CN102760130A - Information processing method and device - Google Patents
Information processing method and device Download PDFInfo
- Publication number
- CN102760130A CN102760130A CN2011101075213A CN201110107521A CN102760130A CN 102760130 A CN102760130 A CN 102760130A CN 2011101075213 A CN2011101075213 A CN 2011101075213A CN 201110107521 A CN201110107521 A CN 201110107521A CN 102760130 A CN102760130 A CN 102760130A
- Authority
- CN
- China
- Prior art keywords
- information
- return information
- return
- judged result
- junk
- 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
Links
Images
Abstract
The invention discloses information processing method and device, and belongs to the field of computers. The method comprises the following steps: receiving replay information on the user generation content from any one user, and judging whether the reply information is spam; if yes, attributing the reply information into spam classification so as to see the reply information secondary judgment of all reply information users in the spam classification, and recording the judgment result; and counting the number on that the reply information judgment results are normal information from all reply information users in the spam classification, and judging whether the number on that the reply information judgment results are normal information meets a preset threshold; and if yes, marking the reply information as normal information.
Description
Technical field
The present invention relates to computer realm, particularly a kind of method and apparatus of process information.
Background technology
Along with Internet development; The particularly arrival in 2.0 epoch of Web, network application more and more is deep into daily life, various UGC (User Generated Content; User-generated content) application has become people's record and has showed the oneself; Promote an important platform of emotional interaction between kith and kin,, comprise network applications such as blog, message board, microblogging, photograph album such as personal space.But thing followed SPAM (junk information), also more and more rampant, promptly malicious user possibly insert advertisement in UGC uses, or replys fallacious message.These SPAM contents are the labor Internet resources not only, and the online that influences numerous netizens is experienced, and bring economic loss possibly for the not high netizen of awareness of safety, even possibly cause social labile factor.
Decision scheme to SPAM during at present UGC uses basically all is based on the characteristic of waiting to judge content, comprises key word in post people's attribute, the content, content repetition degree etc.The SPAM decision-making system is at first set up the weight table of a characteristic item, when a new UGC information arrives, and the value of all characteristic items in extraction and the computing information; And the weight weighted sum of pressing each characteristic item; Obtain probable value about the whether SPAM of this UGC information, when probable value greater than pre-configured threshold values, think that then this UGC information is SPAM; System removes (or marking) automatically from user data block, make the user who delivers UGC can't see this junk information.
After prior art is analyzed; The inventor finds that prior art has following shortcoming at least: existing SPAM decision scheme is only relevant with UGC content itself, judges according to the content characteristic of UGC whether it is junk information, but for same UGC content; Though system determines that it is SPAM; The user who has possibly think also that it is SPAM, but other users possibly think that it is a normal information, are not SPAM.Therefore existing decision procedure to SPAM owing to do not consider user's idea, the erroneous judgement and the situation of failing to judge occur through regular meeting; Particularly erroneous judgement, greatly the emotion of harm users lets the SPAM fabricator deposit idea of leaving things to chance and fail to judge; Continue to be engaged in this illegal work, disturb normal network environment.
Summary of the invention
In order to determine SPAM more accurately, the embodiment of the invention provides a kind of method and apparatus of process information.Said technical scheme is following:
On the one hand, a kind of method of process information is provided, said method comprises:
Receive the return information that arbitrary user to user generates content, and judge whether said return information is junk information;
Write down said judged result, make all users that see said return information carry out secondary and judge, and write down said all users' secondary judged result said return information;
Secondary judged result according to said all users is labeled as normal information or junk information with said return information.
Saidly judge that whether said return information is junk information, comprising:
Extract each characteristic item of said return information;
Whether to said each characteristic item weighted sum, obtaining said return information is the probable value of junk information;
If the said probable value that obtains is greater than pre-set threshold value, then said return information is a junk information.
The said judged result of said record makes all users that see said return information carry out secondary to said return information and judges, and writes down said all users' secondary judged result, comprising:
If said judged result is for being; Then said return information is grouped in the classification of junk information; Make all users that in the classification of said junk information, see said return information carry out secondary and judge, and write down said all users' judged result said return information;
Correspondingly, said secondary judged result according to said all users is labeled as normal information with said return information, comprising:
Statistics is seen said return information in the classification of said junk information all users are the number of normal information to the judged result of said return information, judge judged result to said return information is whether the number of normal information satisfies preset threshold value;
If then said return information is labeled as normal information.
Said said return information is labeled as normal information, also comprises before:
Judge whether sensitive information is arranged in the said return information;
If, then said return information is examined once more, after passing through, audit continues execution in step again.
Said said return information is labeled as normal information, also comprises afterwards:
Record sees that the user of said return information is judged as said junk information the result of normal information;
Weight according to each characteristic item of the said user's of said record judged result adjustment return information.
The said judged result of said record makes all users that see said return information carry out secondary to said return information and judges, and writes down said all users' secondary judged result, comprising:
If said return information is not a junk information; Then said return information is grouped in the classification of normal information; Make all users that in the classification of said normal information, see said return information carry out secondary and judge, and write down said all users' judged result said return information;
Correspondingly, said secondary judged result according to said all users is labeled as junk information with said return information, comprising:
Statistics is seen said return information in the classification of said normal information all users are the number of junk information to the judged result of said return information, and judge judged result to said return information is whether the number of junk information satisfies preset threshold value;
If then said return information is labeled as junk information.
Said said return information is labeled as junk information, also comprises afterwards:
Record sees that the user of said return information is judged as said normal information the result of junk information;
Weight according to each characteristic item of the said user's of said record judged result adjustment return information.
On the other hand, a kind of device of process information is provided, said device comprises:
First judge module is used to receive the return information that arbitrary user to user generates content, and judges whether said return information is junk information;
Logging modle is used to write down said judged result, makes all users that see said return information carry out secondary to said return information and judges, and write down said all users' secondary judged result;
Second judge module is used for the secondary judged result according to said all users, and said return information is labeled as normal information or junk information.
Said first judge module comprises:
Extraction unit is used to extract each characteristic item of said return information;
Computing unit is used for said each characteristic item weighted sum, and whether obtain said return information is the probable value of junk information;
Judging unit, if be used for said probable value that said computing unit obtains greater than pre-set threshold value, then said return information is a junk information.
Said logging modle specifically is used for:
If the judged result of said first judge module is for being; Then said return information is grouped in the classification of junk information; Make all users that in the classification of said junk information, see said return information carry out secondary and judge, and write down said all users' judged result said return information;
Correspondingly, said second judge module specifically is used for:
Statistics is seen said return information in the classification of said junk information all users are the number of normal information to the judged result of said return information, judge judged result to said return information is whether the number of normal information satisfies preset threshold value; If then said return information is labeled as normal information.
Said device also comprises:
The 3rd judge module is used for said return information is labeled as before the normal information, judges whether sensitive information is arranged in the said return information; If, then said return information is examined once more, after passing through, audit continues execution in step again.
Said device also comprises:
First adjusting module is used for said return information is labeled as after the normal information, and record sees that the user of said return information is judged as said junk information the result of normal information; Weight according to each characteristic item of the said user's of said record judged result adjustment return information.
Said logging modle specifically is used for:
If the judged result of said first judge module is for denying; Then said return information is grouped in the classification of normal information; Make all users that in the classification of said normal information, see said return information carry out secondary and judge, and write down said all users' judged result said return information;
Correspondingly, said second judge module specifically is used for:
Statistics is seen said return information in the classification of said normal information all users are the number of junk information to the judged result of said return information, and judge judged result to said return information is whether the number of junk information satisfies preset threshold value; If then said return information is labeled as junk information.
Said device also comprises:
Second adjusting module is used for said return information is labeled as after the junk information, and record sees that the user of said return information is judged as said normal information the result of junk information; Weight according to each characteristic item of the said user's of said record judged result adjustment return information.
The technical scheme that the embodiment of the invention provides; Select the method for SPAM in the auxiliary judgment UGC content according to the user; Can let the user see and participate in the judgement of system to SPAM, accuracy and judgement speed that the raising system is judged SPAM in the UGC content, and the user can reply the judgement of submissions oneself in the personal space all; Have an opportunity system judge by accident, the content of non-SPAM brings order out of chaos the regular content classification down; Also can reply the wall scroll in own space and classify as SPAM, improve the accurate rate that SPAM judges, promote user experience.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art; To do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below; Obviously, the accompanying drawing in describing below only is some embodiments of the present invention, for those of ordinary skills; Under the prerequisite of not paying creative work property, can also obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the process flow diagram of the method for a kind of process information of providing of the embodiment of the invention 1;
Fig. 2 is the process flow diagram of the method for a kind of process information of providing of the embodiment of the invention 2;
Fig. 3 is the schematic representation of apparatus of a kind of process information of providing of the embodiment of the invention 3;
Fig. 4 is the schematic representation of apparatus of the another kind of process information that provides of the embodiment of the invention 3.
Embodiment
For making the object of the invention, technical scheme and advantage clearer, will combine accompanying drawing that embodiment of the present invention is done to describe in detail further below.
Embodiment 1
Referring to Fig. 1, the embodiment of the invention provides a kind of method of process information, comprising:
Step 101: receive the return information that arbitrary user to user generates content, and judge whether return information is junk information;
Step 102: the record judged result makes all users that see return information carry out secondary to return information and judges, and writes down all users' secondary judged result;
Step 103: the secondary judged result according to all users is labeled as normal information or junk information with return information.
Wherein, judge that whether said return information is junk information, comprising:
Extract each characteristic item of said return information;
Whether to said each characteristic item weighted sum, obtaining said return information is the probable value of junk information;
If the said probable value that obtains is greater than pre-set threshold value, then said return information is a junk information.
Wherein, the secondary judged result according to all users is labeled as normal information or junk information with return information, comprising:
If judged result then is grouped into return information in the classification of junk information for being, makes all users that in the classification of junk information, see return information carry out secondary and judge, and write down all users' judged result return information;
Correspondingly, the secondary judged result according to the user is arranged is labeled as normal information with return information, comprising:
Statistics is seen return information in the classification of junk information all users are the number of normal information to the judged result of return information, judge judged result to return information is whether the number of normal information satisfies preset threshold value; If then return information is labeled as normal information.
Alternatively, return information is labeled as normal information, also comprises before:
Judge whether sensitive information is arranged in the return information;
If, then return information is examined once more, after passing through, audit continues execution in step again.
Alternatively, return information is labeled as normal information, also comprises afterwards:
Record sees that the user of return information is judged as junk information the result of normal information;
Adjust the weight of each characteristic item of return information according to the user's who writes down judged result.
Further, according to all users' secondary judged result, return information is labeled as normal information or junk information in the present embodiment, comprises:
If return information is not a junk information, then return information is grouped in the classification of normal information, make all users that in the classification of normal information, see return information carry out secondary and judge, and write down all users' judged result return information;
Correspondingly, the secondary judged result according to the user is arranged is labeled as junk information with return information, comprising:
Statistics is seen return information in the classification of normal information all users are the number of junk information to the judged result of said return information, and judge judged result to return information is whether the number of junk information satisfies preset threshold value;
If then return information is labeled as junk information.
Alternatively, return information is labeled as junk information, also comprises afterwards:
Record sees that the user of return information is judged as normal information the result of junk information;
Adjust the weight of each characteristic item of return information according to the said user's who writes down judged result.
The technical scheme that the embodiment of the invention provides; Select the method for SPAM in the auxiliary judgment UGC content according to the user; Can let the user see and participate in the judgement of system to SPAM, accuracy and judgement speed that the raising system is judged SPAM in the UGC content, and the user can reply the judgement of submissions oneself in the personal space all; Have an opportunity system judge by accident, the content of non-SPAM brings order out of chaos the regular content classification down; Also can reply the wall scroll in own space and classify as SPAM, improve the accurate rate that SPAM judges, promote user experience.
Embodiment 2
Referring to Fig. 2, the embodiment of the invention provides a kind of method of process information, comprising:
Step 201:SPAM decision-making system receives the return information of UGC.
In the present embodiment, because UGC delivers on the internet, the user on the internet can see this UGC through certain approach, and replys, and wherein the user on the internet has this good friend who delivers the user, also has advertiser or other malicious users.In order to protect the clean and tidy and safety in individual subscriber space, whether each of UGC replied is all needed to verify through the SPAM system earlier, be junk information to judge it.
Step 202: judge whether this return information is junk information, if then execution in step 203, otherwise execution in step 206.
Wherein, the SPAM decision-making system is at first set up the weight table of a characteristic item, after receiving the return information of UGC, extracts the correlation properties item of return information according to the record of this characteristic list item, thereby judges that whether this return information is junk information, specifically comprises:
1) value of all characteristic items in extraction and the calculating return information;
2) whether to the weight weighted sum of each characteristic item, obtaining return information is the probable value of junk information;
3) if the probable value that obtains greater than pre-set threshold value, then return information is a junk information, otherwise return information is a normal information.
In the present embodiment, alternatively, for the content that is judged to be SPAM, whether system also can this content of mark comprise sensitive information, so that the user when judging once more, if this SPAM is judged to non-SPAM, can judge the content that comprises sensitive information once more.
Step 203: return information is grouped in the junk information classification, makes all users that in the classification of junk information, see return information carry out secondary and judge, and write down all users' judged result to return information.
Wherein, System alternatively, is grouped in the junk information classification this return information or in the normal information classification after judging this return information and being SPAM or non-SPAM; Make the user when opening personal space; Can see directly that which is a junk information, which is non-junk information, further return information is verified on this basis again.Wherein, can for junk information classification with normal information classification set up different files respectively and press from both sides, also can adopt other mode that these two kinds of information are classified, this present embodiment is not done concrete qualification.
Step 204: statistics is seen return information in the classification of junk information all users are the number of normal information to the judged result of return information.
In the present embodiment, for the user's that thinks in terms of the majority impression, can be according to the judged result of certain user to return information; Just return information is reclassified; But prior setting threshold when the number of holding identical judged result satisfies default value, just reclassifies return information.So system can write down each user's secondary judged result, and the different results' that judge of statistics number.
Step 205: judge judged result to return information is whether the number of normal information satisfies preset threshold value, if then return information is labeled as normal information; Otherwise with this return information deletion.
In the present embodiment, after the SPAM decision-making system is judged the return information of UGC, return information is classified; The return information of the UGC that receives is all existed in user's the personal space; When the user capture space, in different classification results, can see all return informations, further; The user judges once more that to the return information that system has made a determination making the user can not miss any one is information available for this user.As; After system judges that this return information is junk information, it is classified as one type of junk information, then the user can open spam; Check this return information; And judge that according to the demand of self whether this return information is junk information, if then it is removed or marking, otherwise is classified as normal information with it.
Wherein, Because most of personal space is disclosed, Any user can let all netizens see this answer to the non-SPAM judgement of an answer, and for some sensitive informations; This strategy is obviously improper; Therefore for sensitive information, the user can only submit to and reverse application, can not revise the state of this comment at once.So, alternatively, the return information that the user carries out after secondary is judged is examined once more, after passing through, audit continues execution in step again.
Step 206: return information is grouped in the normal information classification, makes all users that in the classification of normal information, see return information carry out secondary and judge, and write down all users' judged result to return information.
In the present embodiment; After system judges that return information is normal information; This return information is grouped in the classification of normal information, the user can see this return information in the classification of normal information, and it is judged once more; The judged result of recording user is so that statistics is delivered the number of unified judged result.
Step 207: statistics is seen return information in the classification of normal information all users are the number of junk information to the judged result of return information.
Step 208: judge judged result to return information is whether the number of junk information satisfies preset threshold value, if, then with this return information deletion.
In the present embodiment; After system judges that this return information is non-junk information (normal information); This return information is classified as one type of normal information, and then the user checks the return information that is classified as normal information by system, judges according to the demand of self whether this return information is junk information; If then it is removed or marking, otherwise it is classified as normal information.
Because in internet UGC uses; All contents all are that the user submits to, and the user values the cyberspace of oneself very much, have a mind to safeguard clean and tidy in the own space; Do not hope the existence of SPAM; Therefore in SPAM judges, introduce user's decision factor in the present embodiment, the user can very first time update the system result of determination, then system's accuracy and directly lifting of accurate rate that SPAM is judged.And because the difference of user personality; Same UGC replied; Whether different user is that the judgement of SPAM maybe be inconsistent to it, and the user can revise in personal space whether certain bar UGC answer is the judgement of SPAM, but the result of determination that can't influence system immediately twists.
In the present embodiment, the user can see the SPAM content that system is judged at personal space, also can see normal content (system thinks that content is normal).To be judged to be normal answer by system be SPAM if the user thinks wherein one; He can be this answer mark SPAM directly at personal space, and this answer meeting disappears from his space immediately, and alternatively; User's selection can feed back to system; Influence the judge of system, and recording user is adjusted the weight of each characteristic item of return information to the judged result of return information according to the user's who writes down judged result to other similar answers.
If the user thinks that wherein an answer that is judged to be SPAM by system is a normal content; And this answer does not comprise sensitive information; Then the user can be this answer mark normal directly at personal space, and this answer can reappear in his space, and alternatively; User's selection can feed back to system, influences the judge of system to other similar answers; If this answer comprises sensitive information, then user's selection can not come into force at once, needs to wait for that background audit could determine whether this information can classify as normally.
Wherein, step 203-208 is SPAM decision-making system record self judged result, makes all users that see return information carry out secondary to return information and judges, and write down all users' secondary judged result; And, return information is labeled as the concrete execution in step of normal information or junk information according to all users' secondary judged result.
The beneficial effect of the technical scheme that the embodiment of the invention provides is: the method for selecting SPAM in the auxiliary judgment UGC content according to the user; Can let the user see and participate in the judgement of system to SPAM; Accuracy and judgement speed that the raising system is judged SPAM in the UGC content; And the user can reply submit own judgement to in the personal space all, have an opportunity system judge by accident, the content of non-SPAM brings order out of chaos the regular content classification down, also can classify as SPAM to the answer of the wall scroll in own space; Improve the accurate rate that SPAM judges, promote user experience.
Embodiment 3
Referring to Fig. 3, the embodiment of the invention provides a kind of device of process information, and said device comprises: first judge module 301, logging modle 302, second judge module 303.
Wherein, referring to Fig. 4, first judge module 301 comprises:
Judging unit 301c, if be used for probable value that computing unit obtains greater than pre-set threshold value, then return information is a junk information.
Wherein, logging modle 302 specifically is used for:
If the judged result of first judge module then is grouped into return information in the classification of junk information for being, makes all users that in the classification of junk information, see return information carry out secondary and judge, and write down all users' judged result return information;
Correspondingly, second judge module specifically is used for:
Statistics is seen return information in the classification of junk information all users are the number of normal information to the judged result of return information, judge judged result to return information is whether the number of normal information satisfies preset threshold value; If then return information is labeled as normal information.
Referring to Fig. 4, alternatively, device also comprises:
The 3rd judge module 304 is used for return information is labeled as before the normal information, judges whether sensitive information is arranged in the return information; If, then return information is examined once more, after passing through, audit continues execution in step again.
Referring to Fig. 4, alternatively, device also comprises:
First adjusting module 305 is used for return information is labeled as after the normal information, and record sees that the user of return information is judged as junk information the result of normal information; Adjust the weight of each characteristic item of return information according to the user's who writes down judged result.
Referring to Fig. 4, alternatively, logging modle 302 specifically is used for:
If the judged result of first judge module then is grouped into return information in the classification of normal information for not, makes all users that in the classification of normal information, see return information carry out secondary and judge, and write down all users' judged result return information;
Correspondingly, second judge module 303 specifically is used for:
Statistics is seen return information in the classification of normal information all users are the number of junk information to the judged result of return information, and judge judged result to return information is whether the number of junk information satisfies preset threshold value; If then return information is labeled as junk information.
Referring to Fig. 4, alternatively, device also comprises:
The technical scheme that the embodiment of the invention provides; Select the method for SPAM in the auxiliary judgment UGC content according to the user; Can let the user see and participate in the judgement of system to SPAM, accuracy and judgement speed that the raising system is judged SPAM in the UGC content, and the user can reply the judgement of submissions oneself in the personal space all; Have an opportunity system judge by accident, the content of non-SPAM brings order out of chaos the regular content classification down; Also can reply the wall scroll in own space and classify as SPAM, improve the accurate rate that SPAM judges, promote user experience.
The device that present embodiment provides, specifically can, belong to same design with method embodiment, its concrete implementation procedure sees method embodiment for details, repeats no more here.
The all or part of of the technique scheme that the embodiment of the invention provides can be accomplished through the relevant hardware of programmed instruction; Said program can be stored in the storage medium that can read, and this storage medium comprises: various media that can be program code stored such as ROM, RAM, magnetic disc or CD.
The above is merely preferred embodiment of the present invention, and is in order to restriction the present invention, not all within spirit of the present invention and principle, any modification of being done, is equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (14)
1. the method for a process information is characterized in that, said method comprises:
Receive the return information that arbitrary user to user generates content, judge whether said return information is junk information;
Write down said judged result, make all users that see said return information carry out secondary and judge, and write down said all users' secondary judged result said return information;
Secondary judged result according to said all users is labeled as normal information or junk information with said return information.
2. method according to claim 1 is characterized in that, saidly judges that whether said return information is junk information, comprising:
Extract each characteristic item of said return information;
Whether to said each characteristic item weighted sum, obtaining said return information is the probable value of junk information;
If the said probable value that obtains is greater than pre-set threshold value, then said return information is a junk information.
3. method according to claim 1 is characterized in that, the said judged result of said record makes all users that see said return information carry out secondary to said return information and judges, and writes down said all users' secondary judged result, comprising:
If said judged result is for being; Then said return information is grouped in the classification of junk information; Make all users that in the classification of said junk information, see said return information carry out secondary and judge, and write down said all users' judged result said return information;
Correspondingly, said secondary judged result according to said all users is labeled as normal information with said return information, comprising:
Statistics is seen said return information in the classification of said junk information all users are the number of normal information to the judged result of said return information, judge judged result to said return information is whether the number of normal information satisfies preset threshold value;
If then said return information is labeled as normal information.
4. method according to claim 3 is characterized in that, said said return information is labeled as normal information, also comprises before:
Judge whether sensitive information is arranged in the said return information;
If, then said return information is examined once more, after passing through, audit continues execution in step again.
5. method according to claim 3 is characterized in that, said said return information is labeled as normal information, also comprises afterwards:
Record sees that the user of said return information is judged as said junk information the result of normal information;
Weight according to each characteristic item of the said user's of said record judged result adjustment return information.
6. method according to claim 1 is characterized in that, the said judged result of said record makes all users that see said return information carry out secondary to said return information and judges, and writes down said all users' secondary judged result, comprising:
If said judged result is for denying; Then said return information is grouped in the classification of normal information; Make all users that in the classification of said normal information, see said return information carry out secondary and judge, and write down said all users' judged result said return information;
Correspondingly, said secondary judged result according to said all users is labeled as junk information with said return information, comprising:
Statistics is seen said return information in the classification of said normal information all users are the number of junk information to the judged result of said return information, and judge judged result to said return information is whether the number of junk information satisfies preset threshold value;
If then said return information is labeled as junk information.
7. method according to claim 6 is characterized in that, said said return information is labeled as junk information, also comprises afterwards:
Record sees that the user of said return information is judged as said normal information the result of junk information;
Weight according to each characteristic item of the said user's of said record judged result adjustment return information.
8. the device of a process information is characterized in that, said device comprises:
First judge module is used to receive the return information that arbitrary user to user generates content, and judges whether said return information is junk information;
Logging modle is used to write down said judged result, makes all users that see said return information carry out secondary to said return information and judges, and write down said all users' secondary judged result;
Second judge module is used for the secondary judged result according to said all users, and said return information is labeled as normal information or junk information.
9. device according to claim 8 is characterized in that, said first judge module comprises:
Extraction unit is used to extract each characteristic item of said return information;
Computing unit is used for said each characteristic item weighted sum, and whether obtain said return information is the probable value of junk information;
Judging unit, if be used for said probable value that said computing unit obtains greater than pre-set threshold value, then said return information is a junk information.
10. device according to claim 8 is characterized in that, said logging modle specifically is used for:
If the judged result of said first judge module is for being; Then said return information is grouped in the classification of junk information; Make all users that in the classification of said junk information, see said return information carry out secondary and judge, and write down said all users' judged result said return information;
Correspondingly, said second judge module specifically is used for:
Statistics is seen said return information in the classification of said junk information all users are the number of normal information to the judged result of said return information, judge judged result to said return information is whether the number of normal information satisfies preset threshold value; If then said return information is labeled as normal information.
11. device according to claim 10 is characterized in that, said device also comprises:
The 3rd judge module is used for said return information is labeled as before the normal information, judges whether sensitive information is arranged in the said return information; If, then said return information is examined once more, after passing through, audit continues execution in step again.
12. device according to claim 10 is characterized in that, said device also comprises:
First adjusting module is used for said return information is labeled as after the normal information, and record sees that the user of said return information is judged as said junk information the result of normal information; Weight according to each characteristic item of the said user's of said record judged result adjustment return information.
13. device according to claim 8 is characterized in that, said dress logging modle specifically is used for:
If the judged result of said first judge module is for denying; Then said return information is grouped in the classification of normal information; Make all users that in the classification of said normal information, see said return information carry out secondary and judge, and write down said all users' judged result said return information;
Correspondingly, said second judge module specifically is used for:
Statistics is seen said return information in the classification of said normal information all users are the number of junk information to the judged result of said return information, and judge judged result to said return information is whether the number of junk information satisfies preset threshold value; If then said return information is labeled as junk information.
14. device according to claim 13 is characterized in that, said device also comprises:
Second adjusting module is used for said return information is labeled as after the junk information, and record sees that the user of said return information is judged as said normal information the result of junk information; Weight according to each characteristic item of the said user's of said record judged result adjustment return information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110107521.3A CN102760130B (en) | 2011-04-27 | 2011-04-27 | The method and apparatus of process information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110107521.3A CN102760130B (en) | 2011-04-27 | 2011-04-27 | The method and apparatus of process information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102760130A true CN102760130A (en) | 2012-10-31 |
| CN102760130B CN102760130B (en) | 2016-11-16 |
Family
ID=47054588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110107521.3A Active CN102760130B (en) | 2011-04-27 | 2011-04-27 | The method and apparatus of process information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102760130B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970832A (en) * | 2014-04-01 | 2014-08-06 | 百度在线网络技术（北京）有限公司 | Method and device for recognizing spam |
| CN104252479A (en) * | 2013-06-27 | 2014-12-31 | 华为技术有限公司 | Method, device and system for processing information |
| CN104753758A (en) * | 2013-12-30 | 2015-07-01 | 深圳市腾讯计算机系统有限公司 | Information attribute identification method and device |
| CN111289276A (en) * | 2020-01-20 | 2020-06-16 | 北京韬盛科技发展有限公司 | Intelligent lifting safety detection method and device for climbing frame |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6421709B1 (en) * | 1997-12-22 | 2002-07-16 | Accepted Marketing, Inc. | E-mail filter and method thereof |
| CN1809821A (en) * | 2003-03-03 | 2006-07-26 | 微软公司 | Feedback loop for spam prevention |
-
2011
- 2011-04-27 CN CN201110107521.3A patent/CN102760130B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6421709B1 (en) * | 1997-12-22 | 2002-07-16 | Accepted Marketing, Inc. | E-mail filter and method thereof |
| CN1809821A (en) * | 2003-03-03 | 2006-07-26 | 微软公司 | Feedback loop for spam prevention |
Non-Patent Citations (3)
| Title |
|---|
| 王鑫等: "基于用户反馈和增量学习的垃圾邮件识别方", 《清华大学学报》 * |
| 王鑫等: "基于用户反馈和增量学习的垃圾邮件识别方法", 《清华大学学报》 * |
| 陈建发等: "一种基于用户行为分析的协同反垃圾邮件策略", 《电脑知识与技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104252479A (en) * | 2013-06-27 | 2014-12-31 | 华为技术有限公司 | Method, device and system for processing information |
| CN104252479B (en) * | 2013-06-27 | 2018-05-18 | 华为技术有限公司 | Processing method, the device and system of information |
| CN104753758A (en) * | 2013-12-30 | 2015-07-01 | 深圳市腾讯计算机系统有限公司 | Information attribute identification method and device |
| CN104753758B (en) * | 2013-12-30 | 2019-04-26 | 深圳市腾讯计算机系统有限公司 | A kind of information attribute recognition methods and device |
| CN103970832A (en) * | 2014-04-01 | 2014-08-06 | 百度在线网络技术（北京）有限公司 | Method and device for recognizing spam |
| CN111289276A (en) * | 2020-01-20 | 2020-06-16 | 北京韬盛科技发展有限公司 | Intelligent lifting safety detection method and device for climbing frame |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102760130B (en) | 2016-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190179861A1 (en) | Containing disinformation spread using customizable intelligence channels | |
| US9071560B2 (en) | Tagging email and providing tag clouds | |
| KR100723867B1 (en) | Apparatus and method for blocking access to phishing web page | |
| CN106453061B (en) | A kind of method and system identifying network fraudulent act | |
| CN104714970B (en) | Method, transmitting terminal, receiving terminal and the system that Email is sorted out | |
| CN106383852A (en) | Docker container-based log acquisition method and apparatus | |
| CN106921777B (en) | Information processing method and device, computer equipment and computer readable medium | |
| CN104951542A (en) | Method and device for recognizing class of social contact short texts and method and device for training classification models | |
| CN104348817B (en) | The guard method of user account number and device | |
| CN107465592A (en) | A kind of method for message interaction and system | |
| CN101488868A (en) | Social collaborative message prioritization system and method | |
| CN104009964A (en) | Network link detection method and system | |
| CN102760130A (en) | Information processing method and device | |
| Patel et al. | Perceptual representation of spam and phishing emails | |
| CN105095004B (en) | Information processing method and electronic equipment | |
| CN102811177A (en) | Method and system for sharing network information | |
| CN105208009A (en) | Safety detection method and apparatus of account number | |
| Mertler | Quantitative methodology in adolescent research | |
| CN103941953A (en) | Information processing method and device | |
| CN107391543A (en) | The kind identification method and device of a kind of hotspot | |
| Jenkins et al. | Phished: Automated contextual feedback for reported phishing | |
| CN111047455A (en) | Personal statue method and system for mail | |
| CN109359274A (en) | The method, device and equipment that the character string of a kind of pair of Mass production is identified | |
| Bly | The New Email Revolution: Save Time, Make Money, and Write Emails People Actually Want to Read! | |
| Zheng et al. | Phishing to improve detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |