Movatterモバイル変換


[0]ホーム

URL:


CN105323145A - Malicious information identification method, device and system - Google Patents

Malicious information identification method, device and system
Download PDF

Info

Publication number
CN105323145A
CN105323145ACN201410341818.XACN201410341818ACN105323145ACN 105323145 ACN105323145 ACN 105323145ACN 201410341818 ACN201410341818 ACN 201410341818ACN 105323145 ACN105323145 ACN 105323145A
Authority
CN
China
Prior art keywords
fallacious message
doubtful
fallacious
session
message
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201410341818.XA
Other languages
Chinese (zh)
Other versions
CN105323145B (en
Inventor
张龙攀
贺啸
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co LtdfiledCriticalTencent Technology Shenzhen Co Ltd
Priority to CN201410341818.XApriorityCriticalpatent/CN105323145B/en
Publication of CN105323145ApublicationCriticalpatent/CN105323145A/en
Application grantedgrantedCritical
Publication of CN105323145BpublicationCriticalpatent/CN105323145B/en
Expired - Fee Relatedlegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Landscapes

Abstract

Translated fromChinese

本发明提供一种恶意信息识别方法、恶意信息识别装置及系统,该恶意信息识别方法包括获取会话群组的实时会话信息;使用恶意信息模型,对实时会话信息进行恶意信息判定,以获取疑似恶意信息;对会话群组的用户发起疑似恶意信息的恶意信息判定请求,并接收用户输入的判定结果;以及根据判定结果以及预设判定方法,识别疑似恶意信息中的恶意信息。本发明还提供一种恶意信息识别装置及系统。本发明的恶意信息识别方法、恶意信息识别装置及系统通过会话群组的用户对疑似恶意信息进行恶意信息判定,提高了恶意信息的识别准确度。

The present invention provides a malicious information identification method, a malicious information identification device and a system. The malicious information identification method includes obtaining real-time session information of a session group; information; initiate a malicious information determination request for suspected malicious information to users of the conversation group, and receive a determination result input by the user; and identify malicious information in the suspected malicious information according to the determination result and a preset determination method. The invention also provides a malicious information identification device and system. The malicious information identifying method, malicious information identifying device and system of the present invention improve the identification accuracy of malicious information by performing malicious information identification on suspected malicious information through the users of the conversation group.

Description

Fallacious message recognition methods, fallacious message recognition device and system
Technical field
The present invention relates to internet security technical field, particularly relate to a kind of fallacious message recognition methods, fallacious message recognition device and system.
Background technology
Along with the development of Internet technology, people carry out information communication by various session group, and this session group can be QQ group or micro-letter group etc.Also there is increasing people to utilize above-mentioned session group to issue fallacious message, as swindle information, malice advertising message and pornography etc. simultaneously.
The existing monitoring for fallacious message in above-mentioned session group is main in the following ways:
One, monitor the Word message in session group, as detected there is the word such as " bank card ", " remittance " in communication, and session group can carry out prevention to the user in session group and remind.
Two, monitor the behavior of user in session group, as found, user carries out a series of malicious act operation, and as frequently sent web site url, then session group also can carry out prevention prompting to the user in session group or carry out masking operation to this malicious act.
But above-mentioned policer operation judges essentially by the model based on machine, this Construction of A Model based on machine is complicated and accuracy is not high.Renewal speed simultaneously due to fallacious message is more and more faster, and the model based on machine usually cannot just identify up-to-date fallacious message.Therefore cause the fallacious message recognition accuracy of the existing model based on machine lower.
Summary of the invention
The embodiment of the present invention provide a kind of can the fallacious message recognition methods that fallacious message is identified of precise and high efficiency, with the technical problem that the fallacious message recognition accuracy solving existing fallacious message recognition methods is lower.
The embodiment of the present invention also provide a kind of can the fallacious message recognition device that fallacious message is identified of precise and high efficiency, with the technical problem that the fallacious message recognition accuracy solving existing fallacious message recognition device is lower.
The embodiment of the present invention also provide a kind of can the fallacious message recognition system that fallacious message is identified of precise and high efficiency, with the technical problem that the fallacious message recognition accuracy solving existing fallacious message recognition system is lower.
For solving the problem, technical scheme provided by the invention is as follows:
The embodiment of the present invention provides a kind of fallacious message recognition methods, and it comprises:
Obtain the real-time session information of session group;
Use fallacious message model, fallacious message judgement is carried out to described real-time session information, to obtain doubtful fallacious message;
The user of described session group is initiated to the fallacious message decision request of described doubtful fallacious message, and receive the result of determination of described user input; And
According to described result of determination and default decision method, identify the fallacious message in described doubtful fallacious message.
The embodiment of the present invention also provides a kind of fallacious message recognition device, and it comprises:
Data obtaining module, for obtaining the real-time session information of session group;
Doubtful fallacious message acquisition module, for using fallacious message model, carries out fallacious message judgement to described real-time session information, to obtain doubtful fallacious message;
Determination module, for initiating the fallacious message decision request of described doubtful fallacious message to the user of described session group, and receives the result of determination of described user input; And
Identification module, for according to described result of determination and default decision method, identifies the fallacious message in described doubtful fallacious message.
The embodiment of the present invention also provides a kind of fallacious message recognition methods, and it comprises:
Receive the fallacious message decision request of the doubtful fallacious message of session cluster server, and show described fallacious message decision request at current sessions window;
According to the input of user, generate the result of determination of user's input; And
The result of determination that described user inputs is sent to described session cluster server.
The embodiment of the present invention also provides a kind of fallacious message recognition device, and it comprises:
Receiving display module, for receiving the fallacious message decision request of the doubtful fallacious message of session cluster server, and showing described fallacious message decision request at current sessions window;
Result of determination generation module, for the input according to user, generates the result of determination of user's input; And
Sending module, the result of determination for described user being inputted is sent to described session cluster server.
The embodiment of the present invention also provides a kind of fallacious message recognition methods, and it comprises:
Session cluster server obtains the real-time session information of session group;
Described session cluster server uses fallacious message model, carries out fallacious message judgement, to obtain doubtful fallacious message to described real-time session information;
The multiple users of described session cluster server to described session group initiate the fallacious message decision request of described doubtful fallacious message;
Session group client receives the described fallacious message decision request of described session cluster server, and shows described fallacious message decision request at current sessions window;
Described session group client, according to the input of user, generates the result of determination of user's input;
The result of determination that described user inputs is sent to described session cluster server by described session group client; And
Described session cluster server, according to described result of determination and default decision method, identifies the fallacious message in described doubtful fallacious message.
The embodiment of the present invention also provides a kind of fallacious message recognition system, and it comprises:
Session cluster server, comprising:
Data obtaining module, for obtaining the real-time session information of session group;
Doubtful fallacious message acquisition module, for using fallacious message model, carries out fallacious message judgement to described real-time session information, to obtain doubtful fallacious message;
Determination module, for initiating the fallacious message decision request of described doubtful fallacious message to multiple users of described session group, and receives the result of determination of described user input; And
Identification module, for according to described result of determination and default decision method, identifies the fallacious message in described doubtful fallacious message; And
Multiple session group client, comprising:
Receiving display module, for receiving the fallacious message decision request of described session cluster server, and showing described fallacious message decision request at current sessions window;
Result of determination generation module, for the input according to user, generates the result of determination of user's input; And
Sending module, the result of determination for described user being inputted is sent to described session cluster server.
Compared to the fallacious message recognition methods of prior art, fallacious message recognition device and system, fallacious message recognition methods of the present invention and fallacious message recognition device carry out fallacious message judgement by the user of session group to doubtful fallacious message, improve the recognition accuracy of fallacious message; Solve the technical problem that the fallacious message recognition accuracy of existing fallacious message recognition methods and fallacious message recognition device is lower.
Accompanying drawing explanation
Fig. 1 is the flow chart of the first preferred embodiment of fallacious message recognition methods of the present invention;
Fig. 2 is the flow chart of the second preferred embodiment of fallacious message recognition methods of the present invention;
Fig. 3 is the structural representation of the first preferred embodiment of fallacious message recognition device of the present invention;
Fig. 4 is the structural representation of the second preferred embodiment of fallacious message recognition device of the present invention;
Fig. 5 is the flow chart of the 3rd preferred embodiment of fallacious message recognition methods of the present invention;
Fig. 6 is the structural representation of the 3rd preferred embodiment of fallacious message recognition device of the present invention;
Fig. 7 is the flow chart of the 4th preferred embodiment of fallacious message recognition methods of the present invention;
Fig. 8 is the structural representation of the preferred embodiment of fallacious message recognition system of the present invention;
Fig. 9 is the use sequential chart of fallacious message recognition methods of the present invention.
Embodiment
Please refer to graphic, wherein identical element numbers represents identical assembly, and principle of the present invention implements to illustrate in a suitable computing environment.The following description is based on the illustrated specific embodiment of the invention, and it should not be regarded as limiting the present invention not at other specific embodiment that this describes in detail.
In the following description, specific embodiments of the invention illustrate, unless otherwise stating clearly with reference to the step of the operation performed by or multi-section computer and symbol.Therefore, it can recognize these steps and operation, wherein have and will mention as being performed by computer for several times, include and handled with the computer processing unit of the electronic signal of the data in a structuring pattern by representing.These data of this manipulation transforms or the position maintained in the memory system of this computer, its reconfigurable or other running changing this computer in a manner familiar to those skilled in the art.The data structure that these data maintain is the provider location of this internal memory, and it has the particular characteristics defined by this data format.But the principle of the invention illustrates with above-mentioned word, it is not represented as a kind of restriction, and those skilled in the art can recognize that the plurality of step of the following stated and operation also may be implemented in the middle of hardware.
" assembly ", " module ", " system ", " interface ", " process " etc. are usually intended to refer to computer related entity as used herein the term: the combination of hardware, hardware and software, software or executory software.Such as, assembly can be but be not limited to be run process on a processor, processor, object, can perform application, the thread performed, program and/or computer.By diagram, run application on the controller and this both controller can be assembly.One or more assembly can have in the process and/or thread that are to perform, and assembly and/or can be distributed between two or more computers on a computer.
And claimed theme may be implemented as and uses standard program and/or engineering to produce software, firmware, hardware or its combination in any with the method for the theme disclosed in computer for controlling realization, device or manufacture.Term as used herein " manufacture " is intended to comprise can from the computer program of any computer readable device, carrier or medium access.Certainly, those skilled in the art will recognize that and can carry out many amendments to this configuration, and do not depart from scope or the spirit of claimed theme.
Fallacious message recognition device of the present invention is with being arranged on the server of session group, and this server includes but not limited to minicom, mainframe computer and any distributed computing environment (DCE) etc.Fallacious message recognition methods of the present invention is implemented by the server of session group, realizes identifying the information in session group.
Fallacious message recognition device of the present invention and fallacious message recognition methods can be used for identifying fallacious message, also can be used for the customizing messages identifying user's setting, as the information etc. of specific user.
Please refer to Fig. 1, Fig. 1 is the flow chart of the first preferred embodiment of fallacious message recognition methods of the present invention.The fallacious message recognition methods of this preferred embodiment comprises:
Step S101, obtains the real-time session information of session group;
Step S102, uses fallacious message model, carries out fallacious message judgement, to obtain doubtful fallacious message to real-time session information;
Step S103, initiates the fallacious message decision request of doubtful fallacious message to the user of session group, and receives the result of determination of user's input;
Step S104, according to result of determination and default decision method, identifies the fallacious message in doubtful fallacious message.
The following detailed description of the idiographic flow of each step in the fallacious message recognition methods of this preferred embodiment.
In step S101, session cluster server obtains the real-time session information of session group, and real-time session information here can be the live chat message in micro-letter group, also can be the real time information of community forum.Certainly can obtain the whole real-time session information of session group here, also can obtain the real-time session information of session Group Partial.Preferably, obtain the real-time session information of each in-time generatin in session group, such as, instant message in the current sessions window of session group, can carry out the identification of fallacious message so in time, further increase the fail safe of session in subsequent step to real-time session information.Forward step S102 to subsequently.
In step s 102, session cluster server uses fallacious message model, carries out fallacious message judgement to the real-time session information obtained.Here fallacious message model is the model based on machine learning for identifying fallacious message, namely carries out learning training by support vector machine to existing fallacious message, thus forms the model based on machine learning.Obtain doubtful fallacious message by fallacious message model like this, doubtful fallacious message is possible be the real-time session information of fallacious message.As the real-time session information of Real-time Obtaining in-time generatin in step S101, the identification of fallacious message also immediately can be carried out in this step to the real-time session information obtained, to improve the fail safe of session further.Forward step S103 to subsequently.
In step s 103, the user of session group to session group initiates the fallacious message decision request of doubtful fallacious message, namely allows all online users carry out fallacious message judgement to doubtful fallacious message, determines whether this doubtful fallacious message is fallacious message.Receive the result of determination of user's input subsequently, generally this result of determination is that this doubtful fallacious message is fallacious message, this doubtful fallacious message is not fallacious message or abandons judging (i.e. invalid judgement).Forward step S104 to subsequently.
In step S104, the result of determination that session group obtains according to step S103 and default decision method, identify the fallacious message in doubtful fallacious message, the result of determination that this default decision method is used for inputting according to all users finally determines whether this doubtful fallacious message is fallacious message, it is fallacious message that the result of determination that the user that can set (set point) above quantity more than 90% here inputs is this doubtful fallacious message, just judge that this doubtful fallacious message is as fallacious message, certainly the result of determination of user's input of 60%-95% quantity can also be set as recognition result.
So namely, achieve the fallacious message identifying of the fallacious message recognition methods of this preferred embodiment.
Preferably, after step s 104, recognition result also can be fed back (displaying) to the user of session group by session group, particularly online user, such user can know final recognition result fast and accurately, and the recognition result as final has problem, can directly complaint handling.
Preferably, after step s 104, session group also can use recognition result to revise fallacious message model, makes the judgement of doubtful fallacious message in step s 102 more accurate like this.The recognition accuracy of further raising fallacious message, achieves the upgrading that upgrades in time of the fallacious message model based on machine.
Preferably, after step s 102, session cluster server also can receive the operation requests of the doubtful fallacious message of client, in order to improve the fail safe of the network information further, session cluster server can according to the operation requests of this doubtful fallacious message, to the client transmit operation information of operation requests, to point out this information for for fallacious message, user careful operation may please be carried out to this information.
The fallacious message recognition methods of this preferred embodiment carries out fallacious message judgement by the user of session group to doubtful fallacious message, improves the recognition accuracy of fallacious message.
Please refer to Fig. 2, Fig. 2 is the flow chart of the second preferred embodiment of fallacious message recognition methods of the present invention.The fallacious message recognition methods of this preferred embodiment comprises:
Step S201, obtains the real-time session information of session group from reporting of user port;
Step S202, is set to doubtful fallacious message by the real-time session information obtained from reporting of user port;
Step S203, initiates the fallacious message decision request of doubtful fallacious message to the user of session group, and receives the result of determination of described user input;
Step S204, according to result of determination and default decision method, identifies the fallacious message in doubtful fallacious message.
The following detailed description of the idiographic flow of each step in the fallacious message recognition methods of this preferred embodiment.
In step s 201, session cluster server is provided with a reporting of user port on session group class boundary face, the user of session group submits the fallacious message in real-time session information to by this reporting of user port, can well avoid fallacious message model cannot to identify up-to-date fallacious message like this, manually judged by user, the loss of fallacious message can decline greatly.In order to avoid artificial malice submits fallacious message to, certain restriction can be carried out to submitting to the user of fallacious message, as needs spend certain cash pledge to submit to, after being defined as fallacious message, doublely can return cash pledge; Or a definite limitation is carried out to the grade of the user submitting fallacious message to, prevent user from using registration trumpet to carry out malice and submit to.Forward step S202 to subsequently.
In step S202, because the accuracy rate of the fallacious message of artificial judgment is higher, therefore the real-time session information obtained from reporting of user port is directly set to doubtful fallacious message by session cluster server.Forward step S203 to subsequently.
In step S203, the user of session group to session group initiates the fallacious message decision request of doubtful fallacious message, namely allows all online users carry out fallacious message judgement to doubtful fallacious message, determines whether this doubtful fallacious message is fallacious message.Receive the result of determination of user's input subsequently, generally this result of determination is that this doubtful fallacious message is fallacious message, this doubtful fallacious message is not fallacious message or abandons judging.Forward step S204 to subsequently.
In step S204, the result of determination that session group obtains according to step S203 and default decision method, identify the fallacious message in doubtful fallacious message, the result of determination that this default decision method is used for inputting according to all users finally determines whether this doubtful fallacious message is fallacious message, here can set more than more than 90% quantity user's result of determination as this doubtful fallacious message be fallacious message, just judge that this doubtful fallacious message is as fallacious message, certainly also can set the result of determination of user's input of 60%-95% quantity as recognition result.
So namely, realize the fallacious message identifying of the fallacious message recognition methods of this preferred embodiment.
Preferably, after step s 204, recognition result also can be fed back to the user of session group by session group, particularly online user, such user can know final recognition result fast and accurately, and the recognition result as final has problem, can directly complaint handling.
Preferably, after step s 204, session group also can use recognition result to revise fallacious message model, makes the judgement of doubtful fallacious message in step s 102 more accurate like this.The recognition accuracy of further raising fallacious message, achieves the upgrading that upgrades in time of the fallacious message model based on machine.
The fallacious message recognition methods of this preferred embodiment directly carries out fallacious message judgement to the real-time session information that reporting of user port is submitted on the basis of the first preferred embodiment, further increases the recognition accuracy of fallacious message.
The present invention also provides a kind of fallacious message recognition device, please refer to Fig. 3, and Fig. 3 is the structural representation of the first preferred embodiment of fallacious message recognition device of the present invention.The fallacious message recognition device 30 of this preferred embodiment can use the first preferred embodiment of above-mentioned fallacious message recognition methods to implement.This fallacious message recognition device 30 comprises data obtaining module 31, doubtful fallacious message acquisition module 32, determination module 33 and identification module 34.
Wherein data obtaining module 31 is for obtaining the real-time session information of session group 37A; Doubtful fallacious message acquisition module 32, for using fallacious message model 38, carries out fallacious message judgement to real-time session information, to obtain doubtful fallacious message; Determination module 33 for initiating the fallacious message decision request of doubtful fallacious message to the user 37B of session group 37A, and receives the result of determination of user 37B; Identification module 34, for according to result of determination and default decision method 39, identifies the fallacious message in doubtful fallacious message.
When the fallacious message recognition device 30 of this preferred embodiment uses, first data obtaining module 31 obtains the real-time session information of session group 37A, and real-time session information here can be the live chat message in micro-letter group, also can be the real time information of community forum.Certainly can obtain the whole real-time session information of session group 37A here, also can obtain the real-time session information of session group 37A part.Preferably, data obtaining module 31 can obtain the real-time session information of each in-time generatin in session group, such as, instant message in the current sessions window of session group, the identification of fallacious message can be carried out so in time to real-time session information in subsequent step, further increase the fail safe of session.
Doubtful fallacious message acquisition module 32 uses fallacious message model 38 subsequently, carries out fallacious message judgement to the real-time session information obtained.Here fallacious message model 38 is the model based on machine learning for identifying fallacious message, namely carries out learning training by support vector machine to existing fallacious message, thus forms the model based on machine learning.Obtain doubtful fallacious message by fallacious message model 38 like this, doubtful fallacious message is possible be the real-time session information of fallacious message.As the real-time session information of data obtaining module 31 Real-time Obtaining in-time generatin, doubtful fallacious message acquisition module 32 also can carry out the identification of fallacious message immediately to the real-time session information obtained, to improve the fail safe of session further.
Then the user 37B of determination module 33 couples of session group 37A initiates the fallacious message decision request of doubtful fallacious message, namely allows all online users carry out fallacious message judgement to doubtful fallacious message, determines whether this doubtful fallacious message is fallacious message.Determination module 33 receives the result of determination of user 37B subsequently, and generally this result of determination is that this doubtful fallacious message is fallacious message, this doubtful fallacious message is not fallacious message or abandons judging.
The result of determination that last identification module 34 obtains according to determination module 33 and default decision method 39, identify the fallacious message in doubtful fallacious message, for the result of determination inputted according to all users, this default decision method 39 finally determines whether this doubtful fallacious message is fallacious message, here can set more than more than 90% quantity user's result of determination as this doubtful fallacious message be fallacious message, just judge that this doubtful fallacious message is as fallacious message, certainly also can set the result of determination of user's input of 60%-95% quantity as recognition result.
So namely, achieve the fallacious message identifying of the fallacious message recognition device 30 of this preferred embodiment.
Preferably, the fallacious message recognition device 30 of this preferred embodiment also comprises feedback module 35, and this feedback module 35 is for feeding back to the user 37B of session group 37A by recognition result.Recognition result is fed back to the user 37B, particularly online user of session group 37A by feedback module 35, and such user 37B can know final recognition result fast and accurately, and the recognition result as final has problem, can directly complaint handling.
Preferably, the fallacious message recognition device 30 of this preferred embodiment also comprises correcting module 36, and this correcting module 36 is revised fallacious message model 38 for using recognition result.Correcting module 36 uses recognition result to revise fallacious message model 38, and the doubtful fallacious message making doubtful fallacious message acquisition module 32 obtain like this is more accurate.The recognition accuracy of further raising fallacious message, achieves the upgrading that upgrades in time of the fallacious message model based on machine.
Preferably, the fallacious message recognition device 30 of this preferred embodiment also comprises operation requests receiver module (not shown) and operation prompt information sending module (not shown).Operation requests receiver module is for receiving the operation requests of doubtful fallacious message; Operation prompt information sending module for sending the operation requests according to doubtful fallacious message, to the client transmit operation information of operation requests.
Operation requests receiver module also can receive the operation requests of the doubtful fallacious message of client, in order to improve the fail safe of the network information further, operation prompt information sending module can according to the operation requests of this doubtful fallacious message, to the client transmit operation information of operation requests, to point out this information for for fallacious message, user careful operation may please be carried out to this information.
The fallacious message recognition device of this preferred embodiment carries out fallacious message judgement by the user of session group to doubtful fallacious message, improves the recognition accuracy of fallacious message.
Please refer to Fig. 4, Fig. 4 is the structural representation of the second preferred embodiment of fallacious message recognition device of the present invention.The fallacious message recognition device 40 of this preferred embodiment can use the second preferred embodiment of above-mentioned fallacious message recognition methods to implement.This fallacious message recognition device 40 comprises data obtaining module 41, doubtful fallacious message acquisition module 42, determination module 43 and identification module 44.
Data obtaining module 41 for obtaining the real-time session information of session group 47A, and obtains the real-time session information of session group 47A from reporting of user port; Doubtful fallacious message acquisition module 42, for using fallacious message model 48, carries out fallacious message judgement to real-time session information, to obtain doubtful fallacious message, and the real-time session information obtained from reporting of user port is set to doubtful fallacious message; Determination module 43 for initiating the fallacious message decision request of doubtful fallacious message to the user 47B of session group 47A, and receives the result of determination of user 47B; Identification module 44, for according to result of determination and default decision method 49, identifies the fallacious message in doubtful fallacious message.
Be with the difference of the first preferred embodiment, when the fallacious message recognition device 40 of this preferred embodiment uses, data obtaining module 41 is also provided with a reporting of user port on session group class boundary face, the user 47B of session group 47A submits the doubtful fallacious message in real-time session information to by this reporting of user port, can well avoid fallacious message model cannot to identify up-to-date fallacious message like this, manually judged by user, the loss of fallacious message can decline greatly.In order to avoid artificial malice submits fallacious message to, certain restriction can be carried out to submitting to the user 47B of fallacious message, as needs spend certain cash pledge to submit to, after being defined as fallacious message, doublely can return cash pledge; Or a definite limitation is carried out to the grade of the user 47B submitting fallacious message to, prevent user 47B from using registration trumpet to carry out malice and submit to.
Subsequently, because the accuracy rate of the fallacious message of artificial judgment is higher, therefore the real-time session information obtained from reporting of user port is directly set to doubtful fallacious message by doubtful fallacious message acquisition module 42.
Then the user 47B of determination module 43 couples of session group 47A initiates the fallacious message decision request of doubtful fallacious message, namely allows all online users carry out fallacious message judgement to doubtful fallacious message, determines whether this doubtful fallacious message is fallacious message.Determination module 43 receives the result of determination of user 47B subsequently, and generally this result of determination is that this doubtful fallacious message is fallacious message, this doubtful fallacious message is not fallacious message or abandons judging.
The result of determination that last identification module 44 obtains according to determination module 43 and default decision method 49, identify the fallacious message in doubtful fallacious message, for the result of determination inputted according to all users, this default decision method 49 finally determines whether this doubtful fallacious message is fallacious message, here can set more than more than 90% quantity user's result of determination as this doubtful fallacious message be fallacious message, just judge that this doubtful fallacious message is as fallacious message, certainly also can set the result of determination of user's input of 60%-95% quantity as recognition result.
So namely, achieve the fallacious message identifying of the fallacious message recognition device 40 of this preferred embodiment.
Preferably, the fallacious message recognition device 40 of this preferred embodiment also comprises feedback module 45, and this feedback module 45 is for feeding back to the user 47B of session group 47A by recognition result.Recognition result is fed back to the user 47B, particularly online user of session group 47A by feedback module 45, and such user 47B can know final recognition result fast and accurately, and the recognition result as final has problem, can directly complaint handling.
Preferably, the fallacious message recognition device 40 of this preferred embodiment also comprises correcting module 46, and this correcting module 46 is revised fallacious message model 48 for using recognition result.Correcting module 46 uses recognition result to revise fallacious message model 48, and the doubtful fallacious message making doubtful fallacious message acquisition module 42 obtain like this is more accurate.The recognition accuracy of further raising fallacious message, achieves the upgrading that upgrades in time of the fallacious message model based on machine.
The fallacious message recognition device of this preferred embodiment directly carries out fallacious message judgement to the real-time session information that reporting of user port is submitted on the basis of the first preferred embodiment, further increases the recognition accuracy of fallacious message.
The present invention also provides a kind of fallacious message recognition device, and this fallacious message recognition device also can be arranged in the session group client of session group.Session group client includes but not limited to personal computer, server computer, hand-hold type or laptop devices, mobile device (such as mobile phone, personal digital assistant (PDA), media player etc.).Fallacious message recognition methods of the present invention is implemented by session group client, realizes identifying the information in session group.
Please refer to Fig. 5, Fig. 5 is the flow chart of the 3rd preferred embodiment of fallacious message recognition methods of the present invention.The fallacious message recognition methods of this preferred embodiment comprises:
Step S501, receives the fallacious message decision request of the doubtful fallacious message of session cluster server, and shows fallacious message decision request at current sessions window;
Step S502, according to the input of user, generates the result of determination of user's input;
Step S503, is sent to session cluster server by the result of determination that user inputs.
The following detailed description of the idiographic flow of each step in the fallacious message recognition methods of this preferred embodiment.
In step S501, session group client receives the fallacious message decision request of the doubtful fallacious message of session cluster server, and directly show this fallacious message decision request at current sessions window, user carries out fallacious message judgement by this fallacious message decision request to this doubtful fallacious message, forwards step S502 to subsequently.
In step S502, user judges doubtful fallacious message, namely inputs corresponding determination information, thus generates the result of determination of user's input, forwards step S503 to subsequently.
In step S503, the result of determination that the user generated in step S502 inputs is sent to session cluster server by session group client.
So namely, achieve the fallacious message identifying of the fallacious message recognition methods of this preferred embodiment.
Preferably, after step S503, session cluster server, according to result of determination and default decision method, identifies the fallacious message in doubtful fallacious message, generates recognition result feedback.Session group client subsequently receives the recognition result feedback of session cluster server, and such user can know final recognition result fast and accurately, and the recognition result as final has problem, can directly complaint handling.
Preferably, session group client also can arrange reporting of user port on current sessions window, and user reports the real-time session information of session group by reporting of user port.Can well avoid fallacious message model cannot to identify up-to-date fallacious message like this, manually judged by user, the loss of fallacious message can decline greatly.
The fallacious message recognition methods of this preferred embodiment carries out fallacious message judgement by the user of session group to doubtful fallacious message, improves the recognition accuracy of fallacious message.
Please refer to Fig. 6, Fig. 6 is the structural representation of the 3rd preferred embodiment of fallacious message recognition device of the present invention.The fallacious message recognition device 60 of this preferred embodiment can use the 3rd preferred embodiment of above-mentioned fallacious message recognition methods to implement.This fallacious message recognition device 60 comprises reception display module 61, result of determination generation module 62, sending module 63, feedback receive module 64 and reporting module (not shown).
Receive display module 61 for receiving the fallacious message decision request of the doubtful fallacious message of session cluster server, and show fallacious message decision request at current sessions window; Result of determination generation module 62, for the input according to user, generates the result of determination of user's input; Sending module 63 is sent to session cluster server for result of determination user inputted; Feedback receive module 64 is for receiving the recognition result feedback of session cluster server; Wherein recognition result feedback is generated according to result of determination and default decision method by session cluster server.Reporting module 65 is for reporting the real-time session information of session group from reporting of user port.
When the fallacious message recognition device 60 of this preferred embodiment uses, receive the fallacious message decision request that display module 61 receives the doubtful fallacious message of session cluster server, and directly showing this fallacious message decision request at current sessions window, user carries out fallacious message judgement by this fallacious message decision request to this doubtful fallacious message.
User judges doubtful fallacious message subsequently, namely inputs corresponding determination information, thus result of determination generation module 62 generates the result of determination of user's input.
The result of determination of user's input that result of determination generation module generates by last sending module 63 is sent to session cluster server.
So namely, achieve the fallacious message identifying of the fallacious message recognition device 60 of this preferred embodiment.
Preferably, session cluster server, according to result of determination and default decision method, identifies the fallacious message in doubtful fallacious message, generates recognition result feedback.Feedback receive module 64 receives the recognition result feedback of session cluster server subsequently, and such user can know final recognition result fast and accurately, and the recognition result as final has problem, can directly complaint handling.
Preferably, user can use the reporting module of fallacious message recognition device 60 to report the real-time session information of session group by reporting of user port.Can well avoid fallacious message model cannot to identify up-to-date fallacious message like this, manually judged by user, the loss of fallacious message can decline greatly.
The fallacious message recognition device of this preferred embodiment carries out fallacious message judgement by the user of session group to doubtful fallacious message, improves the recognition accuracy of fallacious message.
Please refer to Fig. 7, Fig. 7 is the flow chart of the 4th preferred embodiment of fallacious message recognition methods of the present invention.The fallacious message recognition methods of this preferred embodiment comprises:
Step S701, session cluster server obtains the real-time session information of session group;
Step S702, session cluster server uses fallacious message model, carries out fallacious message judgement, to obtain doubtful fallacious message to real-time session information;
Step S703, the multiple users of session cluster server to session group initiate the fallacious message decision request of doubtful fallacious message;
Step S704, session group client receives the fallacious message decision request of session cluster server, and shows fallacious message decision request at current sessions window;
Step S705, session group client, according to the input of user, generates the result of determination of user's input;
Step S706, the result of determination that user inputs is sent to session cluster server by session group client;
Step S707, session cluster server, according to result of determination and default decision method, identifies the fallacious message in doubtful fallacious message.
The specific works flow process of the fallacious message recognition methods of this preferred embodiment is identical with the associated description in the 3rd preferred embodiment with the first preferred embodiment of above-mentioned fallacious message recognition methods, specifically refers to the associated description in the first preferred embodiment of above-mentioned fallacious message recognition methods and the 3rd preferred embodiment.
The fallacious message recognition methods of this preferred embodiment carries out fallacious message judgement by the user of session group to doubtful fallacious message, improves the recognition accuracy of fallacious message.
The present invention also provides a kind of fallacious message recognition system, please refer to Fig. 8, and Fig. 8 is the structural representation of the preferred embodiment of fallacious message recognition system of the present invention.The fallacious message recognition system of this preferred embodiment comprises session cluster server 81 and multiple session group client 82.Session cluster server 81 comprises data obtaining module 811, doubtful fallacious message acquisition module 812, determination module 813 and identification module 814.Session group client 82 comprises reception display module 821, result of determination generation module 822 and sending module 823.
Wherein data obtaining module 811 is for obtaining the real-time session information of session group; Doubtful fallacious message acquisition module 812, for using fallacious message model, carries out fallacious message judgement to real-time session information, to obtain doubtful fallacious message; Determination module 813 for initiating the fallacious message decision request of doubtful fallacious message to multiple users of session group, and receives the result of determination of user's input; Identification module 814, for according to result of determination and default decision method, identifies the fallacious message in doubtful fallacious message.
Receive display module 821 for receiving the fallacious message decision request of session cluster server, and show fallacious message decision request at current sessions window; Result of determination generation module 822, for the input according to user, generates the result of determination of user's input; Sending module 823 is sent to session cluster server for result of determination user inputted.
The specific works flow process of the fallacious message recognition system of this preferred embodiment is identical with the associated description in the 3rd preferred embodiment with the first preferred embodiment of above-mentioned fallacious message recognition device, specifically refers to the associated description in the first preferred embodiment of above-mentioned fallacious message recognition device and the 3rd preferred embodiment.
The fallacious message recognition system of this preferred embodiment carries out fallacious message judgement by the user of session group to doubtful fallacious message, improves the recognition accuracy of fallacious message.
The specific works principle of fallacious message recognition methods of the present invention is described below by a specific embodiment.Please refer to Fig. 9, Fig. 9 is the use sequential chart of the specific embodiment of fallacious message recognition methods of the present invention.
One, the live chat message in the social group of the fallacious message Model Monitoring of session group, thus obtain doubtful fallacious message; Certainly also can arrange reporting of user port here, the user in social group reports doubtful fallacious message by this reporting of user port.
Two, session group initiates fallacious message evaluation request (namely initiating ballot) for doubtful fallacious message to user.
Three, the user of session group carries out ballot generation result of determination.
Four, according to result of determination, fallacious message is confirmed, and use the fallacious message after confirming to revise fallacious message model, and the fallacious message after confirming is shown in social group.
Fallacious message recognition methods of the present invention, fallacious message recognition device and system carry out fallacious message judgement by the user of session group to doubtful fallacious message, in fallacious message judges, add the judgement factor of people, improve the recognition accuracy of fallacious message; Use recognition result to revise fallacious message model simultaneously, achieve upgrading in time fast of fallacious message model.The fallacious message recognition accuracy solving existing fallacious message recognition methods and fallacious message recognition device is lower, the slow-footed technical problem of fallacious message model modification.
Each functional unit in the embodiment of the present invention can be integrated in a processing module, also can be that the independent physics of unit exists, also can be integrated in a module by two or more unit.Above-mentioned integrated module both can adopt the form of hardware to realize, and the form of software function module also can be adopted to realize.If described integrated module using the form of software function module realize and as independently production marketing or use time, also can be stored in a computer read/write memory medium.The above-mentioned storage medium mentioned can be read-only memory, disk or CD etc.Above-mentioned each device or system, can perform the method in correlation method embodiment.
In sum; although the present invention discloses as above with preferred embodiment; but above preferred embodiment is also not used to limit the present invention; those of ordinary skill in the art; without departing from the spirit and scope of the present invention; all can do various change and retouching, the scope that therefore protection scope of the present invention defines with claim is as the criterion.

Claims (24)

CN201410341818.XA2014-07-172014-07-17 Malicious information identification method, malicious information identification device and systemExpired - Fee RelatedCN105323145B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN201410341818.XACN105323145B (en)2014-07-172014-07-17 Malicious information identification method, malicious information identification device and system

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN201410341818.XACN105323145B (en)2014-07-172014-07-17 Malicious information identification method, malicious information identification device and system

Publications (2)

Publication NumberPublication Date
CN105323145Atrue CN105323145A (en)2016-02-10
CN105323145B CN105323145B (en)2020-09-04

Family

ID=55249776

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN201410341818.XAExpired - Fee RelatedCN105323145B (en)2014-07-172014-07-17 Malicious information identification method, malicious information identification device and system

Country Status (1)

CountryLink
CN (1)CN105323145B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN108009934A (en)*2017-11-172018-05-08上海哔哩哔哩科技有限公司Server, case distribution method and system, event dispatcher method and system
CN108040295A (en)*2017-11-172018-05-15上海哔哩哔哩科技有限公司Many sanction methods, server, user terminal and many sanction systems
CN108737243A (en)*2018-04-202018-11-02平安科技(深圳)有限公司Conversation message quality detecting method and device
CN108921530A (en)*2018-06-222018-11-30Oppo广东移动通信有限公司Information judgment method and device, storage medium and terminal
CN114841247A (en)*2022-03-312022-08-02前锦网络信息技术(上海)有限公司Malicious user identification method and system

Citations (13)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20050102210A1 (en)*2003-10-022005-05-12Yuh-Shen SongUnited crimes elimination network
CN101079877A (en)*2006-07-272007-11-28腾讯科技(深圳)有限公司Filtering method and filtering system for communication information in communication system
CN101080044A (en)*2007-06-272007-11-28华为技术有限公司SMS forward and processing method and device
JP2010081444A (en)*2008-09-262010-04-08Brother Ind LtdIntercom device
CN101697621A (en)*2009-11-042010-04-21中兴通讯股份有限公司Method and system for processing varietal litter message
US20100123579A1 (en)*2008-11-182010-05-20James MidkiffVirtual watch
JP2010114544A (en)*2008-11-052010-05-20Brother Ind LtdIntercom system, and program and method for receiving visitor
WO2010102587A1 (en)*2009-03-132010-09-16华为技术有限公司Method, device and system for reporting junk information
US7860928B1 (en)*2007-03-222010-12-28Google Inc.Voting in chat system without topic-specific rooms
WO2011022969A1 (en)*2009-08-282011-03-03中兴通讯股份有限公司System and method for monitoring junk information
CN102394762A (en)*2011-11-012012-03-28陈晓亮Many-people-involved on-line communication system method
CN102752262A (en)*2011-04-182012-10-24腾讯科技(深圳)有限公司Method and server for restricting malicious information propagation
CN103136255A (en)*2011-11-302013-06-05腾讯科技(深圳)有限公司Method and device for information management

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
US20050102210A1 (en)*2003-10-022005-05-12Yuh-Shen SongUnited crimes elimination network
CN101079877A (en)*2006-07-272007-11-28腾讯科技(深圳)有限公司Filtering method and filtering system for communication information in communication system
US7860928B1 (en)*2007-03-222010-12-28Google Inc.Voting in chat system without topic-specific rooms
CN101080044A (en)*2007-06-272007-11-28华为技术有限公司SMS forward and processing method and device
JP2010081444A (en)*2008-09-262010-04-08Brother Ind LtdIntercom device
JP2010114544A (en)*2008-11-052010-05-20Brother Ind LtdIntercom system, and program and method for receiving visitor
US20100123579A1 (en)*2008-11-182010-05-20James MidkiffVirtual watch
WO2010102587A1 (en)*2009-03-132010-09-16华为技术有限公司Method, device and system for reporting junk information
WO2011022969A1 (en)*2009-08-282011-03-03中兴通讯股份有限公司System and method for monitoring junk information
CN101697621A (en)*2009-11-042010-04-21中兴通讯股份有限公司Method and system for processing varietal litter message
CN102752262A (en)*2011-04-182012-10-24腾讯科技(深圳)有限公司Method and server for restricting malicious information propagation
CN102394762A (en)*2011-11-012012-03-28陈晓亮Many-people-involved on-line communication system method
CN103136255A (en)*2011-11-302013-06-05腾讯科技(深圳)有限公司Method and device for information management

Cited By (9)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN108009934A (en)*2017-11-172018-05-08上海哔哩哔哩科技有限公司Server, case distribution method and system, event dispatcher method and system
CN108040295A (en)*2017-11-172018-05-15上海哔哩哔哩科技有限公司Many sanction methods, server, user terminal and many sanction systems
US10810686B2 (en)2017-11-172020-10-20Shanghai Bilibili Technology Co., Ltd.Identification of rule violations in a network community
CN108009934B (en)*2017-11-172021-03-12上海哔哩哔哩科技有限公司Server, case distribution method and system, and event distribution method and system
CN108040295B (en)*2017-11-172021-05-07上海哔哩哔哩科技有限公司Public cutting method, server, user side and public cutting system
CN108737243A (en)*2018-04-202018-11-02平安科技(深圳)有限公司Conversation message quality detecting method and device
CN108921530A (en)*2018-06-222018-11-30Oppo广东移动通信有限公司Information judgment method and device, storage medium and terminal
CN108921530B (en)*2018-06-222022-06-28Oppo广东移动通信有限公司Information judgment method and device, storage medium and terminal
CN114841247A (en)*2022-03-312022-08-02前锦网络信息技术(上海)有限公司Malicious user identification method and system

Also Published As

Publication numberPublication date
CN105323145B (en)2020-09-04

Similar Documents

PublicationPublication DateTitle
JP6744480B2 (en) Network-based ad data traffic latency reduction
CN103294800B (en)A kind of information-pushing method and device
KR20180099812A (en) Identifying entities using the deep learning model
US11483322B1 (en)Proactive suspicious activity monitoring for a software application framework
WO2014193399A1 (en)Influence score of a brand
CN109246027B (en)Network maintenance method and device and terminal equipment
CN108234283A (en)The external social media message of detection
US20180032907A1 (en)Detecting abusive language using character n-gram features
US11308141B2 (en)Template generation using directed acyclic word graphs
CN105323145A (en)Malicious information identification method, device and system
US11886597B2 (en)Detection of common patterns in user generated content with applications in fraud detection
WO2022116421A1 (en)Federated learning worker node selecting method and system, terminal, and storage medium
US9521034B2 (en)Method and apparatus for generating resource address, and system thereof
WO2013172888A2 (en)Mediation computing device and associated method for generating semantic tags
US11032316B1 (en)Using machine learning techniques to detect imposter pages in an online system
WO2016200408A1 (en)Hybrid classification system
CN113326375A (en)Public opinion processing method, device, electronic equipment and storage medium
CN113592036A (en)Flow cheating behavior identification method and device, storage medium and electronic equipment
CN115002211A (en)Cloud-native-based after-sale micro-service implementation method, device, equipment and medium
CN112966193B (en)Travel intention deducing method, model training method, related device and electronic equipment
US20160241671A1 (en)Profile update evaluator
CN114401121A (en)Application program login method and device, electronic equipment and readable storage medium
CN118709195A (en) Method and device for applying large language model
CN111666317A (en)Cheating information mining method and cheating information identification method and device
CN117492822A (en)Change contrast method, device, electronic equipment and storage medium

Legal Events

DateCodeTitleDescription
C06Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant
CF01Termination of patent right due to non-payment of annual fee
CF01Termination of patent right due to non-payment of annual fee

Granted publication date:20200904


[8]ページ先頭

©2009-2025 Movatter.jp