CN112153426A - Content account management method and device, computer equipment and storage medium - Google Patents

Content account management method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN112153426A
CN112153426A CN202010993062.2A CN202010993062A CN112153426A CN 112153426 A CN112153426 A CN 112153426A CN 202010993062 A CN202010993062 A CN 202010993062A CN 112153426 A CN112153426 A CN 112153426A
Authority
CN
China
Prior art keywords
content
account
target user
user account
historical
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010993062.2A
Other languages
Chinese (zh)
Other versions
CN112153426B (en
Inventor
刘刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN202010993062.2A priority Critical patent/CN112153426B/en
Publication of CN112153426A publication Critical patent/CN112153426A/en
Application granted granted Critical
Publication of CN112153426B publication Critical patent/CN112153426B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H04N21/25866—Management of end-user data
    • H04N21/25891—Management of end-user data being end-user preferences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/252—Processing of multiple end-users' preferences to derive collaborative data
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The embodiment of the application discloses a content account management method, a content account management device, computer equipment and a storage medium, and can acquire historical content issued by a target user account in a client; at least acquiring account activity, field concentration and content quality of the target user account based on the historical content; and fusing the account number activity, the field concentration and the content quality to determine the account number grade of the target user account number. The efficiency and the accuracy of determining the account number grade are improved.

Description

Content account management method and device, computer equipment and storage medium
Technical Field
The application relates to the technical field of data processing, in particular to a content account management method and device, computer equipment and a storage medium.
Background
Currently, in order to screen and protect premium user accounts, such as self-media accounts for original works, on one hand, the author signs an original promise with a platform for content distribution, and feedback information is collected by platform reports and complaints from copyright owners or interest-related parties, and non-premium user accounts are discovered by platform verification. On the other hand, the level of the user account is usually set manually by an operator according to the popularity of the user account in the industry, the performance of the user account on other platforms and the personal experience of the operator, and the level of the user account is updated manually at regular intervals.
Because the grade of the user account needs to be set manually, the method is influenced by subjective factors of people, the accuracy of setting the grade of the user account is low, and the method faces mass user accounts, the manual processing efficiency is low, the updating period of the grade of the user account is slow, and the growth of potential user accounts can be hindered.
Disclosure of Invention
The embodiment of the application provides a content account management method and device, a computer device and a storage medium, which can improve the efficiency and accuracy of account level determination.
In order to solve the above technical problem, an embodiment of the present application provides the following technical solutions:
the embodiment of the application provides a content account management method, which comprises the following steps:
acquiring historical content issued by a target user account in a client;
at least acquiring account activity, field concentration and content quality of the target user account based on the historical content;
and fusing the account number activity, the field concentration and the content quality to determine the account number grade of the target user account number.
According to an aspect of the present application, there is also provided a content account management apparatus, including:
the first acquisition unit is used for acquiring historical content issued by a target user account in the client;
a second obtaining unit, configured to obtain at least account liveness, domain concentration, and content quality of the target user account based on the historical content;
and the fusion unit is used for fusing the account number activity, the field concentration and the content quality to determine the account number grade of the target user account number.
According to an aspect of the present application, there is also provided a computer device, including a processor and a memory, where the memory stores a computer program, and the processor executes any one of the content account management methods provided in the embodiments of the present application when calling the computer program in the memory.
According to an aspect of the present application, a storage medium is further provided, where the storage medium is used to store a computer program, and the computer program is loaded by a processor to perform the steps in any content account management method provided in the embodiments of the present application.
According to the method and the device for determining the account level of the target user account, the historical content issued by the target user account in the client can be obtained, then at least the account activity, the field concentration and the content quality of the target user account can be obtained based on the historical content, and the account activity, the field concentration and the content quality are fused to determine the account level of the target user account. Therefore, the account level can be automatically and quickly determined without manually determining the account level, and the efficiency and the accuracy of determining the account level are improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a content account management system according to an embodiment of the present application;
fig. 2 is a flowchart illustrating a content account management method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a content listing display provided by an embodiment of the present application;
fig. 4 is a schematic diagram of a cluster server architecture provided in an embodiment of the present application;
fig. 5 is another schematic flow chart of a content account management method according to an embodiment of the present application;
fig. 6 is another schematic flow chart of a content account management method according to an embodiment of the present application;
fig. 7 is another schematic flow chart of a content account management method according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of a content account management apparatus according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.
The embodiment of the application provides a content account management method and device, computer equipment and a storage medium.
Referring to fig. 1, fig. 1 is a schematic view of a scenario of a content account management system according to an embodiment of the present disclosure, where the content delivery system may include a content account management device, the content account management device may be specifically integrated in a server 10, the server 10 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server that provides basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, big data, and an artificial intelligence platform, but is not limited thereto.
The server 10 may be configured to obtain historical content issued by a target user account in the client, then obtain at least an account activity, a field concentration, and a content quality of the target user account based on the historical content, and fuse the account activity, the field concentration, and the content quality to accurately and quickly determine an account level of the target user account. When the content needs to be published, the content to be published can be accurately published in time according to the account number level, for example, the server 10 can push the content to be published to a terminal 20 establishing communication connection with the server 10, and the terminal can be a mobile phone, a tablet computer, a notebook computer, a desktop computer, a wearable device, an intelligent television or the like. The terminal 20 may be configured to display the content to be published for viewing by the user.
The terminal 20 may include a first terminal, a second terminal, and the like, when the first terminal is used as a production end for producing content, and the second terminal is used as a consumption end for displaying content, a first client may be set on the first terminal, and a second client may be set on the second terminal, when content needs to be published, a first user account corresponding to the first client may generate content to be published, and upload the content to be published to the server 10, the server 10 may obtain an account level of the first user account, and publish the content to be published to the second client according to the account level of the first user account, for example, the content to be published has a high account level, and the second client may display the content to be published.
It should be noted that the scene schematic diagram of the content account management system shown in fig. 1 is merely an example, and the content account management system and the scene described in the embodiment of the present application are for more clearly illustrating the technical solution of the embodiment of the present application, and do not form a limitation on the technical solution provided in the embodiment of the present application.
The following are detailed below. It should be noted that the following description of the embodiments is not intended to limit the preferred order of the embodiments.
The content account management method provided by the embodiment of the application relates to technologies such as a machine learning technology in artificial intelligence, and the artificial intelligence technology and the machine learning technology are explained first below.
Artificial intelligence is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.
The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. Artificial intelligence infrastructures generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operating/interactive systems, and mechatronics. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
Machine Learning (ML) is a multi-domain cross discipline, involving multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and formal learning.
In this embodiment, a description will be given from the perspective of a content account management apparatus, which may be specifically integrated in a single server or a server cluster.
Referring to fig. 2, fig. 2 is a flowchart illustrating a content account management method according to an embodiment of the present application. The content account management method may include:
s101, obtaining historical content issued by a target user account in a client.
The client may be integrated on a terminal such as a mobile phone or a computer in the form of an application program, and the target user account may be a certain self-media account that the user applies for registration through the client on the terminal. The historical content may be generated by the target user account and may include content pushed to the client on each terminal through the server, and the historical content may include at least one of video, audio, text and pictures that have been published through the target user account, where the text may include a text of the content, a title of the content, a summary of the content, and the like, and the historical content may further include information of a publication author, a publication time, and the like.
It should be noted that the time for obtaining the history content may be flexibly set according to actual needs, for example, the history content issued by the target user account in the client may be obtained from a preset database in which the history content is pre-stored at preset time intervals (for example, every month) or at regular time intervals (for example, every 1 day of january, every 2 days of 2 months, and every 3 days of march, etc.); for another example, when an update instruction of the account level is received, historical content issued by a target user account in the client is acquired from a preset database in which historical content is stored in advance; for another example, when receiving content to be published sent by a target user account, obtaining historical content published by the target user account in a client from a preset database in which historical content is stored in advance; and so on.
In some embodiments, obtaining the published history content of the target user account in the client may include: acquiring a plurality of candidate contents issued by a target user account in a client according to a preset time period; and screening out the historical contents issued by the target user account based on the similarity among the candidate contents.
In order to avoid analyzing the repeatedly issued historical content of the target user account, the accuracy of determining the account level of the target user account is improved, and the repeatedly issued historical content can be screened. For example, a plurality of candidate contents issued by the target user account in the client may be acquired according to a preset time period, and the preset time period may be flexibly set according to actual needs, for example, the preset time period may be one month. Then, the similarity between the candidate contents may be counted, wherein the higher the similarity between two candidate contents is, the higher the possibility of the duplication between the two candidate contents is, and conversely, the lower the similarity between the two candidate contents is, the lower the possibility of the duplication between the two candidate contents is. At this time, the history content released by the target user account may be obtained by screening out two candidate contents with the similarity smaller than or equal to the preset threshold for reservation, and reserving only one of the two candidate contents with the similarity larger than the preset threshold. The preset threshold value can be flexibly set according to actual needs, and specific values are not limited here.
In some embodiments, screening out the historical content published by the target user account based on the similarity between the candidate contents may include: vectorizing at least one of the title, the cover picture, the content text, the video fingerprint and the audio fingerprint of the candidate contents to obtain vector data corresponding to at least one of the title, the cover picture, the content text, the video fingerprint and the audio fingerprint; determining the similarity between every two candidate contents according to at least one corresponding vector data in the title, the cover picture, the content text, the video fingerprint and the audio fingerprint; and removing one of the two candidate contents with the similarity larger than a preset threshold value to obtain the released historical content of the target user account.
In order to improve the accuracy and reliability of screening the historical content published by the target user account, at least one of title, cover page, content text, video and audio contained in the historical content may be subjected to deduplication processing. Specifically, when the history content contains video and audio, a video fingerprint may be generated based on the video, and an audio fingerprint may be generated based on the audio, and then vectorization processing may be performed on at least one of a title, a jacket photograph, a content body text, the video fingerprint, and the audio fingerprint in the plurality of candidate contents, to obtain vector data corresponding to at least one of the title, the jacket photograph, the content body text, the video fingerprint, and the audio fingerprint. For example, a simhash algorithm and a bert (bidirectional Encoder retrieval from transforms) algorithm may be used to obtain vector data corresponding to at least one of a title, a cover picture, and a content body, construct vector data based on at least one of a video fingerprint and an audio fingerprint, calculate distances between the vector data of different historical contents, which may include euclidean distances or hamming distances, for example, and determine similarities between different historical contents based on the distances.
The greater the distance between the two historical contents, the greater the similarity between the two historical contents, the greater the possibility of duplication between the two historical contents, and conversely, the smaller the distance between the two historical contents, the smaller the similarity between the two historical contents, and the smaller the similarity between the two historical contents, the less the possibility of duplication between the two historical contents.
At this time, the similarity between each two candidate contents may be determined according to vector data corresponding to at least one of the title, the jacket photograph, the text of the content, the video fingerprint, and the audio fingerprint. When the multi-class information in the historical content needs to be subjected to duplicate removal, the distance corresponding to each class of information can be obtained through calculation based on the vector data of the multi-class information, then the distance corresponding to each class of information is subjected to weighted summation operation to obtain the total distance, and the similarity between different historical contents is measured by utilizing the total distance. And removing one of the two candidate contents with the similarity greater than a preset threshold (the preset threshold can be flexibly set according to actual needs), reserving the historical content with the similarity less than or equal to the preset threshold, and reserving one of the two candidate contents with the similarity greater than the preset threshold, so as to obtain the historical content issued by the target user account. At least one of title deduplication, jacket picture deduplication, content text deduplication, video deduplication and audio deduplication is achieved.
S102, at least the account activity, the field concentration and the content quality of the target user account are obtained based on the historical content.
The account liveness can be represented by the frequency of issuing contents by the target user account, the higher the frequency of issuing the contents is, the higher the account liveness is, and otherwise, the lower the frequency of issuing the contents is, the lower the account liveness is.
The domain attentiveness can be represented by a domain category to which the content issued by the target user account belongs, where the domain category may include finance, sports, science and technology, entertainment, and society, and the more a certain domain category to which the content issued by the target user account belongs, the higher the domain attentiveness of the target user account in the certain domain category is indicated, and conversely, the less a certain domain category to which the content issued by the target user account belongs, the lower the domain attentiveness of the target user account in the certain domain category is indicated.
The content quality may be characterized based on the browsing times, the like number, the comment number (which may be a forward and neutral comment number), and the total number of interactions (for example, forwarding, sharing, or collecting) of the user on the content, where the higher the browsing times, the like number, the comment number, and the total number of interactions, the higher the content quality is, and the lower the browsing times, the like number, the comment number, and the total number of interactions, the lower the content quality is. The content quality can be determined by weighted summation of browsing times, praise number, comment number and total number of interactions.
In some embodiments, obtaining the account liveness of the target user account based on the historical content may include: at least acquiring time parameters and content quantity of historical content release; and determining the account activity of the target user account according to the time parameter and the content quantity.
The time parameter may include a period of content distribution, such as the number of days or weeks of content distribution, and the time parameter may further include the number of days between content distributions. The time parameter, the content quantity and the like correspondingly issued by the acquired historical content can be counted, so that the account activity of the target user account can be accurately determined according to the time parameter and the content quantity.
In some embodiments, determining the account liveness of the target user account according to the time parameter and the content amount may include: acquiring a smoothing coefficient of every two days and a control parameter of content release; and determining the account number activity of the target user account number according to the smoothing coefficient, the control parameter, the time parameter and the content quantity.
In order to improve the accuracy and reliability of account activity determination, the account activity of the target user account may be determined based on a smoothing coefficient, a control parameter, a time parameter, a content quantity, and the like, and may specifically be represented by the following formula (1):
Figure BDA0002691600410000081
wherein HiIndicates the account activity, W, of the ith target user accountiThe period of content release of the ith target user account within a preset time period (for example, a month is close) is represented, that is, the period of a message, the message may refer to the release content, and the period of the message may be the number of weeks or days of the message, and the like.
publishkAnd the content quantity (also called the number of rowkeys, which is the unique identifier of the content of the text, namely the space of the text of the k-th day) of the k-th day of the ith target user account is represented.
t0-tkIndicating the number of days between the day and the k-th day.
Alpha represents a control parameter of a period of a message, beta represents a control parameter of a single-day message, and x represents a control parameter of active performance of the message within a preset time period (for example, the whole month).
η1Representing the smoothing coefficient, η1The value of (2) can be flexibly set according to actual needs, for example, eta can be set1＝10.0。
In some embodiments, obtaining the domain concentration of the target user account based on the historical content may include: acquiring the domain types which are sent by the target user account and most started in a preset time period based on historical content; counting the number of messages and the number of messages which are started and correspond to the field type; and setting the ratio of the number of the texts to the number of the texts and the number of the invoices as the field concentration degree of the target user account.
The issuing and enabling can refer to the issued content which meets the content quality standard which can be issued and passes the auditing (including automatic auditing or manual auditing of the server). To improve the accuracy of the domain attentiveness determination, the domain attentiveness of the target user account may be determined based on the number of utterances and activations corresponding to the most activated domain categories. For example, the target user account sends and enables the most domain categories (such as finance, sports, science and technology, entertainment and the like) within a preset time period (the preset time period can be flexibly set according to actual needs, for example, the last month) based on historical content. Then, the number of the messages and the enabling messages corresponding to the field category are counted. At this time, the ratio of the number of texts to the number of texts and enabling may be set as the domain concentration degree of the target user account, that is, the domain concentration degree is the number of texts/number of texts and enabling.
In some embodiments, obtaining the content quality of the target user account based on the historical content may include: acquiring feedback data of historical content, wherein the feedback data comprises browsing times and total interaction number; and determining the content quality of the target user account according to the feedback data of the historical content.
The feedback data may include at least one of browsing times, total number of interactions, total number of praise and comment numbers, the comment numbers include forward and neutral comment numbers, and the total number of interactions includes total number of interactions such as forwarding, sharing and collecting. Under the same exposure stage, the performance of the praise, comment and the like of the content with good quality is better, that is, the praise rate or comment rate of the content with good quality is higher, so that feedback data corresponding to the acquired historical content, such as browsing times, praise number, comment number, total number of interactions and the like, can be counted, and the content quality of the target user account can be accurately determined based on the feedback data such as browsing times, praise number, comment number, total number of interactions and the like. It should be noted that, in order to improve the accuracy of content quality determination, the published and enabled historical content (i.e., the checked content) may be screened from the obtained historical content, and the content quality of the target user account may be determined based on the number of times of browsing, the number of praise, the number of comments, the total number of interactions, and the like of the published and enabled historical content.
In some embodiments, determining the content quality of the target user account from the feedback data of the historical content may include: acquiring a first smoothing coefficient of browsing times and a second smoothing coefficient of interaction total; and determining the content quality of the target user account according to the first smoothing coefficient, the second smoothing coefficient and the feedback data.
In order to improve the accuracy of content quality determination, the content quality of the target user account may be determined based on feedback data such as smooth coefficient browsing times, praise numbers, comment numbers, and total number of interactions, which may be specifically represented by the following formula (2):
Figure BDA0002691600410000091
wherein Q isiIndicating the content quality of the ith target user account.
pvkIndicating the number of views on day k.
zanCntkIndicating the number of praise on day k.
cmtCntkNumber of reviews for day k is indicated, including forward and neutral reviews.
Cnt denotes the total number of interactions for forwarding, sharing, and collecting, etc.
The value of the first smoothing coefficient indicating the browsing times may be flexibly set according to actual needs, for example, may be set to 1.0.
η2A second smoothing coefficient, η, representing the total number of interactions2The value of (2) can be flexibly set according to actual needs, for example, eta can be set2＝10.0。
d represents a constant, and the value of d can be flexibly set according to actual needs, for example, d can be set to 3.
S103, fusing account number activity, field concentration and content quality to determine the account number level of the target user account number.
After the account activity, the field concentration and the content quality of the target user account are obtained, the account activity, the field concentration and the content quality can be fused to determine the account level of the target user account, so that the change conditions of the account activity, the field concentration and the content quality can be fed back timely on the account level. The higher the account number level of the target user account number is, the higher the quality of the target user account number is, and on the contrary, the lower the account number level of the target user account number is, the lower the quality of the target user account number is.
For example, account liveness, domain concentration, and content quality of the target user account may be weighted and summed to obtain an account rating of the target user account. For another example, the account activity, the field concentration and the content quality of the target user account can be averaged to obtain the account level of the target user account; and so on.
In some embodiments, fusing the account liveness, the domain concentration, and the content quality to determine the account level of the target user account specifically includes: the popularity of the target user account is also acquired; and fusing the popularity, the account activity, the field concentration and the content quality to determine the account level of the target user account.
The popularity can be represented by the total number of fans, the larger the total number of fans of the target user account is, the more popular the target user account is, and on the contrary, the smaller the total number of fans of the target user account is, the less popular the target user account is. In some embodiments, obtaining the popularity of the target user account may include: and acquiring the fan total amount of the target user account, determining the popularity of the target user account based on the fan total amount, wherein the fan total amount of the target user account and the popularity of the target user account are in a direct proportional relation. At this time, the popularity, the account activity, the domain concentration and the content quality can be fused to determine the account level of the target user account. For example, the popularity, the account liveness, the domain concentration, and the content quality of the target user account may be weighted and summed, or averaged, etc. to obtain the account rating of the target user account.
In some implementations, fusing the popularity, account liveness, domain concentration, and content quality to determine the account rating of the target user account may include: obtaining respective corresponding weight values of popularity, account number activity, field concentration and content quality; and fusing the popularity, the account activity, the field concentration, the content quality and the corresponding weight value to determine the account level of the target user account.
The weighting values may include a first weighting value, a second weighting value, a third weighting value, a fourth weighting value, and the like, and in order to improve accuracy and reliability of determination of the account number level of the target user account number, the first weighting value corresponding to popularity, the second weighting value corresponding to account number activity, the third weighting value corresponding to field concentration, and the fourth weighting value corresponding to content quality may be acquired. Then, the popularity, the account activity, the field concentration, the content quality and the weight value corresponding thereto may be fused to determine the account level of the target user account, which may be specifically represented by the following formula (3):
Figure BDA0002691600410000111
wherein S isiIndicating the account rating of the ith target user account.
AiIndicating the popularity of the ith target user account.
HiAnd the account activity of the ith target user account is represented.
ZiRepresenting the domain concentration of the ith target user account.
QiIndicating the content quality of the ith target user account.
a1、a2、a3And a4Are all constants, a1、a2、a3And a4The value can be flexibly set according to actual needs, for example, a can be set1＝1，a2＝0.0000001，a3＝0.0001，a4＝0.000001。
b1First weight value representing popularity, b2Second weight value representing account number activity, b3Third weight value representing degree of area concentration, b4Fourth weight value representing content quality, b1、b2、b3And b4Can be flexibly set according to actual needs, for example, b can be set1＝0.5，b2＝1，b3＝1，b4＝2。
In some embodiments, after the account number level is obtained, whether the account number level of the target user account number is greater than a preset threshold value or not may be determined, and when the account number level of the target user account number is greater than the preset level threshold value, it is determined that the target user account number is a high-quality account number, and at this time, the high-quality account number may be supported (such as subsidy), where the preset level threshold value may be flexibly set according to actual needs.
In some embodiments, after obtaining the account rating, the account rating may be displayed in a display interface after the target user account logs in, or the account rating and the like may be displayed in an information viewing interface for the user to view.
In some embodiments, after the account number level is obtained, if the content needs to be published, the content to be published may be published according to the account number level. Specifically, when the target user account needs to publish the content, the content to be published may be published according to the account level of the target user account, for example, if the account level of the target user account is higher, the content to be published corresponding to the target user account is preferentially recommended to a client corresponding to a consumption terminal (e.g., a mobile phone or a computer) for display; and if the account number level of the target user account number is lower, recommending the content to be issued corresponding to the target user account number to a client corresponding to the consumption end for displaying the content later.
In some embodiments, after determining the account level of the target user account, the content account management method may further include: when a plurality of target user accounts need to release content, generating a release sequence of the content to be released of each target user account based on the sequence of the account grades of the plurality of target user accounts from high to low; and issuing the contents to be issued of each target user account according to the issuing sequence.
For example, when a plurality of target user accounts need to release content, the account level of each target user account may be obtained, then the account levels of each target user account are sorted from high to low to obtain a release order of the content to be released of each target user account, at this time, the content to be released of each target user account may be released according to the release order, that is, the content to be released corresponding to the target user account with a high account level is preferentially released. As shown in fig. 3, a client corresponding to a consumer terminal (e.g., a mobile phone or a computer, etc.) may receive contents issued by each target user account (which may be simply referred to as a user account), and sequentially display the issued contents according to the order from high to low of the account levels of the target user accounts, that is, preferentially display the contents issued by the target user accounts with high account levels. For example, in fig. 3, the account level of user account 1 is higher than the account level of user account 2, and the account level of user account 2 is higher than the account level of user account 3.
According to the method and the device for determining the account level of the target user account, the historical content issued by the target user account in the client can be obtained, then at least the account activity, the field concentration and the content quality of the target user account can be obtained based on the historical content, and the account activity, the field concentration and the content quality are fused to determine the account level of the target user account. Therefore, the account level can be automatically and quickly determined without manually determining the account level, and the efficiency and the accuracy of determining the account level are improved. When the content needs to be issued, the content to be issued can be issued according to the account number level, and the accuracy of issuing the content is improved.
The method described in the above embodiments is further illustrated in detail by way of example.
In this embodiment, an integrated server of a content account management device is taken as an example, where the server is a cluster server, the cluster server may include servers such as an uplink and downlink content interface server, a content storage server, a scheduling center server, a deduplication server, an audit server, a recommendation distribution server, a content distribution outlet server, a statistics reporting interface server, a statistics data storage server, and an account identification server, and a connection relationship between the servers in the cluster server may be as shown in fig. 4, where the cluster server may be in communication connection with a content production end through the uplink and downlink content interface server, and in communication connection with a content consumption end through the uplink and downlink content interface server, the statistics reporting interface server, or the content distribution outlet server. The content producing end may be a client end that produces the content to be published, the content consuming end may be a client end that receives the content to be published pushed by the cluster server and displays the content to be published, the content producing end may include one or more content consuming ends, and the content consuming end may include one or more content consuming ends.
Referring to fig. 5, fig. 5 is a schematic flow chart of a content account management method according to an embodiment of the present application. The method flow can comprise the following steps:
and S10, the uplink and downlink content interface server receives the content to be released uploaded by the content production end.
The Content producing end may generate the Content to be published through a User account corresponding to Content production such as Professional produced Content (PGC), User Generated Content (UGC), Multi-Channel Network (MCN), or Professional User produced Content (pupc), for example, through an Application Programming Interface (API) of the Content producing end (i.e., the mobile end) or the back end, through image and text Content provided by a local or web publishing system or through uploading video Content (including short videos and small videos) to wait for publishing the Content. The content production end can establish communication connection with the uplink and downlink content interface servers, obtain server interface addresses of the uplink and downlink content interface servers, and then send the content to be published to the uplink and downlink content interface servers based on the server interface addresses, and at the moment, the uplink and downlink content interface servers receive the content to be published uploaded by the content production end.
And S11, the uplink and downlink content interface server writes the content to be issued and the meta information into the content storage server.
All the meta information of the content distributed by the content production end can be stored in the content storage server. The information in the content storage server can be read in the content auditing (including manual auditing) process, and the auditing result and state can also be returned to the content storage server for storage. The content storage server may also store processing results of the deduplication server, the account identification server, and the like.
The meta information may include content size, cover page link, title, release time, account number author, source channel, and storage time (i.e., storage time), and the meta information may also include classification of content during content review, which may include first-level classification, second-level classification, third-level classification, and tag information, for example, a piece of content explaining the XX brand of mobile phone, the first-level classification is science and technology, the second-level classification is a smart phone, the third-level classification is a domestic mobile phone, and the tag information is the XX brand and the XX model.
It should be noted that different content pools may be set in the content storage server according to the categories of different contents, and the contents of different categories may be stored in the corresponding content pools. The recommendation and distribution server and the deduplication server need to acquire content from the content storage server, for example, the deduplication server may load content that has been put into storage for a period of time (e.g., a week) in the past according to a service requirement, add a filtering flag to the content that is repeatedly put into storage again, and no longer provide the content to the recommendation and distribution server for distribution.
And S12, the uplink and downlink content interface server writes the content to be issued into the dispatching center server.
It should be noted that the execution sequence of step S11 and step S12 may be flexibly set according to actual needs, for example, step S11 and step S12 may be executed simultaneously, or step S11 is executed first and then step S12 is executed, or step S12 is executed first and then step S11 is executed.
The scheduling center server may be configured to be responsible for a whole scheduling process of the content stream, receive, through the uplink and downlink content interface servers, the content stored in the content storage server, and obtain meta information of the content from the content storage server.
And S13, the dispatching center server calls the content re-ranking service of the re-ranking server.
The scheduling center server can schedule the duplication elimination server, mark and filter the content repeatedly stored in the content storage server, generate duplication elimination flow information, and synchronize the duplication elimination flow information to the account identification fusion model in the account identification server as input.
The scheduling center server can also schedule a scheduling account number recognition server, evaluate and calculate the account number level ranking of each user account number, and is used in practical application scenes of follow-up auditing scheduling, account number right reduction in the distribution process, directional flow support and the like.
The deduplication operation of the deduplication server may include title deduplication, cover map deduplication, content text deduplication, video fingerprint and audio fingerprint deduplication, and the like, for example, the title, the cover map and the content text may be vectorized by using a simhash algorithm and a BERT algorithm, vectors are constructed for the video content by extracting the video fingerprint and the audio fingerprint, and then distances (such as euclidean distances) between the vectors are calculated to determine whether to duplicate, and the duplicate content is filtered. The duplicate removal server can acquire the account number grade of the user account number from the account number identification server in the process of executing the duplicate removal operation, and enables the content of the user account number with higher account number grade rank under the condition that the content is the same.
Before invoking the content deduplication service of the deduplication server, the scheduling center server may obtain an account level of the user account, and a flow of determining the account level may be as shown in fig. 6, including:
and S20, the dispatching center server calls the account identification service of the account identification server.
S21, the account recognition server constructs an account recognition fusion model.
And S22, the account number recognition server reads the statistical data from the statistical data storage server and determines the account number grade by using the account number recognition fusion model.
And S23, the account number recognition server sends the account number grade to the repetition eliminating server.
The account identification fusion model may be a model constructed by using the above formula (1), formula (2), formula (3), and the like, and the statistical data may include browsing times, praise number, comment number (the comment number may be a forward and neutral comment number) of the content, total number of interactions (such as forwarding, sharing, or collection), time parameter of content publishing, content quantity, and the like. The statistical data may include prior user account text data (i.e., unpublished content) and a posteriori user account text data (i.e., published content). The account identification server can calculate the popularity, the account activity, the field concentration, the content quality and the like of the user account based on the statistical data, and the account identification fusion model is utilized to perform fusion based on the four dimensions of the popularity, the account activity, the field concentration, the content quality and the like of the user account so as to determine the account level of the user account. The account grades can be used for auditing scheduling sequencing (user accounts with low grades are arranged at the tail of an auditing queue) and high-quality content support weighting, and the probability of high-quality content distribution can be improved based on more flow exposure opportunities.
The account identification server can send the account grades to the repetition ranking server and send the account grades to the scheduling center server, so that the scheduling center server can mark the account grades of the user accounts and provide reference for utilizing the account grades of the user in subsequent service scenes. For example, the duplication elimination server may preferentially enable the content of the user account with the higher account rank, the audit server may preferentially audit the content of the user account with the higher account rank, and the recommendation distribution server may preferentially recommend the content of the user account with the higher account rank.
Wherein, the storage process of the statistical data pre-stored in the statistical data storage server can be as shown in fig. 7,
and S30, the uplink and downlink content interface server receives the content to be released uploaded by the content production end.
S31, the uplink and downlink content interface server obtains the content index and the published content from the content consumption end.
And S32, the uplink and downlink content interface server reports the user account issuing content and the terminal statistical information to the statistical report interface server.
And S33, the statistical reporting interface server writes the statistical data obtained based on the user account number release content and the terminal statistical information into the statistical data storage server.
The published content is history content, the content consuming end can be in communication connection with the uplink and downlink content interface server, and the uplink and downlink content interface server can obtain the content index and the published content from the content consuming end, for example, the content index can be obtained by recommending and distributing through message source Feeds.
The reporting of the user account release content to the statistics report interface server by the uplink and downlink content interface server may include: the content to be published is obtained from the content production end, and the published content is obtained from the content consumption end. The end statistical information may include operation behaviors of the statistical user based on the published content, such as comments, forwarding, sharing, collecting, or praise, and exposure data of the Feeds content (the exposure data may refer to a visual portion of the content display).
In the embodiment, an account identification fusion model can be constructed, quantitative modeling of account grades is achieved through an unsupervised machine learning algorithm, the account grades of the target user accounts are comprehensively considered and are independently quantized on the basis of four dimensions such as popularity, account activity, field concentration and content quality, and finally the features are fused into a quantization fraction to sort the accounts, threshold values of different grades can be set according to different conditions, and therefore the accounts are clearly graded and distinguished. The account identification fusion model can update the account level of the user account at any time according to the change of data every day, and ensures that the account level change and the performance of the user account keep linking in time. Therefore, the content of the high-quality user account can be preferentially started to enter the recommendation pool for distribution, the flow can be concentrated on the real high-quality content creator, the waste of the high-quality flow is reduced, the high-quality and active authors required by the platform can obtain the maximum incentive, meanwhile, the unsupervised modeling method does not need manual marking, the cost is reduced, the processing timeliness is improved, and the whole content ecology enters a benign cycle and forms a healthy content ecology.
And S14, the dispatching center server calls the content auditing service of the auditing server.
The content is audited by an audit model established by the audit server, or the audit server audits the content manually. The auditing model can be flexibly set according to actual needs, for example, words in the content can be cut through the auditing model, semantic analysis is performed on words obtained by the words, analysis of sensitive words or safety problems is performed based on semantic analysis results, if the sensitive words or the safety problems exist, the auditing is not passed, and the content can be prohibited from being issued; identifying the picture in the content, determining whether the picture contains a part prohibited to be published, if so, not passing the audit, and at the moment, prohibiting to publish the content; and so on. When the manual review is called, the information stored in the content storage server can be read in the manual review process, and meanwhile, the result and the state of the manual review can be transmitted back to the content storage server for storage.
And S15, the dispatching center server updates the meta information in the content storage server based on the auditing result.
For example, when the audit is passed, the updated meta-information may include related information that the content audit is passed, and when the audit is not passed, the updated meta-information may include related information that the content audit is not passed.
And S16, the dispatching center server sends the content to be issued to the recommendation distribution server.
Before sending the content to be published to the recommended distribution server, the scheduling center server may determine the account level based on a process of determining the account level as shown in fig. 6, and after determining the account level, the scheduling center server may send the account level and the content to be published together to the recommended distribution server.
And S17, the recommendation distribution server sends the content to be published to the content distribution export server.
And the recommendation and distribution server sends the content to be issued to the content distribution export server based on the account number level.
S18, the content distribution outlet server pushes the content to be published to the content consumption end.
The content export service can be a group of access servers which are locally deployed nearby near the content consumption end, the content export service can acquire the recommended distribution result and push the content to be published to the content consumption end, and the content consumption end can display the content to be published after receiving the content to be published.
According to the embodiment of the application, the account number grade of the user account number can be determined by fusing the account number activity, the field concentration degree and the content quality based on the popularity, the account number activity, the field concentration degree and the content quality of the user account number through an unsupervised account number identification fusion model. When the content needs to be published, the content to be published can be published according to the account number level, the content of a high-quality user account number can be preferentially enabled to enter a recommendation pool for distribution, the flow can be concentrated on a real high-quality content creator, waste of the high-quality flow is reduced, the high-quality and active authors needed by the platform can obtain the maximum incentive, the efficiency and the accuracy of account number level determination are improved, and the accuracy of content publishing is improved.
In order to better implement the content account management method provided by the embodiment of the present application, an embodiment of the present application further provides a device based on the content account management method. The meaning of the noun is the same as that in the content account management method, and specific implementation details may refer to the description in the method embodiment.
Referring to fig. 8, fig. 8 is a schematic structural diagram of a content account management apparatus according to an embodiment of the present disclosure, where the content account management apparatus may include a first obtaining unit 301, a second obtaining unit 302, a fusing unit 303, and the like.
The first obtaining unit 301 is configured to obtain historical content issued by a target user account in a client;
a second obtaining unit 302, configured to obtain at least account liveness, domain concentration, and content quality of the target user account based on the historical content;
the fusion unit 303 is configured to fuse the account liveness, the field concentration, and the content quality to determine the account level of the target user account.
In some embodiments, the fusion unit 303 comprises:
the first acquisition subunit is used for acquiring the popularity of the target user account;
and the fusion subunit is used for fusing the popularity, the account activity, the field concentration and the content quality to determine the account level of the target user account.
In some embodiments, the fusion subunit is specifically for:
obtaining respective corresponding weight values of popularity, account number activity, field concentration and content quality;
and fusing the popularity, the account activity, the field concentration, the content quality and the corresponding weight value to determine the account level of the target user account.
In some embodiments, the second obtaining unit 302 includes:
the second acquisition subunit is used for acquiring at least the time parameter and the content quantity of the historical content release;
and the first determining subunit is used for determining the account activity of the target user account according to the time parameter and the content quantity.
In some embodiments, the first determining subunit is specifically configured to:
acquiring a smoothing coefficient of every two days and a control parameter of content release;
and determining the account number activity of the target user account number according to the smoothing coefficient, the control parameter, the time parameter and the content quantity.
In some embodiments, the second obtaining unit 302 includes:
the third acquisition subunit is used for acquiring the domain types which are sent by the target user account and are started most in the preset time period based on the historical content;
the counting subunit is used for counting the number of the messages corresponding to the field categories and the number of the messages which are started;
and the setting subunit is used for setting the ratio of the number of the texts to the number of the texts and the number of the launched texts as the field concentration degree of the account of the target user.
In some embodiments, the second obtaining unit 302 includes:
the fourth acquisition subunit is used for acquiring feedback data of the historical content, wherein the feedback data comprises browsing times and total interaction number;
and the second determining subunit is used for determining the content quality of the target user account according to the feedback data of the historical content.
In some embodiments, the second determining subunit is specifically configured to:
acquiring a first smoothing coefficient of browsing times and a second smoothing coefficient of interaction total;
and determining the content quality of the target user account according to the first smoothing coefficient, the second smoothing coefficient and the feedback data.
In some embodiments, the first obtaining subunit 301 is specifically configured to:
and acquiring the total fan amount of the target user account, and determining the popularity of the target user account based on the total fan amount.
In some embodiments, the first obtaining unit 301 includes:
the fifth acquiring subunit is configured to acquire, according to a preset time period, multiple candidate contents that have been issued by a target user account in the client;
and the screening subunit is used for screening out the historical contents issued by the target user account based on the similarity among the candidate contents.
In some embodiments, the screening subunit is specifically for:
vectorizing at least one of the title, the cover picture, the content text, the video fingerprint and the audio fingerprint of the candidate contents to obtain vector data corresponding to at least one of the title, the cover picture, the content text, the video fingerprint and the audio fingerprint;
determining the similarity between every two candidate contents according to at least one corresponding vector data in the title, the cover picture, the content text, the video fingerprint and the audio fingerprint;
and removing one of the two candidate contents with the similarity larger than a preset threshold value to obtain the released historical content of the target user account.
In some embodiments, the content account management apparatus further includes:
when a plurality of target user accounts need to release content, generating a release sequence of the content to be released of each target user account based on the sequence of the account grades of the plurality of target user accounts from high to low;
and issuing the contents to be issued of each target user account according to the issuing sequence.
In the embodiment of the application, the first obtaining unit 301 may obtain historical content issued by a target user account in a client, then the second obtaining unit 302 may obtain at least account activity, field concentration and content quality of the target user account based on the historical content, and the fusion unit 303 fuses the account activity, the field concentration and the content quality to determine an account level of the target user account. Therefore, the account level can be automatically and quickly determined without manually determining the account level, and the efficiency and the accuracy of determining the account level are improved.
The embodiment of the present application further provides a computer device, where the computer device may be a server, as shown in fig. 9, which shows a schematic structural diagram of a server according to the embodiment of the present application, and specifically:
the server may include components such as a processor 401 of one or more processing cores, memory 402 of one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will appreciate that the server architecture shown in FIG. 9 does not constitute a limitation on the servers, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components. Wherein:
the processor 401 is a control center of the server, connects various parts of the entire server using various interfaces and lines, and performs various functions of the server and processes data by running or executing software programs and/or modules stored in the memory 402 and calling data stored in the memory 402, thereby performing overall monitoring of the server. Optionally, processor 401 may include one or more processing cores; preferably, the processor 401 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 the processor 401.
The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by operating the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage 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 created according to the use of the server, and the like. Further, the memory 402 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 access to the memory 402.
The server further includes a power supply 403 for supplying power to each component, and preferably, the power supply 403 may be logically connected to the processor 401 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system. The power supply 403 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.
The server may also include an input unit 404, the input unit 404 being operable to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the server may further include a display unit and the like, which will not be described in detail herein. Specifically, in this embodiment, the processor 401 in the server loads the executable file corresponding to the process of one or more application programs into the memory 402 according to the following instructions, and the processor 401 runs the application program stored in the memory 402, thereby implementing various functions as follows:
acquiring historical content issued by a target user account in a client, and acquiring at least account activity, field concentration and content quality of the target user account based on the historical content; and fusing the account number activity, the field concentration and the content quality to determine the account number grade of the target user account number.
In some embodiments, in fusing account liveness, domain attentiveness, and content quality to determine an account rating of the target user account, the processor 401 further performs: obtaining the popularity of the target user account; and fusing the popularity, the account activity, the field concentration and the content quality to determine the account level of the target user account.
In some embodiments, in fusing the popularity, the account liveness, the domain attentiveness, and the content quality to determine the account rating of the target user account, the processor 401 further performs: obtaining respective corresponding weight values of popularity, account number activity, field concentration and content quality; and fusing the popularity, the account activity, the field concentration, the content quality and the corresponding weight value to determine the account level of the target user account.
In some embodiments, in obtaining the account activity of the target user account based on the historical content, the processor 401 further performs: at least acquiring time parameters and content quantity of historical content release; and determining the account activity of the target user account according to the time parameter and the content quantity.
In some embodiments, in determining the account activity of the target user account according to the time parameter and the content amount, the processor 401 further performs: acquiring a smoothing coefficient of every two days and a control parameter of content release; and determining the account number activity of the target user account number according to the smoothing coefficient, the control parameter, the time parameter and the content quantity.
In some embodiments, in obtaining the domain attentiveness of the target user account based on the historical content, the processor 401 further performs: acquiring the domain types which are sent by the target user account and most started in a preset time period based on historical content; counting the number of messages and the number of messages which are started and correspond to the field type; and setting the ratio of the number of the texts to the number of the texts and the number of the invoices as the field concentration degree of the target user account.
In some embodiments, when obtaining the content quality of the target user account based on the historical content, the processor 401 further performs: acquiring feedback data of historical content, wherein the feedback data comprises browsing times and total interaction number; and determining the content quality of the target user account according to the feedback data of the historical content.
In some embodiments, when determining the content quality of the target user account according to the feedback data of the historical content, the processor 401 further performs: acquiring a first smoothing coefficient of browsing times and a second smoothing coefficient of interaction total; and determining the content quality of the target user account according to the first smoothing coefficient, the second smoothing coefficient and the feedback data.
In some embodiments, in obtaining the popularity of the target user account, the processor 401 further performs: and acquiring the total fan amount of the target user account, and determining the popularity of the target user account based on the total fan amount.
In some embodiments, in obtaining the historical content published by the target user account in the client, the processor 401 further performs: acquiring a plurality of candidate contents issued by a target user account in a client according to a preset time period; and screening out the historical contents issued by the target user account based on the similarity among the candidate contents.
In some embodiments, when filtering out the historical content published by the target user account based on the similarity between the respective candidate contents, the processor 401 further performs: vectorizing at least one of the title, the cover picture, the content text, the video fingerprint and the audio fingerprint of the candidate contents to obtain vector data corresponding to at least one of the title, the cover picture, the content text, the video fingerprint and the audio fingerprint; determining the similarity between every two candidate contents according to at least one corresponding vector data in the title, the cover picture, the content text, the video fingerprint and the audio fingerprint; and removing one of the two candidate contents with the similarity larger than a preset threshold value to obtain the released historical content of the target user account.
In some embodiments, processor 401 further performs: when a plurality of target user accounts need to release content, generating a release sequence of the content to be released of each target user account based on the sequence of the account grades of the plurality of target user accounts from high to low; and issuing the contents to be issued of each target user account according to the issuing sequence.
In the above embodiments, the descriptions of the embodiments have respective emphasis, and parts that are not described in detail in a certain embodiment may refer to the above detailed description of the content account management method, and are not described herein again.
According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided in the various alternative implementations of the above embodiments.
It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, an embodiment of the present application provides a storage medium, where a plurality of instructions are stored, where the instructions can be loaded by a processor to execute any one of the content account management methods provided in the embodiment of the present application.
The above operations can be implemented in the foregoing embodiments, and are not described in detail herein.
Wherein the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
Since the instructions stored in the storage medium may execute the steps in any content account management method provided in the embodiment of the present application, beneficial effects that can be achieved by any content account management method provided in the embodiment of the present application may be achieved, which are detailed in the foregoing embodiments and will not be described herein again.
The content account management method, the content account management apparatus, the computer device, and the storage medium provided in the embodiments of the present application are described in detail above, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (15)

1. A content account management method is characterized by comprising the following steps:
acquiring historical content issued by a target user account in a client;
at least acquiring account activity, field concentration and content quality of the target user account based on the historical content;
and fusing the account number activity, the field concentration and the content quality to determine the account number grade of the target user account number.
2. The content account management method according to claim 1, wherein the fusing the account liveness, the domain concentration, and the content quality to determine the account level of the target user account comprises:
obtaining the popularity of the target user account;
and fusing the popularity, the account activity, the field concentration and the content quality to determine the account level of the target user account.
3. The content account management method according to claim 2, wherein fusing the popularity, the account liveness, the domain concentration and the content quality to determine the account level of the target user account comprises:
acquiring weighted values corresponding to the popularity, the account number activity, the field concentration and the content quality respectively;
and fusing the popularity, the account activity, the field concentration and the content quality and the corresponding weight value thereof to determine the account level of the target user account.
4. The content account management method according to claim 1, wherein the obtaining the account activity of the target user account based on the historical content includes:
at least acquiring time parameters and content quantity of the historical content release;
and determining the account activity of the target user account according to the time parameter and the content quantity.
5. The content account management method according to claim 4, wherein the determining the account activity of the target user account according to the time parameter and the content amount comprises:
acquiring the smoothing coefficient of the interval days and the control parameter of content release;
and determining the account number activity of the target user account number according to the smoothing coefficient, the control parameter, the time parameter and the content quantity.
6. The content account management method according to claim 1, wherein the obtaining of the domain concentration of the target user account based on the historical content includes:
acquiring the domain types which are sent by the target user account and most started in a preset time period based on the historical content;
counting the number of the messages corresponding to the field type and the number of the messages which are started;
and setting the ratio of the number of the texts to the number of the texts and the number of the invoices as the field concentration degree of the target user account.
7. The content account management method according to claim 1, wherein the obtaining of the content quality of the target user account based on the historical content includes:
acquiring feedback data of the historical content, wherein the feedback data comprises browsing times and total interaction number;
and determining the content quality of the target user account according to the feedback data of the historical content.
8. The content account management method according to claim 7, wherein the feedback data further includes at least one of a number of praise and a number of comments, and the determining the content quality of the target user account according to the feedback data of the historical content includes:
acquiring a first smoothing coefficient of the browsing times and a second smoothing coefficient of the total interaction number;
and determining the content quality of the target user account according to the first smoothing coefficient, the second smoothing coefficient and the feedback data.
9. The content account management method according to claim 2, wherein the obtaining of the popularity of the target user account comprises:
and acquiring the total fan amount of the target user account, and determining the popularity of the target user account based on the total fan amount.
10. The content account management method according to any one of claims 1 to 9, wherein the acquiring historical content that has been issued by a target user account in a client includes:
acquiring a plurality of candidate contents issued by a target user account in a client according to a preset time period;
and screening out the historical contents issued by the target user account based on the similarity among the candidate contents.
11. The content account management method according to claim 10, wherein the filtering out the historical content that has been released by the target user account based on the similarity between the candidate contents includes:
vectorizing at least one of the title, the cover map, the content text, the video fingerprint and the audio fingerprint of the candidate contents to obtain vector data corresponding to at least one of the title, the cover map, the content text, the video fingerprint and the audio fingerprint;
determining the similarity between every two candidate contents according to the vector data corresponding to at least one of the title, the cover picture, the content text, the video fingerprint and the audio fingerprint;
and removing one of the two candidate contents with the similarity larger than a preset threshold value to obtain the released historical content of the target user account.
12. The content account management method according to any one of claims 1 to 9, wherein after determining the account level of the target user account, the content account management method further includes:
when a plurality of target user accounts need to release content, generating a release sequence of the content to be released of each target user account based on the sequence of the account grades of the target user accounts from high to low;
and issuing the contents to be issued of each target user account according to the issuing sequence.
13. A content account management apparatus, comprising:
the first acquisition unit is used for acquiring historical content issued by a target user account in the client;
a second obtaining unit, configured to obtain at least account liveness, domain concentration, and content quality of the target user account based on the historical content;
and the fusion unit is used for fusing the account number activity, the field concentration and the content quality to determine the account number grade of the target user account number.
14. A computer device comprising a processor and a memory, the memory storing a computer program therein, the processor executing the content account management method according to any one of claims 1 to 12 when calling the computer program in the memory.
15. A storage medium for storing a computer program loaded by a processor to execute the content account management method according to any one of claims 1 to 12.
CN202010993062.2A 2020-09-21 2020-09-21 Content account management method and device, computer equipment and storage medium Active CN112153426B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010993062.2A CN112153426B (en) 2020-09-21 2020-09-21 Content account management method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010993062.2A CN112153426B (en) 2020-09-21 2020-09-21 Content account management method and device, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112153426A true CN112153426A (en) 2020-12-29
CN112153426B CN112153426B (en) 2023-08-29

Family

ID=73893463

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010993062.2A Active CN112153426B (en) 2020-09-21 2020-09-21 Content account management method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112153426B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112883316A (en) * 2021-03-02 2021-06-01 广州市百果园信息技术有限公司 Data processing method and device, electronic equipment and storage medium
CN113079396A (en) * 2021-03-18 2021-07-06 海南视联通信技术有限公司 Service control method, device, terminal equipment and storage medium
CN113342626A (en) * 2021-05-28 2021-09-03 深圳市前海房极客网络科技有限公司 Content processing method and device, electronic equipment and storage medium
CN113626624A (en) * 2021-10-12 2021-11-09 腾讯科技（深圳）有限公司 Resource identification method and related device
CN113709572A (en) * 2021-08-27 2021-11-26 北京达佳互联信息技术有限公司 Content promotion method and device, electronic equipment and storage medium
WO2023020252A1 (en) * 2021-08-20 2023-02-23 腾讯科技（深圳）有限公司 Content recommendation method and apparatus, and device and readable storage medium

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105391654A (en) * 2015-11-26 2016-03-09 中国建设银行股份有限公司 Account activeness-based system resource allocation method and device
CN106355507A (en) * 2016-09-05 2017-01-25 北京蓝色光标品牌管理顾问股份有限公司 Official account activity level ranking method and ranking system
CN108898418A (en) * 2018-05-31 2018-11-27 康键信息技术（深圳）有限公司 User account detection method, device, computer equipment and storage medium
CN110120912A (en) * 2019-05-10 2019-08-13 腾讯科技（深圳）有限公司 Rich-media content processing method, device, readable storage medium storing program for executing and computer equipment
CN110297987A (en) * 2019-07-02 2019-10-01 武汉斗鱼网络科技有限公司 A kind of model recommended method, device, equipment and storage medium
CN110535849A (en) * 2019-08-23 2019-12-03 深圳市新系区块链技术有限公司 Account information management method and device
CN110690987A (en) * 2019-08-23 2020-01-14 深圳市新系区块链技术有限公司 Account information management method, device and equipment
CN111325580A (en) * 2020-02-26 2020-06-23 支付宝(杭州)信息技术有限公司 User account management method, device, equipment and storage medium
CN111639291A (en) * 2020-05-29 2020-09-08 腾讯科技（武汉）有限公司 Content distribution method, content distribution device, electronic equipment and storage medium

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105391654A (en) * 2015-11-26 2016-03-09 中国建设银行股份有限公司 Account activeness-based system resource allocation method and device
US20170153917A1 (en) * 2015-11-26 2017-06-01 China Construction Bank Corporation Account activity level based-system resource allocating method and device
CN106355507A (en) * 2016-09-05 2017-01-25 北京蓝色光标品牌管理顾问股份有限公司 Official account activity level ranking method and ranking system
CN108898418A (en) * 2018-05-31 2018-11-27 康键信息技术（深圳）有限公司 User account detection method, device, computer equipment and storage medium
CN110120912A (en) * 2019-05-10 2019-08-13 腾讯科技（深圳）有限公司 Rich-media content processing method, device, readable storage medium storing program for executing and computer equipment
CN110297987A (en) * 2019-07-02 2019-10-01 武汉斗鱼网络科技有限公司 A kind of model recommended method, device, equipment and storage medium
CN110535849A (en) * 2019-08-23 2019-12-03 深圳市新系区块链技术有限公司 Account information management method and device
CN110690987A (en) * 2019-08-23 2020-01-14 深圳市新系区块链技术有限公司 Account information management method, device and equipment
CN111325580A (en) * 2020-02-26 2020-06-23 支付宝(杭州)信息技术有限公司 User account management method, device, equipment and storage medium
CN111639291A (en) * 2020-05-29 2020-09-08 腾讯科技（武汉）有限公司 Content distribution method, content distribution device, electronic equipment and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘晶;王峰;胡亚慧;李石君;: "基于微博行为数据的不活跃用户探测", 电子科技大学学报, no. 03, pages 92 - 96 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112883316A (en) * 2021-03-02 2021-06-01 广州市百果园信息技术有限公司 Data processing method and device, electronic equipment and storage medium
CN113079396A (en) * 2021-03-18 2021-07-06 海南视联通信技术有限公司 Service control method, device, terminal equipment and storage medium
CN113079396B (en) * 2021-03-18 2024-03-29 海南视联通信技术有限公司 Service management and control method and device, terminal equipment and storage medium
CN113342626A (en) * 2021-05-28 2021-09-03 深圳市前海房极客网络科技有限公司 Content processing method and device, electronic equipment and storage medium
CN113342626B (en) * 2021-05-28 2022-11-11 深圳市前海房极客网络科技有限公司 Content processing method, content processing device, electronic equipment and storage medium
WO2023020252A1 (en) * 2021-08-20 2023-02-23 腾讯科技（深圳）有限公司 Content recommendation method and apparatus, and device and readable storage medium
CN113709572A (en) * 2021-08-27 2021-11-26 北京达佳互联信息技术有限公司 Content promotion method and device, electronic equipment and storage medium
CN113626624A (en) * 2021-10-12 2021-11-09 腾讯科技（深圳）有限公司 Resource identification method and related device
CN113626624B (en) * 2021-10-12 2021-12-21 腾讯科技（深圳）有限公司 Resource identification method and related device

Also Published As

Publication number Publication date
CN112153426B (en) 2023-08-29

Similar Documents

Publication Publication Date Title
CN110225373B (en) Video auditing method and device and electronic equipment
CN112153426A (en) Content account management method and device, computer equipment and storage medium
CN111885399B (en) Content distribution method, device, electronic equipment and storage medium
CN112749608B (en) Video auditing method, device, computer equipment and storage medium
CN107463698B (en) Method and device for pushing information based on artificial intelligence
CN110704674A (en) Video playing integrity prediction method and device
CN108874832A (en) Target, which is commented on, determines method and device
CN111444357A (en) Content information determination method and device, computer equipment and storage medium
CN111090813B (en) Content processing method and device and computer readable storage medium
US20100223099A1 (en) Method and apparatus for a multi-dimensional offer optimization (mdoo)
CN112231563B (en) Content recommendation method, device and storage medium
CN113748439A (en) Prediction of successful quotient for motion pictures
US20140122504A1 (en) Systems and Methods for Collection and Automatic Analysis of Opinions on Various Types of Media
CN108595526B (en) Resource recommendation method and device
CN112202849A (en) Content distribution method, content distribution device, electronic equipment and computer-readable storage medium
CN114240101A (en) Risk identification model verification method, device and equipment
CN114357204B (en) Media information processing method and related equipment
CN112995690B (en) Live content category identification method, device, electronic equipment and readable storage medium
CN112989167B (en) Method, device and equipment for identifying transport account and computer readable storage medium
CN114996435A (en) Information recommendation method, device, equipment and storage medium based on artificial intelligence
CN113457167A (en) Training method of user classification network, user classification method and device
CN114996486A (en) Data recommendation method and device, server and storage medium
CN114596108A (en) Object recommendation method and device, electronic equipment and storage medium
CN115146136A (en) Account classification method and device, electronic equipment and storage medium
CN114077710B (en) Social network account identification method and device and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 40035429

Country of ref document: HK

SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant