Multimedia content management and push system

Abstract

The invention discloses a multimedia content management and push system, and relates to the technical field of content management and push, the multimedia content management and push system comprises a control center, the control center is in communication connection with a database, a user portrait generation module, a derivative portrait set acquisition module, a push content generation module and a feedback result processing module; the database is used for storing multimedia content information, user information and browsing records; the user portrait generation module is used for generating a user portrait according to the user information and the browsing record; the derivative portrait set acquisition module is used for acquiring a corresponding derivative portrait set according to a user portrait; the push content generation module is used for generating push content according to the user portrait and the corresponding derivative portrait set; and the feedback result processing module is used for acquiring a browsing result of the user on the pushed content and generating a corresponding adjustment strategy according to the browsing result.

Description

Technical Field

[0001] The present invention relates to the technical field of content management and push technology, and in particular to a multimedia content management and push system. Background Art

[0002] With the development of big data technology, user portraits have become one of the core technologies in personalized push systems. By analyzing user behavior data (such as browsing history, click habits, search preferences, etc.), it is possible to build a portrait that meets user characteristics, and then predict user interests and provide relevant content.

[0003] Therefore, the push content generated based on user feature portraits is often too repetitive, which can easily cause users to have aesthetic fatigue. How to generate corresponding extended push content based on user feature portraits so that users can further expand their interests to new content based on their original preferences is an issue we need to consider at present. Summary of the invention

[0004] In order to solve the above problems, the present invention aims to provide a multimedia content management and push system.

[0005] The object of the present invention can be achieved by the following technical solutions: A multimedia content management and push system includes a control center, the control center is communicatively connected with a database, a user portrait generation module, a derivative portrait set acquisition module, a push content generation module and a feedback result processing module;

[0006] The database is used to store multimedia content information, user information and browsing records;

[0007] The user portrait generation module is used to generate a user portrait based on user information and browsing history;

[0008] The derived portrait set acquisition module is used to acquire the corresponding derived portrait set according to the user portrait;

[0009] The push content generation module is used to generate push content according to the user portrait and its corresponding derivative portrait set;

[0010] The feedback result processing module is used to obtain the user's browsing result on the pushed content, and generate a corresponding adjustment strategy according to the browsing result.

[0011] Further, the database includes a content information unit, a user information unit and a browsing record unit;

[0012] The content information unit is used to store multimedia content information, and the content information includes content name, content link, content type, name keyword and content duration;

[0013] The user information unit is used to store the user's identity information, which includes user name, user ID, mobile phone number and login password;

[0014] The browsing record unit includes several browsing record sub-units, each of which is used to store the user's browsing record and each browsing record sub-unit has its corresponding user ID; the browsing record includes a browsing link and a browsing time, wherein the browsing link corresponds to the content link in the content information unit.

[0015] Furthermore, the process of generating a user portrait based on user information and browsing history includes:

[0016] Obtain a user ID corresponding to the user, and record the user ID as the target ID;

[0017] Obtaining a browsing record corresponding to the target ID, and then obtaining a content link corresponding to the browsing link in the browsing record, and marking the content category and name keyword corresponding to the content link as an explicit category and an explicit keyword respectively;

[0018] Generate a dominant category set according to the dominant categories;

[0019] Generate an explicit keyword set based on the explicit keywords;

[0020] Set a dominant threshold; obtain the dominant categories that appear in the dominant category set and their corresponding occurrence times, and record the dominant categories whose occurrence times are greater than or equal to the dominant threshold as high-frequency categories;

[0021] Generate user portraits corresponding to target IDs based on high-frequency categories and explicit keyword sets.

[0022] Furthermore, the process of obtaining the corresponding derivative portrait set according to the user portrait includes:

[0023] Obtain user portraits corresponding to other user IDs except the target ID, obtain user IDs corresponding to user portraits in which high-frequency categories in the user portraits are consistent with high-frequency categories in the user portraits corresponding to the target ID, and mark the user IDs as derived IDs;

[0024] Obtain a user portrait corresponding to a derivative ID, and mark the user portrait as a derivative portrait;

[0025] Generate a derivative image set based on the derivative ID and derivative image.

[0026] Furthermore, the process of generating push content based on the user portrait and its corresponding derivative portrait set includes:

[0027] The push content includes broad category push content and anchor push content;

[0028] Obtain the high-frequency categories and explicit keywords corresponding to the user portrait of the target ID, and mark them as target categories and target keywords respectively;

[0029] Get the derivative ID in the derivative portrait set;

[0030] Generate browsing data links based on the derived ID, and generate anchored push content based on the target category, target keyword and browsing data links;

[0031] Generate broad category push content based on target categories and derived portrait sets.

[0032] Further, the process of generating a browsing data link according to the derived ID and generating anchored push content according to the target category, target keyword and the browsing data link includes:

[0033] Generate query information according to the derived ID, submit the query information to the browsing record unit, and obtain the browsing record subunit corresponding to the derived ID;

[0034] Obtaining browsing records in the browsing record subunit, sorting browsing links according to browsing time in the browsing records, recording the sorted browsing links as browsing nodes, and generating a browsing data link according to the browsing nodes;

[0035] If there is a browsing node in the browsing data chain whose corresponding browsing link corresponds to a content type that is consistent with the target type, the browsing node is marked as an anchor node;

[0036] If there is a browsing node in the browsing data chain whose name keyword corresponding to the corresponding browsing link is consistent with the target keyword, then the browsing node is marked as an anchor node;

[0037] Acquire a browsing node that is adjacent to the anchor node and located behind the anchor node when the anchor node is located in front, and mark the browsing node as a pushed node;

[0038] Obtain the browsing link corresponding to the push node, and record the content link corresponding to the browsing link as the anchored push content

[0039] Furthermore, the process of generating the push content of major categories according to the target category and the derived portrait set includes:

[0040] Set frequency threshold;

[0041] Obtain high-frequency categories other than the target category and the number of occurrences thereof corresponding to each derivative portrait in the derivative portrait set, and record the high-frequency category corresponding to the number of occurrences greater than or equal to the frequency threshold as the push category;

[0042] Generate a query signal according to the push type, submit the query signal to the content information unit, obtain a content link in the content information unit corresponding to the content type and the push type, and record the content link as a large category of push content.

[0043] Furthermore, the process of obtaining the browsing result of the user on the pushed content and generating a corresponding adjustment strategy according to the browsing result includes:

[0044] Set offline duration, repetition threshold, and statistical threshold;

[0045] Set up greylist and blacklist;

[0046] Step a1: obtaining a user ID corresponding to the user, and generating a browsing data link according to the user ID according to the principle process of generating a browsing data link through a derived ID;

[0047] Step a2: obtaining a content link corresponding to the pushed content, obtaining a browsing node corresponding to the pushed content in the browsing data chain according to the content link, and marking the browsing node as a verification node;

[0048] Step a3: obtaining a browsing link corresponding to the verification node, and recording the content duration corresponding to the content link corresponding to the browsing link as the effective duration of the verification node;

[0049] Step a4: Obtain a browsing node that is adjacent to the position of the check node and is located behind the check node when the check node is located in front, and obtain the time interval between the check node and the browsing node. If the time interval is greater than or equal to the valid time of the check node and less than the offline time, the browsing result of the pushed content corresponding to the check node is successful, and the check node is a valid node; otherwise, the browsing result of the pushed content corresponding to the check node is failed, and the check node is an invalid node;

[0050] Step a5: Obtain the browsing link corresponding to the invalid node, and send the content type and name keyword corresponding to the content link corresponding to the browsing link to the gray list;

[0051] Step a6: Repeat steps a1 to a5, and count the gray list in the process of repeated execution, and obtain the content types, name keywords, content type occurrence times and name keyword occurrence times in the gray list according to the statistical results; if the content type occurrence times corresponding to a certain content type in the gray list is greater than the repetition threshold, the content type is sent to the blacklist; if the name keyword occurrence times corresponding to a certain name keyword in the gray list is greater than the repetition threshold, the name keyword is sent to the blacklist; when a certain content type appears for the first time in the gray list statistical results, the subsequent (Num-1) statistical results are obtained, if the content type occurrence times corresponding to the content type in the first to the subsequent (Num-1) statistical results are all less than or equal to the repetition threshold, the content type is deleted from the gray list; when a certain name keyword appears for the first time in the gray list statistical results, the subsequent (Num-1) statistical results are obtained, if the name keyword occurrence times corresponding to the name keyword in the first to the subsequent (Num-1) statistical results are all less than or equal to the repetition threshold, the name keyword is deleted from the gray list; wherein Num=statistical threshold;

[0052] If the high-frequency category corresponding to the derivative image in the derivative image set is consistent with the content category in the blacklist, the derivative image will be deleted;

[0053] If the explicit keyword corresponding to the derivative portrait in the derivative portrait set is consistent with the name keyword in the blacklist, the derivative portrait will be deleted.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] 1. The present invention obtains a derivative portrait set corresponding to the user portrait, generates the user's push content through the derivative portrait set, obtains the corresponding derivative push content based on the multimedia content that the user has the same hobbies as, reasonably expands the user's exploration scope of multimedia content, and improves user stickiness;

[0056] 2. The present invention sets a gray list and a black list, and implements the screening of derivative portraits through the black list. The gray list implements a buffer area for screening derivative portraits to prevent the generation and deletion of derivative portraits due to operational errors. The gray list and the black list make the derivative portrait set further fit the user's user portrait, so that the subsequent pushed multimedia content generated according to the derivative portrait set is more in line with the user's interests and hobbies. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0058] like Figure 1As shown, a multimedia content management and push system includes a control center, wherein the control center is connected to a database, a user portrait generation module, a derivative portrait set acquisition module, a push content generation module, and a feedback result processing module;

[0059] The database is used to store multimedia content information, user information and browsing records;

[0060] The user portrait generation module is used to generate a user portrait based on user information and browsing history;

[0061] The derived portrait set acquisition module is used to acquire the corresponding derived portrait set according to the user portrait;

[0062] The push content generation module is used to generate push content according to the user portrait and its corresponding derivative portrait set;

[0063] The feedback result processing module is used to obtain the user's browsing results on the pushed content, and generate corresponding adjustment strategies according to the browsing results;

[0064] It should be further explained that, in the specific implementation process, the database includes a content information unit, a user information unit and a browsing record unit;

[0065] The content information unit is used to store multimedia content information, and the content information includes content name, content link, content type, name keyword and content duration; the name keyword is the keyword in the content name;

[0066] The user information unit is used to store the user's identity information, which includes the user name, user ID, mobile phone number and login password; the user ID is unique;

[0067] The browsing record unit includes a plurality of browsing record subunits, each of which is used to store the browsing record of the user and each of which has a corresponding user ID, that is, the browsing record subunit is used to store the browsing record of the user corresponding to its corresponding user ID; the browsing record includes a browsing link and a browsing time, wherein the browsing link corresponds to the content link in the content information unit;

[0068] It should be further explained that, in the specific implementation process, the process of generating a user portrait based on user information and browsing history includes:

[0069] Obtain a user ID corresponding to the user, and record the user ID as the target ID;

[0070] Obtaining a browsing record corresponding to the target ID, and then obtaining a content link corresponding to the browsing link in the browsing record, and marking the content category and name keyword corresponding to the content link as an explicit category and an explicit keyword respectively;

[0071] Generate a dominant category set according to the dominant categories;

[0072] The explicit category set = {explicit category 1, explicit category 2, ..., explicit category n}, where n is a positive integer;

[0073] Generate an explicit keyword set according to the explicit keywords; the explicit keyword set = {explicit keyword 1, explicit keyword 2, ..., explicit keyword n}, where n is a positive integer;

[0074] Set the explicit threshold;

[0075] Obtain the dominant categories and their corresponding occurrence times in the dominant category set, and record the dominant categories whose occurrence times are greater than or equal to the dominant threshold as high-frequency categories;

[0076] Generate a user profile corresponding to the user ID based on high-frequency categories and explicit keyword sets;

[0077] It should be further explained that, in the specific implementation process, the process of obtaining the corresponding derivative portrait set according to the user portrait includes:

[0078] Obtain user portraits corresponding to other user IDs except the target ID, obtain user IDs corresponding to user portraits in which high-frequency categories in the user portraits are consistent with high-frequency categories in the user portraits corresponding to the target ID, and mark the user IDs as derived IDs;

[0079] Obtain a user portrait corresponding to a derivative ID, and mark the user portrait as a derivative portrait;

[0080] Generate a derivative portrait set based on the derivative ID and derivative portrait;

[0081] The derivative image set = , where n is a positive integer;

[0082] It should be further explained that, in the specific implementation process, the process of generating push content based on the user portrait and its corresponding derivative portrait set includes:

[0083] The push content includes broad category push content and anchor push content;

[0084] Obtain the high-frequency categories and explicit keywords corresponding to the user portrait of the target ID, and mark them as target categories and target keywords respectively;

[0085] Get the derivative ID in the derivative portrait set;

[0086] Generate browsing data links based on the derived ID, and generate anchored push content based on the target category, target keyword and browsing data links;

[0087] Generate push content in broad categories based on target categories and derived portrait sets;

[0088] The process of generating a browsing data link according to the derived ID and generating anchored push content according to the target type, target keyword and browsing data link includes:

[0089] Generate query information according to the derived ID, submit the query information to the browsing record unit, and obtain the browsing record subunit corresponding to the derived ID;

[0090] Obtaining browsing records in the browsing record subunit, sorting browsing links according to browsing time in the browsing records, recording the sorted browsing links as browsing nodes, and generating a browsing data link according to the browsing nodes;

[0091] The browsing data chain includes a plurality of browsing nodes, one browsing node corresponds to one browsing link, and the browsing nodes are sequentially connected in position, and the time interval between the browsing time corresponding to the browsing node at the rear and the current time of two adjacent browsing nodes is smaller than the time interval between the browsing time corresponding to the browsing node at the front and the current time;

[0092] Assume there is a browsing node P i and browse node P i+1 , browse node P i and browse node P i+1 are two adjacent browsing nodes, and browsing node P i The browsing node P is located in the front. i+1 For the browsing node at the back;

[0093] If you browse node P i The corresponding browsing time is Pt i , browse node P i+1 The corresponding browsing time is Pt i+1 , set the current time to Nt, then the time interval between the browsing time corresponding to the browsing node at the back and the current time is smaller than the time interval between the browsing time corresponding to the browsing node at the front and the current time, which is |Pt i -Nt|>|Pt i+1 -Nt|;

[0094] If there is a browsing node in the browsing data chain whose corresponding browsing link corresponds to a content type that is consistent with the target type, the browsing node is marked as an anchor node;

[0095] If there is a browsing node in the browsing data chain whose name keyword corresponding to the corresponding browsing link is consistent with the target keyword, then the browsing node is marked as an anchor node;

[0096] Acquire a browsing node that is adjacent to the anchor node and located behind the anchor node when the anchor node is located in front, and mark the browsing node as a pushed node;

[0097] Obtaining a browsing link corresponding to the push node, and recording a content link corresponding to the browsing link as the anchored push content;

[0098] The process of generating large-category push content based on target categories and derived image sets includes:

[0099] Set frequency threshold;

[0100] Obtain high-frequency categories other than the target category and the number of occurrences thereof corresponding to each derivative portrait in the derivative portrait set, and record the high-frequency category corresponding to the number of occurrences greater than or equal to the frequency threshold as the push category;

[0101] Generate a query signal according to the push type, submit the query signal to the content information unit, obtain a content link in the content information unit corresponding to the content type and the push type, and record the content link as a major push content;

[0102] It should be further explained that, in the specific implementation process, the process of obtaining the user's browsing result of the pushed content and generating a corresponding adjustment strategy according to the browsing result includes:

[0103] Set offline duration, repetition threshold, and statistical threshold;

[0104] Set up greylist and blacklist;

[0105] Step a1: obtaining a user ID corresponding to the user, and generating a browsing data link according to the user ID according to the principle process of generating a browsing data link through a derived ID;

[0106] Step a2: obtaining a content link corresponding to the pushed content, obtaining a browsing node corresponding to the pushed content in the browsing data chain according to the content link, and marking the browsing node as a verification node;

[0107] Step a3: obtaining a browsing link corresponding to the verification node, and recording the content duration corresponding to the content link corresponding to the browsing link as the effective duration of the verification node;

[0108] Step a4: Obtain a browsing node that is adjacent to the position of the check node and is located behind the check node when the check node is located in front, and obtain the time interval between the check node and the browsing node. If the time interval is greater than or equal to the valid time of the check node and less than the offline time, the browsing result of the pushed content corresponding to the check node is successful, and the check node is a valid node; otherwise, the browsing result of the pushed content corresponding to the check node is failed, and the check node is an invalid node;

[0109] Step a5: Obtain the browsing link corresponding to the invalid node, and send the content type and name keyword corresponding to the content link corresponding to the browsing link to the gray list;

[0110] Step a6: Repeat steps a1 to a5, and count the gray list in the process of repeated execution, and obtain the content types, name keywords, content type occurrence times and name keyword occurrence times in the gray list according to the statistical results; if the content type occurrence times corresponding to a certain content type in the gray list is greater than the repetition threshold, the content type is sent to the blacklist; if the name keyword occurrence times corresponding to a certain name keyword in the gray list is greater than the repetition threshold, the name keyword is sent to the blacklist; when a certain content type appears for the first time in the gray list statistical results, the subsequent (Num-1) statistical results are obtained, if the content type occurrence times corresponding to the content type in the first to the subsequent (Num-1) statistical results are all less than or equal to the repetition threshold, the content type is deleted from the gray list; when a certain name keyword appears for the first time in the gray list statistical results, the subsequent (Num-1) statistical results are obtained, if the name keyword occurrence times corresponding to the name keyword in the first to the subsequent (Num-1) statistical results are all less than or equal to the repetition threshold, the name keyword is deleted from the gray list; wherein Num=statistical threshold;

[0111] If the high-frequency category corresponding to the derivative image in the derivative image set is consistent with the content category in the blacklist, the derivative image will be deleted;

[0112] If the explicit keyword corresponding to the derivative portrait in the derivative portrait set is consistent with the name keyword in the blacklist, the derivative portrait will be deleted;

[0113] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A multimedia content management and push system, comprising a control center, characterized in that: The control center is communicatively connected to a database, a user portrait generation module, a derivative portrait set acquisition module, a promotion content generation module and a feedback result processing module; The database is used to store multimedia content information, user information and browsing records; The user portrait generation module is used to generate a user portrait based on user information and browsing history; The derived portrait set acquisition module is used to acquire the corresponding derived portrait set according to the user portrait; The push content generation module is used to generate push content according to the user portrait and its corresponding derivative portrait set; The feedback result processing module is used to obtain the user's browsing result on the pushed content, and generate a corresponding adjustment strategy according to the browsing result.

2. A multimedia content management and push system according to claim 1, characterized in that: The database includes a content information unit, a user information unit and a browsing record unit; The content information unit is used to store multimedia content information, and the content information includes content name, content link, content type, name keyword and content duration; The user information unit is used to store the user's identity information, which includes user name, user ID, mobile phone number and login password; The browsing record unit includes several browsing record sub-units, each of which is used to store the user's browsing record and each browsing record sub-unit has its corresponding user ID; the browsing record includes a browsing link and a browsing time, wherein the browsing link corresponds to the content link in the content information unit.

3. A multimedia content management and push system according to claim 2, characterized in that: The process of generating a user profile based on user information and browsing history includes: Obtain a user ID corresponding to the user, and record the user ID as the target ID; Obtaining a browsing record corresponding to the target ID, and then obtaining a content link corresponding to the browsing link in the browsing record, and marking the content category and name keyword corresponding to the content link as an explicit category and an explicit keyword respectively; Generate a dominant category set according to the dominant categories; Generate an explicit keyword set based on the explicit keywords; Set a dominant threshold; obtain the dominant categories that appear in the dominant category set and their corresponding occurrence times, and record the dominant categories whose occurrence times are greater than or equal to the dominant threshold as high-frequency categories; Generate user portraits corresponding to target IDs based on high-frequency categories and explicit keyword sets.

4. A multimedia content management and push system according to claim 3, characterized in that: The process of obtaining the corresponding derivative portrait set based on the user portrait includes: Obtain user portraits corresponding to other user IDs except the target ID, obtain user IDs corresponding to user portraits in which high-frequency categories in the user portraits are consistent with high-frequency categories in the user portraits corresponding to the target ID, and mark the user IDs as derived IDs; Obtain a user portrait corresponding to a derivative ID, and mark the user portrait as a derivative portrait; Generate a derivative image set based on the derivative ID and derivative image.

5. A multimedia content management and push system according to claim 4, characterized in that: The process of generating push content based on user portraits and their corresponding derivative portrait sets includes: The push content includes broad category push content and anchor push content; Obtain the high-frequency categories and explicit keywords corresponding to the user portrait of the target ID, and mark them as target categories and target keywords respectively; Get the derivative ID in the derivative portrait set; Generate browsing data links based on the derived ID, and generate anchored push content based on the target category, target keyword and browsing data links; Generate broad category push content based on target categories and derived portrait sets.

6. A multimedia content management and push system according to claim 5, characterized in that: The process of generating a browsing data chain based on the derived ID and generating anchored push content based on the target category, target keyword and browsing data chain includes: Generate query information according to the derived ID, submit the query information to the browsing record unit, and obtain the browsing record subunit corresponding to the derived ID; Obtaining browsing records in the browsing record subunit, sorting browsing links according to browsing time in the browsing records, recording the sorted browsing links as browsing nodes, and generating a browsing data link according to the browsing nodes; If there is a browsing node in the browsing data chain whose corresponding browsing link corresponds to a content type that is consistent with the target type, the browsing node is marked as an anchor node; If there is a browsing node in the browsing data chain whose name keyword corresponding to the corresponding browsing link is consistent with the target keyword, then the browsing node is marked as an anchor node; Acquire a browsing node that is adjacent to the anchor node and located behind the anchor node when the anchor node is located in front, and mark the browsing node as a pushed node; A browsing link corresponding to the push node is obtained, and a content link corresponding to the browsing link is recorded as the anchored push content.

7. A multimedia content management and push system according to claim 6, characterized in that: The process of generating push content in large categories based on target categories and derived image sets includes: Set frequency threshold; Obtain high-frequency categories other than the target category and the number of occurrences thereof corresponding to each derivative portrait in the derivative portrait set, and record the high-frequency category corresponding to the number of occurrences greater than or equal to the frequency threshold as the push category; Generate a query signal according to the push type, submit the query signal to the content information unit, obtain a content link in the content information unit corresponding to the content type and the push type, and record the content link as a large category of push content.

8. A multimedia content management and push system according to claim 7, characterized in that: The process of obtaining the browsing result of the user on the pushed content and generating a corresponding adjustment strategy according to the browsing result includes: Set offline duration, repetition threshold, and statistical threshold; Set up greylist and blacklist; Step a1: obtaining a user ID corresponding to the user, and generating a browsing data link according to the user ID according to the principle process of generating a browsing data link through a derived ID; Step a2: obtaining a content link corresponding to the pushed content, obtaining a browsing node corresponding to the pushed content in the browsing data chain according to the content link, and marking the browsing node as a verification node; Step a3: obtaining a browsing link corresponding to the verification node, and recording the content duration corresponding to the content link corresponding to the browsing link as the effective duration of the verification node; Step a4: Obtain a browsing node that is adjacent to the position of the check node and is located behind the check node when the check node is located in front, and obtain the time interval between the check node and the browsing node. If the time interval is greater than or equal to the valid time of the check node and less than the offline time, the browsing result of the pushed content corresponding to the check node is successful, and the check node is a valid node; otherwise, the browsing result of the pushed content corresponding to the check node is failed, and the check node is an invalid node; Step a5: Obtain the browsing link corresponding to the invalid node, and send the content type and name keyword corresponding to the content link corresponding to the browsing link to the gray list; Step a6: Repeat steps a1 to a5, and count the gray list in the process of repeated execution, and obtain the content types, name keywords, content type occurrence times and name keyword occurrence times in the gray list according to the statistical results; if the content type occurrence times corresponding to a certain content type in the gray list is greater than the repetition threshold, the content type is sent to the blacklist; if the name keyword occurrence times corresponding to a certain name keyword in the gray list is greater than the repetition threshold, the name keyword is sent to the blacklist; when a certain content type appears for the first time in the gray list statistical results, the subsequent (Num-1) statistical results are obtained, if the content type occurrence times corresponding to the content type in the first to the subsequent (Num-1) statistical results are all less than or equal to the repetition threshold, the content type is deleted from the gray list; when a certain name keyword appears for the first time in the gray list statistical results, the subsequent (Num-1) statistical results are obtained, if the name keyword occurrence times corresponding to the name keyword in the first to the subsequent (Num-1) statistical results are all less than or equal to the repetition threshold, the name keyword is deleted from the gray list; wherein Num=statistical threshold; If the high-frequency category corresponding to the derivative image in the derivative image set is consistent with the content category in the blacklist, the derivative image will be deleted; If the explicit keyword corresponding to the derivative portrait in the derivative portrait set is consistent with the name keyword in the blacklist, the derivative portrait will be deleted.

Images