the played text is watched, in order to enrich the number and the types of the video barrages, the played text does not need to be shielded for the account for watching the video for multiple times, and the use experience can be improved.

Thus, as shown in fig. 2, fig. 2 is a flowchart illustrating a video bullet screen display method according to an exemplary embodiment. A particular method may include the following steps.

S201: and determining the drama-through bullet screen in the bullet screen corresponding to the target video.

The method for specifically determining the drama-popup screen may include: determining a pivot barrage in the barrage corresponding to the target video through a pre-trained natural language processing model, and specifically marking the determined pivot text as a pivot type barrage; or determining a popup with higher similarity to any determined pivot popup in the corresponding popup of the target video as the pivot popup, specifically, marking the determined pivot text as a "pivot-like popup"; when the account sends a bullet screen for the target video, the account may click on an option "containing the pivot content", and the bullet screen sent in the case of clicking this option may be directly determined as the pivot bullet screen, specifically, the sent pivot text may be marked as a "pivot-like bullet screen".

Furthermore, auditors of the service party can determine the corresponding pivot bullet screen of the target video according to experience, and check the pivot bullet screen determined by other methods. Specifically, the auditor may mark the determined pivot bullet as a "pivot bullet" directly under the condition that the pivot bullet is determined, and may cancel the mark of the pivot bullet when it is determined that the pivot bullet determined by some other method does not actually relate to pivot.

Alternatively, a bullet screen database may be provided, in which the correspondence between the videos and the bullet screens is stored. And for the barrage information, a field can be added for marking the 'drama type barrage'.

S202: and judging whether the target account is an initial viewing account or not aiming at the target account requesting to acquire the target video. If it is the primary viewing account, S203 may be executed; if it is not a first view account, S204 may be performed.

Wherein, when the account does not finish watching the main content (not taking the trailer) of the movie/tv play/fantasy, the account can be regarded as the "primary watching account" of the video, otherwise, the account can be regarded as the "multi-watching account".

Alternatively, when the account plays a movie/tv show/comedy last episode to the end or the end of the episode, the status of the account that has finished playing the video is recorded, and the account that has recorded the status may be regarded as the "multi-view account" of the movie/tv show/comedy.

If this status is not recorded, the account may be considered as the "first time viewing account" for the video.

Optionally, the account video database may store a correspondence between the account and the video that is played completely, where the account identifier and the video identifier may be included to characterize that the account is for the corresponding video and is not an initial viewing account.

Therefore, whether the account is the primary viewing account or not is specifically judged, and whether the video identifier corresponding to the target account contains the target video identifier or not can be judged through the account video database. If so, the target account is not a primary viewing account; if not, the target account is a first view account.

S203: and sending the bullet screens except the full-play bullet screen to the target account in the bullet screens corresponding to the target video.

S204: and sending the bullet screen corresponding to the target video to the target account.

In the embodiment, for an account that only watches videos, the account cannot see the "drama-through type barrage" when "watching" one video for the first time. When the account wants to re-watch the video, all the barrages including the "drama-type barrages" can be seen. Thereby allowing a usage experience for accounts that are viewed for the first time and for multiple times.

Aiming at the account for sending the bullet screen, the check box containing the pivot content can be seen when the bullet screen is sent, if the bullet screen is worried about the pivot influence, the check box can be checked to send the bullet screen, the bullet screen can be prevented from not being sent due to the worried about the pivot influence, and the use experience of the account for sending the bullet screen is improved.

The embodiment can improve the experience of watching the video account for many times and provide a plurality of types/quantities of barrages; the experience of watching the video account for the first time can be improved, and the drama-type barrage is determined and shielded in advance; the experience of the bullet screen producer can be improved, and the bullet screen is not dared to be sent due to the fact that the bullet screen producer contains the dramatic information.

FIG. 3 is a block diagram illustrating a text presentation device according to an exemplary embodiment. Referring to fig. 3, the apparatus includes an acquisition unit 301 and a transmission unit 302.

An acquisition unit 301 configured to perform: acquiring a first to-be-displayed text set corresponding to a target multimedia, and determining a pivot text in the acquired first to-be-displayed text set; the plot position of the drama text is behind the display position; the plot position is a position corresponding to plot information contained in the perspective text in the target multimedia; the presentation position is a position where the pivot text is presented in the target multimedia.

A transmitting unit 302 configured to perform: and deleting the pivot text in the first text set to be displayed to obtain a second text set to be displayed under the condition that the target account requesting to acquire the target multimedia does not meet the preset acquisition requirement, and sending the obtained second text set to be displayed to the target account.

Optionally, the sending unit 302 includes: a rejection subunit 302a configured to perform: and under the condition that the target account refuses to acquire the pivot text, sending the obtained second text set to be displayed to the target account.

Optionally, the obtaining unit 301 includes: a pivot text determination subunit 301a configured to perform one or more of the following methods of determining pivot text:

determining the text to be displayed with the pivot identification in the acquired first text set to be displayed as a pivot text; the pivot identification is added aiming at a text to be displayed specified by the operation of a preset account; the preset account operation is used for designating a pivot text;

determining the corresponding position of the contained preset pivot key word in the target multimedia aiming at the text to be displayed containing any preset pivot key word in the acquired first text set to be displayed; if the determined position is behind the display position of the aimed text to be displayed, determining the aimed text to be displayed as a pivot text;

and determining the text to be displayed, which has the coincidence degree with any determined pivot text and is larger than the preset coincidence degree, as the pivot text in the acquired first text set to be displayed.

Optionally, the obtaining unit 301 includes: a model determining subunit 301b configured to perform: determining a text recognition model corresponding to the target multimedia at present; the model is used for identifying the corresponding pivot text of the target multimedia; inputting the text characteristics and the display position of the text to be displayed in the acquired first text set to be displayed into the model, and determining the pivot text according to the output of the model.

Optionally, the obtaining unit 301 includes: a model training subunit 301c configured to perform: acquiring a training sample according to a pivot text currently corresponding to the target multimedia; the sample features of the training sample comprise text features and a display position of the perspective text; and training to obtain a text recognition model corresponding to the target multimedia currently according to the obtained training sample.

Optionally, the model training subunit 301c includes: a sample acquiring subunit 301c1 configured to perform one or more of the following methods of acquiring training samples:

taking the text feature and the display position of the pivot text corresponding to the target multimedia as sample features, and adding a label for representing the pivot text to obtain a training sample;

generating a newly added text with the coincidence degree of any pivot text currently corresponding to the target multimedia being greater than a preset coincidence degree, taking the text characteristics of the newly added text and the display position of the pivot text as sample characteristics, and adding a label for representing the pivot text to obtain a training sample;

and determining a text to be displayed, which has the coincidence degree greater than the preset coincidence degree, of any pivot text corresponding to the target multimedia from the text to be displayed currently corresponding to the target multimedia, taking the text characteristics of the determined text to be displayed and the display position of the pivot text as sample characteristics, and adding a label for representing the pivot text to obtain a training sample.

Optionally, the preset obtaining requirement is used for characterizing that the target account has obtained the main scenario content of the target multimedia.

Optionally, the main scenario content includes:

presetting the content of a position in the target multimedia; and/or

The content with the proportion larger than the preset proportion in the target multimedia; and/or

The content with the account interest degree larger than the preset interest degree in the target multimedia; and/or

Content having a primary storyline indicia in the target multimedia.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

An embodiment of the present disclosure also provides an electronic device, including:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the text presentation method according to any of the above embodiments.

Embodiments of the present disclosure also provide a computer-readable storage medium, where instructions of the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the text presentation method according to any one of the above embodiments.

Embodiments of the present disclosure further provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the text presentation method according to any of the above embodiments is implemented.

FIG. 4 is a schematic block diagram illustrating an electronic device in accordance with an exemplary embodiment. Referring to fig. 4, electronic device 500 may include one or more of the following components: processing component 502, memory 504, power component 506, multimedia component 508, audio component 510, input/output (I/O) interface 512, sensor component 514, and communication component 518. The electronic device/server described above may employ a similar hardware architecture.

The processing component 502 generally controls overall operation of the electronic device 500, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. Processing component 502 may include one or more processors 520 to execute instructions to perform all or a portion of the steps of the text presentation method described above. Further, the processing component 502 can include one or more modules that facilitate interaction between the processing component 502 and other components. For example, the processing component 502 can include a multimedia module to facilitate interaction between the multimedia component 508 and the processing component 502.

The memory 504 is configured to store various types of data to support operations at the electronic device 500. Examples of such data include instructions for any application or method operating on the electronic device 500, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 504 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 506 provides power to the various components of the electronic device 500. The power components 506 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the electronic device 500.

The multimedia component 508 includes a screen that provides an output interface between the electronic device 500 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 500 is in an operating mode, such as a shooting mode or a video mode. Each of the front camera and the rear camera may be a fixed or optical lens system with a focal length and optical zoom capability.

The audio component 510 is configured to output and/or input audio signals. For example, the audio component 510 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 500 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 504 or transmitted via the communication component 518. In some embodiments, audio component 510 further includes a speaker for outputting audio signals.

The I/O interface 512 provides an interface between the processing component 502 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the electronic device 500. For example, the sensor assembly 514 may detect an open/closed state of the electronic device 500, the relative positioning of components, such as a display and keypad of the electronic device 500, the sensor assembly 514 may detect a change in the position of the electronic device 500 or a component of the electronic device 500, the presence or absence of user contact with the electronic device 500, orientation or acceleration/deceleration of the electronic device 500, and a change in the temperature of the electronic device 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 514 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 518 is configured to facilitate wired or wireless communication between the electronic device 500 and other devices. The electronic device 500 may access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component 518 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 518 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an embodiment of the present disclosure, the electronic device 500 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above text presentation method.

In an embodiment of the present disclosure, a computer-readable storage medium comprising instructions, such as the memory 504 comprising instructions, executable by the processor 520 of the electronic device 500 to perform the text presentation method described above is also provided. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

It is noted that, in the present disclosure, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The method and apparatus provided by the embodiments of the present disclosure are described in detail above, and the principles and embodiments of the present disclosure are explained herein by applying specific examples, and the above description of the embodiments is only used to help understanding the method and core ideas of the present disclosure; meanwhile, for a person skilled in the art, based on the idea of the present disclosure, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present disclosure should not be construed as a limitation to the present disclosure.

Claims (10)

1. A text presentation method, comprising:

acquiring a first to-be-displayed text set corresponding to a target multimedia, and determining a pivot text in the acquired first to-be-displayed text set; the plot position of the drama text is behind the display position; the plot position is a position corresponding to plot information contained in the perspective text in the target multimedia; the display position is the position where the perspective text is displayed in the target multimedia;

and deleting the pivot text in the first text set to be displayed to obtain a second text set to be displayed under the condition that the target account requesting to acquire the target multimedia does not meet the preset acquisition requirement, and sending the obtained second text set to be displayed to the target account.

2. The method of claim 1, wherein sending the obtained second set of text to be presented to the target account comprises:

and under the condition that the target account refuses to acquire the pivot text, sending the obtained second text set to be displayed to the target account.

3. The method of claim 1, wherein determining the pivot text comprises one or more of:

determining the text to be displayed with the pivot identification in the acquired first text set to be displayed as a pivot text; the pivot identification is added aiming at a text to be displayed specified by the operation of a preset account; the preset account operation is used for designating a pivot text;

determining the corresponding position of the contained preset pivot key word in the target multimedia aiming at the text to be displayed containing any preset pivot key word in the acquired first text set to be displayed; if the determined position is behind the display position of the aimed text to be displayed, determining the aimed text to be displayed as a pivot text;

and determining the text to be displayed, which has the coincidence degree with any determined pivot text and is larger than the preset coincidence degree, as the pivot text in the acquired first text set to be displayed.

4. The method of claim 1, wherein determining the pivot text in the acquired first set of texts to be presented comprises:

determining a text recognition model corresponding to the target multimedia at present; the model is used for identifying the corresponding pivot text of the target multimedia;

inputting the text characteristics and the display position of the text to be displayed in the acquired first text set to be displayed into the model, and determining the pivot text according to the output of the model.

5. The method according to claim 1, wherein the preset obtaining requirement is used for characterizing that the target account has obtained the main scenario content of the target multimedia.

6. The method of claim 5, wherein the main storyline content comprises one or more of:

presetting the content of a position in the target multimedia;

the content with the proportion larger than the preset proportion in the target multimedia;

the content with the account interest degree larger than the preset interest degree in the target multimedia;

and the target multimedia has content with preset main scenario marks.

7. A text presentation device, comprising:

an acquisition unit configured to perform: acquiring a first to-be-displayed text set corresponding to a target multimedia, and determining a pivot text in the acquired first to-be-displayed text set; the plot position of the drama text is behind the display position; the plot position is a position corresponding to plot information contained in the perspective text in the target multimedia; the display position is the position where the perspective text is displayed in the target multimedia;

a transmitting unit configured to perform: and deleting the pivot text in the first text set to be displayed to obtain a second text set to be displayed under the condition that the target account requesting to acquire the target multimedia does not meet the preset acquisition requirement, and sending the obtained second text set to be displayed to the target account.

8. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the text presentation method of any one of claims 1 to 6.

9. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the text presentation method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program realizes the text presentation method of any one of claims 1 to 6 when executed by a processor.

Images