Audit method, device and equipment for community content and readable storage medium

Abstract

The invention discloses an auditing method, device and equipment for community content and a readable storage medium. The method comprises the following steps: acquiring to-be-audited information published by a community user in a network community; whether the community user exists in a preset white list or not is judged, if yes, the to-be-audited information is directly published, and the to-be-audited information is stored in a preset cache so as to wait for subsequent audit of the to-be-audited information through a preset low-level strategy; when the to-be-audited information does not exist in the white list, judging whether the community user is a new user, if so, auditing the to-be-audited information through a preset high-level strategy, and if not, auditing the to-be-audited information through a preset middle-level strategy; according to the invention, the information published in the network community can be audited efficiently and accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method, apparatus, device and readable storage medium for auditing community content. Background Art

[0002] In recent years, with the increasing development of technology, the frequency of people using mobile phones has become higher and higher, and the Internet population has become more and more complex. As an important place in the Internet ecosystem for users to express their opinions, the content community is easily exploited by malicious users to spread some illegal content on the platform. Therefore, in order to purify the network and enable users to enjoy the convenience of the network more safely, it is necessary to audit the content published in the content community; the existing auditing methods are manual auditing or content auditing only through keywords, which have the problems of low efficiency and low accuracy. Therefore, how to audit the content published on the network more efficiently and accurately has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, apparatus, device and readable storage medium for auditing community content, which can efficiently and accurately audit the information published in the network community.

[0004] According to one aspect of the present invention, a method for auditing community content is provided, and the method includes:

[0005] Obtain the information to be audited published by the community user in the network community;

[0006] Judge whether the community user exists in a preset white list. If so, directly publish the information to be audited and store the information to be audited in a preset cache to wait for subsequent auditing of the information to be audited through a preset low-level policy;

[0007] When not existing in the white list, judge whether the community user is a new user. If so, audit the information to be audited through a preset high-level policy. If not, audit the information to be audited through a preset medium-level policy.

[0008] Optionally, the judging whether the community user exists in a preset white list specifically includes:

[0009] Judge whether the identity identification information of the community user or the device identification information used by the community user exists in a preset black list;

[0010] If so, reject the publication of the information to be audited. If not, continue to judge whether the community user exists in a preset white list.

[0011] Optionally, storing the information to be reviewed in a preset cache to wait for subsequent review of the information to be reviewed through a preset low-level policy specifically includes:

[0012] Adopting a set time interval, regularly sorting each piece of information to be reviewed in the preset cache in descending order of the cached duration to obtain a sorting result;

[0013] According to the sorting result, sequentially review each piece of information to be reviewed through the low-level policy;

[0014] When there is information to be reviewed that fails the review, delete the published information to be reviewed that fails the review from the network community.

[0015] Optionally, judging whether the community user is a new user specifically includes:

[0016] Judging whether the registration duration of the community user is less than a first preset duration. If so, determine that the community user is a new user;

[0017] Judging whether the cumulative online duration of the community user is less than a second preset duration. If so, determine that the community user is a new user; or,

[0018] Judging whether the number of times the community user has cumulatively published information is less than a preset threshold. If so, determine that the community user is a new user.

[0019] Optionally, reviewing the information to be reviewed through a preset high-level policy specifically includes:

[0020] Step 1: Judge whether there is a preset sensitive word in the information to be reviewed. If so, reject the publication of the information to be reviewed. If not, execute Step 2;

[0021] Step 2: Use a preset classification model to judge whether the information to be reviewed belongs to a preset violation type. If so, reject the publication of the information to be reviewed. If not, execute Step 3:

[0022] Step 3: Judge whether the community user has published the information to be reviewed within a time period of a third preset duration from the current time point. If so, reject the publication of the information to be reviewed. If not, execute Step 4;

[0023] Step 4: Send the information to be reviewed to a preset terminal for manual review;

[0024] Step 5: When receiving a review-pass message sent by the preset terminal, publish the information to be reviewed in the network community. Or, when receiving a review-fail message sent by the preset terminal, reject the publication of the information to be reviewed.

[0025] Optionally, after obtaining the information to be reviewed posted by the community user in the online community, the method further includes:

[0026] Obtain the territorial information used by the community user to post the information to be reviewed;

[0027] Obtain the regional policy corresponding to the territorial information, and perform content review on the information to be reviewed through the regional policy.

[0028] To achieve the above object, the present invention further provides an audit device for community content, and the device includes:

[0029] An obtaining module, configured to obtain information to be reviewed posted by a community user in an online community;

[0030] A judgment module, configured to judge whether the community user exists in a preset white list. If so, directly post the information to be reviewed and store the information to be reviewed in a preset cache to wait for subsequent review of the information to be reviewed through a preset low-level policy;

[0031] An audit module, configured to, when not existing in the white list, judge whether the community user is a new user. If so, audit the information to be reviewed through a preset high-level policy, and if not, audit the information to be reviewed through a preset medium-level policy.

[0032] Optionally, the judgment module is specifically configured to:

[0033] Judge whether the identity identification information of the community user or the device identification information used by the community user exists in a preset black list;

[0034] If so, reject posting the information to be reviewed, and if not, continue to judge whether the community user exists in a preset white list.

[0035] To achieve the above object, the present invention further provides a computer device, which specifically includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the above-described audit method for community content are implemented.

[0036] To achieve the above object, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-described audit method for community content are implemented.

[0037] The auditing method, device, equipment and readable storage medium for community content provided by the present invention classify community users according to the historical behaviors of community users, so as to audit the information published by different categories of community users using strategies of different levels in a targeted manner, thereby completing content auditing more efficiently while ensuring the auditing accuracy rate. The present invention adopts a multi-dimensional and refined auditing method, and the entire auditing process achieves all-round and blind-spot-free auditing, having better auditing flexibility and higher security of the audited content compared with other products on the market. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0039] Figure 1 FIG. is an alternative flowchart of the auditing method for community content provided for Embodiment 1;

[0040] Figure 2 FIG. is an alternative structural composition diagram of the auditing device for community content provided for Embodiment 2;

[0041] Figure 3 FIG. is an alternative hardware architecture diagram of the computer equipment provided for Embodiment 3. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0043] Embodiment 1

[0044] The embodiment of the present invention provides an auditing method for community content, as Figure 1 shown, the method specifically includes the following steps:

[0045] Step S101: Obtain the information to be audited published by a community user in the online community.

[0046] Among them, the information to be audited includes at least one of the following: user nickname information, user signature information, user post information, user comment information.

[0047] Step S102: Determine whether the community user exists in a preset whitelist. If so, directly publish the information to be reviewed and store the information to be reviewed in a preset cache to wait for subsequent review of the information to be reviewed through a preset low-level policy.

[0048] In this embodiment, a whitelist will be set in advance according to user behavior, and users with good behavior will be added to the whitelist; for the information published by community users on the whitelist, a "publish first and then review" policy will be implemented, so as to avoid the situation of delayed speech of high-quality users and improve the user speech experience.

[0049] Specifically, the determination of whether the community user exists in a preset whitelist includes:

[0050] Determine whether the identity identification information of the community user or the device identification information used by the community user exists in a preset blacklist;

[0051] If so, reject the publication of the information to be reviewed. If not, continue to determine whether the community user exists in the preset whitelist.

[0052] In this embodiment, in addition to setting a whitelist in advance, a blacklist is also set in advance according to user behavior, and users with poor behavior are added to the blacklist; in this embodiment, when it is detected that a community user publishes information, first determine whether the community user exists in the blacklist. If so, reject the publication of the information. If not, continue to determine whether the community user exists in the whitelist. When the user exists in the whitelist, the information will be directly published. When the user does not exist in the whitelist, the information needs to be reviewed using a preset review policy.

[0053] Further, the storing the information to be reviewed in a preset cache to wait for subsequent review of the information to be reviewed through a preset low-level policy specifically includes:

[0054] Step A1: At a set time interval, regularly sort each piece of information to be reviewed in the preset cache in descending order of the cached duration to obtain a sorting result;

[0055] Step A2: According to the sorting result, review each piece of information to be reviewed in turn through the low-level policy;

[0056] Step A3: When there is information to be reviewed that fails the review, delete the published information to be reviewed that fails the review from the network community.

[0057] In this embodiment, in order to avoid the situation that the information to be reviewed in the cache is not reviewed for a long time, the information to be reviewed in the cache will be sorted regularly to give priority to reviewing the information to be reviewed with a too long cache time.

[0058] In practical applications, Kafka can be used as a message queue to cache the information to be audited; by using Kafka for decoupling and peak shaving, a large amount of information can be received, improving the scalability, maintainability, robustness, etc. of the system; compared with other message middleware, Kafka has great advantages in throughput, and consumers can also consume in batches, with high scalability.

[0059] Furthermore, the step of auditing each piece of information to be audited through the low-level policy specifically includes:

[0060] Judge whether there are preset sensitive words in the information to be audited. If so, delete the published information to be audited from the network community.

[0061] In this embodiment, for community users in the whitelist, only sensitive word detection is performed through a preset thesaurus; in practical applications, the thesaurus may include: a sensitive word library, a violation word library, a negative content word library, an anti-rudeness word library, and a thesaurus blacklist; that is, judge whether there are words belonging to the thesaurus in the information to be audited. If so, the published information needs to be deleted from the network community.

[0062] Step S103: When not in the whitelist, judge whether the community user is a new user. If so, audit the information to be audited through a preset high-level policy. If not, audit the information to be audited through a preset medium-level policy.

[0063] Specifically, the judgment of whether the community user is a new user includes:

[0064] Judge whether the registration duration of the community user is less than a first preset duration. If so, determine that the community user is a new user;

[0065] Judge whether the cumulative online duration of the community user is less than a second preset duration. If so, determine that the community user is a new user; or,

[0066] Judge whether the number of times the community user has published information is less than a preset threshold. If so, determine that the community user is a new user.

[0067] Further, the auditing of the information to be audited through a preset high-level policy specifically includes:

[0068] Step B1: Judge whether there are preset sensitive words in the information to be audited. If so, reject the publication of the information to be audited. If not, execute step B2;

[0069] Step B2: Use a preset classification model to determine whether the information to be reviewed belongs to a preset violation type. If so, reject the publication of the information to be reviewed. If not, execute Step B3:

[0070] Preferably, determine whether the information to be reviewed belongs to any of the following violation types according to the preset classification model: advertising content, political speech, personal attack, pornographic content, violent and terrorist content, bloody content; in this embodiment, the classification model is trained in advance using text samples and a preset algorithm to review the information to be reviewed through the classification model;

[0071] Step B3: Determine whether the community user has published the information to be reviewed within a time period of the third preset duration from the current time point. If so, reject the publication of the information to be reviewed. If not, execute Step B4;

[0072] Step B4: Send the information to be reviewed to a preset terminal for manual review;

[0073] Step B5: When receiving a review passed message sent by the preset terminal, publish the information to be reviewed in the network community, or when receiving a review not passed message sent by the preset terminal, reject the publication of the information to be reviewed.

[0074] Further, the review of the information to be reviewed through the preset medium-level policy specifically includes:

[0075] Step C1: Determine whether there are preset sensitive words in the information to be reviewed. If so, reject the publication of the information to be reviewed. If not, execute Step C2;

[0076] Step C2: Use a preset classification model to determine whether the information to be reviewed belongs to a preset violation type. If so, reject the publication of the information to be reviewed. If not, execute Step C3:

[0077] Step C3: Determine whether the community user has published the information to be reviewed within a time period of the third preset duration from the current time point. If so, reject the publication of the information to be reviewed. If not, publish the information to be reviewed in the network community.

[0078] In this embodiment, not only are community users classified and defined, but also the review policies are classified. Specifically, the following three review policies are set: low-level policy, medium-level policy, and high-level policy; among them, the low-level policy only needs to perform sensitive word detection, the medium-level policy needs to perform sensitive word detection, violation detection using a preset classification model, and duplicate publication detection in addition, and an artificial review link is set in the high-level policy.

[0079] In addition, in practical applications, a first queue, a second queue, and a third queue can also be set up. Among them, the first queue stores the information to be reviewed that needs to be reviewed using low-level policies, the second queue stores the information to be reviewed that needs to be reviewed using medium-level policies, and the third queue stores the information to be reviewed that needs to be reviewed using high-level policies. Among them, the review priority of the second queue is higher than that of the first queue, and the review priority of the first queue is higher than that of the third queue. That is, processing threads are preferentially allocated to the second queue to preferably review the information to be reviewed in the second queue. Since the information to be reviewed in the third queue may require manual review, and the information published by new users does not have to be immediately published, the review priority of the third queue is the lowest. In addition, since the information to be reviewed in the first queue has been published and the review time required for the information to be reviewed in the first queue is short, it does not have to occupy a large number of threads to be processed first. Compared with the first queue and the third queue, the number of information to be reviewed in the second queue is the largest, so a large number of threads need to be occupied to be processed first. Through the above method, the information to be reviewed can be more reasonably reviewed, improving the review efficiency while ensuring the review accuracy.

[0080] Further, after the step S101, the method further includes:

[0081] Step D1: Obtain the territorial information used by the community user to publish the information to be reviewed;

[0082] Step D2: Obtain the regional policy corresponding to the territorial information, and perform content review on the information to be reviewed through the regional policy.

[0083] In this embodiment, a two-level review system is adopted. Among them, the above steps S102 to S103 are the first-level review system, that is, the general review system; and the above steps D1 to D2 are the second-level review system, that is, the regional review system. When the information to be reviewed is reviewed and completed through the first-level review system, it should also be reviewed through the second-level review system. Since the online community may be global, that is, community users may come from different countries, and the legal systems of each country are different, therefore, the corresponding regional policy of the region should also be obtained according to the territorial information of the community user to continue to review the information to be reviewed, and the information can only be published after the regional policy review is passed.

[0084] In addition, the method further includes:

[0085] Step E1: Determine whether there is a picture in the information to be reviewed. If so, execute step E2; if not, execute step E3;

[0086] Step E2: When it is detected that the picture contains a QR code or an external link, reject the publication of the information to be reviewed;

[0087] Step E3: Use OCR recognition to determine whether the picture contains illegal text content. If so, reject the release of the information to be reviewed.

[0088] In this embodiment, the content (text, pictures, audio, video) uploaded, released or shared by users on the online community is reviewed. Its main purpose is to filter out low-quality and vulgar content, so as to produce high-quality content, prevent the reduction of user experience, and maintain a good content tone.

[0089] In this embodiment, community users are classified according to their historical behaviors, so as to use different levels of strategies to conduct targeted reviews on the information released by different categories of community users, so that content review can be completed more efficiently while ensuring the accuracy of the review. This embodiment adopts a multi-dimensional and refined review method, and the entire review process achieves a full-range and blind-spot-free review, with better review flexibility and higher security of the reviewed content than other products on the market.

[0090] Embodiment 2

[0091] An embodiment of the present invention provides an audit device for community content, as Figure 2 shown, the device specifically includes the following components:

[0092] An acquisition module 201, configured to acquire information to be reviewed released by a community user in an online community;

[0093] A judgment module 202, configured to judge whether the community user exists in a preset white list. If so, directly release the information to be reviewed and store the information to be reviewed in a preset cache to wait for subsequent review of the information to be reviewed through a preset low-level strategy;

[0094] An audit module 203, configured to, when not existing in the white list, judge whether the community user is a new user. If so, audit the information to be reviewed through a preset high-level strategy, and if not, audit the information to be reviewed through a preset medium-level strategy.

[0095] Specifically, when implementing the function of judging whether the community user exists in the preset white list, the judgment module 202 is configured to:

[0096] Judge whether the identity identification information of the community user or the device identification information used by the community user exists in a preset black list;

[0097] If so, reject the release of the information to be reviewed. If not, continue to judge whether the community user exists in the preset white list.

[0098] Further, the judgment module 202 is further configured to:

[0099] At set time intervals, regularly sort each piece of information to be reviewed in the preset cache in descending order of the cached duration to obtain a sorting result;

[0100] According to the sorting result, review each piece of information to be reviewed in turn through the low-level policy;

[0101] When there is information to be reviewed that fails the review, delete the information to be reviewed that has been published from the network community.

[0102] Specifically, when the review module 203 implements the function of judging whether the community user is a new user, it is configured to:

[0103] Judge whether the registration duration of the community user is less than a first preset duration. If so, determine that the community user is a new user;

[0104] Judge whether the cumulative online duration of the community user is less than a second preset duration. If so, determine that the community user is a new user; or,

[0105] Judge whether the number of times the community user has cumulatively published information is less than a preset threshold. If so, determine that the community user is a new user.

[0106] Further, when the review module 203 implements the function of reviewing the information to be reviewed through a preset high-level policy, it specifically includes:

[0107] Step 1: Judge whether there is a preset sensitive word in the information to be reviewed. If so, reject the publication of the information to be reviewed. If not, execute Step 2;

[0108] Step 2: Use a preset classification model to judge whether the information to be reviewed belongs to a preset violation type. If so, reject the publication of the information to be reviewed. If not, execute Step 3:

[0109] Step 3: Judge whether the community user has published the information to be reviewed within a time period of a third preset duration from the current time point. If so, reject the publication of the information to be reviewed. If not, execute Step 4;

[0110] Step 4: Send the information to be reviewed to a preset terminal for manual review;

[0111] Step 5: When receiving a review passed message sent by the preset terminal, publish the information to be reviewed in the network community. Or, when receiving a review not passed message sent by the preset terminal, reject the publication of the information to be reviewed.

[0112] Further, the device further includes:

[0113] A regional review module, configured to obtain the territorial information used by the community user to publish the information to be reviewed; obtain a regional policy corresponding to the territorial information, and perform content review on the information to be reviewed through the regional policy.

[0114] In this embodiment, the community users are classified according to their historical behaviors, so as to use different levels of policies to specifically review the information published by different categories of community users, so that content review can be completed more efficiently while ensuring the accuracy of the review. This embodiment adopts a multi-dimensional and refined review method, and the entire review process achieves a full-range and blind-spot-free review, with better review flexibility and higher security of the reviewed content compared to other products on the market.

[0115] Embodiment Three

[0116] This embodiment also provides a computer device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server or a cabinet server (including an independent server or a server cluster composed of multiple servers) that can execute programs. As Figure 3 shown, the computer device 30 of this embodiment at least includes, but is not limited to, a memory 301 and a processor 302 that can communicate with each other through a system bus. It should be noted that Figure 3 only the computer device 30 with components 301-302 is shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0117] In this embodiment, the memory 301 (i.e., the readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 301 may be an internal storage unit of the computer device 30, such as the hard disk or memory of the computer device 30. In other embodiments, the memory 301 may also be an external storage device of the computer device 30, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the computer device 30. Of course, the memory 301 may also include both the internal storage unit and the external storage device of the computer device 30. In this embodiment, the memory 301 is generally used to store the operating system and various application software installed on the computer device 30. In addition, the memory 301 may also be used to temporarily store various types of data that have been output or will be output.

[0118] In some embodiments, the processor 302 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other chips for auditing community content. The processor 302 is generally used to control the overall operation of the computer device 30.

[0119] Specifically, in this embodiment, the processor 302 is used to execute the program of the method for auditing community content stored in the memory 301. When the program of the method for auditing community content is executed, the following steps are implemented:

[0120] Obtain the information to be audited published by community users in the online community;

[0121] Determine whether the community user exists in a preset whitelist. If so, directly publish the information to be audited and store the information to be audited in a preset cache to wait for subsequent auditing of the information to be audited through a preset low-level policy;

[0122] When not in the whitelist, determine whether the community user is a new user. If so, audit the information to be audited through a preset high-level policy. If not, audit the information to be audited through a preset medium-level policy.

[0123] For the specific implementation process of the above method steps, reference may be made to Embodiment 1, and this embodiment will not be repeated here.

[0124] Embodiment 4

[0125] This embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored. When the computer program is executed by a processor, the following method steps are implemented:

[0126] Obtain the information to be reviewed published by community users in the online community;

[0127] Determine whether the community user exists in a preset whitelist. If so, directly publish the information to be reviewed and store the information to be reviewed in a preset cache to wait for subsequent review of the information to be reviewed through a preset low-level policy;

[0128] When not in the whitelist, determine whether the community user is a new user. If so, review the information to be reviewed through a preset high-level policy. If not, review the information to be reviewed through a preset medium-level policy.

[0129] For the specific implementation process of the above method steps, reference can be made to Embodiment 1, and this embodiment will not be repeated here.

[0130] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including one..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0131] The serial numbers of the above embodiments of the present invention are only for description and do not represent the superiority or inferiority of the embodiments.

[0132] Through the description of the above embodiments, those skilled in the art can clearly understand the above-mentioned cases, but in many cases the former is a better embodiment.

[0133] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be similarly included in the patent protection scope of the present invention.

Claims

1. A method for auditing community content, characterized in that, The method includes: Obtaining the information to be reviewed posted by community users in the online community; Judging whether the community user exists in a preset whitelist. If so, directly post the information to be reviewed and store the information to be reviewed in a preset cache to wait for subsequent review of the information to be reviewed through a preset low-level policy; When not existing in the whitelist, judging whether the community user is a new user. If so, review the information to be reviewed through a preset high-level policy. If not, review the information to be reviewed through a preset medium-level policy.

2. The content review method for community content according to claim 1, wherein The judging whether the community user exists in a preset whitelist specifically includes: Judging whether the identity identification information of the community user or the device identification information used by the community user exists in a preset blacklist; If so, reject the publication of the information to be reviewed. If not, continue to judge whether the community user exists in a preset whitelist.

3. The content review method for community content according to claim 1 or 2, characterized in that, The storing the information to be reviewed in a preset cache to wait for subsequent review of the information to be reviewed through a preset low-level policy specifically includes: Adopting a set time interval, regularly sorting each piece of information to be reviewed in the preset cache in descending order of the cached duration to obtain a sorting result; According to the sorting result, sequentially review each piece of information to be reviewed through the low-level policy; When there is information to be reviewed that fails the review, delete the published information to be reviewed that fails the review from the online community.

4. The content review method for community content according to claim 1, characterized in that, The judging whether the community user is a new user specifically includes: Judging whether the registration duration of the community user is less than a first preset duration. If so, determine that the community user is a new user; Judging whether the cumulative online duration of the community user is less than a second preset duration. If so, determine that the community user is a new user; or Judging whether the cumulative number of times the community user publishes information is less than a preset threshold. If so, determine that the community user is a new user.

5. The content review method for community content according to claim 1 or 4, characterized in that, The reviewing the information to be reviewed through a preset high-level policy specifically includes: Step 1: Judging whether there is a preset sensitive word in the information to be reviewed. If so, reject the publication of the information to be reviewed. If not, execute Step 2; Step 2: Using a preset classification model, judging whether the information to be reviewed belongs to a preset violation type. If so, reject the publication of the information to be reviewed. If not, execute Step 3; Step 3: Judging whether the community user has published the information to be reviewed within a time period of a third preset duration from the current time point. If so, reject the publication of the information to be reviewed. If not, execute Step 4; Step 4: Sending the information to be reviewed to a preset terminal for manual review; Step 5: When receiving an approval message sent by the preset terminal, publish the information to be reviewed in the online community. Or, when receiving a disapproval message sent by the preset terminal, reject the publication of the information to be reviewed.

6. The content review method for community content according to claim 1, wherein After obtaining the information to be reviewed posted by community users in the online community, the method further includes: Obtain the territorial information used by the community user to post the information to be reviewed; Obtain the regional policy corresponding to the territorial information, and perform content review on the information to be reviewed through the regional policy.

7. An auditing device for community content, characterized in that, The device includes: An acquisition module, configured to acquire information to be reviewed posted by a community user in a network community; A judgment module, configured to judge whether the community user exists in a preset white list. If so, directly post the information to be reviewed and store the information to be reviewed in a preset cache to wait for subsequent review of the information to be reviewed through a preset low-level policy; A review module, configured to, when not in the white list, judge whether the community user is a new user. If so, review the information to be reviewed through a preset high-level policy. If not, review the information to be reviewed through a preset medium-level policy.

8. The content review device for community content according to claim 7, wherein The judgment module is specifically configured to: Judge whether the identity identification information of the community user or the device identification information used by the community user exists in a preset black list; If so, refuse to post the information to be reviewed. If not, continue to judge whether the community user exists in a preset white list.

9. A computer device, the computer device comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when executed by the processor, implements the steps of the method according to any one of claims 1 to 6.

Images