CN104867020A - False evaluation ID judgment and identification system - Google Patents
False evaluation ID judgment and identification system Download PDFInfo
- Publication number
- CN104867020A CN104867020A CN201510251000.3A CN201510251000A CN104867020A CN 104867020 A CN104867020 A CN 104867020A CN 201510251000 A CN201510251000 A CN 201510251000A CN 104867020 A CN104867020 A CN 104867020A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- false
- judge module
- module
- content
- 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.)
- Pending
Links
Abstract
The invention relates to the internet field, and especially relates to a false evaluation ID judgment and identification system. The system comprises a client, a network connection device and a false evaluation judging and marking module. The false evaluation judging and marking module comprises an ID similarity judgment module, an ID cheat factor judgment module, a content similarity judgment module, and a false evaluation marking module which are sequentially connected. The client acquires relevant evaluation data information of a target commodity through the network connection device, outputs the data information to the false evaluation judging and marking module, judges the cheat possibility of IDs on the basis that the same or similar evaluation IDs are identified, performs similarity comparison on the evaluation content given by the identified IDs in order to improve the accuracy of the identification, and finally marks judgment results. The system can accurately identify the false evaluation IDs of a professional evaluation team.
Description
Technical field
The present invention relates to internet arena, particularly a kind of false evaluation ID judges recognition system.
Background technology
In the present age, along with popularizing of internet, ecommerce has become a kind of commerce and trade mode be widely used.Both parties mainly carry out transaction by the webpage of electric business or software.Because ecommerce does not have traditional entity StoreFront, not high to the quantitative requirement of sales force yet, so compare conventional transaction pattern more can control operation cost, thus there is larger price advantage.
The development of current ecommerce is swift and violent, the scale of construction is huge, Seller Number in electricity quotient ring border is numerous, user is difficult to when carrying out purchase decision the authenticity judging descriptive labelling, the dependency degree evaluated commodity is very high, and the situation of buyer's interests loss that the situation of the performance favorable comment degree virtual height of commodity caused because seller evaluates cheating causes is serious.And have a lot of illegal businessman to improve the sales volume of oneself thus employing occupation brush to evaluate team also to manufacture a large amount of false evaluation and carry out false publication to the commodity of oneself, thus deception consumer improves the true sales volume of oneself.These a large amount of false evaluation are to the judgement generation greatly interference of consumer for commodity authenticity, normal market order is disturbed while having cheated consumer, harmful effect is caused to the prestige of the whole platform of ecommerce, under these circumstances, how especially team's cheating serious is like this evaluated for identifying and judging into problem demanding prompt solution in e-commerce development process for engaging occupation to brush to the evaluation cheating row of businessman in ecommerce; Judge the accuracy how improving judgement in false evaluation process, avoid the generation of erroneous judgement situation to be also very important considerations; The deterministic process that relevant device accurately and effectively realizes being correlated with also is lacked in currently available technology.
Summary of the invention
In order to solve problems of the prior art, the invention provides a kind of false evaluation ID and judge recognition system, on the basis judging identical and similar evaluation ID, judge the cheating possibility of these ID, if send the frequency of evaluation apparently higher than normal frequency, then judge that these ID are as false evaluation ID, in order to improve the accuracy of discriminating, the evaluation content that the false ID identified sends is carried out similarity system design, identify identical with similar evaluation content, and eventually through false evaluation mark module by the result queue of judgement out; Present invention achieves the automatic identification of false evaluation ID in end article evaluation, the result of judgement is strictly reliable, and the discriminating accuracy for the evaluation ID of vocational evaluation team is high.
In order to realize foregoing invention object, the invention provides following technical scheme:
A kind of false evaluation ID judges recognition system; Comprise client computer, network connection device and false evaluation judge mark module; Wherein said false evaluation judge mark module, comprises ID similarity judge module, ID practises fraud factor judge module, content similarities judge module and false evaluation mark module; The end article evaluation information got (can be got the relevant information in target web by network connection device by described client computer at present very easily by crawler technology, the speed extracted is fast, the total amount can analyzing data is huge, to extract the analytical approach of data ripe, with low cost) output in described false evaluation judge mark module described ID similarity judge module; Described ID similarity judge module, ID cheating factor judge module, content similarities judge module and false evaluation mark module are connected successively by data line.
During native system work: the end article evaluation information got to output in the described ID similarity judge module in described false evaluation judge mark module by described client computer by network connection device; Described ID similarity judge module judges the identical and similar evaluation ID in evaluation information, and result is input in described ID cheating factor judge module.Current occupation brush evaluation team manually or can utilize automatic register machine, and to register a lot of trumpet, (so-called trumpet refers to, same person registration and different No. ID of using), the small size ID that these vocational evaluation team register and use has certain regularity; Generally vocational evaluation teacher register a series of No. ID also according to system recommendation or automatically generate, such mode No. ID of producing can have larger relevance and similarity, such as ABC1, ABC2, ABC3, ABC4, ABC5.....ABCn.By comparing (the determination methods that current text similarity compares comparative maturity to the text similarity evaluating ID, such as the similarity degree that cosine ratio of similitude can be taked comparatively to judge between content of text, when similarity degree exceedes default threshold value, then can think similar by the content of text compared, concrete comparison procedure repeats no more) just can judge that whether the evaluation ID corresponding to identical or similar evaluation content is identical or similar; If identical or similar, so these ID are that the possibility of false ID is very high.
Further, judged result is input in described ID cheating factor judge module by described ID similarity judge module; Described ID practises fraud factor judge module on the basis of the identical or similar ID judged, analyze frequency and time that corresponding ID sends evaluation, the average ratings frequency of the frequency and end article evaluation that corresponding ID are sent evaluation compares, if its ratio is higher than the threshold value of setting, then these are evaluated ID and be judged as false evaluation ID, and the false evaluation ID judged result judged is input in described content similarities judge module; By native system judge that the process of false evaluation is strict, judged result is comparatively accurate.
In order to improve the accuracy that false evaluation judges further, make the result of judgement stricter, described content similarities judge module has carried out further identification to the evaluation content that described ID practises fraud corresponding to false evaluation ID that the interpretation of factor judge module institute goes out, go out by text similarity multilevel iudge the identical and similar evaluation content that corresponding ID sends, and judged result is input in described false evaluation mark module.If businessman wants by wash sale and evaluates the sales volume and the favorable comment situation that improve system display of commodity at present, the quantity of required false evaluation is larger, people from team evaluated by occupation brush is under these circumstances that the evaluation of fabricating often has higher similarity in evaluation content, or occurs with identical content with regard to direct; The quantity of the identical evaluation of the judge module of content similarities described in present system statistical content, judge the evaluation that content is similar, and count the quantity of the similar evaluation of content, calculate evaluation content likelihood to be compared, compared by the threshold value that similar Assessment Rate result of calculation and module are pre-set, if this similar Assessment Rate exceedes threshold value, then evaluation content to be compared is judged as similar evaluation.The process that such judgement deterministic process evaluates the false ID of the series registered described in team to occupation brush is relatively stricter, and the result of judgement accurately and reliably.
Preferred as one, described ID similarity judge module is that ID similarity judges server; Described ID cheating factor judge module is that the ID cheating factor judges server; Described content similarities judge module is that similar evaluation content judges server; Described false evaluation mark module is false evaluation mark server.Described ID similarity judges that the factor judges server, described similar evaluation content judges server and described false evaluation mark server is connected successively by data connecting line in server, ID cheating.Server is exhibits excellent in processing power, stability, reliability, security, extensibility, manageability etc., relevant content similarities is completed by server, the correlated judgment of ID similarity, can the related data of a large amount of electric business's end article of fast processing, processing speed is fast, and efficiency is high.
Compared with prior art, beneficial effect of the present invention: the invention provides a kind of false evaluation ID and judge recognition system.By the network address of client access end article, crawl the evaluating data of corresponding goods webpage; And by server, the evaluating data crawled is judged, by analyzing evaluation ID, count the quantity of identical ID, and judge the likelihood probability of other ID, the evaluation ID similar threshold value that likelihood probability and machine learning are drawn, determine similar evaluation ID, and add up the judged result of similar ID; The false ID trumpet of series that such judgment mode is evaluated given by team for occupation brush has higher judgment accuracy, being practised fraud by described ID in the basis judging identical and similar ID, to these, identical or similar ID is that the possibility of cheating ID judges to factor judge module, to these ID send time of evaluation and frequency judges, if wait to judge ID send the threshold value of frequency higher than setting of evaluation, then these are evaluated ID and are judged as false ID; In order to improve the accuracy of judgement further, the present invention is further judged the evaluation content that ID practises fraud corresponding to false ID that factor judge module judges by described content similarities judge module, assay content, add up the appearance quantity of identical evaluation content, and calculated the likelihood probability of other evaluation content by text comparison algorithm; This likelihood probability and the evaluation content similar threshold value drawn by machine learning method are compared, determine similar evaluation content, and judged result is input in the false mark module of described falseness, judged result is marked (tag content comprises false evaluation ID and identical and similar evaluation content) by false evaluation mark module; False evaluation determination methods of the present invention can add accurately and comprehensively analyze the false evaluation of end article, similar ID identification has targetedly been carried out to the trumpet of vocational evaluation teacher registration, the identification capability of vocational evaluation teacher evaluation cheating serious is like this engaged to significantly improve to end article, contribute to the confidence level improving electric quotient ring border, be conducive to the formation of normal management and control order.
Accompanying drawing illustrates:
Fig. 1 is that this false evaluation ID judges the overall annexation figure of recognition system.
Fig. 2 is the model calling graph of a relation that this false evaluation ID judges recognition system.
Fig. 3 is the preferred annexation figure that this false evaluation ID judges recognition system.
Embodiment
Below in conjunction with test example and embodiment, the present invention is described in further detail.But this should be interpreted as that the scope of the above-mentioned theme of the present invention is only limitted to following embodiment, all technology realized based on content of the present invention all belong to scope of the present invention.
The invention provides a kind of false evaluation ID and judge recognition system, on the basis judging identical and similar evaluation ID, judge the cheating possibility of these ID, if send the frequency of evaluation apparently higher than normal frequency, then judge that these ID are as false evaluation ID, in order to improve the accuracy of discriminating, the evaluation content that the false ID identified sends is carried out similarity system design, identify identical with similar evaluation content, and eventually through false evaluation mark module by the result queue of judgement out; Present invention achieves the automatic identification of false evaluation ID in end article evaluation, the result of judgement is strictly reliable, and the discriminating accuracy for the evaluation ID of vocational evaluation team is high.
In order to realize foregoing invention object, the invention provides following technical scheme:
A kind of false evaluation ID judges recognition system, as shown in Figure 1 and Figure 2; Comprise client computer, network connection device and false evaluation judge mark module; Wherein said false evaluation judge mark module (wherein shown in dotted line frame), comprises ID similarity judge module, ID practises fraud factor judge module, content similarities judge module and false evaluation mark module; The end article evaluation information got (can be got the relevant information in target web by network connection device by described client computer at present very easily by crawler technology, the speed extracted is fast, the total amount can analyzing data is huge, to extract the analytical approach of data ripe, with low cost) output in described false evaluation judge mark module described ID similarity judge module; Described ID similarity judge module, ID cheating factor judge module, content similarities judge module and false evaluation mark module are connected successively by data line.
During native system work: the end article evaluation information got to output in the described ID similarity judge module in described false evaluation judge mark module by described client computer by network connection device; Described ID similarity judge module judges the identical and similar evaluation ID in evaluation information, and result is input in described ID cheating factor judge module.Current occupation brush evaluation team manually or can utilize automatic register machine, and to register a lot of trumpet, (so-called trumpet refers to, same person registration and different No. ID of using), the small size ID that these vocational evaluation team register and use has certain regularity; Generally vocational evaluation teacher register a series of No. ID also according to system recommendation or automatically generate, such mode No. ID of producing can have larger relevance and similarity, such as ABC1, ABC2, ABC3, ABC4, ABC5.....ABCn.By comparing (the determination methods that current text similarity compares comparative maturity to the text similarity evaluating ID, such as the similarity degree that cosine ratio of similitude can be taked comparatively to judge between content of text, when similarity degree exceedes default threshold value, then can think similar by the content of text compared, concrete comparison procedure repeats no more) just can judge that whether the evaluation ID corresponding to identical or similar evaluation content is identical or similar; If identical or similar, so these ID are that the possibility of false ID is very high.
Further, judged result is input in described ID cheating factor judge module by described ID similarity judge module; Described ID practises fraud factor judge module on the basis of the identical or similar ID judged, analyze frequency and time that corresponding ID sends evaluation, the average ratings frequency of the frequency and end article evaluation that corresponding ID are sent evaluation compares, if its ratio is higher than the threshold value of setting, then these are evaluated ID and be judged as false evaluation ID, and the false evaluation ID judged result judged is input in described content similarities judge module; By native system judge that the process of false evaluation is strict, judged result is comparatively accurate.
About the cheating factor, make following definition, the cheating factor is a value between [0 ~ ∞], is worth larger, represents that the possibility of cheating is higher, otherwise lower.Detailed computing method are as follows: in the average ratings time interval calculating i-th ID, computing formula is as follows:
Wherein t
nsend out the time point evaluated, t n-th time
1send out the time point evaluated the 1st time; Calculate the overall average evaluation intervals of all ID of these commodity, computing formula is as follows:
Calculate the cheating factor, computing formula is as follows:
Wherein η is the cheating factor; The predicting relation of cheating ID is:
(namely during η>=2), (the evaluation time frequency of false ID is 2 times of the evaluation frequency of all evaluations of end article, and wherein the factor of 2 times is through experimental verification, is one and more preferably selects; Namely the interval sending out comment as this ID is less than equispaced
time, namely think that this ID is the ID providing false evaluation).
In order to improve the accuracy that false evaluation judges further, make the result of judgement stricter, described content similarities judge module has carried out further identification to the evaluation content that described ID practises fraud corresponding to false evaluation ID that the interpretation of factor judge module institute goes out, go out by text similarity multilevel iudge the identical and similar evaluation content that corresponding ID sends, and judged result is input in described false evaluation mark module.If businessman wants by wash sale and evaluates the sales volume and the favorable comment situation that improve system display of commodity at present, the quantity of required false evaluation is larger, people from team evaluated by occupation brush is under these circumstances that the evaluation of fabricating often has higher similarity in evaluation content, or occurs with identical content with regard to direct; The quantity of the identical evaluation of the judge module of content similarities described in present system statistical content, judge the evaluation that content is similar, and count the quantity of the similar evaluation of content, calculate evaluation content likelihood to be compared, compared by the threshold value that similar Assessment Rate result of calculation and module are pre-set, if this similar Assessment Rate exceedes threshold value, then evaluation content to be compared is judged as similar evaluation.The process that such judgement deterministic process evaluates the false ID of the series registered described in team to occupation brush is relatively stricter, and the result of judgement accurately and reliably.
Preferred as one, as shown in Figure 3, described ID similarity judge module is that ID similarity judges server; Described ID cheating factor judge module is that the ID cheating factor judges server; Described content similarities judge module is that similar evaluation content judges server; Described false evaluation mark module is false evaluation mark server.Described ID similarity judges that the factor judges server, described similar evaluation content judges server and described false evaluation mark server is connected successively by data connecting line in server, ID cheating.Server is exhibits excellent in processing power, stability, reliability, security, extensibility, manageability etc., relevant content similarities is completed by server, the correlated judgment of ID similarity, can the related data of a large amount of electric business's end article of fast processing, processing speed is fast, and efficiency is high.
Claims (7)
1. false evaluation ID judges a recognition system, it is characterized in that, comprises client computer, network connection device and false evaluation judge mark module; Wherein said false evaluation judge mark module, comprises ID similarity judge module, ID practises fraud factor judge module, content similarities judge module and false evaluation mark module; The end article evaluation information got to output in the described ID similarity judge module in described false evaluation judge mark module by described client computer by network connection device; Described ID similarity judge module, ID cheating factor judge module, content similarities judge module and false evaluation mark module are connected successively by data line.
2. false evaluation ID as claimed in claim 1 judges recognition system, and it is characterized in that, the end article evaluation information got outputs in described ID similarity judge module by described client computer;
Described ID similarity judge module judges the identical and similar evaluation ID in evaluation information, and result is input in described ID cheating factor judge module;
Described ID practise fraud factor judge module to described ID similarity judge module judge that the frequency sending evaluation of identical and similar ID compares, if wait to judge ID send the frequency of evaluation higher than threshold value, then these ID are judged as false evaluation ID by described ID cheating factor judge module, and are input in described content similarities judge module by the false evaluation ID judged result judged;
Described content similarities judge module goes out by text similarity multilevel iudge the identical and similar evaluation content that corresponding ID sends, and judged result is input in described false evaluation judge module.
3. false evaluation ID as claimed in claim 2 judges recognition system, and it is characterized in that, described ID similarity judge module is that ID similarity judges server; Described ID cheating factor judge module is that the ID cheating factor judges server; Described content similarities judge module is that content similarities judges server; Described false evaluation mark module is false evaluation mark server.
4. false evaluation ID as claimed in claim 3 judges recognition system, it is characterized in that, described ID similarity judges that server, the ID cheating factor judges that server, content type judgement server and false evaluation mark server is connected successively by data connecting line.
5. false evaluation ID as claimed in claim 4 judges recognition system, it is characterized in that, described content similarities is judged that the false evaluation content that server is judged and corresponding ID are marked by described false evaluation mark module.
6. false evaluation ID as claimed in claim 5 judges recognition system, it is characterized in that, described ID similarity judge module, by carrying out text identification to the evaluation ID in evaluating data, counting identical and similar evaluation ID respectively.
7. false evaluation ID as claimed in claim 5 judges recognition system, it is characterized in that, described content similarities judge module, by carrying out text identification to the evaluation content in evaluating data, counts identical evaluation content and similar evaluation content respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510251000.3A CN104867020A (en) | 2015-05-16 | 2015-05-16 | False evaluation ID judgment and identification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510251000.3A CN104867020A (en) | 2015-05-16 | 2015-05-16 | False evaluation ID judgment and identification system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104867020A true CN104867020A (en) | 2015-08-26 |
Family
ID=53912838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510251000.3A Pending CN104867020A (en) | 2015-05-16 | 2015-05-16 | False evaluation ID judgment and identification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104867020A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110390549A (en) * | 2018-04-20 | 2019-10-29 | 腾讯科技（深圳）有限公司 | A kind of small size recognition methods of registration, device, server and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020482A (en) * | 2013-01-05 | 2013-04-03 | 南京邮电大学 | Relation-based spam comment detection method |
| CN103778186A (en) * | 2013-12-31 | 2014-05-07 | 南京财经大学 | Method for detecting sockpuppet |
| CN103984673A (en) * | 2013-02-11 | 2014-08-13 | 谷歌股份有限公司 | Automatic detection of fraudulent ratings/comments related to an application store |
-
2015
- 2015-05-16 CN CN201510251000.3A patent/CN104867020A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020482A (en) * | 2013-01-05 | 2013-04-03 | 南京邮电大学 | Relation-based spam comment detection method |
| CN103984673A (en) * | 2013-02-11 | 2014-08-13 | 谷歌股份有限公司 | Automatic detection of fraudulent ratings/comments related to an application store |
| CN103778186A (en) * | 2013-12-31 | 2014-05-07 | 南京财经大学 | Method for detecting sockpuppet |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110390549A (en) * | 2018-04-20 | 2019-10-29 | 腾讯科技（深圳）有限公司 | A kind of small size recognition methods of registration, device, server and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI712981B (en) | Risk identification model training method, device and server | |
| CN104867017A (en) | Electronic commerce client false evaluation identification system | |
| CN104881795A (en) | E-commerce false comment judging and recognizing method | |
| WO2018040944A1 (en) | System, method, and device for identifying malicious address/malicious purchase order | |
| CN104881796A (en) | False comment judgment system based on comment content and ID recognition | |
| CN109711955B (en) | Poor evaluation early warning method and system based on current order and blacklist base establishment method | |
| CN108665159A (en) | A kind of methods of risk assessment, device, terminal device and storage medium | |
| WO2019061994A1 (en) | Electronic device, insurance product recommendation method and system, and computer readable storage medium | |
| US20140351109A1 (en) | Method and apparatus for automatically identifying a fraudulent order | |
| CN103577988A (en) | Method and device for recognizing specific user | |
| US20170053213A1 (en) | Method and system for filtering goods evaluation information | |
| TW201939412A (en) | Identification method, device, server and storage medium for fraudulent transaction | |
| RU2010125682A (en) | GROUP TRADE FORECASTING METHODS AND DEVICE | |
| WO2019071906A1 (en) | Financial product recommendation device and method, and computer-readable storage medium | |
| CN110009297A (en) | A kind of fiduciary qualification signal auditing method, device and equipment | |
| CN110135684A (en) | A kind of capability comparison method, capability comparison device and terminal device | |
| CN104867032A (en) | Electronic commerce client evaluation identification system | |
| CN108961019A (en) | A kind of detection method and device of user account | |
| WO2015118616A1 (en) | Document analysis system, document analysis method, and document analysis program | |
| CN104867018A (en) | Electronic commerce evaluation judgment system based on evaluation content and ID similarity identification | |
| CN114118816A (en) | Risk assessment method, device and equipment and computer storage medium | |
| CN104867020A (en) | False evaluation ID judgment and identification system | |
| CN111784053A (en) | Transaction risk detection method, device and readable storage medium | |
| CN109509023A (en) | A kind of big data intelligent marketing system | |
| CN104867033A (en) | Electronic commerce client evaluation judging and marking system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150826 |
|
| WD01 | Invention patent application deemed withdrawn after publication |