CN109446528A - The recognition methods of new fraudulent gimmick and device - Google Patents
The recognition methods of new fraudulent gimmick and device Download PDFInfo
- Publication number
- CN109446528A CN109446528A CN201811276062.XA CN201811276062A CN109446528A CN 109446528 A CN109446528 A CN 109446528A CN 201811276062 A CN201811276062 A CN 201811276062A CN 109446528 A CN109446528 A CN 109446528A
- Authority
- CN
- China
- Prior art keywords
- participle
- swindle
- defined algorithm
- adjacency matrix
- module
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 33
- 239000011159 matrix material Substances 0.000 claims abstract description 27
- 239000013598 vector Substances 0.000 claims abstract description 27
- 230000011218 segmentation Effects 0.000 claims description 20
- 230000000717 retained effect Effects 0.000 claims 1
- 241000212384 Bifora Species 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Alarm Systems (AREA)
Abstract
The present invention relates to technical field of data processing, more particularly to a kind of new fraudulent gimmick recognition methods and device, this method comprises: being segmented to a plurality of data of receiving a crime report, and then the term vector of each participle is calculated separately using the first pre-defined algorithm, the Euclidean distance for successively calculating the term vector of every two participle obtains adjacency matrix, finally is classified to obtain different swindle types to the corresponding participle of adjacency matrix using the second pre-defined algorithm again.It can be seen that, scheme intelligence provided by the invention is to data of receiving a crime report by participle, calculating term vector and adjacency matrix to obtain swindle type, so that public security officer can store each swindle type, and the measure that corresponding every kind of swindle type of storage may be taken, in order to which the similar swindle case of subsequent processing can refer to, improve work efficiency.
Description
Technical field
The present invention relates to technical field of data processing, in particular to a kind of new fraudulent gimmick recognition methods and dress
It sets.
Background technique
Fraud tactics emerge one after another at present, usually the different swindle ways such as Stock discrimination and telecommunication fraud, current public affairs
Peace system is all stored with the swindle way and the corresponding treating method of different swindle ways of different swindle types mostly, so that
Public security officer can refer to existing processing mode and handled when encountering similar swindle case.But swindle case layer goes out
It is not poor, and swindle type is also more and more diversified, carries out intelligent classification to different swindle cases for the ease of staff, so as to
It can be referred to when subsequent processing case, providing a kind of is very necessary to swindling gimmick to carry out knowledge method for distinguishing.
Summary of the invention
The purpose of the present invention is to provide a kind of new fraudulent gimmick recognition methods, are carried out with realizing to new fraudulent gimmick
Identification in order to carry out intelligent classification to swindle way, while facilitating public security officer to carry out the work.
Another object of the present invention is to provide a kind of new fraudulent gimmick identification devices, to realize to new fraudulent gimmick
It is identified, in order to carry out intelligent classification to swindle way, while public security officer being facilitated to carry out the work.
To achieve the goals above, technical solution used in the embodiment of the present invention is as follows:
In a first aspect, the embodiment of the invention provides a kind of new fraudulent gimmick recognition methods, which comprises to more
Item data of receiving a crime report are segmented；The term vector of each participle is calculated separately using the first pre-defined algorithm；Successively calculate every two point
The Euclidean distance of the term vector of word obtains adjacency matrix；The corresponding participle of the adjacency matrix is carried out using the second pre-defined algorithm
Classification obtains different swindle types.
Second aspect, the embodiment of the invention also provides a kind of new fraudulent gimmick identification device, described device includes: point
Word module, for being segmented to a plurality of data of receiving a crime report；First computing module, for being calculated separately often using the first pre-defined algorithm
The term vector of a participle；Second computing module is abutted for successively calculating the Euclidean distance of term vector of every two participle
Matrix；Categorization module is different for being classified to obtain to the corresponding participle of the adjacency matrix using the second pre-defined algorithm
Swindle type.
A kind of new fraudulent gimmick recognition methods provided in an embodiment of the present invention and device, this method comprises: being connect to a plurality of
Alert data are segmented, and then the term vector of each participle is calculated separately using the first pre-defined algorithm, successively calculate every two point
The Euclidean distance of the term vector of word obtains adjacency matrix, finally again using the second pre-defined algorithm it is corresponding to adjacency matrix segment into
Row classification obtains different swindle types.It can be seen that scheme intelligence provided by the invention is to data of receiving a crime report by participle, calculating
Term vector and adjacency matrix are to obtain swindle type, so that public security officer can store each swindle type, and right
The measure that every kind of swindle type may be taken should be stored, in order to which the similar swindle case of subsequent processing can refer to, improves work
Make efficiency.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of flow diagram of new fraudulent gimmick recognition methods provided in an embodiment of the present invention.
Fig. 2 shows a kind of the functional block diagrams of new fraudulent gimmick identification device provided in an embodiment of the present invention.
Diagram: 100- new fraudulent gimmick identification device；110- word segmentation module；120- removes module；Mould is arranged in 130-
Block；The first computing module of 140-；The second computing module of 150-；160- categorization module.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Meanwhile of the invention
In description, term " first ", " second " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
What a kind of new fraudulent gimmick recognition methods provided in an embodiment of the present invention can receive public security system a plurality of connects
Alert data obtain this and receive a crime report the swindle types of data after being handled, so public security system this can be received a crime report situation carry out it is standby
Case, and the processing method of the synchronous typing situation of receiving a crime report, if so that subsequent encounter similar alarm case, public security officer
Processing means before can refer to are handled, to greatly improve the working efficiency of public security officer.
Fig. 1 is please referred to, is a kind of flow diagram of new fraudulent gimmick recognition methods provided in an embodiment of the present invention, it should
Method includes:
Step S110 segments a plurality of data of receiving a crime report.
Specifically, such as public security system can receive the report of citizen by telephone call or a variety of type of alarms of network alarming
It is alert, it is readily appreciated that, more universal type of alarm is telephone call.If the possible alarm condition of citizen has, " someone puts Chinese chess
Final phase of a chess game swindle ", " looking for part-time cheated 300 yuans " " part-time cheated " " opening bishop ending " " buying commodity " etc., it can be seen that, citizen's
Alarm condition may be there are many type, it is also possible to the case type duplicated.In turn, the data of receiving a crime report received are divided
Word, the word segmentation regulation can self-setting according to actual needs, such as can be to " someone puts bishop ending's swindle " this data point of receiving a crime report
Word is " someone " " pendulum " " bishop ending " " swindle ", can also be segmented as " someone " " pendulum bishop ending " " swindle ".
Step S120 removes the invalid participle in word segmentation result, retains effectively participle.
Specifically, a data of receiving a crime report, which are segmented, to obtain the word segmentation result comprising multiple words, the word segmentation result
In include some invalid participles, also include some effective participles.The participle knot of data of such as receiving a crime report " someone put bishop ending swindle "
Fruit is " someone " " pendulum " " bishop ending " " swindle ", wherein " someone " indicates appellation and the word of meaning is not invalid
Participle, " bishop ending " " swindle " are then effectively participle.
To the invalid method of determination segmented and effectively segment in word segmentation result are as follows: will be in the word segmentation result for data of receiving a crime report
Each participle is successively compared with prepending non-significant participle list, and multiple invalid points are enumerated in prepending non-significant participle list
Word.If the participle in word segmentation result is present in prepending non-significant participle list, which is invalid participle, the word segmentation result
In participle do not exist in the prepending non-significant participle list in, then the participle be effectively participle, and then remove word segmentation result in
Invalid participle retains effectively participle.
Serial number is arranged to each participle respectively using the first pre-defined algorithm in step S130.
Specifically, in embodiments of the present invention, which is TF-IDF algorithm, and then first predetermined by this
Serial number is arranged to each effective participle in algorithm, such as ' the final phase of a chess game ': 5, ' Chinese chess ': 8, ' swindle ': 7, ' Gao Wang ': 9, ' big mountain area ':
2, ' great Lin ': 3, ' cheated ': 6, ' part-time ': 0, ' hill ': 4, ' buying commodity ': 1 }, wherein 0-9 is respectively the sequence of corresponding participle
Number.
Step S140 calculates separately the term vector of each participle using the first pre-defined algorithm.
I other words the term vector of each participle is calculated separately using TF-IDF algorithm, the set of the term vector of each participle
It can be expressed as,
Step S150, the Euclidean distance for successively calculating the term vector of every two participle obtain adjacency matrix.
Specifically, calculating the Euclidean distance of every two participle according to the term vector of every two participle, each Euclidean distance can
It is unified to be indicated by an adjacency matrix.Such as adjacency matrix can be with are as follows:
In addition to this, the distance between the term vector of every two participle calculates, and can not only be calculated with Euclidean distance,
The methods of Jacard coefficient, cosine similarity can also be used to seek the distance between two term vectors.
Step S160 is classified to obtain different swindlenesses using the second pre-defined algorithm to the corresponding participle of the adjacency matrix
Deceive type.
Specifically, the second pre-defined algorithm is clustering algorithm, specially DBSCAN algorithm in embodiments of the present invention, this is removed
Except, this clustering algorithm of OPTICS can also be used.In turn, it will abut against the Europe of the participle in matrix by the second pre-defined algorithm
Formula distance is compared with preset threshold, and the participle that Euclidean distance is less than preset threshold is classified as one kind, different classes of to obtain
Swindle type.The data that will such as receive a crime report " Chongqing someone puts bishop ending's swindle " and " Chongqing subway puts bishop ending's swindle " point
After word obtains term vector, if the Euclidean distance being calculated between every two participle is 0.5, which is 1, then it is assumed that
This two participles are same swindle type.
And then other are analyzed in the same way, different swindle types can be obtained, such as:
0th group, group: { 0,3,4 }.Keyword: ' the final phase of a chess game ': 3, ' Chinese chess ': 3, ' swindle ': 1 }
1st group, group: { 1,2,5 }.Keyword: ' Gao Wang ': 2, ' big mountain area ': 1, ' great Lin ': 2, ' cheated ': 3, ' simultaneous
Duty ': 3, ' hill ': 1 }
2nd group, group: { 6 }.Keyword: ' buy commodity ': 1, ' cheated ': 1 }
Above represent " bishop ending's swindle " " part-time cheated " " buying commodity " three kinds of swindle types.
It should be noted that there is ductility between participle when the participle to characterization swindle type divides classification.It is
Say, if participle A and segment B between Euclidean distance be less than preset threshold, segment B and segment C between Euclidean distance again smaller than
Preset threshold, then segment A, participle B and participle C belongs to same category of swindle type；If segmenting A and segmenting the Europe between B
Formula distance is less than preset threshold, and the Euclidean distance for segmenting A and segmenting between C is less than preset threshold, but segments between B and participle C
Euclidean distance be greater than preset threshold, then segment A, participle B and participle C should also be as belonging to same category of swindle type.
In turn, after the swindle type that intelligent recognition goes out data of receiving a crime report, which can be stored in public affairs by public security officer
In peace system, and the corresponding processing method for storing this kind swindle type, in order to which next public security officer can refer to this processing
Mode improves working efficiency.
It referring to figure 2., is a kind of functional module of new fraudulent gimmick identification device 100 provided in an embodiment of the present invention
Schematic diagram, the device include word segmentation module 110, removal module 120, setup module 130, the first computing module 140, second meter
Calculate module 150 and categorization module 160.
Word segmentation module 110, for being segmented to a plurality of data of receiving a crime report.
In embodiments of the present invention, step S110 can be executed by word segmentation module 110.
Module 120 is removed, for removing the invalid participle in word segmentation result, retains effectively participle.
In embodiments of the present invention, step S120 can be executed by removal module 120.
Setup module 130, for serial number to be arranged to each participle respectively using the first pre-defined algorithm.
In embodiments of the present invention, step S130 can be executed by setup module 130.
First computing module 140, for calculating separately the term vector of each participle using the first pre-defined algorithm.
In embodiments of the present invention, step S140 can be executed by the first computing module 140.
Second computing module 150 obtains adjacency matrix for successively calculating the Euclidean distance of term vector of every two participle.
In embodiments of the present invention, step S150 can be executed by the second computing module 150.
Categorization module 160, for being classified to obtain to the corresponding participle of the adjacency matrix using the second pre-defined algorithm
Different swindle types.
In embodiments of the present invention, step S160 can be executed by categorization module 160.
Due to having been described in new fraudulent gimmick recognition methods part, details are not described herein.
In conclusion a kind of new fraudulent gimmick recognition methods provided in an embodiment of the present invention and device, this method comprises:
A plurality of data of receiving a crime report are segmented, and then calculate separately the term vector of each participle using the first pre-defined algorithm, are successively calculated
The Euclidean distance of the term vector of every two participle obtains adjacency matrix, finally corresponding to adjacency matrix using the second pre-defined algorithm again
Classified obtain different swindle types.It can be seen that scheme intelligence provided by the invention through data of receiving a crime report
Participle calculates term vector and adjacency matrix to obtain swindle type, so that public security officer can carry out each swindle type
Storage, and the measure that every kind of swindle type of corresponding storage may be taken, in order to which the similar swindle case of subsequent processing can refer to,
It improves work efficiency.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to an entity or behaviour
Make with another entity or operate distinguish, without necessarily requiring or implying between these entities or operation there are it is any this
The actual relationship of kind or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to nonexcludability
Include so that include a series of elements process, method, article or equipment not only include those elements, but also
Including other elements that are not explicitly listed, or further include for this process, method, article or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method, article or equipment of element.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of new fraudulent gimmick recognition methods, which is characterized in that the described method includes:
A plurality of data of receiving a crime report are segmented；
The term vector of each participle is calculated separately using the first pre-defined algorithm；
The Euclidean distance for successively calculating the term vector of every two participle obtains adjacency matrix；
The corresponding participle of the adjacency matrix is classified using the second pre-defined algorithm to obtain different swindle types.
2. the method as described in claim 1, which is characterized in that it is described a plurality of data of receiving a crime report are segmented after further include step
It is rapid:
The invalid participle in word segmentation result is removed, effectively participle is retained.
3. method according to claim 2, which is characterized in that the invalid participle in the removal word segmentation result retains effective
The step of participle includes:
Each of described word segmentation result participle is successively compared with prepending non-significant participle list, removal is present in described
Prepending non-significant segments the invalid participle in list, retains effectively participle.
4. the method as described in claim 1, which is characterized in that it is described a plurality of data of receiving a crime report are segmented after further include step
It is rapid:
Serial number is arranged to each participle respectively using the first pre-defined algorithm.
5. the method as described in claim 1, which is characterized in that described corresponding to the adjacency matrix using the second pre-defined algorithm
The step of obtaining different swindle types of being classified include:
The Euclidean distance of the participle in the adjacency matrix is compared with preset threshold using the second pre-defined algorithm, it will be described
The participle that Euclidean distance is less than preset threshold is classified as one kind to obtain different classes of swindle type.
6. a kind of new fraudulent gimmick identification device, which is characterized in that described device includes:
Word segmentation module, for being segmented to a plurality of data of receiving a crime report；
First computing module, for calculating separately the term vector of each participle using the first pre-defined algorithm；
Second computing module obtains adjacency matrix for successively calculating the Euclidean distance of term vector of every two participle；
Categorization module, for being classified to obtain different swindlenesses to the corresponding participle of the adjacency matrix using the second pre-defined algorithm
Deceive type.
7. device as claimed in claim 6, which is characterized in that described device further include:
Module is removed, for removing the invalid participle in word segmentation result, retains effectively participle.
8. device as claimed in claim 7, which is characterized in that the removal module is specifically used for: will be in the word segmentation result
Each participle be successively compared with prepending non-significant participle list, removal is present in prepending non-significant participle list
Invalid participle retains effectively participle.
9. device as claimed in claim 6, which is characterized in that described device further include:
Setup module, for serial number to be arranged to each participle respectively using the first pre-defined algorithm.
10. device as claimed in claim 6, which is characterized in that the categorization module is specifically used for: using the second pre-defined algorithm
The Euclidean distance of participle in the adjacency matrix is compared with preset threshold, the Euclidean distance is less than preset threshold
Participle be classified as one kind to obtain different classes of swindle type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811276062.XA CN109446528A (en) | 2018-10-30 | 2018-10-30 | The recognition methods of new fraudulent gimmick and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811276062.XA CN109446528A (en) | 2018-10-30 | 2018-10-30 | The recognition methods of new fraudulent gimmick and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109446528A true CN109446528A (en) | 2019-03-08 |
Family
ID=65549762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811276062.XA Pending CN109446528A (en) | 2018-10-30 | 2018-10-30 | The recognition methods of new fraudulent gimmick and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109446528A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111210827A (en) * | 2020-04-20 | 2020-05-29 | 成都派沃特科技股份有限公司 | Method and device for responding to alarm, electronic equipment and readable storage medium |
| CN111274818A (en) * | 2020-01-17 | 2020-06-12 | 腾讯科技（深圳）有限公司 | Word vector generation method and device |
| WO2021012913A1 (en) * | 2019-07-23 | 2021-01-28 | 平安科技（深圳）有限公司 | Data recognition method and system, electronic device and computer storage medium |
| CN112613888A (en) * | 2020-12-25 | 2021-04-06 | 厦门市美亚柏科信息股份有限公司 | Fraud suspicion identification method and device based on APP list analysis |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890698A (en) * | 2012-06-20 | 2013-01-23 | 杜小勇 | Method for automatically describing microblogging topic tag |
| CN104657466A (en) * | 2015-02-11 | 2015-05-27 | 厦门美柚信息科技有限公司 | Method and device for identifying user interest based on forum post features |
| CN105516499A (en) * | 2015-12-14 | 2016-04-20 | 北京奇虎科技有限公司 | Method and device for classifying short messages, communication terminal and server |
| CN105631049A (en) * | 2016-02-17 | 2016-06-01 | 北京奇虎科技有限公司 | Method and system for recognizing defrauding short messages |
| CN106227718A (en) * | 2016-07-18 | 2016-12-14 | 中国民航大学 | Land based on CNN sky call semantic consistency method of calibration |
| CN107103081A (en) * | 2017-04-26 | 2017-08-29 | 成都智库二八六信息技术有限公司 | A kind of method of the text knowledge's synthesis clustered based on integrated level |
| CN107357837A (en) * | 2017-06-22 | 2017-11-17 | 华南师范大学 | The electric business excavated based on order-preserving submatrix and Frequent episodes comments on sensibility classification method |
| CN108566627A (en) * | 2017-11-27 | 2018-09-21 | 浙江鹏信信息科技股份有限公司 | A kind of method and system identifying fraud text message using deep learning |
| CN108595418A (en) * | 2018-04-03 | 2018-09-28 | 上海透云物联网科技有限公司 | A kind of commodity classification method and system |
-
2018
- 2018-10-30 CN CN201811276062.XA patent/CN109446528A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890698A (en) * | 2012-06-20 | 2013-01-23 | 杜小勇 | Method for automatically describing microblogging topic tag |
| CN104657466A (en) * | 2015-02-11 | 2015-05-27 | 厦门美柚信息科技有限公司 | Method and device for identifying user interest based on forum post features |
| CN105516499A (en) * | 2015-12-14 | 2016-04-20 | 北京奇虎科技有限公司 | Method and device for classifying short messages, communication terminal and server |
| CN105631049A (en) * | 2016-02-17 | 2016-06-01 | 北京奇虎科技有限公司 | Method and system for recognizing defrauding short messages |
| CN106227718A (en) * | 2016-07-18 | 2016-12-14 | 中国民航大学 | Land based on CNN sky call semantic consistency method of calibration |
| CN107103081A (en) * | 2017-04-26 | 2017-08-29 | 成都智库二八六信息技术有限公司 | A kind of method of the text knowledge's synthesis clustered based on integrated level |
| CN107357837A (en) * | 2017-06-22 | 2017-11-17 | 华南师范大学 | The electric business excavated based on order-preserving submatrix and Frequent episodes comments on sensibility classification method |
| CN108566627A (en) * | 2017-11-27 | 2018-09-21 | 浙江鹏信信息科技股份有限公司 | A kind of method and system identifying fraud text message using deep learning |
| CN108595418A (en) * | 2018-04-03 | 2018-09-28 | 上海透云物联网科技有限公司 | A kind of commodity classification method and system |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021012913A1 (en) * | 2019-07-23 | 2021-01-28 | 平安科技（深圳）有限公司 | Data recognition method and system, electronic device and computer storage medium |
| CN111274818A (en) * | 2020-01-17 | 2020-06-12 | 腾讯科技（深圳）有限公司 | Word vector generation method and device |
| CN111274818B (en) * | 2020-01-17 | 2023-07-14 | 腾讯科技（深圳）有限公司 | Word vector generation method and device |
| CN111210827A (en) * | 2020-04-20 | 2020-05-29 | 成都派沃特科技股份有限公司 | Method and device for responding to alarm, electronic equipment and readable storage medium |
| CN111210827B (en) * | 2020-04-20 | 2020-08-21 | 成都派沃特科技股份有限公司 | Method and device for responding to alarm, electronic equipment and readable storage medium |
| CN112613888A (en) * | 2020-12-25 | 2021-04-06 | 厦门市美亚柏科信息股份有限公司 | Fraud suspicion identification method and device based on APP list analysis |
| CN112613888B (en) * | 2020-12-25 | 2022-09-02 | 厦门市美亚柏科信息股份有限公司 | Fraud suspicion identification method and device based on APP list analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Video anomaly detection based on locality sensitive hashing filters | |
| CN107392222B (en) | Face clustering method and device and storage medium | |
| CN109446528A (en) | The recognition methods of new fraudulent gimmick and device | |
| US10891465B2 (en) | Methods and apparatuses for searching for target person, devices, and media | |
| Laishram et al. | Curie: A method for protecting SVM classifier from poisoning attack | |
| US8724904B2 (en) | Anomaly detection in images and videos | |
| Bhuyan et al. | An effective unsupervised network anomaly detection method | |
| CN101980242B (en) | Human face discrimination method and system and public safety system | |
| Varuna et al. | An integration of k-means clustering and naïve bayes classifier for Intrusion Detection | |
| CN109344617A (en) | A kind of Internet of Things assets security portrait method and system | |
| CN107169106A (en) | Video retrieval method, device, storage medium and processor | |
| CN106960153B (en) | Virus type identification method and device | |
| Bhattacharjee et al. | Context-aware graph-based analysis for detecting anomalous activities | |
| CN109145801A (en) | A kind of face identification method and face identification system | |
| CN112001170A (en) | Method and system for recognizing deformed sensitive words | |
| Zandian et al. | Feature extraction method based on social network analysis | |
| CN108681720A (en) | A kind of testimony of a witness veritification management system and method | |
| CN116933252A (en) | Security monitoring method, device, equipment and medium | |
| Zaheer et al. | Clustering aided weakly supervised training to detect anomalous events in surveillance videos | |
| Arshad et al. | Anomalous situations recognition in surveillance images using deep learning | |
| Altowairqi et al. | A Review of the Recent Progress on Crowd Anomaly Detection | |
| Zhang et al. | Face occlusion detection using cascaded convolutional neural network | |
| CN110443187A (en) | The recording method of characteristic information and device | |
| Shuoyan et al. | Abnormal behavior detection based on the motion-changed rules | |
| Gao | Anomaly detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190308 |
|
| RJ01 | Rejection of invention patent application after publication |