阅读说明：本技术 一种对海量用户生产内容进行自动内容管控的方法 (Method for automatically managing and controlling mass user production content ) 是由 李森和 于 2019-09-20 设计创作，主要内容包括：本发明提供了一种对海量用户生产内容进行自动内容管控的方法,包括如下的步骤：步骤1)用户输入内容,点击发送至客户端,客户端提示包含敏感词的窗口命令,是否进行确认修改；步骤2)客户端根据其内设置的本地敏感词库验证,查看是否存在敏感词；如过包含敏感词,返回至步骤1),如果不包含敏感词进入下一步骤；步骤3)客户端将用户ID以及发送的内容推送至服务器端；步骤4)服务器端接收用户ID以及发送的内容,通过敏感词系统判断风险,步骤5)依据步骤4)的结果判断是否存在高风险,依次判断频道风险等级和文章风险等级,若频道风险等级和文章风险等级均在正常范围内,服务器端将接收到的用户ID发送的内容进行推送并发布至相关频道下。(The invention provides a method for automatically managing and controlling mass user production content, which comprises the following steps: step 1) a user inputs content, clicks and sends the content to a client, and the client prompts a window command containing sensitive words and determines whether to modify the window command; step 2) the client checks whether the sensitive words exist according to the verification of a local sensitive word bank arranged in the client; if the sensitive word is contained, returning to the step 1), and if the sensitive word is not contained, entering the next step; step 3) the client pushes the user ID and the sent content to the server; and 4) the server receives the user ID and the sent content, judges the risk through a sensitive word system, and 5) judges whether high risk exists according to the result of the step 4), sequentially judges the channel risk level and the article risk level, and pushes the received content sent by the user ID to a related channel if the channel risk level and the article risk level are both in a normal range.)

1. A method for automatically managing and controlling the production content of mass users is characterized by comprising the following steps:

step 1) a user inputs content, clicks and sends the content to a client, and the client prompts a window command containing sensitive words and determines whether to modify the window command;

step 2) the client checks whether the sensitive words exist according to the verification of a local sensitive word bank arranged in the client; if the sensitive word is contained, returning to the step 1), and if the sensitive word is not contained, entering the next step;

step 3) the client pushes the user ID and the sent content to the server;

step 4) the server receives the user ID and the sent content, judges the risk through a sensitive word system and big data semantic analysis, and specifically comprises the following steps:

before risk judgment, pre-storing received content sent by a user into at least one picture in a readable format, and caching the picture in the readable format to a server side;

firstly, the method comprises the following steps: determining risk by sensitive word system, including

The server is provided with a scanning window module, the scanning window module is used for identifying the boundary of the picture in the readable format, a driving module is embedded in the scanning window module, the driving module drives a sliding template to slide in the boundary identified by the scanning window module, text information on the picture in the readable format is identified, the identified text information is compared with a sensitive word bank set by the server, whether sensitive words exist or not is checked, the whole boundary is traversed, and the risk result of the sensitive words is judged and summarized;

II, secondly: big data semantic analysis judges risk, including

The server is provided with a scanning window module, the scanning window module is used for identifying the boundary of a picture in a readable format, a driving module is embedded in the scanning window module and drives a floating window module to slide in the boundary identified by the scanning window module, the floating window module breaks sentences according to identified special fields and sends the obtained broken sentences to a semantic analysis module, the semantic analysis module processes the broken sentences, records emotion grades expressed by the sentences, traverses the whole boundary and judges and summarizes emotion grade risk results expressed by the sentences;

step 5) judging whether high risk exists according to the result of the step 4), if so, shielding the content sent by the server and recording the ID of the user by the server, and executing the processes of login limitation, user language prohibition, channel language prohibition and article language prohibition according to the historical data and the severity level under the ID of the user; if the high risk does not exist, judging and recording the risk level of the user according to the historical data level under the user ID, if the risk level of the user exceeds a set threshold value, sending the user ID to a manual review client side for manual review, if the risk level of the user does not exceed the set threshold value, sequentially judging the channel risk level and the article risk level, and if the channel risk level and the article risk level are both in a normal range, pushing the received content sent by the user ID by the server side and issuing the content to a related channel.

2. The method for performing automatic content management and control on mass production content of users according to claim 1, wherein in step 5), if there is a high risk in manual review, the manual client enters a feedback command to the server to shield the content sent by the server and record the ID of the user, and performs processing of login limitation, user language inhibition, channel language inhibition and article language inhibition according to historical data and severity level under the ID of the user; and if the high risk does not exist in the manual examination, sequentially judging the channel risk level and the article risk level, and if the channel risk level and the article risk level are both in a normal range, pushing the received content sent by the user ID by the server side and releasing the content to a related channel.

3. The method for performing automatic content management and control on mass user production content according to claim 1 or 2, characterized in that in step 5), the channel risk level is judged, if the channel risk level is not within a normal range, the server shields the content sent by the server and records the ID of the user, and performs processing of restricting login, prohibiting users from speaking, prohibiting channels from speaking, and prohibiting articles from speaking according to the historical data and the severity level under the ID of the user.

4. The method for performing automatic content management and control on mass user production content according to claim 1 or 2, characterized in that in step 5), the article risk level is judged, if the article risk level is not in a normal range, the server shields the content sent by the article risk level and records the ID of the user, and performs processing of login limitation, user language prohibition, channel language prohibition and article language prohibition according to the historical data and the severity level under the ID of the user.

Technical Field

The invention provides the technical field of computers, relates to a content publishing management and control technology, and particularly relates to a method for automatically managing and controlling content of mass user production.

Background

The term "content" is derived from the creation in the publishing media industry, books, newspapers, magazines, video tapes, and is called content, so the early content management cm (content management) is biased towards the management of published products and makes the system with storage, flow, and Metadata (Metadata) as the key elements. Content management refers to the process of organizing, sorting, managing, etc. information resources (often referred to as information assets) in various formats and media types within an organization, often as a component of digital library or enterprise knowledge management.

With the widespread use of networks, content management shows a trend of big data management, the existing content management only filters key sensitive words of published content, the filtering of the key sensitive words can not completely filter some words such as harmonic characters, head-hidden characters and the like, and semantic analysis can not be carried out to obtain risk factors in the content.

Disclosure of Invention

In view of this, the present invention provides a method for performing automatic content management and control on mass user production content.

The technical scheme adopted by the invention is as follows:

a method for automatically managing and controlling the production content of mass users comprises the following steps:

step 1) a user inputs content, clicks and sends the content to a client, and the client prompts a window command containing sensitive words and determines whether to modify the window command;

step 2) the client checks whether the sensitive words exist according to the verification of a local sensitive word bank arranged in the client; if the sensitive word is contained, returning to the step 1), and if the sensitive word is not contained, entering the next step;

step 3) the client pushes the user ID and the sent content to the server;

step 4) the server receives the user ID and the sent content, judges the risk through a sensitive word system and big data semantic analysis, and specifically comprises the following steps:

before risk judgment, pre-storing received content sent by a user into at least one picture in a readable format, and caching the picture in the readable format to a server side;

firstly, the method comprises the following steps: determining risk by sensitive word system, including

The server is provided with a scanning window module, the scanning window module is used for identifying the boundary of the picture in the readable format, a driving module is embedded in the scanning window module, the driving module drives a sliding template to slide in the boundary identified by the scanning window module, text information on the picture in the readable format is identified, the identified text information is compared with a sensitive word bank set by the server, whether sensitive words exist or not is checked, the whole boundary is traversed, and the risk result of the sensitive words is judged and summarized;

II, secondly: big data semantic analysis judges risk, including

The server is provided with a scanning window module, the scanning window module is used for identifying the boundary of a picture in a readable format, a driving module is embedded in the scanning window module and drives a floating window module to slide in the boundary identified by the scanning window module, the floating window module breaks sentences according to identified special fields and sends the obtained broken sentences to a semantic analysis module, the semantic analysis module processes the broken sentences, records emotion grades expressed by the sentences, traverses the whole boundary and judges and summarizes emotion grade risk results expressed by the sentences;

step 5) judging whether high risk exists according to the result of the step 4), if so, shielding the content sent by the server and recording the ID of the user by the server, and executing the processes of login limitation, user language prohibition, channel language prohibition and article language prohibition according to the historical data and the severity level under the ID of the user; if the high risk does not exist, judging and recording the risk level of the user according to the historical data level under the user ID, if the risk level of the user exceeds a set threshold value, sending the user ID to a manual review client side for manual review, if the risk level of the user does not exceed the set threshold value, sequentially judging the channel risk level and the article risk level, and if the channel risk level and the article risk level are both in a normal range, pushing the received content sent by the user ID by the server side and issuing the content to a related channel.

In step 5), if the manual review has high risk, the manual client end inputs a feedback command to the server to shield the content sent by the server and record the ID of the user, and executes the processes of limited login, user banning, channel banning and article banning according to the historical data and the severity level under the ID of the user; and if the high risk does not exist in the manual examination, sequentially judging the channel risk level and the article risk level, and if the channel risk level and the article risk level are both in a normal range, pushing the received content sent by the user ID by the server side and releasing the content to a related channel.

In step 5), judging the channel risk level, if the channel risk level is not in the normal range, shielding the content sent by the server and recording the ID of the user by the server, and executing the processes of login limitation, user language inhibition, channel language inhibition and article language inhibition according to the historical data and the severity level under the ID of the user.

In step 5), judging the risk level of the article, if the risk level of the article is not in the normal range, shielding the content sent by the server and recording the ID of the user by the server, and executing the processes of login limitation, user language prohibition, channel language prohibition and article language prohibition according to the historical data and the severity level under the ID of the user.

The invention has the beneficial effects that:

compared with the traditional technology, the method comprises the steps of scanning through sensitive words, pre-storing received contents sent by a user into at least one readable format picture, caching the readable format picture to a server side, identifying the boundary of the readable format picture by a scanning window module, sliding in the boundary identified by the scanning window module, identifying character information on the readable format picture, comparing the identified character information with a sensitive word library set by the server, checking whether sensitive words exist or not, traversing the whole boundary, and judging and summarizing sensitive word risk results; the scanning window module can slide transversely, longitudinally and obliquely according to a certain angle in the identified boundary, so that the scanning window module can carry out omnibearing sensitive word checking on the whole content.

Compared with the traditional technology, the risk is judged through big data semantic analysis, the received content sent by a user is prestored into at least one readable format picture, the readable format picture is cached to a server side, the floating window module slides in a boundary identified by the scanning window module, the floating window module breaks sentences according to identified special fields and sends the obtained broken sentences to the semantic analysis module, the semantic analysis module processes the broken sentences, records the emotion level expressed by the sentences, traverses the whole boundary, and judges and summarizes emotion level risk results expressed by the sentences; the emotional level expressed by the sentence includes whether the sentence contains an angry emotion, whether the sentence contains a harmonic vocabulary, and the like.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a flow chart of the method of the present invention.

DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION

The present invention will now be described in detail with reference to the drawings and specific embodiments, wherein the exemplary embodiments and descriptions of the present invention are provided to explain the present invention without limiting the invention thereto.