CN112417352A

CN112417352A - Method and device for processing release content, electronic equipment and storage medium

Info

Publication number: CN112417352A
Application number: CN202011211177.8A
Authority: CN
Inventors: 王霄汉; 彭飞; 邓竹立
Original assignee: Beijing 58 Information Technology Co Ltd
Current assignee: Beijing 58 Information Technology Co Ltd
Priority date: 2020-11-03
Filing date: 2020-11-03
Publication date: 2021-02-26

Abstract

The invention discloses a method, a device, electronic equipment and a storage medium for processing release content, wherein the method comprises the following steps: acquiring published content of a client; inputting the published content into an evaluation generation model to obtain comment content output by the evaluation generation model; the evaluation generation model is obtained by training a preset model by taking a plurality of sample pairs as training samples, wherein each sample pair comprises a content sample and a comment sample corresponding to the content sample; generating a virtual user account aiming at the comment content, wherein the virtual user account is different along with the comment content; and outputting reply content of the virtual user account aiming at the published content according to the comment content. By adopting the technical scheme of the invention, the corresponding contents in the comment can be automatically generated according to the characteristics of the published contents, and the comment contents can be automatically replied to all the published contents. And further improves the activity of the Internet community.

Description

Method and device for processing release content, electronic equipment and storage medium

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for processing a distribution content.

Background

With the popularization of the internet, users can release some self life records, current affair viewpoints and other contents in a network community provided by the internet so as to share self feelings with a plurality of users on the network and transfer self thought viewpoints. When more comments are obtained from one content published by the user, the more attention is drawn to the content published by the user, and a better experience feeling can be brought to the user publishing the content.

In the related art, in order to activate the atmosphere of the internet community, the content released by the user needs to be manually replied, that is, each time the user releases a new content, some replied content is manually edited for the new content and then released. However, when the number of released contents is large, the manual reply for these new contents is very labor intensive, and requires a very high labor cost.

Disclosure of Invention

In view of the foregoing problems, embodiments of the present invention provide a method, an apparatus, an electronic device, and a storage medium for processing published contents, which aim to solve the problem in the related art that the efficiency of manually replying to a user published contents is low.

In order to solve the technical problem, the invention adopts the following scheme:

in a first aspect, an embodiment of the present invention provides a method for processing a published content, including:

acquiring published content of a client;

inputting the published content into an evaluation generation model, and obtaining comment content which is output by the evaluation generation model and corresponds to the published content, wherein the evaluation generation model is obtained by training a preset model by taking a plurality of sample pairs as training samples, and each sample pair comprises a content sample and a comment sample corresponding to the content sample;

generating a virtual user account aiming at the comment content, wherein the virtual user account is different along with the comment content;

and outputting reply content of the virtual user account for the published content according to the comment content.

Optionally, after outputting reply content of the virtual user account for the published content according to the comment content, the method further includes:

and pushing a notification message to the client so as to enable the client to display the reply content of the virtual user account for the published content.

Optionally, outputting reply content of the virtual user account for the published content according to the comment content includes:

taking the comment content as reply content of the virtual user account for the published content, and displaying the reply content on a page where the published content is located; and/or

When a refresh request of other clients for the page where the published content is located is detected, sending a refreshed page to the other clients, wherein the refreshed page is a page taking the comment content as reply content of the virtual user account for the published content.

Optionally, the evaluation generation model is obtained by:

obtaining a plurality of content samples;

for each content sample, determining a comment sample corresponding to the content sample from a plurality of comment samples replying to the content sample, and combining the content sample and the comment sample corresponding to the content sample into a sample pair;

and taking a plurality of sample pairs as training samples, and carrying out non-supervised training on the preset model to obtain the evaluation generation model.

Optionally, for each content sample, determining a comment sample corresponding to the content sample from a plurality of comment samples that reply to the content sample includes:

for each content sample, determining a comment sample corresponding to the content sample according to a user behavior parameter value corresponding to each of a plurality of comment samples replying to the content sample, wherein the user behavior parameter value is at least one of the following: browsing times, times marked as a preset tag, and times replied.

Optionally, before outputting reply content of the virtual user account for the published content according to the comment content, the method further includes:

establishing an incidence relation between a plurality of comment contents and a plurality of virtual user accounts, and writing the incidence relation into a database;

according to the comment content, outputting reply content of the virtual user account for the published content, wherein the reply content comprises:

reading the virtual user account and the comment content associated with the virtual user account from the database;

and outputting reply content of the virtual user account for the published content according to the comment content associated with the virtual user account.

In a second aspect, an embodiment of the present invention provides an apparatus for processing published content, including:

the content obtaining module is used for obtaining published content of the first client;

the comment generation module is used for inputting the published content into an evaluation generation model to obtain comment content which is output by the evaluation generation model and corresponds to the published content; the evaluation generation model is obtained by training a preset model by taking a plurality of sample pairs as training samples, wherein each sample pair comprises a content sample and a comment sample corresponding to the content sample;

the virtual account generation module is used for generating a virtual user account aiming at the comment content, wherein the virtual user account is different along with the comment content;

and the reply content output module is used for outputting the reply content of the virtual user account aiming at the published content according to the comment content.

Optionally, the apparatus further comprises:

and the pushing module is used for pushing a notification message to the client so as to enable the client to display the reply content of the virtual user account aiming at the published content.

Optionally, the reply content output module includes:

the first output unit is used for displaying the comment content as reply content of the virtual user account for the published content on a page where the published content is located; and/or

And a second output unit, configured to send a refreshed page to another client when a refresh request of the other client for a page where the published content is located is detected, where the refreshed page is a page in which the comment content is used as reply content of the published content by the virtual user account.

Optionally, the apparatus further comprises the following modules:

a sample obtaining module for obtaining a plurality of content samples;

the sample pair combination module is used for determining comment samples corresponding to the content samples from a plurality of comment samples replying the content samples aiming at each content sample, and combining the content samples and the comment samples corresponding to the content samples into a sample pair;

and the training module is used for carrying out non-supervised training on the preset model by taking a plurality of sample pairs as training samples to obtain the evaluation generation model.

Optionally, the sample pairing module includes a comment sample obtaining unit, where the comment sample obtaining unit is configured to, for each content sample, determine, according to a user behavior parameter value corresponding to each of a plurality of comment samples that reply the content sample, a comment sample corresponding to the content sample;

wherein the user behavior parameter value is at least one of: browsing times, times marked as a preset tag, and times replied.

Optionally, the apparatus further comprises:

the data writing module is used for establishing an association relationship between a plurality of comment contents and a plurality of virtual user accounts and writing the association relationship into a database;

the reply content output module includes:

the data reading unit is used for reading the virtual user account and the comment content related to the virtual user account from the database;

and the data publishing unit is used for outputting reply content of the virtual user account aiming at the published content according to the comment content associated with the virtual user account.

In a third aspect, an embodiment of the present invention provides an electronic device, including: memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method of processing post content according to the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method for processing published content as described in the first aspect.

In the embodiment of the invention, the published content of the client can be acquired, the published content is input into the evaluation generation model, the comment content which is output by the evaluation generation model and corresponds to the published content is acquired, the virtual user account is generated aiming at the comment content, and the reply content of the virtual user account aiming at the published content is output according to the comment content. The published content can be input into the evaluation generation model, so that the corresponding comment content can be automatically generated according to the published content, and the virtual user account is automatically generated according to the comment content, so that the whole process of publishing the comment content can be independently completed by the server or the client, the labor cost and workload consumed by manually editing the reply content are avoided, and the labor cost is reduced. And because the corresponding comment content is generated according to the published content, the published content is fully utilized, so that the generated reply content is closely associated with the published content, the matching degree between the characteristics of the reply content and the published content is improved, and the quality of the reply content is improved.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without inventive labor.

FIG. 1 is a flow chart of one step in obtaining an evaluation generative model in an embodiment of the present invention;

FIG. 2 is a flow chart of steps in a method of processing published content in an embodiment of the invention;

FIG. 3 is a flow chart of steps in a method of processing published content in accordance with an embodiment of the invention;

fig. 4 is a schematic structural diagram of an apparatus for processing published content in an embodiment of the present invention;

fig. 5 is a schematic diagram of a hardware structure of a terminal device in the embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In the internet technology, a user can publish his own feelings and viewpoints in a network community, for example, in some network communities with posting as a main, such as a skyline community, a watch, a microblog and the like, the user can publish some posts, namely published content, through his own account. In the related art, in order to create an atmosphere in which a network community is very active, improve the attractiveness of the network community to users, and reduce user loss, generally, contents published by users can be pushed to some users, but the contents are often pushed to the users, which are not interesting to the users, so that the method has little effect on improving the activity.

In the related art, the organization staff member manually replies the comment content to the posts issued by the user, for example, manually replies some newly issued posts with their own account numbers. However, in this method, the posts can only be replied when the number of posts is small, and if there are a large number of posts to be replied, a large amount of work is required, and it takes a long time to complete the replying of the posts, and the labor cost is also high.

In view of this, the applicant proposes a method and a system that can automatically generate the comment content of the content when detecting that the user publishes a new content, and then automatically reply the comment content to the new content just published by the user through a virtual user account, so that each newly published content can obtain the corresponding comment content, thereby improving the liveness of the network community, optimizing the posting experience of the user, and improving the enthusiasm of posting of the user.

The method for processing the release content in the embodiment of the invention can be applied to a client or a server in communication connection with the client, wherein the client is installed on a terminal device, and the terminal device can be an intelligent device such as a mobile phone, a notebook computer, a tablet computer, a network television and the like.

Firstly, in order to improve the intelligence and efficiency of generating the comment content, improve the contact degree between the comment content and the published content and reduce the labor, an evaluation generation model may be trained first, and the comment content corresponding to the published content is generated through the evaluation generation model.

Referring to fig. 1, a flowchart illustrating steps of obtaining an evaluation generative model according to an embodiment is shown, and as shown in fig. 1, the evaluation generative model can be obtained by the following steps:

step S11: a plurality of content samples is obtained.

The content sample may be content already published in a network community, the content sample may not be limited to content already published by a client publishing the published content, and in practice, content published by other clients may be all used as the content sample.

In practice, in order to enable the evaluation generation model to generate the comment content with better quality, a certain screening condition may be preset for obtaining a plurality of content samples, and specifically, the content samples used for model training may be screened from a plurality of published contents according to the screening condition. The screening condition may be that the number of the comments of the reply content reaches a virtual number, so that the published content with a large reply amount is used as the content sample.

Of course, in practice, the filtering condition may also be a preset user tag, that is, the content published by the user with the preset user tag is used as the content sample, for example, the content published by the star user is filtered as the content sample. In practice, the flow of the star user is large, and the returned comment content is more, so that the better comments can be screened out subsequently when a comment sample is selected.

Step S22: for each content sample, determining a comment sample corresponding to the content sample from a plurality of comment samples replying to the content sample, and combining the content sample and the comment sample corresponding to the content sample into a sample pair.

In this embodiment, one of the comments in the plurality of comments returned to the content sample may be selected as a comment sample according to a preset selection condition, so that the content sample and the selected comment sample serve as a sample pair. The preset selection condition may be random selection, or may be selection according to the ranking order of the comments in the comment area, for example, the comment arranged first is selected as a comment sample. In practice, the comments arranged in the first place are generally the comments with the largest number of praise, so that the comments with higher quality can be selected directly according to the sorting sequence in the comment area, and the efficiency of screening the comment samples is improved.

In practice, the content samples and the comment samples corresponding to the content samples may be sorted, so that the sorted sample pairs are input to the preset model. For example, the content samples and the comment samples are separated by vertical lines to form sample pairs, which can be specifically referred to as the following format:

[ "post content 1| high-quality comment 1",

"post content 2| high quality comment 2",

"post content 3| high quality comment 2",

"post content 4| high quality comment 1",

"post content 5| high quality comment 1",

......，

"post content 100000| premium comment 100000",

......]。

in another embodiment, when a comment sample corresponding to each content sample is selected, the comment sample corresponding to the content sample may be determined according to the user behavior parameter value corresponding to each of the plurality of comment samples that reply to the content sample.

The user behavior parameter value may be used to describe a situation that the comment is operated by a user, and the behavior parameter value may be at least one of: browsing times, times marked as a preset tag, and times replied. The preset tag may be an approval tag when the comment is approved, and the number of times of being replied may be the number of times of replying the comment by other users.

Therefore, when the comment samples are screened, screening can be performed from three dimensions of browsing times, approved times and replied times. In practice, the more browsing times, the more the comment is concerned by a plurality of users, and the comment is shown to be a high-quality comment in practice; the more the comment is voted, the more the comment can be represented to obtain approval, and the comment is also represented to be a high-quality comment approved by the user; the more replies indicates that the comment attracts more attention and interaction, indicating that the comment has higher topicality. Therefore, by screening the comment samples according to the three dimensions, the comments with the best quality in one published content can be screened out. For example, the screened comment sample can be the comment with the highest browsing frequency and the highest approval frequency, and the comment with the highest reply quality is obtained.

Step S23: and taking a plurality of sample pairs as training samples, and carrying out non-supervised training on the preset model to obtain an evaluation generation model.

In this embodiment, the sample pair may be directly input to the preset model for training, and the preset model automatically performs feature extraction on the sample pair, thereby outputting the predicted comment content. The unsupervised training is a data processing method for classifying samples by analyzing data of a large number of samples of a researched object under the condition of no class information.

Therefore, through unsupervised training, the sample pairs are not marked manually, so that the human resources can be further reduced, and the operation cost is reduced.

By adopting the training method for the evaluation generation model, on one hand, the existing content resources of the network community can be fully utilized, namely, the existing published content and the reply content of the published content are fully utilized to train to obtain the evaluation generation model, so that the existing content resources are fully mined, high-quality comments can be used as the comment sample training model, and the quality of the generated comment content is improved. On the other hand, the evaluation generation model is obtained through unsupervised learning, so that the workload caused by manually labeling content samples is avoided, and the labor cost is reduced. The whole process can be independently finished by a machine, so that the comment content is automatically generated by utilizing the evaluation generation model from the model training to the later stage, and the reply content is output according to the comment content in an automatic process, thereby reducing the manual participation to the greatest extent and saving the operation cost.

Therefore, when the model is trained for enough times and reaches convergence, the evaluation generation model can be obtained. The comment content of the posted content can be generated by using the evaluation generation model.

Referring to fig. 2, a flowchart illustrating steps of a method for processing published content according to an embodiment of the present invention is shown, and as shown in fig. 2, the method for processing published content may specifically include the following steps:

step S21: and acquiring the published content of the client.

In this embodiment, the client may be an application having a posting function and a function of replying to a posted post, and the client may be installed on a mobile phone or a computer. The user can log in the client to publish the content on a posting interface provided by the client, wherein the published content is published content. The published content may be content whose content is text, and of course, in some examples, the published content may also be content whose content includes pictures and text.

In practice, the published content may be content that meets the preset condition and is published by the client, so that when the published content of the client is obtained, the content that meets the preset condition may be obtained from a plurality of contents published by the client. The preset condition may be that the number of replies does not reach the preset number, or that a time difference between the release time and the current time does not reach the preset time difference, or that the number of replies to which the malicious tag is attached is set. The published content may be content with a small number of ratings, new content just published by the client, or content with a large number of malicious ratings.

When the preset condition is the content which is evaluated maliciously, high-quality comment content can be generated for the published content through the method, so that the comment on the published content is guided to be carried out in a more positive direction, and the health order of the network community is maintained.

Step S22: and inputting the published content into an evaluation generation model to obtain comment content which is output by the evaluation generation model and corresponds to the published content.

The evaluation generation model is obtained by training a preset model by taking a plurality of sample pairs as training samples, wherein each sample pair comprises a content sample and a comment sample corresponding to the content sample.

In this embodiment, the feature of the published content may refer to a feature extracted from the published content, and the feature may represent a theme of the published content. In particular implementation, the feature may be a keyword in the published content, a word with a high frequency of occurrence, or a word used to describe emotional tendency in the published content, such as a word of affection, hate, and complain. In practice, the feature may be extracted as required.

In this embodiment, according to the extracted features, comment content conforming to the theme of the published content may be automatically generated, and the comment content may be text content.

Step S23: and generating a virtual user account aiming at the comment content.

The virtual user account is different according to different comment contents.

In this embodiment, the virtual user account may be understood as a user account that is not registered by the real user, and is used for posting the comment content. In specific implementation, a virtual user account matched with the characteristics can be generated according to the characteristics of the comment content, and the characteristics can be key word characteristics of the comment content. In practice, in order to increase the authenticity of the reply comment, when the virtual user account is generated, the virtual nickname of the virtual user account may be randomly generated.

And different comment contents correspond to different virtual user accounts. Therefore, the number of replies to comments on published content can be increased, so that the network community is more active, the attribution feeling of the user to the network community is improved, and the loss of the user is avoided.

Step S24: and outputting reply content of the virtual user account aiming at the published content according to the comment content.

In this embodiment, after the comment content is generated, the comment content may be replied to the published content. Specifically, when the comment content is replied to the published content, the reply content of the virtual user account for the published content can be output, that is, the comment content is replied to the published content by using the virtual user account, and the reply content of the published content is obtained. The reply content may be the comment content, or the content including the comment content, or may be the content after further optimization processing is performed on the comment content, for example, the comment content is converted into other content consistent with the semantic representation of the comment content, so as to improve the authenticity of the reply content.

According to the embodiment of the invention, the corresponding comment content is automatically generated by utilizing the evaluation generation model, and the reply content of the virtual user account aiming at the published content is output according to the comment content. Therefore, corresponding evaluation content can be generated for each published content needing to be commented, and the virtual user account replies to the published content. Compared with the related art, the technical scheme of the embodiment of the invention has the following advantages:

first, the reply content can be generated and issued independently by the server or the client in the whole process, so that the labor cost and workload consumed by manually editing the reply content are avoided, and the labor cost is reduced.

Secondly, because the evaluation generation model is the comment content generated according to the characteristics of the published content sample in the training process, the corresponding comment content is generated according to the characteristics of the published content, so that the published content is fully utilized, the generated reply content is closely associated with the published content, the matching degree between the characteristics of the reply content and the published content is improved, and the quality of the reply content is improved.

Thirdly, the reply content is issued through the virtual account, so that different issued contents can be issued by different virtual accounts, and the problem of low efficiency caused by frequently switching the account number to issue the reply content when the reply content is manually issued is solved.

Fourthly, the generation and the release of the reply content can be automatically completed by the server or the client, so that the operation efficiency of an enterprise is improved, each released content can obtain the corresponding comment content in a short time, and the activity of the community and the attraction of a new user are improved.

Referring to fig. 3, a flowchart illustrating steps of a further method for processing published content in an embodiment of the present invention is shown, where the method may apply an evaluation generation module to generate corresponding comment content, and as shown in fig. 3, the method may specifically include the following steps:

step S31: and acquiring the published content of the client.

This step S31 is similar to step S11 described above. Specifically, reference may be made to the step S11, which is not described herein again.

Step S32: and inputting the published content into an evaluation generation model, and performing feature extraction on the published content through the evaluation generation model.

The evaluation generating model may be obtained through the processes of the steps S11 to S13, that is, the evaluation generating model is obtained by training a preset model with a plurality of sample pairs as training samples, where each sample pair includes a content sample and a comment sample corresponding to the content sample.

Step S33: and obtaining comment content which is output by the evaluation generation model and corresponds to the published content.

In specific implementation, if the method can be applied to a client, an evaluation generation model can be embedded in the client, and a data transmission interface is arranged between the evaluation generation model and published content, so that the acquired published content is input to the evaluation generation model through the data transmission interface. If the method can be applied to the terminal equipment provided with the client, the evaluation generation model can be embedded into the terminal equipment, so that the published content can be automatically input into the evaluation generation model through a data transmission interface between the terminal equipment and the client. If the method is applied to the server, the evaluation generation model can be configured in the server, and when the client uploads the published content, the server can input the published content into the evaluation generation model to obtain the comment content output by the evaluation generation model.

Step S34: and generating a virtual user account aiming at the comment content.

The virtual user account is different according to different comment contents.

In an embodiment, if there are multiple comment contents, that is, when multiple corresponding comment contents need to be generated for published contents published by multiple users at the same time, the generated multiple comment contents can be obtained at the same time. In this case, an association relationship between a plurality of comment contents and a plurality of virtual user accounts may be established, and the association relationship may be written into the database.

In an embodiment, in order to save virtual user account resources, multiple comment contents may be optionally grouped, each group includes a preset number of comment contents, the comment contents in the same group correspond to the same virtual user account, and the comment contents in different groups correspond to different virtual user accounts.

The association relationship between the comment content and the virtual user account can be understood as a corresponding assignment relationship, that is, the association relationship can be used to specify to which virtual user account a comment content is assigned. In specific implementation, when the association relationship is written into the database, the comment content, the virtual user account, and the association relationship between the comment content and the virtual user account may be written into the database.

Step S35: and outputting reply content of the virtual user account aiming at the published content according to the comment content.

In this embodiment, since the association relationship between the comment content and the virtual user account is recorded in the database, when the reply content of the virtual user account for the published content is output according to the comment content, the virtual user account and the comment content associated with the virtual user account can be read from the database; and outputting reply content of the virtual user account aiming at the published content according to the comment content associated with the virtual user account.

In this embodiment, the reply content may be comment content, and the comment content may be displayed in a page where the published content is located. When the virtual user account number has the virtual nickname, the virtual nickname can be displayed on a page where the published content is located, so that other users see the comment content replied by the nickname for the user who is actually registered, and the authenticity of replying the automatically generated comment content to the published content is improved.

Of course, in practice, when a refresh request of another client for the page where the published content is located is detected, the refreshed page may also be sent to the other client. The refreshed page is a page which takes the comment content as reply content of the virtual user account for the published content.

By adopting the embodiment, when the client refreshes the page where the published content is, the page displaying the comment content can be sent to the client, and in this case, the reply content is also the comment content. Therefore, when a user refreshes the page where the published content is, the published content can be seen to be replied with comments, and the enthusiasm of the user for participating in the comments on the published content is improved.

Step S36: and pushing a notification message to the client so as to enable the client to display the reply content of the virtual user account for the published content.

In practice, the communication message may be sent to a terminal designated by the user who logs in to the client, for example, a notification message may be sent to the mobile phone of the user. The notification message can be a text notification message, and the content of the notification message can include comment content and a virtual user account and is used for notifying the user that the virtual user account has commented on the published content, so that the user can timely know that the content just published by the user is evaluated, an interaction mechanism between the network community and the user is optimized, the satisfaction degree of the user on the network community is improved, and the attraction to new users is increased.

In some embodiments, in order to improve the liveness of the web community, the number of the comment contents output by the evaluation generation model may be multiple, that is, for one published content, multiple comment contents may be automatically generated, and then, according to the multiple comment contents, multiple reply contents of multiple virtual user accounts for the published content may be output.

By adopting the technical scheme of the embodiment, comment content corresponding to published content can be generated by utilizing the evaluation generation model, and then reply content of the virtual user account for the published content is output.

A method for processing the distribution content according to this embodiment is described below with reference to an example:

first, a post content post1 to be commented newly issued by a user1 is obtained.

Then, the post content post1 is input to the evaluation generation model, and the comment content output by the evaluation generation model is obtained. Specifically, the evaluation generation model performs feature extraction on the input post content post1 generation, and generates high-quality comment content that best matches the feature.

Then, a user account user2 is randomly generated, the comment content output by the evaluation generation model is distributed to the randomly generated user2, and the user account user2 replies the high-quality comment to the corresponding post content post 1.

Then, the post content post1 replying with the comment content is pushed to the user1 in real time through an Android (Android) client, an iOS client or a webpage pushing system, and the post content post1 is notified that the high-quality comment replied by the user2 already exists.

Thus, when the user1 refreshes and views the post1 issued by the user on the webpage, Android client or iOS client, the user can surprisingly find that the post content post1 just issued by the user already has a good comment.

Referring to fig. 4, a schematic structural diagram of an apparatus for processing published content according to an embodiment of the present invention is shown, and as shown in fig. 4, the apparatus may be applied to a mobile terminal, a server, or a client, and specifically may include the following modules:

a content obtaining module 41, configured to obtain published content of a first client;

a comment generation module 42, configured to input the published content into an evaluation generation model, and obtain comment content output by the evaluation generation model and corresponding to the published content; the evaluation generation model is obtained by training a preset model by taking a plurality of sample pairs as training samples, wherein each sample pair comprises a content sample and a comment sample corresponding to the content sample;

a virtual account generation module 43, configured to generate a virtual user account for the comment content, where the virtual user account is different according to different comment contents;

and the reply content output module 44 may be configured to output, according to the comment content, reply content of the virtual user account for the published content.

Optionally, the apparatus may further include the following modules:

a sample obtaining module operable to obtain a plurality of content samples;

the sample pair combination module may be configured to determine, for each content sample, a comment sample corresponding to the content sample from among a plurality of comment samples that reply to the content sample, and combine the content sample and the comment sample corresponding to the content sample into a sample pair;

the training module may be configured to perform unsupervised training on the preset model by using a plurality of sample pairs as training samples, so as to obtain the evaluation generation model.

Optionally, the sample pairing module includes a comment sample obtaining unit, where the comment sample obtaining unit may be configured to, for each content sample, determine a comment sample corresponding to the content sample according to a user behavior parameter value corresponding to each of a plurality of comment samples that reply to the content sample;

wherein the user behavior parameter value may be at least one of: browsing times, times marked as a preset tag, and times replied.

Optionally, the apparatus may further include the following modules:

the data writing module can be used for establishing an association relationship between a plurality of comment contents and a plurality of virtual user accounts and writing the association relationship into a database;

the reply content output module 44 may include the following units:

the data reading unit can be used for reading the virtual user account and the comment content related to the virtual user account from the database;

and the data publishing unit may be configured to output reply content of the virtual user account for the published content according to the comment content associated with the virtual user account.

Optionally, the apparatus may further include the following modules:

the pushing module may be configured to push a notification message to the client, so that the client displays reply content of the virtual user account for the published content.

Optionally, the reply content output module 44 may specifically include the following units:

the first output unit may be configured to display the comment content as reply content of the virtual user account to the published content on a page where the published content is located; and/or

The second output unit may be configured to send a refreshed page to another client when detecting a refresh request of the other client for a page where the published content is located, where the refreshed page is a page in which the comment content is used as reply content of the virtual user account for the published content.

For the embodiment of the apparatus for processing the release content, since it is similar to the embodiment of the method for processing the release content, reference may be made to the embodiment of the method for processing the release content for relevant points, and details are not described here again.

Fig. 5 is a schematic diagram of a hardware structure of a terminal device for implementing various embodiments of the present invention.

The terminal device 500 includes but is not limited to: a radio frequency unit 501, a network module 502, an audio output unit 503, an input unit 504, a sensor 505, a display unit 506, a user input unit 507, an interface unit 508, a memory 509, a processor 510, and a power supply 511. Those skilled in the art will appreciate that the terminal device configuration shown in fig. 5 does not constitute a limitation of the terminal device, and that the terminal device may include more or fewer components than shown, or combine certain components, or a different arrangement of components. In the embodiment of the present invention, the terminal device includes, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted terminal, a wearable device, a pedometer, and the like.

It should be understood that, in the embodiment of the present invention, the radio frequency unit 501 may be used for receiving and sending signals during a message sending and receiving process or a call process, and specifically, receives downlink data from a base station and then processes the received downlink data to the processor 510; in addition, the uplink data is transmitted to the base station. In general, radio frequency unit 501 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like. In addition, the radio frequency unit 501 can also communicate with a network and other devices through a wireless communication system.

The terminal device provides the user with wireless broadband internet access through the network module 502, such as helping the user send and receive e-mails, browse webpages, access streaming media, and the like.

The audio output unit 503 may convert audio data received by the radio frequency unit 501 or the network module 502 or stored in the memory 509 into an audio signal and output as sound. Also, the audio output unit 503 may also provide audio output related to a specific function performed by the terminal apparatus 500 (e.g., a call signal reception sound, a message reception sound, etc.). The audio output unit 503 includes a speaker, a buzzer, a receiver, and the like.

The input unit 504 is used to receive an audio or video signal. The input Unit 504 may include a Graphics Processing Unit (GPU) 5041 and a microphone 5042, and the Graphics processor 5041 processes image data of a still picture or video obtained by an image capturing device (e.g., a camera) in a video capturing mode or an image capturing mode. The processed image frames may be displayed on the display unit 506. The image frames processed by the graphic processor 5041 may be stored in the memory 509 (or other storage medium) or transmitted via the radio frequency unit 501 or the network module 502. The microphone 5042 may receive sounds and may be capable of processing such sounds into audio data. The processed audio data may be converted into a format output transmittable to a mobile communication base station via the radio frequency unit 501 in case of the phone call mode.

The terminal device 500 further comprises at least one sensor 505, such as light sensors, motion sensors and other sensors. Specifically, the light sensor includes an ambient light sensor that adjusts the luminance of the display panel 5051 according to the brightness of ambient light, and a proximity sensor that turns off the display panel 5051 and/or a backlight when the terminal device 500 is moved to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), detect the magnitude and direction of gravity when stationary, and can be used to identify the terminal device posture (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration identification related functions (such as pedometer, tapping), and the like; the sensors 505 may also include fingerprint sensors, pressure sensors, iris sensors, molecular sensors, gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., which are not described in detail herein.

The display unit 506 is used to display information input by the user or information provided to the user. The Display unit 506 may include a Display panel 5051, and the Display panel 5051 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like.

The user input unit 507 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the terminal device. Specifically, the user input unit 507 includes a touch panel 5071 and other input devices 5072. Touch panel 5071, also referred to as a touch screen, may collect touch operations by a user on or near it (e.g., operations by a user on or near touch panel 5071 using a finger, stylus, or any suitable object or attachment). The touch panel 5071 may include two parts of a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 510, and receives and executes commands sent by the processor 510. In addition, the touch panel 5071 may be implemented in various types such as a resistive type, a capacitive type, an infrared ray, and a surface acoustic wave. In addition to the touch panel 5071, the user input unit 507 may include other input devices 5072. In particular, other input devices 5072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which are not described in detail herein.

Further, a touch panel 5071 may be overlaid on the display panel 5051, and when the touch panel 5071 detects a touch operation thereon or thereabout, the touch panel is transmitted to the processor 510 to determine the type of touch event, and then the processor 510 provides a corresponding visual output on the display panel 5051 according to the type of touch event. Although in fig. 5, the touch panel 5071 and the display panel 5051 are implemented as two separate components to implement the input and output functions of the terminal device, in some embodiments, the touch panel 5071 and the display panel 5051 may be integrated to implement the input and output functions of the terminal device, and are not limited herein.

The interface unit 508 is an interface for connecting an external device to the terminal apparatus 500. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device having an identification module, an audio input/output (I/O) port, a video I/O port, an earphone port, and the like. The interface unit 508 may be used to receive input (e.g., data information, power, etc.) from an external device and transmit the received input to one or more elements within the terminal apparatus 500 or may be used to transmit data between the terminal apparatus 500 and the external device.

The memory 509 may be used to store software programs as well as various data. The memory 509 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 509 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.

The processor 510 is a control center of the terminal device, connects various parts of the entire terminal device by using various interfaces and lines, and performs various functions of the terminal device and processes data by running or executing software programs and/or modules stored in the memory 509 and calling data stored in the memory 509, thereby performing overall monitoring of the terminal device. Processor 510 may include one or more processing units; preferably, the processor 510 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 510.

The terminal device 500 may further include a power supply 511 (e.g., a battery) for supplying power to various components, and preferably, the power supply 511 may be logically connected to the processor 510 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system.

In addition, the terminal device 500 includes some functional modules that are not shown, and are not described in detail herein.

An embodiment of the present invention further provides an electronic device, including: the processor, the memory, and the computer program stored in the memory and capable of running on the processor, when executed by the processor, implement each process of the above method embodiment for processing the release content, and can achieve the same technical effect, and are not described herein again to avoid repetition.

The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program implements each process of the above method for processing release content, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.

The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.

It should be noted that, in this document, 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 like elements in a process, method, article, or apparatus that comprises the element.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.

While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for processing published content, comprising:

acquiring published content of a client;

2. The method of claim 1, wherein the evaluation generative model is obtained by:

obtaining a plurality of content samples;

3. The method of claim 2, wherein for each content sample, determining a comment sample corresponding to the content sample from a plurality of comment samples in reply to the content sample comprises:

4. The method according to any one of claims 1 to 3, wherein before outputting, according to the comment content, reply content to the published content by a virtual user account, the method further comprises:

5. The method according to any one of claims 1 to 3, wherein outputting reply content of the virtual user account to the published content according to the comment content comprises:

6. The method according to any one of claims 1 to 3, wherein after outputting reply content of the virtual user account for the published content according to the comment content, the method further comprises:

7. An apparatus for processing published content, comprising:

8. The apparatus of claim 7, further comprising the following modules:

a sample obtaining module for obtaining a plurality of content samples;

9. The apparatus according to claim 8, wherein the sample combination module includes a comment sample obtaining unit, and the comment sample obtaining unit is configured to, for each content sample, determine a comment sample corresponding to the content sample according to a user behavior parameter value corresponding to each of a plurality of comment samples that reply to the content sample;

10. The apparatus of claim 7, further comprising:

the reply content output module includes:

11. The apparatus according to any one of claims 7 to 10, wherein the reply content output module includes:

12. The apparatus of any of claims 7-10, further comprising:

13. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the method of processing published content as claimed in any one of claims 1 to 6.

14. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of processing a distribution content according to any one of claims 1 to 6.