CN117956217A

CN117956217A - Live title replacement method, device, medium and equipment

Info

Publication number: CN117956217A
Application number: CN202410084615.0A
Authority: CN
Inventors: 谢纨楠; 安�晟; 高必梵
Original assignee: Shuhang Technology Beijing Co ltd
Current assignee: Shuhang Technology Beijing Co ltd
Priority date: 2024-01-19
Filing date: 2024-01-19
Publication date: 2024-04-30

Abstract

The embodiment of the application provides a live title replacement method, a live title replacement device, a live title replacement medium and live title replacement equipment, wherein the live title replacement method comprises the following steps: displaying a live broadcast interface of a target live broadcast room; displaying target candidate titles in response to a title change event of a target live broadcasting room, the target candidate titles being generated based on association information of the target live broadcasting room; and in response to the triggering operation for the target candidate title, replacing the live title of the target live broadcasting room with the target candidate title. According to the method and the device for generating the target candidate title, the association information of the live broadcast interface is acquired, the target candidate title matched with the live broadcast interface is generated according to the association information, and the target candidate title generated based on the association information of the live broadcast interface not only can assist a host to set a proper title for a live broadcast room, but also can enable reasonable titles to attract users to enter the live broadcast room while facilitating users to know the content of the live broadcast room so as to improve user traffic.

Description

Live title replacement method, device, medium and equipment

Technical Field

The present application relates to the field of electronic communications technologies, and in particular, to a video page switching technology, and in particular, to a method, an apparatus, a medium, and a device for replacing a live title.

Background

In a multimedia playing platform, such as a network live platform, in order to help a user to quickly understand live content in a live broadcast room or attract the user to enter the live broadcast room to promote user traffic in the live broadcast room, a title is generally defined for current live content in the live broadcast room, and most of common titles are custom created by a host or selected from preset reference titles in the live broadcast platform. But the method of custom creation by the anchor is very good in testing the text work bottoms and summarizing capability of the live broadcast, and for the anchor with a relatively poor level, more user traffic is difficult to obtain by setting the title of the live broadcast room, while the reference title provided by the live broadcast platform is mostly lack of pertinence, the construction logic is relatively simple, and the title of the live broadcast room capable of obtaining more user traffic cannot be generated.

Disclosure of Invention

The embodiment of the application provides a live title replacing method, a device, a medium and equipment, and aims to solve the problem that titles created by a common title creation mode cannot provide help for improving user flow.

In one aspect, an embodiment of the present application provides a live title replacement method, where the live title replacement method includes:

Displaying a live broadcast interface of a target live broadcast room;

In response to a title change event of the target live broadcasting room, displaying target candidate titles, wherein the target candidate titles are generated based on associated information of the target live broadcasting room, and the associated information at least comprises main broadcasting information of the target live broadcasting room and/or live broadcasting content of the target live broadcasting room;

And responding to the triggering operation aiming at the target candidate title, and replacing the live title of the target live broadcasting room with the target candidate title.

In the live title replacement method according to the embodiment of the present application, before the response to the title replacement event of the target live room, the method further includes:

receiving a title replacement request aiming at the target live broadcasting room, and generating a title replacement event according to the title replacement request; or (b)

Detecting whether the play type corresponding to the live broadcast content of the target live broadcast room changes or not, and generating a title replacement event when detecting that the play type changes.

In the live title replacement method according to the embodiment of the present application, before the displaying of the target candidate title, the method further includes:

acquiring live broadcast content of the live broadcast interface;

And inputting the live broadcast content into a pre-trained type identification model to perform play type identification operation to obtain a target play type corresponding to the live broadcast content, and taking the target play type as the associated information of the live broadcast interface.

And acquiring the anchor information corresponding to the live broadcast interface, and taking the anchor information as the associated information of the live broadcast interface.

acquiring live broadcast content of the live broadcast interface;

inputting the live broadcast content into a pre-trained keyword extraction model to perform keyword extraction operation to obtain a plurality of target keywords corresponding to the live broadcast content;

Inputting the target keywords into a pre-trained sentence pattern generation model to perform sentence construction operation, obtaining target sentences containing the target keywords, and taking the target sentences as the associated information of the live broadcast interface.

In the live title replacement method according to the embodiment of the present application, the step of inputting the plurality of target keywords into a pre-trained sentence pattern generation model to perform sentence construction operation, to obtain a target sentence including the plurality of target keywords includes:

constructing an initial sentence pattern generation model;

Obtaining a training sample, training the initial sentence pattern generation model through the training sample, and obtaining a sentence pattern generation model to be evaluated after training;

evaluating the sentence pattern generation model to be evaluated based on a preset baseline model, and determining a pre-trained sentence pattern generation model passing the evaluation;

And acquiring the target keywords, inputting the target keywords into the sentence pattern generation model, and generating target sentences corresponding to the target keywords.

In the live title replacement method according to the embodiment of the present application, the sentence pattern generation model is a transform model, and includes a word embedding layer, an encoder and a decoder;

Inputting the target keywords into the sentence pattern generation model to generate target sentences corresponding to the target keywords, wherein the generating comprises the following steps:

inputting the keywords into the sentence pattern generation model, and generating an input sequence according to the keywords;

determining a distributed vector of the input sequence according to the word embedding layer;

coding the distributed vector of the input sequence according to the coder to obtain a hidden state sequence;

And according to the decoder analyzing the hidden state sequence, determining each word of the target sentence, and further determining the target sentence.

acquiring a pre-trained title generation model;

generating title construction prompt words by at least one associated information corresponding to the target live broadcasting room and a preset template, wherein the preset template comprises preset prompt information for guiding the title generation model to generate target candidate titles aiming at the at least one associated information;

and inputting the title construction prompt word into the title generation model to perform title generation operation, so as to obtain target candidate titles adapted to the live broadcast interface.

In the live title replacement method according to the embodiment of the present application, before the title generation operation is performed by inputting the title construction prompting word into the title generation model, the method further includes:

And setting a weight value of a target play type corresponding to the live content to be larger than a weight value of the anchor information, so that when the associated information simultaneously comprises the target play type and the anchor information and the target play type is not matched with the anchor information, the target play type is taken as a dominant in the process of generating by constructing a prompt word through the title.

In the method for replacing a live title according to the embodiment of the present application, after the live interface of the target live room is displayed, the method further includes:

According to the live broadcast content of the target live broadcast room, at least one candidate note matched with the live broadcast content is identified from the notes issued by the anchor account of the target live broadcast room, and at least one note icon corresponding to the candidate note is displayed;

And responding to clicking operation aiming at a target note icon in the at least one note icon, associating the jump link of the target living broadcast room with a target note corresponding to the target note icon, and adding a living broadcast entrance of the target living broadcast room on a cover page or a detail page corresponding to the target note so that a user can jump from the cover page or the detail page of the target note to the target living broadcast room through the living broadcast entrance.

In the live title replacement method in this embodiment, after the replacing the live title of the target live room with the target candidate title, the method further includes:

and recording the user browsing amount of the live interface corresponding to the target candidate title from the beginning of the effective state in real time.

Correspondingly, another aspect of the embodiment of the present application further provides a live title replacing device, where the live title replacing device includes:

the display module is used for displaying a live broadcast interface of the target live broadcast room;

The response module is used for responding to the title replacement event of the target live broadcasting room, displaying target candidate titles, wherein the target candidate titles are generated based on the association information of the target live broadcasting room, and the association information at least comprises the main broadcasting information of the target live broadcasting room and/or the live broadcasting content of the target live broadcasting room;

and the replacing module is used for responding to the triggering operation aiming at the target candidate title and replacing the live title of the target live broadcasting room with the target candidate title.

Accordingly, another aspect of the embodiments of the present application provides a storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the live title replacement method as described above.

Correspondingly, the embodiment of the application also provides a terminal device, which comprises a processor and a memory, wherein the memory stores a plurality of instructions, and the processor loads the instructions to execute the live title replacement method.

The embodiment of the application provides a live title replacement method, a live title replacement device, a live title replacement medium and live title replacement equipment, wherein the live title replacement method is used for displaying a live interface of a target live broadcasting room; displaying target candidate titles in response to a title change event of a target live broadcasting room, the target candidate titles being generated based on association information of the target live broadcasting room; and in response to the triggering operation for the target candidate title, replacing the live title of the target live broadcasting room with the target candidate title. According to the method and the device for generating the target candidate title, the association information of the live broadcast interface is acquired, the target candidate title matched with the live broadcast interface is generated according to the association information, and the target candidate title generated based on the association information of the live broadcast interface not only can assist a host to set a proper title for a live broadcast room, but also can enable reasonable titles to attract users to enter the live broadcast room while facilitating users to know the content of the live broadcast room so as to improve user traffic.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is evident that the drawings in the following description are only some embodiments of the application and that other drawings may be obtained from these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flow chart of a live title replacement method according to an embodiment of the present application.

Fig. 2 is another flow chart of a live title replacement method according to an embodiment of the present application.

Fig. 3 is another flow chart of a live title replacement method according to an embodiment of the present application.

Fig. 4 is another flow chart of a live title replacement method according to an embodiment of the present application.

Fig. 5 is another flow chart of a live title replacement method according to an embodiment of the present application.

Fig. 6 is another flow chart of a live title replacement method according to an embodiment of the present application.

Fig. 7 is a schematic structural diagram of a live title replacement device according to an embodiment of the present application.

Fig. 8 is another schematic structural diagram of a live title replacement apparatus according to an embodiment of the present application.

Fig. 9 is a schematic structural diagram of a terminal device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by a person skilled in the art without any inventive effort, are intended to be within the scope of the present application based on the embodiments of the present application.

It should be noted that the present solution is mainly developed around the technical problem of how to generate reasonable multimedia association titles to promote user traffic. It can be appreciated that in a multimedia playing platform, such as a network live platform, in order to help a user quickly understand live content in a live broadcast room or attract the user to enter the live broadcast room to promote user traffic in the live broadcast room, a title is generally defined for current live content in the live broadcast room, and most of common titles are custom created by a host or selected from preset reference titles in the live broadcast platform. But the method of custom creation by the anchor is very good in testing the text work bottoms and summarizing capability of the live broadcast, and for the anchor with a relatively poor level, more user traffic is difficult to obtain by setting the title of the live broadcast room, while the reference title provided by the live broadcast platform is mostly lack of pertinence, the construction logic is relatively simple, and the title of the live broadcast room capable of obtaining more user traffic cannot be generated.

In order to solve the technical problems, an embodiment of the present application provides a live title replacement method. By the live title replacing method provided by the embodiment of the application, the association information of the live title is obtained by determining the live title interface to be generated, the target candidate title matched with the live title is generated according to the association information, the target candidate title generated based on the association information of the live title can assist the host to set a proper title for the live broadcasting room, and reasonable titles can attract users to enter the live broadcasting room to promote user flow while facilitating users to know the content of the live broadcasting room.

The term "and/or" appearing in the present application may be an association relationship describing an associated object, and indicates that three relationships may exist, for example, a and/or B, and may indicate that: a exists alone, A and B exist together, and B exists alone. In the present application, the character "/" generally indicates that the front and rear related objects are an or relationship.

The terms first, second and the like in the description and in the claims and in the above-described figures, 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 may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or modules is not necessarily limited to only those steps or modules that are expressly listed or inherent to such process, method, article, or apparatus. The naming or numbering of the steps in the present application does not mean that the steps in the method flow must be executed according to the time/logic sequence indicated by the naming or numbering, and the execution sequence of the steps in the flow that are named or numbered may be changed according to the technical purpose to be achieved, so long as the same or similar technical effects can be achieved. The division of the modules in the present application is a logical division, and may be implemented in another manner in practical applications, for example, a plurality of modules may be combined or integrated in another system, or some features may be omitted or not implemented, and further, coupling or direct coupling or communication connection between the modules shown or discussed may be through some interfaces, and indirect coupling or communication connection between the modules may be electrical or other similar manners, which are not limited in the present application. The modules or sub-modules described as separate components may be physically separated or not, or may be distributed in a plurality of circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the present application.

The live title replacing method related to the embodiment of the application is mainly applied to terminal equipment, such as smart phones, tablet computers, notebook computers, desktop computers, intelligent voice interaction equipment, intelligent household appliances, vehicle-mounted terminals, servers and the like, and is not limited herein. Alternatively, the server may be an independent physical server, or a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network ), and basic cloud computing services such as big data and artificial intelligence platform, which are not limited herein.

Referring to fig. 1, fig. 1 is a flowchart illustrating a live title replacement method according to an embodiment of the present application. The execution subjects of each step in the live title replacement method can be the same or different.

In an embodiment, the method may comprise the steps of:

step 101, displaying a live interface of the target live broadcasting room.

It should be noted that, the live title replacing method provided by the scheme can provide a starting control on the live interface of the title to be generated, and the title intelligent recommending function can be started or closed through the starting control, so that an operator can select to automatically recommend the title by the system or create the title by the operator according to the own requirement.

Step 102, in response to the title replacement event of the target live broadcasting room, displaying target candidate titles, wherein the target candidate titles are generated based on the association information of the target live broadcasting room, and the association information at least comprises the main broadcasting information of the target live broadcasting room and/or the live broadcasting content of the target live broadcasting room.

When an operator switches the starting control to an on state, the system is endowed with the authority of automatically generating a title for the currently determined live broadcast interface and recommending the title to the operator, the system can automatically generate title replacement events at preset time intervals (for example, 5 min), can automatically generate title replacement events when detecting that the play type corresponding to the live broadcast content of the target live broadcast room changes, and can also generate title replacement events by actively initiating a title replacement request by the operator. As shown in fig. 2, when the title replacement event of the target living broadcast room is responded, the system collects the material materials required for creating the target candidate title, namely, the related information of the target living broadcast room (including but not limited to the living broadcast content of the target living broadcast room, the anchor information of the target living broadcast room, etc.), after the material materials are collected, the task request for generating the title is sent to a designated generating task queue, and then waits until the title returned by the system is obtained from the generating result queue, the system inquires whether the anchor is adopted, if so, the follow-up conventional distribution logic is completed, and the generated title is displayed and distributed as the title of the living broadcast room.

In this embodiment, the associated information refers to information capable of guiding generation of a target candidate title adapted to a live broadcast interface, and includes a target play type corresponding to live broadcast content, anchor information corresponding to the live broadcast interface, sentences constructed by keywords proposed by the live broadcast content, and the like.

In an example, when the associated information is a target play type corresponding to the live content, the target play type may be a car, cosmetic, or the like type. The method for acquiring the association information can be used for acquiring the live content of the live interface, inputting the live content into a pre-trained type identification model for play type identification operation, obtaining a target play type corresponding to the live content, and taking the target play type as the association information of the live interface.

In another example, when the associated information is the anchor information corresponding to the live broadcast interface, the manner of obtaining the associated information may be obtained by directly obtaining, and it should be explained that the anchor information refers to one or more of a nickname, a personal profile, and a personal signature of the anchor. For example, nicknames "small a love for eyelash raising", personal introduction "concentrate on cosmetic industry xx years", individual signature "no damage to eyelash planting technique".

In another example, when the associated information is a sentence constructed by a keyword proposed by the live broadcast content, the acquiring manner of the associated information may be through acquiring the live broadcast content of the live broadcast interface; inputting the live broadcast content into a pre-trained keyword extraction model to perform keyword extraction operation, so as to obtain a plurality of target keywords corresponding to the live broadcast content; inputting a plurality of target keywords into a pre-trained sentence pattern generation model to perform sentence construction operation, obtaining target sentences containing the target keywords, and taking the target sentences as the associated information of the live broadcast interface. For example, the target keywords include "staff, professional tools, women, nursing, eyebrows", and the constructed target sentence is "staff is using various professional tools, nursing her eyebrows for a woman, making it more upwarp and better looking"

The sentence pattern generation model may be obtained based on neural network training, for example, an encoder-decoder model (transducer) based on Self-Attention (Self-Attention) network, that is, the sentence pattern generation model may be obtained based on transducer model training. The transducer model may include a word embedding layer, an encoder, and a decoder, where parameters in each layer and module are initial values.

The training process of the sentence pattern generation model can be used for constructing an initial sentence pattern generation model; obtaining a training sample, training the initial sentence pattern generation model through the training sample, and obtaining a sentence pattern generation model to be evaluated after training; evaluating the sentence pattern generation model to be evaluated based on a preset baseline model, and determining a pre-trained sentence pattern generation model passing the evaluation; acquiring a plurality of target keywords; and inputting the target keywords into the sentence pattern generation model to generate target sentences corresponding to the target keywords.

The training model is required to be evaluated, and whether the accuracy of the training model reaches the expectations is evaluated. The evaluation method can be to design a baseline model, wherein the input of the baseline model is a keyword, the output of the baseline model is a sentence generated by the keyword, and the evaluation index corresponding to the sentence output by the baseline model is used as the minimum standard to detect whether the sentence output by the sentence pattern generation model reaches the minimum standard.

Optionally, the evaluating process may obtain a baseline sentence output by the baseline model by inputting the test sample set into a preset baseline model, and inputting the test sample set into a text generating model to be evaluated to obtain a sentence to be evaluated output by the text generating model to be evaluated.

Alternatively, the baseline model may include a variety of models, and embodiments of the present invention enumerate three possible models, a transducer model that controls the decoder, a prefix fine-tuning transducer model, and a reordering model, respectively.

If the sentence pattern generation model is obtained based on a transformation model training, the sentence pattern generation model comprises a word embedding layer, an encoder and a decoder, keywords are input into the sentence pattern generation model by using the sentence pattern generation model with qualified evaluation, and an input sequence is generated according to the keywords; determining a distributed vector of the input sequence according to the word embedding layer; coding the distributed vector of the input sequence according to the coder to obtain a hidden state sequence; and according to the decoder analyzing the hidden state sequence, determining each word of the target sentence, and further determining the target sentence.

In the conventional live broadcasting process, after the operator creates the live broadcasting room, if the operator does not formally start the live broadcasting at this time, the operator can enter the live broadcasting setting interface through the setting control provided by the live broadcasting platform, and create a title for the current live broadcasting room at the live broadcasting setting interface.

In this embodiment, as shown in fig. 3, guide information may be added to the title setting area of the live broadcast setting interface, for example, if it is detected that the title is not successfully set currently, "do not select title? Clicking a first jump control for setting AI optimization, automatically jumping to a preset sub-page after clicking the first jump control by an operator, wherein a starting control is displayed on the preset sub-page, and starting a title intelligent recommending function when the operator switches the starting control to an on state, so that the system intelligently recommends titles according to a currently determined live broadcast interface. Meanwhile, when an operator returns to the live broadcast setting interface from the current preset sub-page, the current intelligent recommendation can be identified by adding an AI mark in the title setting area.

If it is detected that the title setting area has been set up and the title is created by the operator, a second jump control for supporting AI optimization click setting of the current title is displayed below the title setting area, so as to prompt the user that the set title can be intelligently optimized.

In some embodiments, the title information generated by the history can also be recorded in the preset sub-page, and the title information is checked through the detail expansion control. The title information comprises titles generated by user definition and/or automatically generated by a system, and each title records corresponding live broadcast starting time and user browsing amount or click rate of a live broadcast interface corresponding to the recorded title from the beginning of effectiveness. The effectiveness of a user-defined title or a title automatically generated by the system can be evaluated based on the user's browsing amount or click rate.

In some embodiments, as shown in FIG. 4, the creation of target candidate titles may be accomplished by:

Generating a model by acquiring a pre-trained title; generating title construction prompt words by using the association information of at least one corresponding target live broadcasting room and a preset template, wherein the preset template comprises preset prompt information for guiding the title generation model to generate target candidate titles aiming at the at least one association information; and inputting the title construction prompting words into a title generation model to perform title generation operation, so as to obtain target candidate titles adapted to the live broadcast interface.

It should be explained that, as shown in fig. 5, the preset prompting information is pre-stored in a preset template, for example, "please generate a title according to the above information", when the collected associated information is "target sentence: staff is using various professional tools to care her eyebrows for a woman, making it more cocked and better looking. Target play type: and (5) beautifying. A nickname of the anchor: the Xiaoyao love uplocks the eyelashes. Anchor personality signature: focusing on the intact eyelash keratin stick-up technique, the eyelashes, whether long or short, can make the radian of stick-up, and at the same time, full keratin essence is injected into the eyelashes, when your eyes are brighter and the eyelashes are healthier and stronger, a title construction prompt word can be generated by combining the preset prompt information, please output a live title according to the information.

In some embodiments, the title generation model may employ large language model (large language model), a deep learning algorithm that may perform various Natural Language Processing (NLP) tasks. By inputting the title construction prompt words into the title generation model, the title generation operation is performed by utilizing the language processing capability of the title generation model, so as to obtain target candidate titles adapted to the live interface, such as 'highest boundary of eyelash planting'.

In some embodiments, since the associated information is generally more than one type, and when different types of associated information create a title in the title generation model, a problem of collision may occur, for example, when the target play type and the anchor information occur simultaneously, and the target play type (make-up) does not match with the anchor information (good taste explanation), at this time, there is obviously no association between the two types of associated information, if the two types of associated information are referred to simultaneously, inconvenience is brought to the processing of the title generation model, and multiple target candidate titles are generated, and the selection of the user is affected, so that the weight value of the target play type is set to be greater than the weight value of the anchor information according to the principle that the dominance of the play type is higher than that of the anchor information, so that when the associated information includes both the target play type and the anchor information, and the target play type does not match with the anchor information, the target play type is used as the dominant in the generation operation by the cue word.

In some embodiments, after obtaining the target candidate title adapted to the live interface, the system automatically pushes the target candidate title to the live interface for the user to confirm operation, and only when the user confirms use, the target candidate title is used as the title of the live interface, and the target candidate title is displayed in the title display area of the live interface.

In some embodiments, before pushing the target candidate title to the live interface for the user to confirm, in order to avoid the condition that the title automatically generated by the system is not compliant, the target candidate title may be sent to a machine auditing system for automatic auditing before being sent to display; the specific auditing mode can be realized based on a keyword recognition technology and in combination with a preset sensitive word triggering rule, for example, the generated target candidate title is the highest boundary of eyelash planting, the keyword can be obtained after keyword extraction operation is carried out, the obtained keyword is compared with a sensitive word stock, if no triggering sensitive word recognition is carried out, the target candidate title formed by the keyword can be directly pushed to a live broadcast interface for user confirmation through auditing, and if one or more keywords trigger sensitive word recognition is carried out, the target candidate title formed by the keyword can not pass auditing.

Considering that the automatic auditing mechanism may have misjudgment, when the auditing result is that the auditing result is failed, the target candidate titles can be pushed to the manual auditing system for further manual auditing, and the alternative target candidate titles are obtained in the manual auditing process and pushed to the live interface for the user to confirm operation, so that the waiting time of the user is avoided to be too long.

And step 103, replacing the live title of the target live broadcasting room with the target candidate title in response to the triggering operation for the target candidate title.

In some embodiments, not only can the live title be displayed on the live interface, but also the published notes of the main broadcasting account can be associated according to the current live content, so that the user can quickly jump to the note detail page of interest while watching the live room. It should be explained that notes refer to one type of content that is authored and shared by the anchor on the platform. Such content is typically in the form of text, pictures, and videos, for example, recording the life experiences of the host, shopping hearts, travel stories, and beauty hearts.

Specifically, as shown in fig. 6, at least one candidate note matched with the live broadcast content is identified from the published notes of the main broadcast account number of the target live broadcast room according to the live broadcast content of the target live broadcast room, and at least one note icon corresponding to the candidate note is displayed on a live broadcast interface; when the clicking operation of an operator on the target note icon in at least one note icon is responded, associating the jump link of the target living broadcast room with the target note corresponding to the target note icon, and adding a living broadcast entrance of the target living broadcast room on a cover or a detail page of the corresponding target note, so that a user can jump to the target living broadcast room from the cover or the detail page of the target note through the living broadcast entrance.

Any combination of the above optional solutions may be adopted to form an optional embodiment of the present application, which is not described herein.

In particular, the application is not limited by the order of execution of the steps described, as some of the steps may be performed in other orders or concurrently without conflict.

From the above, the live title replacement method provided by the embodiment of the application displays the live interface of the target live broadcasting room; displaying target candidate titles in response to a title change event of a target live broadcasting room, the target candidate titles being generated based on association information of the target live broadcasting room; and in response to the triggering operation for the target candidate title, replacing the live title of the target live broadcasting room with the target candidate title. According to the method and the device for generating the target candidate title, the association information of the live broadcast interface is acquired, the target candidate title matched with the live broadcast interface is generated according to the association information, and the target candidate title generated based on the association information of the live broadcast interface not only can assist a host to set a proper title for a live broadcast room, but also can enable reasonable titles to attract users to enter the live broadcast room while facilitating users to know the content of the live broadcast room so as to improve user traffic.

The embodiment of the application also provides a live title replacing device which can be integrated in the terminal equipment.

Referring to fig. 7, fig. 7 is a schematic structural diagram of a live title replacing device according to an embodiment of the application. The live title replacement apparatus 30 may include:

a display module 31, configured to display a live interface of the target live broadcasting room;

A response module 32, configured to respond to a title replacement event of the target live broadcast room, and display a target candidate title, where the target candidate title is generated based on association information of the target live broadcast room, and the association information at least includes main broadcasting information of the target live broadcast room and/or live broadcasting content of the target live broadcast room;

And a replacing module 33, configured to replace a live title of the target live broadcasting room with the target candidate title in response to a triggering operation for the target candidate title.

In some embodiments, the apparatus further comprises an event generation module for receiving a title change request for the target live room, generating a title change event according to the title change request; or detecting whether the play type corresponding to the live broadcast content of the target live broadcast room changes, and generating a title replacement event when detecting that the play type changes.

In some embodiments, the apparatus further comprises a first acquisition module configured to acquire live content of the live interface; and inputting the live broadcast content into a pre-trained type identification model to perform play type identification operation to obtain a target play type corresponding to the live broadcast content, and taking the target play type as the associated information of the live broadcast interface.

In some embodiments, the apparatus further includes a second obtaining module, configured to obtain anchor information corresponding to the live broadcast interface, and use the anchor information as association information of the live broadcast interface.

In some embodiments, the apparatus further comprises a third acquisition module configured to acquire live content of the live interface; inputting the live broadcast content into a pre-trained keyword extraction model to perform keyword extraction operation to obtain a plurality of target keywords corresponding to the live broadcast content; inputting the target keywords into a pre-trained sentence pattern generation model to perform sentence construction operation, obtaining target sentences containing the target keywords, and taking the target sentences as the associated information of the live broadcast interface.

In some embodiments, the third obtaining module is configured to construct an initial sentence pattern generation model; obtaining a training sample, training the initial sentence pattern generation model through the training sample, and obtaining a sentence pattern generation model to be evaluated after training; evaluating the sentence pattern generation model to be evaluated based on a preset baseline model, and determining a pre-trained sentence pattern generation model passing the evaluation; acquiring the target keywords; and inputting the target keywords into the sentence pattern generation model to generate target sentences corresponding to the target keywords.

In some embodiments, the sentence-based generation model is a transducer model, including a word embedding layer, an encoder, and a decoder; the third acquisition module is used for inputting the keywords into the sentence pattern generation model and generating an input sequence according to the keywords; determining a distributed vector of the input sequence according to the word embedding layer; coding the distributed vector of the input sequence according to the coder to obtain a hidden state sequence; and according to the decoder analyzing the hidden state sequence, determining each word of the target sentence, and further determining the target sentence.

In some embodiments, the apparatus further comprises a building module for obtaining a pre-trained title generation model; generating title construction prompt words by at least one associated information corresponding to the target live broadcasting room and a preset template, wherein the preset template comprises preset prompt information for guiding the title generation model to generate target candidate titles aiming at the at least one associated information; and inputting the title construction prompt word into the title generation model to perform title generation operation, so as to obtain target candidate titles adapted to the live broadcast interface.

In some embodiments, the apparatus further includes a preset module, configured to set a weight value of a target play type corresponding to the live content to be greater than a weight value of the anchor information, so that when the associated information includes both a target play type and anchor information, and the target play type does not match with the anchor information, the target play type is dominant in the generating operation performed by the cue word.

In some embodiments, the apparatus further includes a skip module, configured to identify, according to live content of the target live room, at least one candidate note matching with the live content from among notes published by a main cast account of the target live room, and display at least one note icon corresponding to the candidate note; and responding to clicking operation aiming at a target note icon in the at least one note icon, associating the jump link of the target living broadcast room with a target note corresponding to the target note icon, and adding a living broadcast entrance of the target living broadcast room on a cover page or a detail page corresponding to the target note so that a user can jump from the cover page or the detail page of the target note to the target living broadcast room through the living broadcast entrance.

In some embodiments, the apparatus further includes a recording module configured to record, in real time, a user browsing amount of the live interface corresponding to the target candidate title since the target candidate title was validated.

In specific implementation, each module may be implemented as a separate entity, or may be combined arbitrarily and implemented as the same entity or several entities.

As can be seen from the above, the live title replacing device 30 provided in the embodiment of the present application, wherein the display module 31 is configured to display a live interface of a target live broadcasting room; a response module 32, configured to respond to a title replacement event of the target live broadcast room, and display a target candidate title, where the target candidate title is generated based on association information of the target live broadcast room, and the association information at least includes main broadcasting information of the target live broadcast room and/or live broadcasting content of the target live broadcast room; and a replacing module 33, configured to replace a live title of the target live broadcasting room with the target candidate title in response to a triggering operation for the target candidate title.

Referring to fig. 8, fig. 8 is another schematic structural diagram of a live title replacement apparatus according to an embodiment of the present application, where the live title replacement apparatus 30 includes a memory 120, one or more processors 180, and one or more application programs, and the one or more application programs are stored in the memory 120 and configured to be executed by the processors 180; the processor 180 may include a display module 31, a response module 32, and a replacement module 33. For example, the structures and connection relationships of the above respective components may be as follows:

Memory 120 may be used to store applications and data. The memory 120 stores application programs including executable code. Applications may constitute various functional modules. The processor 180 executes various functional applications and data processing by running application programs stored in the memory 120. In addition, memory 120 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 120 may also include a memory controller to provide access to the memory 120 by the processor 180.

The processor 180 is a control center of the device, connects various parts of the entire terminal using various interfaces and lines, and performs various functions of the device and processes data by running or executing application programs stored in the memory 120 and calling data stored in the memory 120, thereby performing overall monitoring of the device. Optionally, the processor 180 may include one or more processing cores; preferably, the processor 180 may integrate an application processor and a modem processor, wherein the application processor primarily processes an operating system, user interfaces, application programs, and the like.

In particular, in this embodiment, the processor 180 loads executable codes corresponding to the processes of one or more application programs into the memory 120 according to the following instructions, and the processor 180 executes the application programs stored in the memory 120, so as to implement various functions:

a display instruction for displaying a live interface of a target live broadcasting room;

The response instruction is used for responding to the title replacement event of the target living broadcast room, displaying target candidate titles, wherein the target candidate titles are generated based on the association information of the target living broadcast room, and the association information at least comprises the main broadcasting information of the target living broadcast room and/or the living broadcast content of the target living broadcast room;

and the replacing instruction is used for responding to the triggering operation aiming at the target candidate title and replacing the live title of the target live broadcasting room with the target candidate title.

In some embodiments, the program further includes event generation instructions for receiving a title change request for the target live room, generating a title change event according to the title change request; or detecting whether the play type corresponding to the live broadcast content of the target live broadcast room changes, and generating a title replacement event when detecting that the play type changes.

In some embodiments, the program further includes first obtaining instructions for obtaining live content of the live interface; and inputting the live broadcast content into a pre-trained type identification model to perform play type identification operation to obtain a target play type corresponding to the live broadcast content, and taking the target play type as the associated information of the live broadcast interface.

In some embodiments, the program further includes a second obtaining instruction, configured to obtain anchor information corresponding to the live broadcast interface, and use the anchor information as association information of the live broadcast interface.

In some embodiments, the program further includes third obtaining instructions for obtaining live content of the live interface; inputting the live broadcast content into a pre-trained keyword extraction model to perform keyword extraction operation to obtain a plurality of target keywords corresponding to the live broadcast content; inputting the target keywords into a pre-trained sentence pattern generation model to perform sentence construction operation, obtaining target sentences containing the target keywords, and taking the target sentences as the associated information of the live broadcast interface.

In some embodiments, the third obtaining instruction is configured to construct an initial sentence pattern generation model; obtaining a training sample, training the initial sentence pattern generation model through the training sample, and obtaining a sentence pattern generation model to be evaluated after training; evaluating the sentence pattern generation model to be evaluated based on a preset baseline model, and determining a pre-trained sentence pattern generation model passing the evaluation; acquiring the target keywords; and inputting the target keywords into the sentence pattern generation model to generate target sentences corresponding to the target keywords.

In some embodiments, the sentence-based generation model is a transducer model, including a word embedding layer, an encoder, and a decoder; the third obtaining instruction is used for inputting the keywords into the sentence pattern generation model and generating an input sequence according to the keywords; determining a distributed vector of the input sequence according to the word embedding layer; coding the distributed vector of the input sequence according to the coder to obtain a hidden state sequence; and according to the decoder analyzing the hidden state sequence, determining each word of the target sentence, and further determining the target sentence.

In some embodiments, the program further comprises build instructions for obtaining a pre-trained title generation model; generating title construction prompt words by at least one associated information corresponding to the target live broadcasting room and a preset template, wherein the preset template comprises preset prompt information for guiding the title generation model to generate target candidate titles aiming at the at least one associated information; and inputting the title construction prompt word into the title generation model to perform title generation operation, so as to obtain target candidate titles adapted to the live broadcast interface.

In some embodiments, the program further includes a preset instruction, configured to set a weight value of a target play type corresponding to the live content to be greater than a weight value of the anchor information, so that when the associated information includes both a target play type and anchor information, and the target play type does not match with the anchor information, the target play type is dominant in the generating operation performed by the cue word.

In some embodiments, the program further includes a skip instruction, configured to identify, according to live content of the target live room, at least one candidate note matching with the live content from among notes already issued by a main cast account of the target live room, and display at least one note icon corresponding to the candidate note; and responding to clicking operation aiming at a target note icon in the at least one note icon, associating the jump link of the target living broadcast room with a target note corresponding to the target note icon, and adding a living broadcast entrance of the target living broadcast room on a cover page or a detail page corresponding to the target note so that a user can jump from the cover page or the detail page of the target note to the target living broadcast room through the living broadcast entrance.

In some embodiments, the program further includes recording instructions for recording, in real time, a user browsing amount of the live interface corresponding to the target candidate title since the target candidate title was validated.

The embodiment of the application also provides terminal equipment. The terminal equipment can be a server, a smart phone, a computer, a tablet personal computer and the like.

Referring to fig. 9, fig. 9 shows a schematic structural diagram of a terminal device according to an embodiment of the present application, where the terminal device may be used to implement the live title replacement method provided in the foregoing embodiment. The terminal device 1200 may be a television or a smart phone or a tablet computer.

As shown in fig. 9, the terminal device 1200 may include an RF (Radio Frequency) circuit 110, a memory 120 including one or more (only one is shown in the figure) computer readable storage mediums, an input unit 130, a display unit 140, a sensor 150, an audio circuit 160, a transmission module 170, a processor 180 including one or more (only one is shown in the figure) processing cores, and a power supply 190. It will be appreciated by those skilled in the art that the configuration of the terminal device 1200 shown in fig. 9 does not constitute a limitation of the terminal device 1200, and may include more or fewer components than shown, or may combine certain components, or may have a different arrangement of components. Wherein:

The RF circuit 110 is configured to receive and transmit electromagnetic waves, and to perform mutual conversion between the electromagnetic waves and the electrical signals, so as to communicate with a communication network or other devices. RF circuitry 110 may include various existing circuit elements for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a Subscriber Identity Module (SIM) card, memory, and the like. The RF circuitry 110 may communicate with various networks such as the internet, intranets, wireless networks, or other devices via wireless networks.

The memory 120 may be used to store software programs and modules, such as program instructions/modules corresponding to the live title replacement method in the above embodiment, and the processor 180 executes various functional applications and data processing by running the software programs and modules stored in the memory 120, so that the vibration reminding mode can be automatically selected to switch video pages according to the current scene where the terminal device is located, thereby not only ensuring that the scenes such as a conference are not disturbed, but also ensuring that the user can perceive an incoming call, and improving the intelligence of the terminal device. Memory 120 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 120 may further include memory remotely located relative to processor 180, which may be connected to terminal device 1200 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input unit 130 may be used to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. In particular, the input unit 130 may comprise a touch sensitive surface 131 and other input devices 132. The touch sensitive surface 131, also referred to as a touch display screen or touch pad, may collect touch operations thereon or thereabout by a user (e.g., operations of the user on the touch sensitive surface 131 or thereabout by any suitable object or accessory such as a finger, stylus, etc.), and actuate the corresponding connection means according to a pre-set program. Alternatively, the touch sensitive surface 131 may comprise two parts, a touch detection device and a touch controller. The touch control detection device detects the touch control direction of a user, detects signals brought by touch control operation and transmits the signals to the touch control controller; the touch controller receives touch information from the touch detection device, converts the touch information into touch coordinates, sends the touch coordinates to the processor 180, and can receive and execute commands sent by the processor 180. In addition, the touch-sensitive surface 131 may be implemented in various types of resistive, capacitive, infrared, surface acoustic wave, and the like. In addition to the touch-sensitive surface 131, the input unit 130 may also comprise other input devices 132. In particular, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, mouse, joystick, etc.

The display unit 140 may be used to display information input by a user or information provided to the user and various graphical user interfaces of the terminal device 1200, which may be composed of graphics, fields, icons, videos, and any combination thereof. The display unit 140 may include a display panel 141, and alternatively, the display panel 141 may be configured in the form of an LCD (Liquid CRYSTAL DISPLAY), an OLED (Organic Light-Emitting Diode), or the like. Further, the touch-sensitive surface 131 may cover the display panel 141, and after the touch-sensitive surface 131 detects a touch operation thereon or thereabout, the touch-sensitive surface is transferred to the processor 180 to determine a type of touch event, and then the processor 180 provides a corresponding visual output on the display panel 141 according to the type of touch event. Although in fig. 9 the touch-sensitive surface 131 and the display panel 141 are implemented as two separate components for input and output functions, in some embodiments the touch-sensitive surface 131 may be integrated with the display panel 141 to implement the input and output functions.

The terminal device 1200 may also include at least one sensor 150, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display panel 141 according to the brightness of ambient light, and a proximity sensor that may turn off the display panel 141 and/or the backlight when the terminal device 1200 moves to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the acceleration in all directions (generally three axes), and can detect the gravity and the direction when the mobile phone is stationary, and can be used for applications of recognizing the gesture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration recognition related functions (such as pedometer and knocking), and the like; other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc. that may also be configured with the terminal device 1200 are not described in detail herein.

Audio circuitry 160, speaker 161, microphone 162 may provide an audio interface between a user and terminal device 1200. The audio circuit 160 may transmit the received electrical signal converted from audio data to the speaker 161, and the electrical signal is converted into a sound signal by the speaker 161 to be output; on the other hand, the microphone 162 converts the collected sound signal into an electrical signal, receives the electrical signal from the audio circuit 160, converts the electrical signal into audio data, outputs the audio data to the processor 180 for processing, transmits the audio data to, for example, another terminal via the RF circuit 110, or outputs the audio data to the memory 120 for further processing. Audio circuitry 160 may also include an ear bud jack to provide communication of the peripheral headphones with terminal device 1200.

Terminal device 1200 may facilitate user email, web browsing, streaming media access, etc. via a transmission module 170 (e.g., wi-Fi module) that provides wireless broadband internet access to the user. Although fig. 9 shows the transmission module 170, it is understood that it does not belong to the essential constitution of the terminal device 1200, and may be omitted entirely as needed within the scope of not changing the essence of the invention.

The processor 180 is a control center of the terminal device 1200, connects various parts of the entire mobile phone using various interfaces and lines, and performs various functions of the terminal device 1200 and processes data by running or executing software programs and/or modules stored in the memory 120, and calling data stored in the memory 120, thereby performing overall monitoring of the mobile phone. Optionally, the processor 180 may include one or more processing cores; in some embodiments, the processor 180 may integrate an application processor that primarily processes operating systems, user interfaces, applications, etc., with a modem processor that primarily processes wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 180.

The terminal device 1200 also includes a power supply 190 that provides power to the various components, and in some embodiments, may be logically coupled to the processor 180 via a power management system to perform functions such as managing discharge, and managing power consumption via the power management system. The power supply 190 may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.

Although not shown, the terminal device 1200 may further include a camera (such as a front camera, a rear camera), a bluetooth module, etc., which will not be described herein. In particular, in the present embodiment, the display unit 140 of the terminal device 1200 is a touch screen display, the terminal device 1200 further includes a memory 120, and one or more programs, wherein the one or more programs are stored in the memory 120 and configured to be executed by the one or more processors 180, the one or more programs include instructions for:

The embodiment of the application also provides terminal equipment. The terminal equipment can be a smart phone, a computer and other equipment.

As can be seen from the above, the embodiment of the present application provides a terminal device 1200, wherein the terminal device 1200 performs the following steps:

Displaying a live broadcast interface of a target live broadcast room;

The embodiment of the application also provides a storage medium, in which a computer program is stored, and when the computer program runs on a computer, the computer executes the live title replacement method according to any one of the embodiments.

It should be noted that, for the live title replacing method according to the present application, it will be understood by those skilled in the art that all or part of the process of implementing the live title replacing method according to the embodiments of the present application may be implemented by controlling related hardware through a computer program, where the computer program may be stored in a computer readable storage medium, such as a memory of a terminal device, and executed by at least one processor in the terminal device, and the execution may include the process of implementing the live title replacing method according to the embodiments of the present application. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a random access Memory (RAM, random Access Memory), or the like.

For the live title replacing device in the embodiment of the application, each functional module can be integrated in one processing chip, each module can exist alone physically, and two or more modules can be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated module, if implemented as a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium such as read-only memory, magnetic or optical disk, etc.

The method, the device, the medium and the equipment for replacing the live title provided by the embodiment of the application are described in detail. The principles and embodiments of the present application have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present application and the core ideas thereof; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, the present description should not be construed as limiting the present application.

Claims

1. A live title replacement method, comprising:

Displaying a live broadcast interface of a target live broadcast room;

2. The live title replacement method of claim 1, wherein prior to the responding to the title replacement event for the target live room, the method further comprises:

3. The live title replacement method of claim 1, wherein prior to the displaying the target candidate title, the method further comprises:

acquiring live broadcast content of the live broadcast interface;

4. The live title replacement method of claim 1, wherein prior to the displaying the target candidate title, the method further comprises:

5. The live title replacement method of claim 1, wherein prior to the displaying the target candidate title, the method further comprises:

acquiring live broadcast content of the live broadcast interface;

6. The method for replacing live titles as set forth in claim 5, wherein said inputting said plurality of target keywords into a pre-trained sentence pattern generation model for sentence construction operation to obtain a target sentence containing said plurality of target keywords comprises:

constructing an initial sentence pattern generation model;

7. The method for replacing a live title of claim 6, wherein the sentence pattern generation model is a transducer model comprising a word embedding layer, an encoder and a decoder;

8. The live title replacement method of claim 1, wherein prior to the displaying the target candidate title, the method further comprises:

acquiring a pre-trained title generation model;

9. The live title replacement method of claim 8, wherein prior to the entering the title construction prompt word into the title generation model for a title generation operation, the method further comprises:

10. The live title replacement method of claim 1, wherein after the displaying of the live interface of the target live room, the method further comprises:

11. The live title replacement method of claim 1, wherein after the replacing the live title of the target live room with the target candidate title, the method further comprises:

12. A live title replacement apparatus, comprising:

13. A computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the live title replacement method of any of claims 1-11.

14. A terminal device comprising a processor and a memory, the memory storing a plurality of instructions, the processor loading the instructions to perform the live title replacement method of any of claims 1-11.