CN113342626B

CN113342626B - Content processing method, content processing device, electronic equipment and storage medium

Info

Publication number: CN113342626B
Application number: CN202110594026.3A
Authority: CN
Inventors: 陈美强
Original assignee: Shenzhen Qianhai Fang Geek Network Technology Co ltd
Current assignee: Shenzhen Qianhai Fang Geek Network Technology Co ltd
Priority date: 2021-05-28
Filing date: 2021-05-28
Publication date: 2022-11-11
Anticipated expiration: 2041-05-28
Also published as: CN113342626A

Abstract

The application discloses a content processing method, a content processing device, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring a plurality of user behavior records aiming at published contents; arranging the user behaviors in the plurality of user behavior records according to the sequence of the trigger time from first to last to obtain a user behavior sequence; calculating a behavior density parameter corresponding to the user feedback behavior; calculating a first score of the published content under the user feedback score according to the basic score corresponding to the user feedback score, and a first adjusting factor and a second adjusting factor of the user feedback score; calculating a second grade of the published content under the content grade item according to the first adjusting factor, the first quantity and the content characteristics of the published content of the content grade item; determining a comprehensive score of the published content according to the first score and the second score; and processing the published content according to the comprehensive score of the published content. The scheme ensures the reliability of the result of the published content processing.

Description

Content processing method, content processing device, electronic equipment and storage medium

Technical Field

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

Background

With the rise of content sharing platforms, more and more contents are released, and in the related art, the contents are scored only according to the exposure of the contents and are used as a basis for processing the contents, so that the problem of low reliability of content processing results exists.

Disclosure of Invention

In view of the foregoing problems, embodiments of the present application provide a content processing method, apparatus, electronic device, and storage medium to improve the foregoing problems.

According to an aspect of an embodiment of the present application, there is provided a content processing method including: acquiring a plurality of user behavior records aiming at published content, wherein the user behavior records indicate user behaviors triggered by the published content and trigger time of the user behaviors; the user behavior comprises a designated user behavior and a user feedback behavior, and the designated user behavior comprises at least one of a user registration behavior and a user incoming line behavior; arranging the user behaviors in the plurality of user behavior records according to the sequence of the trigger time from first to last to obtain a user behavior sequence; the user behavior sequence is used for determining a first adjustment factor of a content scoring item corresponding to the specified user behavior and a first adjustment factor of a user feedback scoring item corresponding to the user feedback behavior; according to the user behavior records, behavior density parameters corresponding to user feedback behaviors are calculated; the behavior density parameter is used for determining a second adjustment factor of the user feedback score item corresponding to the user feedback behavior; calculating a first score of the published content under the user feedback score according to a basic score corresponding to the user feedback score, a first adjustment factor and a second adjustment factor of the user feedback score; calculating a second score of the published content under the content score item according to the first adjusting factor, the first quantity and the content characteristics of the published content of the content score item; the first number is a number of user behavior records of the plurality of user behavior records that correspond to the specified user behavior; determining a composite score of the published content according to the first score and the second score; and processing the published content according to the comprehensive score of the published content.

According to an aspect of an embodiment of the present application, there is provided a content processing apparatus including: a user behavior record obtaining module, configured to obtain a plurality of user behavior records for published content, where the user behavior records indicate user behaviors triggered by the published content and trigger times of the user behaviors; the user behavior comprises a designated user behavior and a user feedback behavior; the user behavior sequence determining module is used for arranging the user behaviors in the user behavior records according to the sequence of the trigger time from first to last to obtain a user behavior sequence; the user behavior sequence is used for determining a first adjusting factor of a content scoring item corresponding to the specified user behavior and a first adjusting factor of a user feedback scoring item corresponding to the user feedback behavior; the behavior density parameter determining module is used for calculating behavior density parameters corresponding to the user feedback behaviors according to the user behavior records; the behavior density parameter is used for determining a second adjustment factor of the user feedback score item corresponding to the user feedback behavior; the first score calculating module is used for calculating a first score of the released content under the user feedback score according to a basic score corresponding to the user feedback score, a first adjusting factor and a second adjusting factor of the user feedback score; the second scoring calculation module is used for calculating a second score of the released content under the content scoring item according to the first adjustment factor of the content scoring item, the first quantity and the content characteristics of the released content; the first number is a number of user behavior records of the plurality of user behavior records that correspond to the specified user behavior; the comprehensive score calculating module is used for determining the comprehensive score of the published content according to the first score and the second score; and the processing module is used for processing the published content according to the comprehensive score of the published content.

According to an aspect of an embodiment of the present application, there is provided an electronic device including: a processor; a memory having computer readable instructions stored thereon which, when executed by the processor, implement a content processing method as described above.

According to an aspect of embodiments herein, there is provided a computer-readable storage medium having stored thereon computer-readable instructions which, when executed by a processor, implement a content processing method as described above.

In the scheme of the application, the scores (namely, the first score and the second score) of the published content in two different dimensions of a content score item and a user feedback score item are calculated based on the dynamic user behavior record, and then the comprehensive score of the published content is determined by combining the scores of the two score items. On one hand, the published content is scored under two scoring items, and compared with scoring under a single dimension, such as only referring to the reading amount or exposure dimension, the reliability and accuracy of the obtained comprehensive score are guaranteed; on the other hand, because the user behavior records are dynamic data, different user behavior records have independence, and different user behavior records can be mutually attested, even if defect data exists in the process of calculating the comprehensive score, the influence of the defect data on the comprehensive score can be weakened according to other user behavior records, and therefore the accuracy of the calculated comprehensive score can be ensured on the basis of the defect data. On the basis, the comprehensive score with high accuracy and high reliability is used as a basis for processing the published content, so that the reliability and the accuracy of the processing result of the published content can be ensured.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.

Fig. 1 shows a schematic diagram of an exemplary system architecture to which the technical solution of the embodiments of the present application can be applied.

Fig. 2 is a flow diagram illustrating a content processing method according to one embodiment of the present application.

FIG. 3 is a flowchart illustrating step 240 according to an embodiment of the present application.

FIG. 4 is a flowchart illustrating step 230 according to an embodiment of the present application.

FIG. 5 is a flowchart illustrating step 420 according to an embodiment of the present application.

FIG. 6 is a flowchart illustrating step 430 according to an embodiment of the present application.

FIG. 7 is a flowchart illustrating step 250 according to an embodiment of the present application.

FIG. 8 is a flowchart illustrating step 720 according to an embodiment of the present application.

Fig. 9 is a block diagram of a content processing apparatus according to an embodiment of the present application.

FIG. 10 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the application.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.

The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

It should be noted that: reference herein to "a plurality" means two or more. "and/or" describes the association relationship of the associated object, indicating that there may be three relationships, for example, a and/or B may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

As shown in fig. 1, the system architecture 100 may include a terminal device (such as one or more of a smartphone 101, a tablet computer 102, a portable computer 103 shown in fig. 1, and a desktop computer, although not limited to the illustrated terminal devices), a network 104, and a server 105. The network 104 serves as a medium for providing communication links between terminal devices and the server 105. Network 104 may include various connection types such as wired communication links, wireless communication links, and the like.

After the content is published in a content publishing platform (such as a wechat public number, a microblog, a blog website and the like), a user can browse the published content in a client, and further propagate the published content by triggering user behaviors of forwarding, sharing, praise, comment, marking, collecting, paying attention to a content author, chatting with the content author in private trust, mutual powdering with the content author, popping a bullet screen and the like aiming at the published content. In the scheme, after detecting the user behavior triggered by the user on the published content, the user behavior record is correspondingly generated and uploaded to the server 105, so that the server 105 can determine the content score of each published content according to the scheme of the application based on the user behavior record reported by each client.

In some embodiments of the present application, the server 105 may receive the user behavior record to one or more content distribution platforms, which is not specifically limited herein.

After calculating the comprehensive score of each published content, the server 105 may further process the published content according to the comprehensive score of the published content, for example, recommend the published content according to the comprehensive score, so as to recommend the content with higher comprehensive score to the user; for example, the score of the author is calculated or the author is recommended based on the composite score of the author of the published content and the published content, which is not limited in detail herein. In the solution of the present application, the published content may be an article (e.g., a blog, a public article, news, a journal article, etc.), a video, an audio-video, an audio, etc., and is not particularly limited herein.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for an implementation. For example, server 105 may be a server cluster comprised of multiple servers, or the like.

The implementation details of the technical solution of the embodiment of the present application are set forth in detail below:

fig. 2 shows a flowchart of a content processing method according to an embodiment of the present application, which may be executed by a computer device with processing capability, such as a server, and is not limited in detail herein. Referring to fig. 2, the method includes at least steps 210 to 270, which are described in detail as follows:

step 210, obtaining a plurality of user behavior records for published content, where the user behavior records indicate user behaviors triggered by the published content and trigger times of the user behaviors; the user behavior comprises a designated user behavior and a user feedback behavior, and the designated user behavior comprises at least one of a user registration behavior and a user incoming line behavior.

As described above, the published content may be an article, video, audio, audiovisual, caricature, picture, etc., and is not particularly limited herein. In some embodiments of the present application, due to differences in presentation forms of different content forms of content, content scores of published content can be calculated according to the scheme of the present application for each content form of content in a content form.

The user behavior record is generated after detecting a user behavior triggered by the user for the published content, the user behavior record indicating the triggered user behavior and a trigger time for the user behavior.

The user feedback behavior can be approval, forwarding, collection, sharing, marking, commenting, approval, watching, copying, screen capturing and the like, and for published contents in the forms of videos and audios and videos, the user feedback behavior can also be bullet screen launching, downloading and the like. It will be appreciated that the type of user feedback behavior is related to the controls provided by the content publication platform for interaction. For example, for the action of forwarding the user feedback, the user feedback may be forwarded to a friend alone, or forwarded to a group in the instant messaging software, or forwarded from a content sharing platform to another content sharing platform in another content platform, for example, the published content of the public account is forwarded to the QQ space, forwarded to the microblog, or the like.

The specified user behavior is different from the user feedback behavior, and specifically in the scheme, the specified user behavior comprises at least one of a user registration behavior and a user incoming line behavior. The user registration behavior may be a behavior of an author paying attention to the published content, a behavior registered in a content platform, a behavior of adding a friend with the author of the published content, and the like. The user incoming behavior may be a behavior of private chat with an author of the published content, entering a link in the published content, and the like, and is not particularly limited herein. The specified user behavior in the obtained user behavior record is also related to a control provided by the content platform and used for triggering the specified user behavior, for example, for content published in a public account, the user can pay attention to the public account when browsing favorite content; if the link capable of triggering entry is provided in the published content, the user can trigger clicking to enter the page indicated by the link when browsing the published content.

Step 220, arranging the user behaviors in the plurality of user behavior records according to the sequence of the trigger time from first to last to obtain a user behavior sequence; the user behavior sequence is used for determining a first adjustment factor of the content scoring item corresponding to the specified user behavior and a first adjustment factor of the user feedback scoring item corresponding to the user feedback behavior.

In some embodiments of the present application, each of the designated user behaviors uniquely corresponds to one of the content scoring items, and each of the user feedback behaviors uniquely corresponds to one of the user feedback scoring items. In a specific embodiment, the content scoring items may include one or more, and similarly, the user feedback scoring items may include one or more, which may be specifically set according to actual needs.

The content scoring item and the user feedback behavior scoring item are dimensions for scoring the published content, wherein the content scoring item is used for scoring the published content in the content characteristic dimension; the user feedback behavior scoring item is used for scoring the published content in the user feedback behavior dimension. In the scheme, the content scoring item is related to the specified user behavior (user registration behavior, user incoming line behavior); the user feedback score items are related to the user feedback behavior.

The first adjustment factor is an adjustment factor determined for each of the rating items (content rating item, user feedback rating item) according to the user behavior sequence.

In some embodiments of the present application, a mapping relationship between a specified user sequence segment and a first adjustment factor of a user behavior (a user feedback behavior or a specified user behavior) may be preset, where the specified user sequence segment refers to a sequence formed by combining a set number of user behaviors. On the basis, if a specified user sequence segment exists in the user behavior sequence, the first adjustment factor mapped by the specified user sequence segment is determined as the first adjustment factor of the user behavior specified by the specified user sequence segment. For example, if: if the designated sequence segment L is: registering, forwarding and registering, adjusting the adjustment factor of the content scoring item corresponding to the user registering behavior to t1, and determining that the second adjustment factor of the content scoring item corresponding to the user registering behavior is t1 when the specified sequence segment L exists in the user sequence segment.

In some embodiments of the application, the second adjustment factor of the score item corresponding to each user behavior may also be initially set as an initial setting value, an adjustment condition for adjusting the second adjustment factor corresponding to the user behavior is set, and if it is determined that one user behavior satisfies the corresponding adjustment condition according to the user behavior sequence, the initial setting value corresponding to the user behavior is correspondingly adjusted to obtain an adjusted second adjustment factor. The adjusting condition may be that the number of continuous user behaviors in a certain period of time reaches a set behavior number; it may also be that the magnitude of increase (or rate of increase) in the number of user actions over a specified time period exceeds a set threshold. Of course, the above are merely exemplary examples and are not specifically limited herein.

It should be noted that, if there are a plurality of second adjustment factors corresponding to a certain user behavior determined according to the user behavior sequence, the result of the symbolic superposition of the plurality of second adjustment factors may be used as the second adjustment factor of the scoring item corresponding to the user behavior for calculating the score, and the superposition may be an addition or a multiplication, which is not specifically limited herein. In some embodiments of the present application, a second adjustment factor having the largest influence on the corresponding score in the plurality of second adjustment factors may be further used as the second adjustment factor for calculating the score, or a second adjustment factor whose corresponding time is closest to the current time, for example, may be used as the second adjustment factor for calculating the score.

Step 230, calculating a behavior density parameter corresponding to the user feedback behavior according to the plurality of user behavior records; the behavior density parameter is used for determining a second adjustment factor of the user feedback score item corresponding to the user feedback behavior.

The behavior density parameter is used to describe how dense the user's behavior is. The degree of density may be based on the degree of density in time, or may be based on the degree of density in exposure, reading amount (or playing amount) of published content.

In some embodiments of the present application, the behavior density parameter may be calculated for each user feedback behavior, or the user feedback behaviors may be classified, and the behavior density parameter corresponding to each feedback behavior type is calculated according to a category to which the user feedback behavior belongs.

For example, if the user feedback behavior includes a feedback behavior a, a feedback behavior B, and a feedback behavior C, the behavior density parameter corresponding to the feedback behavior a, the behavior density parameter corresponding to the feedback behavior B, and the behavior density parameter corresponding to the feedback behavior C may be calculated respectively; the feedback behavior a, the feedback behavior B, and the feedback behavior C may also be regarded as a feedback behavior type, and a behavior density parameter of the feedback behavior type is calculated.

The second adjustment factor is determined according to the behavior density parameter of the user feedback behavior. In some embodiments of the present application, a mapping relationship between the second adjustment factor and the behavior density parameter may be preset, and on this basis, after determining a behavior density parameter corresponding to a user feedback behavior, the second adjustment factor of the user feedback score corresponding to the user feedback behavior is determined based on the mapping relationship and by combining the behavior density parameter.

It can be understood that, if the behavior density parameter of a user feedback behavior or a certain type of user feedback behavior is larger, it indicates that the content propagation speed of the published content is faster, and directly reflects the popularity of the published content, and reflects the quality of the published content from the user feedback perspective.

In some embodiments of the application, the second adjustment factor of the user feedback score is in positive correlation with the corresponding behavior density parameter, that is, the larger the behavior density parameter of the user feedback behavior is, the larger the second adjustment factor corresponding to the user feedback behavior is. In some embodiments of the present application, the second adjustment factor of the user feedback score and the corresponding behavior density parameter may be in a direct proportional relationship. Of course, in a specific embodiment, the mapping relationship between the second adjustment factor of the user feedback score and the corresponding behavior density parameter may be set according to actual needs.

And 240, calculating a first score of the released content under the user feedback score item according to the basic score corresponding to the user feedback score item, and the first adjustment factor and the second adjustment factor of the user feedback score item.

The base score corresponding to the user feedback score item may be initially set. Or on the basis of the initial set value, the basic scores corresponding to the user feedback scores are continuously optimized through the training and tuning of positive and negative feedback of the samples. The first score refers to the score of the published content under the user feedback score.

In some embodiments of the application, a scoring coefficient of a user feedback score item may be determined based on a first adjustment factor corresponding to the user feedback score item and a second adjustment factor corresponding to the user feedback score item, and then the scoring coefficient of the user feedback score item is multiplied by a base score of the user feedback score item, so as to obtain a first score of the release content under the user feedback score item.

In a specific embodiment, if the number of the user feedback scoring items is multiple, after the scores under each user feedback scoring item are respectively calculated, the scores under all the user feedback scoring items are added, so that a first score of the released content under the user feedback scoring items is obtained.

Step 250, calculating a second score of the released content under the content score item according to the first adjusting factor, the first quantity and the content characteristic of the released content of the content score item; the first number is a number of user behavior records of the plurality of user behavior records that correspond to the specified user behavior.

The content feature of the published content may be a semantic feature of the published content, a subject of the published content, a description object of the published content, and the like, and is not particularly limited herein.

In some embodiments of the present application, a second adjustment factor corresponding to the content scoring item may be determined based on the content characteristics of the published content, and then a second score of the published content under the content scoring item may be calculated based on the first adjustment factor, the first number, and the second adjustment factor corresponding to the content scoring item. For example, the scoring coefficient corresponding to the content scoring item is determined according to the first adjustment factor, the second adjustment factor and the first quantity corresponding to the content scoring item, and then the scoring coefficient corresponding to the content scoring item is multiplied by the basic score corresponding to the content scoring item to obtain a second score of the published content under the content scoring item.

In some embodiments of the present application, if the content feature is a description object of the published content, a corresponding relationship between the description object and a second adjustment factor corresponding to the score item may be pre-constructed, for example, a price of the description object is used as the second adjustment factor corresponding to the content score item. In published content (e.g., articles in shipment, videos in shipment) that is shipped for a user, a first quantity based on the published content directly represents a quantity in shipment through the published content. Of course, the above are merely exemplary examples. In other embodiments, the mapping relationship between each content feature and the second adjustment factor of the content score item may be initially set in advance, and adjustment may be performed according to actually acquired data.

In some embodiments of the present application, the third adjustment factor corresponding to the content rating item may be determined according to the first number. In some embodiments of the present application, the first number may be in a positive correlation with a third adjustment factor corresponding to the content rating item, for example, the first number is directly used as the third adjustment factor corresponding to the content rating item. In a specific embodiment, the mapping relationship between the first number and the third adjustment factor corresponding to the content score item may be set according to actual needs, and is not specifically limited herein.

In some embodiments of the present application, on the basis of determining the third adjustment factor corresponding to the content rating item, the rating coefficient corresponding to the content rating item may be determined according to the first adjustment factor, the second adjustment factor, and the third adjustment factor corresponding to the content rating item. Specifically, the result of multiplying the first adjustment factor, the second adjustment factor, and the third adjustment factor may be used as the scoring coefficient corresponding to the content scoring item. The result of adding the first adjustment factor, the second adjustment factor and the third adjustment factor may be used as the scoring coefficient corresponding to the content scoring item. The specific setting can be carried out according to actual needs.

Step 260, determining a composite score of the published content according to the first score and the second score.

The first score and the second score reflect the score of the published content in two dimensions, respectively, namely the first score is the score reflecting the published content from the perspective of user feedback, and the second score is the score reflecting the published content from the content feature dimension of the published content. The first score and the second score are fused, so that the published content can be comprehensively scored by combining two dimensions.

In a specific embodiment, the result of adding the first score and the second score may be used as the composite score of the published content. Or the average value of the first score and the second score may be the composite score of the published content.

It is worth mentioning that as time goes on, the user behavior records are continuously increased, and the user behavior sequence, the behavior density parameter of the user feedback behavior and the first number need to be correspondingly updated, and correspondingly, the comprehensive score of the published content is also correspondingly updated. That is, the composite score of the published content calculated according to the scheme is time-dependent, and reflects the aging value of the published content. Meanwhile, the comprehensive score of the published content is calculated by mainly adopting dynamic user behavior records instead of single data, different user behavior records are independent, even if wrong user behavior records are utilized in the process of calculating the comprehensive score once, the user behavior records are continuously updated, and the influence of the wrong user behavior records on the comprehensive score is weakened by the newly-added user behavior records in the long run, so that the accuracy and the effectiveness of the calculated comprehensive score can be ensured by calculating the comprehensive score of the published content by adopting the scheme.

And 270, processing the published content according to the comprehensive score of the published content.

In some embodiments of the present application, the published content may be pushed or recommended based on the composite score of the published content.

In some embodiments of the present application, step 270, comprises: acquiring a comprehensive score of each published content in a candidate push set; determining target content according to the comprehensive score of each released content in the candidate push set; and pushing the target content. The target content refers to published content screened from the candidate push set. The screened target content may be one or more. The candidate push set includes a plurality of published content.

In some embodiments, content ranking of the plurality of published contents may be performed in an order from high to low of the composite score based on the composite score of the published contents, and then a previously set number of published contents may be selected as the target content according to the content ranking. In some embodiments, a score threshold may also be set, and published content whose composite score exceeds the score threshold may be used as a target threshold. The order of pushing the plurality of target contents may be random pushing, or pushing may be performed in an order from high to low of the composite score, and is not particularly limited herein.

In some embodiments of the present application, before determining the target content, for a receiving object of content push, content screening may be performed for the first time according to user portrait characteristics of a receiving object (user) of the content, such as age, occupation, gender, tag, preference subject, location, and the like of the user, and according to user portrait characteristics of the receiving object and content characteristics (such as semantic characteristics, subject, description object, content type to which the published content belongs, and the like) of each published content, and a candidate push set corresponding to the receiving object is determined.

In some embodiments, the matching parameter between the receiving object and the published content may be calculated according to the user portrait characteristics of the receiving object and the content characteristics of the published content, for example, a similarity between a user portrait characteristic vector constructed by the user portrait characteristics and a content characteristic vector constructed based on the content characteristics is used as a matching parameter, the published content whose matching parameter meets a set requirement is screened according to the matching parameter, and the screened published content is added to a candidate push set corresponding to the receiving object. In the embodiment, the target content pushed to the receiving object is determined by combining the matching between the released content and the receiving object and the comprehensive score of the released content, so that not only is the matching between the pushed target content and the receiving object ensured, but also the quality of the pushed content is ensured, the receiving object (user) can conveniently and quickly select the content from the pushed content, the user can obtain the content with high score and high matching degree with the user without carrying out multiple interactions with the server, and the time for the user to carry out content screening is shortened.

In some embodiments of the present application, an author score for an author may also be calculated based on a number of published content published by the author. For example, a reference score is calculated from a composite score of a plurality of published contents published by the same author, and the reference score may be an average score, a specified percentile score, or the like, which is not particularly limited herein. After the author scores of the authors are calculated, author pushing can be carried out according to the author scores of the authors. Specifically, the selected push author may select the process of the target content for pushing according to the foregoing description, which is not described herein again. Of course, if the published content is a public number or a content platform account, the score corresponding to the public number or the content platform account may be calculated according to a method for calculating the score of the author, and push of the public number or the content platform account may be performed correspondingly. In some embodiments of the application, after the author score, the public number score, or the content platform account score of the author is calculated, the grades of the author, the public number, and the content platform account may be further increased according to the corresponding scores.

In the scheme of the application, the scores (namely, the first score and the second score) of the published content in two different dimensions of a content score item and a user feedback score item are calculated based on the dynamic user behavior record, and then the comprehensive score of the published content is determined by combining the scores of the two score items. On one hand, the published content is scored under two scoring items, and compared with scoring under a single dimension, such as only referring to reading amount or exposure dimension, the method ensures the reliability and accuracy of the obtained comprehensive scoring; on the other hand, the comprehensive score of the published content is calculated by combining with the dynamic user behavior records, although the comprehensive score of the published content is constrained by the user behavior records, as the user behavior records are continuously increased, the influence of each user behavior record on the comprehensive score of the published content changes along with the change of time, which is equivalent to calculating the comprehensive score of the published content by adopting a Bayesian probability superposition mode, different user behavior records have independence, and different user behavior records can be mutually attested, even if defect data exists in the process of calculating the comprehensive score, the influence of the defect data on the comprehensive score can be weakened according to the added user behavior records, so that the accuracy of the calculated comprehensive score can be ensured on the basis of the existence of the defect data. On the basis, the published content is processed according to the comprehensive score with high accuracy and high reliability, so that the reliability and the accuracy of the processing result of the published content can be ensured.

In some embodiments of the present application, as shown in fig. 3, step 240, comprises:

and 310, determining a scoring coefficient of the user feedback scoring item according to the first adjusting factor and the second adjusting factor of the user feedback scoring item.

In some embodiments of the present application, the first adjustment factor and the second adjustment factor may be multiplied to obtain a scoring coefficient of the corresponding user feedback scoring item. Or adding the first adjustment factor and the second adjustment factor to obtain the scoring coefficient of the corresponding user feedback scoring item.

And 320, calculating to obtain a first score of the published content under the user feedback scoring item according to the scoring coefficient of the user feedback scoring item and the basic score corresponding to the user feedback behavior.

In some embodiments of the present application, a result of multiplying a scoring coefficient of a user feedback item by a base score corresponding to a user feedback behavior may be used as a first score of the published content under the user feedback scoring item.

In some embodiments of the application, if the user feedback scoring items include multiple scoring coefficients, the scoring coefficients of the user feedback scoring items may be used as weighting coefficients to perform weighting calculation on the basic scores corresponding to all the user feedback behaviors, so as to obtain a first score of the published content under the user feedback scoring items.

In some embodiments of the present application, the user feedback behavior includes a sharing behavior and a content interaction behavior; the user feedback scoring items comprise a first user feedback scoring item corresponding to the sharing behavior and a second user feedback scoring item corresponding to the content interaction behavior; step 310, comprising: determining a scoring coefficient of a first user feedback scoring item according to a first adjusting factor and a second adjusting factor of the first user feedback scoring item corresponding to the sharing behavior; determining a scoring coefficient of a second user feedback scoring item according to a first adjusting factor and a second adjusting factor of the second user feedback scoring item corresponding to the content interaction behavior; in this embodiment, the step 320 includes: and according to the scoring coefficient of the first user feedback scoring item and the scoring coefficient of the second user feedback scoring item, carrying out weighted calculation on the basic score corresponding to the sharing behavior and the basic score corresponding to the content interaction behavior to obtain a first score of the published content under the user feedback scoring item.

The sharing behavior refers to a user behavior for sharing published content, such as forwarding a friend circle, forwarding to a friend, forwarding to a group, and forwarding to another content sharing platform. In some embodiments of the present application, the sharing behavior may be further classified based on different ways of content sharing (e.g., forwarding friend circles, forwarding friends, forwarding to groups).

The content interaction behavior refers to interaction behavior triggered on a content page of the published content for the published content, such as favorite, like, comment, on-watch, like, pop-up, mark, screen capture, and the like, and is not limited in particular.

In some embodiments of the present application, a result of multiplying a first adjustment factor and a second adjustment factor of a first user feedback score item corresponding to the same sharing behavior may be used as a score coefficient of the first user feedback score item. In other embodiments, the result of adding the first adjustment factor and the second adjustment factor of the first user feedback score corresponding to the same sharing behavior may be used as the score coefficient of the first user feedback score.

Similarly, the result of multiplying the first adjustment factor and the second adjustment factor of the second user feedback score item corresponding to the same content interaction behavior may be used as the score coefficient of the second user feedback score item; the result of adding the first adjustment factor and the second adjustment factor of the second user feedback score item corresponding to the same content interaction behavior can also be used as the score coefficient of the second user feedback score item. The specific setting can be carried out according to actual needs.

In some embodiments of the application, the basic scores corresponding to the sharing behaviors and the basic scores corresponding to the content interaction behaviors may be weighted and superimposed according to the scoring coefficient of the first user feedback scoring item and the scoring coefficient of the second user feedback scoring item, and a result of the weighted and superimposed may be used as the first score of the published content under the user feedback scoring item. In some embodiments of the present application, the weighting calculation may be weighted superposition or weighted average, and may be specifically set according to actual needs.

In some embodiments of the present application, as shown in fig. 4, step 230, comprises:

step 410, counting the number of user behavior records corresponding to each sharing behavior and the number of user behavior records corresponding to each content interaction behavior in the plurality of user behavior records.

And step 420, calculating to obtain a behavior density parameter for the sharing behavior according to the number of the user behavior records corresponding to the sharing behaviors and the release duration of the released content.

In an embodiment, a behavior density parameter for sharing behavior is calculated in the time dimension. The behavior density parameter reflects the exposure increment of the published content brought by the forwarding behavior.

In some embodiments of the present application, the behavior density parameter may be calculated for each sharing behavior, or the behavior density parameter of the whole may be calculated by taking all sharing behaviors as a whole.

For example, the sharing behavior may include: a-sharing to friends, B-sharing to groups, C-sharing to circle of friends, the behavior density parameter corresponding to the sharing behavior A, the behavior density parameter corresponding to the sharing behavior B, and the behavior density parameter corresponding to the sharing behavior C can be shared respectively for the sharing behaviors A, B, C. The shared behaviors a, B, C may also be used as a whole to calculate the behavior density parameter.

In some embodiments of the present application, as shown in fig. 5, step 420, comprises: step 510, obtaining sharing weights corresponding to the sharing behaviors. Step 520, performing weighted calculation according to the sharing weight corresponding to each sharing behavior and the number of the user behavior records corresponding to each sharing behavior to obtain the total sharing amount of the published content. Step 530, dividing the total sharing amount of the published content by the publishing duration of the published content to obtain a behavior density parameter for the sharing behavior.

And step 430, calculating the behavior density parameter aiming at the content interaction behavior according to the number of the user behavior records corresponding to the content interaction behaviors and the exposure of the published content.

In some embodiments of the present application, as shown in fig. 6, step 430 includes: step 610, obtaining an interaction weight corresponding to each content interaction behavior. And step 620, performing weighted calculation according to the interaction weight corresponding to each content interaction behavior and the number of user behavior records corresponding to each content interaction behavior to obtain the content interaction total amount of the published content. Step 630, the total content interaction amount of the published content is divided by the exposure amount of the published content to obtain a behavior density parameter for the content interaction behavior.

The interaction weight corresponding to each content interaction behavior can be initially set, or can be determined after adjustment on the basis of the initial setting. In the present embodiment, the behavior density parameter of the content interaction behavior is calculated under the exposure dimension of the published content.

In some embodiments of the present application, as shown in fig. 7, step 250, comprises:

step 710, determining a second adjustment factor corresponding to the content rating item according to the content feature of the released content.

In some embodiments of the present application, a mapping relationship between the content characteristics and the second adjustment factors of the content scoring items may be set, and on this basis, after the content characteristics of the published content are determined, the second adjustment factors corresponding to the content characteristics may be obtained correspondingly.

Step 720, calculating a second rating of the released content under the content rating item according to the first adjustment factor and the first number of the content rating item, the second adjustment factor corresponding to the content rating item, and the basic rating corresponding to the content rating item.

In some embodiments of the present application, as shown in fig. 8, step 720, comprises:

step 810, determining a scoring coefficient corresponding to the content scoring item according to the first quantity, the first adjustment factor of the content scoring item and the second adjustment factor of the content scoring item.

In some embodiments of the present application, a result of multiplying the first number, the first adjustment factor of the content score item, and the second adjustment factor of the content score item may be used as a scoring coefficient corresponding to the content score item.

And 820, calculating to obtain a second score of the released content under the content scoring item according to the scoring coefficient corresponding to the content scoring item and the basic scoring corresponding to the content scoring item.

In some embodiments, the scoring coefficient corresponding to the content scoring item may be multiplied by the base scoring corresponding to the content scoring item, and the multiplied result may be used as the second scoring of the published content under the content scoring item.

In some embodiments of the application, a third adjustment factor corresponding to the content score item may also be determined according to the first number, and then a sum of the first adjustment factor, the second adjustment factor, and the third adjustment factor is used as a score coefficient corresponding to the content score item. Of course, in other embodiments, the result of multiplying the third adjustment factor by the first adjustment factor and the second adjustment factor may also be used as the scoring coefficient corresponding to the content scoring item. Correspondingly, the scoring coefficient corresponding to the content scoring item is multiplied by the basic scoring of the content scoring item, and the multiplication result is used as a second scoring of the published content under the content scoring item.

The process of determining the composite score of the published content is described in detail below with reference to a specific embodiment. Table 1 below shows sharing weights corresponding to sharing behaviors and interaction weights corresponding to content interaction behaviors in a plurality of behavior records

TABLE 1

The composite score of the published content can be calculated according to the following formula:

the composite score = (number of friend circles forwarded × K1 + number of friend forwards × K2 + number of forwarding groups × K3)/time ×) first adjustment factor 1 × base score 1+ (number of review × M1 + number of praise collection times × M2 + number of collection times)/number of exposure (second adjustment factor 2 × base score 2+ (number of incoming lines + number of registration times) × first adjustment factor 3.

The term "(number of friend circles K1 + number of friend circles K2 + number of group forwarding times K3)/time" may be regarded as a first adjustment factor of the first user feedback score corresponding to the sharing behavior, that is, the behavior density parameter for the sharing behavior is used as a first adjustment factor of the first user feedback score corresponding to the sharing behavior. The "(number of comments × M1 + number of praise times × M2 + number of collections × M3)/number of exposures" may be regarded as a second adjustment factor of the second user feedback score corresponding to the content interaction behavior, that is, the behavior density parameter for the content interaction behavior is regarded as a second adjustment factor of the second user feedback score corresponding to the content interaction behavior. The "number of incoming lines + number of registrations" is a first number, which may be regarded as a second adjustment factor of the content rating item, and a third adjustment factor is determined according to the description object of the published content.

Embodiments of the apparatus of the present application are described below, which may be used to perform the methods of the above-described embodiments of the present application. For details which are not disclosed in the embodiments of the apparatus of the present application, reference is made to the above-described embodiments of the method of the present application.

Fig. 9 is a block diagram illustrating a content processing apparatus according to an embodiment, the content processing apparatus including, as illustrated in fig. 9: a user behavior record obtaining module 910, configured to obtain multiple user behavior records for published content, where the user behavior records indicate user behaviors triggered by the published content and trigger times of the user behaviors; the user behavior comprises a designated user behavior and a user feedback behavior; a user behavior sequence determining module 920, configured to arrange the user behaviors in the multiple user behavior records according to a sequence that trigger time is from first to last to obtain a user behavior sequence; the user behavior sequence is used for determining a first adjusting factor of a content scoring item corresponding to the specified user behavior and a first adjusting factor of a user feedback scoring item corresponding to the user feedback behavior; a behavior density parameter determining module 930, configured to calculate, according to the multiple user behavior records, a behavior density parameter corresponding to the user feedback behavior; the behavior density parameter is used for determining a second adjustment factor of the user feedback score item corresponding to the user feedback behavior; a first score calculating module 940, configured to calculate a first score of the published content under the user feedback score according to a base score corresponding to the user feedback score, a first adjustment factor of the user feedback score, and a second adjustment factor of the user feedback score; and a second score calculating module 950, configured to calculate a second score of the published content under the content score item according to the first adjustment factor of the content score item, the first number, and the content feature of the published content; the first number is a number of user behavior records of the plurality of user behavior records that correspond to the specified user behavior; a composite score calculating module 960, configured to determine a composite score of the published content according to the first score and the second score; the processing module 970 is configured to process the published content according to the comprehensive score of the published content.

In some embodiments of the present application, the first score calculating module 940 includes: and the first scoring coefficient determining unit is used for determining the scoring coefficient of the user feedback scoring item according to the first adjusting factor and the second adjusting factor of the user feedback scoring item. And the first score determining unit is used for calculating to obtain a first score of the published content under the user feedback score according to the score coefficient of the user feedback score and the basic score corresponding to the user feedback behavior.

In some embodiments of the present application, the user feedback behavior includes a sharing behavior and a content interaction behavior; the user feedback scoring items comprise a first user feedback scoring item corresponding to the sharing behavior and a second user feedback scoring item corresponding to the content interaction behavior; in this embodiment, the first scoring coefficient determining unit includes: the first coefficient determining unit is used for determining a scoring coefficient of a first user feedback scoring item according to a first adjusting factor and a second adjusting factor of the first user feedback scoring item corresponding to the sharing behavior; the second coefficient determining unit is used for determining the scoring coefficient of the second user feedback scoring item according to the first adjusting factor and the second adjusting factor of the second user feedback scoring item corresponding to the content interaction behavior; in this embodiment, the first score determining unit is configured to: and according to the scoring coefficient of the first user feedback scoring item and the scoring coefficient of the second user feedback scoring item, performing weighted calculation on the basic score corresponding to the sharing behavior and the basic score corresponding to the content interaction behavior to obtain a first score of the published content under the user feedback scoring item.

In some embodiments of the present application, the behavior density parameter determination module 930 comprises: the statistical unit is used for counting the number of user behavior records corresponding to each sharing behavior in the user behavior records and the number of user behavior records corresponding to each content interaction behavior; the first behavior density parameter determining unit is used for calculating behavior density parameters aiming at the sharing behaviors according to the number of user behavior records corresponding to the sharing behaviors and the release duration of the released content; and the second behavior density parameter determining unit is used for calculating the behavior density parameters aiming at the content interaction behaviors according to the number of user behavior records corresponding to the content interaction behaviors and the exposure of the published content.

In some embodiments of the present application, the second adjustment factor of the user feedback score is positively correlated with the corresponding behavior density parameter.

In some embodiments of the present application, the first behavior density parameter determination unit includes: the sharing weight acquiring unit is used for acquiring sharing weights corresponding to the sharing behaviors; the sharing total amount determining unit is used for performing weighting calculation according to the sharing weight corresponding to each sharing behavior and the number of user behavior records corresponding to each sharing behavior to obtain the sharing total amount of the published content; and the first density determining unit is used for dividing the sharing total amount of the published content with the publishing duration of the published content to obtain a behavior density parameter aiming at the sharing behavior.

In some embodiments of the present application, the second behavior density parameter determination unit includes: the interactive weight acquisition unit is used for acquiring interactive weights corresponding to the interactive behaviors of the contents; the content interaction total amount determining unit is used for performing weighted calculation according to the interaction weight corresponding to each content interaction behavior and the number of user behavior records corresponding to each content interaction behavior to obtain the content interaction total amount of the published content; and the second density determining unit is used for dividing the content interaction total amount of the published content with the exposure of the published content to obtain a behavior density parameter aiming at the content interaction behavior.

In some embodiments of the present application, the second score calculating module 950 includes: a second adjustment factor determining unit, configured to determine, according to content features of the published content, a second adjustment factor corresponding to the content score item; and the second score determining unit is used for calculating a second score of the released content under the content scoring item according to the first adjusting factor and the first number of the content scoring items, the second adjusting factor corresponding to the content scoring item and the basic score corresponding to the content scoring item.

In some embodiments of the present application, the second score determining unit comprises: a third coefficient determining unit, configured to determine, according to the first number, the first adjustment factor of the content rating item, and the second adjustment factor of the content rating item, a rating coefficient corresponding to the content rating item; and the second score calculating unit is used for calculating and obtaining a second score of the released content under the content scoring item according to the scoring coefficient corresponding to the content scoring item and the basic score corresponding to the content scoring item.

In some embodiments of the present application, the processing module 970 includes: the comprehensive score obtaining unit is used for obtaining the comprehensive score of each published content in the candidate push set; the target content determining unit is used for determining target content according to the comprehensive score of each released content in the candidate push set; and the pushing unit is used for pushing the target content.

It should be noted that the computer system 1000 of the electronic device shown in fig. 10 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 10, the computer system 1000 includes a Central Processing Unit (CPU) 1001 that can perform various appropriate actions and processes, such as performing the methods in the above-described embodiments, according to a program stored in a Read-Only Memory (ROM) 1002 or a program loaded from a storage portion 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data necessary for system operation are also stored. The CPU1001, ROM1002, and RAM 1003 are connected to each other via a bus 1004. An Input/Output (I/O) interface 1005 is also connected to the bus 1004.

The following components are connected to the I/O interface 1005: an input portion 1006 including a keyboard, a mouse, and the like; an output section 1007 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage portion 1008 including a hard disk and the like; and a communication section 1009 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 1009 performs communication processing via a network such as the internet. The driver 1010 is also connected to the I/O interface 1005 as necessary. A removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1010 as necessary, so that a computer program read out therefrom is mounted into the storage section 1008 as necessary.

In particular, according to embodiments of the present application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication part 1009 and/or installed from the removable medium 1011. When the computer program is executed by a Central Processing Unit (CPU) 1001, various functions defined in the system of the present application are executed.

It should be noted that the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

As another aspect, the present application also provides a computer-readable storage medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable storage medium carries computer readable instructions which, when executed by a processor, implement the method of any of the embodiments described above.

According to an aspect of the present application, there is also provided an electronic device, including: a processor; a memory having computer readable instructions stored thereon which, when executed by the processor, implement the method of any of the above embodiments.

According to an aspect of an embodiment of the present application, there is provided a computer program product or a computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, so that the computer device executes the method in any of the above embodiments.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains.

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

Claims

1. A method of content processing, comprising:

obtaining a plurality of user behavior records for published content, the user behavior records indicating user behaviors triggered for the published content and trigger times for the user behaviors; the user behavior comprises a designated user behavior and a user feedback behavior, and the designated user behavior comprises at least one of a user registration behavior and a user incoming line behavior; wherein the user incoming behavior comprises at least one of a behavior of private chat with an author of the published content and a behavior of entering a link in the published content;

arranging the user behaviors in the user behavior records according to the sequence of the trigger time from first to last to obtain a user behavior sequence; the user behavior sequence is used for determining a first adjustment factor of a content scoring item corresponding to the specified user behavior and a first adjustment factor of a user feedback scoring item corresponding to the user feedback behavior;

according to the user behavior records, behavior density parameters corresponding to user feedback behaviors are calculated; the behavior density parameter is used for determining a second adjustment factor of the user feedback score item corresponding to the user feedback behavior;

calculating a first score of the published content under the user feedback score according to a basic score corresponding to the user feedback score, a first adjustment factor and a second adjustment factor of the user feedback score;

calculating a second score of the published content under the content score item according to the first adjusting factor, the first quantity and the content characteristics of the published content of the content score item; the first number is a number of user behavior records of the plurality of user behavior records that correspond to the specified user behavior;

determining a composite score of the published content according to the first score and the second score;

and processing the published content according to the comprehensive score of the published content.

2. The method of claim 1, wherein the calculating a first score of the published content under the user feedback score according to the base score corresponding to the user feedback score and a first adjustment factor and a second adjustment factor of the user feedback score comprises:

determining a scoring coefficient of the user feedback scoring item according to the first adjusting factor and the second adjusting factor of the user feedback scoring item;

and calculating to obtain a first score of the published content under the user feedback scoring item according to the scoring coefficient of the user feedback scoring item and the basic score corresponding to the user feedback behavior.

3. The method of claim 2, wherein the user feedback behavior comprises a sharing behavior and a content interaction behavior; the user feedback scoring items comprise a first user feedback scoring item corresponding to the sharing behavior and a second user feedback scoring item corresponding to the content interaction behavior;

the determining the scoring coefficient of the user feedback scoring item according to the first adjusting factor and the second adjusting factor of the user feedback scoring item comprises:

determining a scoring coefficient of a first user feedback scoring item according to a first adjusting factor and a second adjusting factor of the first user feedback scoring item corresponding to the sharing behavior;

determining a scoring coefficient of a second user feedback scoring item according to a first adjusting factor and a second adjusting factor of the second user feedback scoring item corresponding to the content interaction behavior;

the calculating to obtain a first score of the published content under the user feedback score according to the score coefficient of the user feedback score and the basic score corresponding to the user feedback behavior comprises:

and according to the scoring coefficient of the first user feedback scoring item and the scoring coefficient of the second user feedback scoring item, performing weighted calculation on the basic score corresponding to the sharing behavior and the basic score corresponding to the content interaction behavior to obtain a first score of the published content under the user feedback scoring item.

4. The method according to claim 3, wherein calculating the behavior density parameter corresponding to the user feedback behavior according to the plurality of user behavior records comprises:

counting the number of user behavior records corresponding to each sharing behavior and the number of user behavior records corresponding to each content interaction behavior in the plurality of user behavior records;

calculating to obtain a behavior density parameter aiming at the sharing behavior according to the number of user behavior records corresponding to the sharing behaviors and the release duration of the released content; and

and calculating the behavior density parameters aiming at the content interaction behaviors according to the number of user behavior records corresponding to the content interaction behaviors and the exposure of the published content.

5. The method according to any one of claims 1 to 4, wherein the second adjustment factor of the user feedback score is positively correlated to the corresponding behavior density parameter.

6. The method according to claim 4, wherein the calculating a behavior density parameter for the sharing behavior according to the number of the user behavior records corresponding to the sharing behaviors and the release duration of the released content includes:

obtaining sharing weight corresponding to each sharing behavior;

performing weighted calculation according to the sharing weight corresponding to each sharing behavior and the number of user behavior records corresponding to each sharing behavior to obtain the total sharing amount of the published content;

and dividing the sharing total amount of the published content by the publishing duration of the published content to obtain a behavior density parameter aiming at the sharing behavior.

7. The method according to claim 4, wherein the calculating a behavior density parameter for the content interaction behaviors according to the number of user behavior records corresponding to the content interaction behaviors and the exposure of the published content comprises:

acquiring interaction weight corresponding to each content interaction behavior;

performing weighted calculation according to the interaction weight corresponding to each content interaction behavior and the number of user behavior records corresponding to each content interaction behavior to obtain the content interaction total amount of the published content;

and dividing the content interaction total amount of the published content with the exposure of the published content to obtain a behavior density parameter aiming at the content interaction behavior.

8. The method of claim 1, wherein calculating the second rating of the published content under the content rating based on the first adjustment factor of the content rating item, the first number, and the content characteristic of the published content comprises:

determining a second adjustment factor corresponding to the content rating item according to the content characteristics of the released content;

and calculating a second score of the released content under the content scoring item according to the first adjusting factor and the first number of the content scoring items, the second adjusting factor corresponding to the content scoring item and the basic scoring corresponding to the content scoring item.

9. The method of claim 8, wherein the calculating a second rating of the published content under the content rating item according to the first adjustment factor and the first number of the content rating items, the second adjustment factor corresponding to the content rating items, and the base rating corresponding to the content rating items comprises:

determining a scoring coefficient corresponding to the content scoring item according to the first quantity, the first adjustment factor of the content scoring item and the second adjustment factor of the content scoring item;

and calculating to obtain a second score of the released content under the content scoring item according to the scoring coefficient corresponding to the content scoring item and the basic score corresponding to the content scoring item.

10. The method according to claim 1, wherein the processing the published content according to the composite score of the published content comprises:

acquiring a comprehensive score of each published content in the candidate push set;

determining target content according to the comprehensive score of each released content in the candidate push set;

and pushing the target content.

11. A content processing apparatus characterized by comprising:

a user behavior record obtaining module, configured to obtain a plurality of user behavior records for published content, where the user behavior records indicate user behaviors triggered by the published content and trigger times of the user behaviors; the user behavior comprises a designated user behavior and a user feedback behavior; wherein the user incoming behavior comprises at least one of a behavior of private chat with an author of the published content and a behavior of entering a link in the published content;

the user behavior sequence determining module is used for arranging the user behaviors in the user behavior records according to the sequence of the trigger time from first to last to obtain a user behavior sequence; the user behavior sequence is used for determining a first adjustment factor of a content scoring item corresponding to the specified user behavior and a first adjustment factor of a user feedback scoring item corresponding to the user feedback behavior;

the behavior density parameter determining module is used for calculating behavior density parameters corresponding to the user feedback behaviors according to the user behavior records; the behavior density parameter is used for determining a second adjustment factor of the user feedback score item corresponding to the user feedback behavior;

the first score calculating module is used for calculating a first score of the released content under the user feedback score according to a basic score corresponding to the user feedback score, a first adjusting factor and a second adjusting factor of the user feedback score; and

the second score calculating module is used for calculating a second score of the released content under the content score item according to the first adjusting factor, the first quantity and the content characteristics of the released content of the content score item; the first number is a number of user behavior records of the plurality of user behavior records that correspond to the specified user behavior;

the comprehensive score calculating module is used for determining the comprehensive score of the published content according to the first score and the second score;

and the processing module is used for processing the published content according to the comprehensive score of the published content.

12. An electronic device, comprising:

a processor;

a memory having computer-readable instructions stored thereon which, when executed by the processor, implement the method of any one of claims 1-10.

13. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the method of any one of claims 1-10.