CN109509048A - The recognition methods of malice order, device, electronic equipment and storage medium - Google Patents
The recognition methods of malice order, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109509048A CN109509048A CN201710833495.XA CN201710833495A CN109509048A CN 109509048 A CN109509048 A CN 109509048A CN 201710833495 A CN201710833495 A CN 201710833495A CN 109509048 A CN109509048 A CN 109509048A
- Authority
- CN
- China
- Prior art keywords
- order
- address information
- malice
- identification model
- current
- 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
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0609—Buyer or seller confidence or verification
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
- G06Q30/0637—Approvals
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Present disclose provides a kind of malice order recognition methods, malice order identification device, electronic equipment and computer readable storage mediums, it is related to technical field of electronic commerce, this method comprises: obtaining the current order address information and multiple History Order address informations when receiving current order request；Calculate the common characters string of the current order address information Yu multiple History Order address informations；It constructs an order identification model and the current order is predicted and identified according to the order identification model and the common characters string.The efficiency and accuracy rate of malice order identification can be improved in this method.
Description
Technical field
This disclosure relates to technical field of electronic commerce, in particular to a kind of malice order recognition methods, malice order
Identification device, electronic equipment and computer readable storage medium.
Background technique
With the fast development of Internet technology, there is a large amount of electric business platform.In each electric business platform, often go out
The now single malice order of a large amount of brushes.
In the prior art, the identification of malice order is carried out general with shipping address information, there are mainly two types of modes: the first
Mode is related to doing address level processing, specifically, do word segmentation processing to address first, i.e., according to province, city, county, area, town,
The normal addresses grade such as street, road carries out cutting, is then based on address rank and other order dimensions is combined to carry out data mart modeling,
Machining feature, and then the identification of malice order is carried out based on disaggregated model on the basis of machined feature；The second way is related to
To malice address addition blacklist processing.
It is above-mentioned to be carried out in malice order knowledge method for distinguishing based on address standard level, since there may be difficult in the address
The content distinguished according to the normal addresses grade such as province, city, county, area, town, these cannot be according in the grade distinction of normal address
Model identification can be interfered by holding, so that leakage be caused to identify；The method that malice address is added to blacklist library is that occurring
Blacklist library just is added in the address on the basis of malice address, there is certain hysteresis quality in time, and maintenance cost compared with
Greatly, it is unfavorable for the Dynamic Recognition of malice address.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure be designed to provide a kind of malice order recognition methods, malice order identification device, electronic equipment with
And computer readable storage medium, and then caused by overcoming the limitation and defect due to the relevant technologies at least to a certain extent
One or more problem.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to one aspect of the disclosure, a kind of malice order recognition methods is provided, comprising:
When receiving current order request, the current order address information and multiple History Order addresses letter are obtained
Breath；
Calculate the common characters string of the current order address information Yu multiple History Order address informations；
It constructs an order identification model and is currently ordered according to the order identification model and the common characters string to described
It is singly predicted and is identified.
In a kind of exemplary embodiment of the disclosure, calculates the current order address information and ordered with multiple history
The common characters string of single address message includes:
The current order address information is calculated using dynamic programming algorithm to order with multiple history in preset duration
The common characters string of single address message.
In a kind of exemplary embodiment of the disclosure, the current order address information is calculated using dynamic programming algorithm
The common characters string with multiple History Order address informations in preset duration includes:
Obtain all History Order address informations in preset duration similar with the current order address information；
The current order address information and each History Order address information are calculated using maximum common sequence algorithm
Longest common characters string.
In a kind of exemplary embodiment of the disclosure, prediction is carried out to the current order and identification includes:
Off-line training is carried out to the order identification model using random forests algorithm；
On-line prediction and identification are carried out to the current order according to the order identification model after off-line training.
In a kind of exemplary embodiment of the disclosure, using random forests algorithm to the order identification model carry out from
Line training includes:
Training data corresponding with the order identification model and test data are obtained, and generates and identifies mould with the order
The corresponding characteristic of type feature；
The training data based on each History Order carries out the characteristic of the order identification model offline
Training；
The test data based on each History Order hands over the order identification model after off-line training
Fork verifying, and export the order identification model.
In a kind of exemplary embodiment of the disclosure, the order identification model is carried out using random forests algorithm
Before off-line training, the method also includes:
The wide table of data characteristics is generated according to the dimensional information of the common characters string and the History Order.
In a kind of exemplary embodiment of the disclosure, obtain similar with the current order address information all described
History Order address information includes:
It inquires in the buffer and obtains all institutes identical with the presupposed information in the current order request address information
State History Order address information.
According to one aspect of the disclosure, a kind of malice order identification device is provided, comprising:
Address information obtains module, for obtaining the current order address information when receiving current order request
And multiple History Order address informations；
Common characters string computing module, for calculating the current order address information and multiple History Order addresses
The common characters string of information；
Order identification module, for constructing an order identification model and according to the order identification model and the public word
Symbol string is predicted and is identified to the current order.
According to one aspect of the disclosure, a kind of computer readable storage medium is provided, computer program is stored thereon with,
The computer program realizes malice order recognition methods described in above-mentioned any one when being executed by processor.
According to one aspect of the disclosure, a kind of electronic equipment is provided, comprising:
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to execute evil described in above-mentioned any one via the executable instruction is executed
Meaning order recognition methods.
The malice order recognition methods of middle offer in the present exemplary embodiment, malice order identification device, electronic equipment and
In computer readable storage medium, by obtaining the common characters string of current order and History Order address information, it can be found that
Relevance between current order and History Order address information avoids in address information in the prior art spcial character to evil
The interference that order of anticipating identifies, so as to efficiently and accurately identify malice order；It on the other hand, can be in real time to current order
It is predicted and is identified, avoid the hysteresis quality for identifying malice order by way of blacklist, improve the identification of malice order
Efficiency, and then ensure that the authenticity and safety of electronic order.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is a kind of schematic diagram of application scenarios of the disclosure；
Fig. 2 schematically shows a kind of structural representation of malice order identifying system platform in disclosure exemplary embodiment
Figure；
Fig. 3 schematically shows a kind of schematic diagram of malice order recognition methods in disclosure exemplary embodiment；
Fig. 4 schematically shows the idiographic flow schematic diagram that malice order identifies in disclosure exemplary embodiment；
Fig. 5 schematically shows a kind of block diagram of malice order identification device in disclosure exemplary embodiment；
Fig. 6 schematically shows a kind of electronic equipment in disclosure exemplary embodiment；
Fig. 7 schematically shows a kind of program product in disclosure exemplary embodiment.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.In the following description, it provides perhaps
More details fully understand embodiment of the present disclosure to provide.It will be appreciated, however, by one skilled in the art that can
It is omitted with technical solution of the disclosure one or more in the specific detail, or others side can be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution to avoid a presumptuous guest usurps the role of the host and
So that all aspects of this disclosure thicken.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
The application scenarios in this example embodiment are explained first.Refering to what is shown in Fig. 1, the malice in this example is ordered
Single recognition methods can be applied between terminal 110 and server 120, which can be by cable network or wireless
Communication connection is established between network and the server 120.Wherein, user can by the browser that is run in the terminal 110 or
The form of person's client logs in e-commerce website, the operation such as places an order to carry out commodity.
Next, the malice order identifying system platform provided in this example is briefly described.Refering to what is shown in Fig. 2,
The malice order identifying system may include off-line model training module, cache module, similar address determination module and online
Order identification module；Wherein:
Cache module can be used for storing all History Order information in preset duration；
Off-line model training module can carry out off-line training to the order identification model of building, generate satisfactory
Order identification model；
Similar address determination module can accurately determine the institute in preset duration similar with the address information of current order
There is the address information of History Order；
Online order identification module can carry out on-line testing to current order based on the order identification module after training,
To prevent malice order in time.
It can be realized and be connected by hardware system between above-mentioned each module, be based on the above order identifying system platform, originally show
Embodiments, provides a kind of malice order recognition methods for example.Refering to what is shown in Fig. 3, the malice order recognition methods may include
Following steps:
Step S310. obtains the current order address information and multiple history when receiving current order request
Order Address information；
Step S320. calculates the common characters of the current order address information Yu multiple History Order address informations
String；
Step S330. constructs an order identification model and according to the order identification model and the common characters string to institute
Current order is stated to be predicted and identified.
The malice order recognition methods provided in the present exemplary embodiment, on the one hand, can be with by longest common characters string
It was found that the relevance between current order and History Order address information, avoids non-type address information pair in the prior art
The interference of malice order identification, so as to effectively identify order；On the other hand, can in real time to current order carry out prediction and
Identification, avoids the hysteresis quality for identifying malice order by way of blacklist, improves operating efficiency, and then ensure that electronics
The authenticity and safety of order.
Next, by detailed explanation is carried out to each step in this example embodiment in the recognition methods of malice order
And explanation.
In step s310, when receiving current order request, the current order address information and multiple is obtained
History Order address information.
In the present exemplary embodiment, user can place an order at the terminal, and the order is sent to server, clothes
Business device is when receiving the order request of terminal transmission, the better address information and multiple history of the available current order
The better address information of order.The address information of the History Order can be obtained from cluster, such as available one
The History Order address information of the corresponding commodity of the order in season or half a year or 1 year, also available certain promotees
The address information of History Order in pin activity, there is no special restriction on this for this example.
The address information of the current order and History Order mainly includes alphabetic character, numerical character and alphabetic character
At least one of, but some spcial characters are also possible that in the address information, such as symbol class character, such as including mark
Point, space etc..For example, the details of Order Address can be " XX is saved, the city XX, the area the XX street XX X ".
In step 320, it calculates between the current order address information and multiple History Order address informations
Common characters string.
In the present exemplary embodiment, before being identified to current order address information, first by above-mentioned spcial character
It is deleted, in order to avoid influencing the subsequent identification to the Order Address information, improves the accuracy of identification.The common characters string
It can be used to indicate that the relevance of the better address information of the current order and the better address information of multiple History Orders.Two
Common characters string between a character string can have multiple, such as given two character strings are respectively " abab ", " baba ", and two
Common characters string between character string may include " a ", " b ", " ab ", " ba ", " aba ", " bab ".
Specifically, in this example embodiment, with calculating the current order address information and multiple History Orders
The common characters string of location information may include:
The current order address information is calculated using dynamic programming algorithm to order with multiple history in preset duration
The common characters string of single address message.
In the present exemplary embodiment, in order to more accurately identify the devious conduct such as malice order, it may only obtain default
The order that the address information of History Order in duration, the i.e. History Order are preset duration before receiving order request.It is described pre-
If duration can be N hours, N can be configured according to actual needs, such as 12 hours or 30 hours etc..
In this example, common characters string can be obtained using dynamic programming algorithm.Its specific calculating process are as follows: will be to be solved
PROBLEM DECOMPOSITION first solves subproblem at several subproblems, then obtains the solution of former problem from the solution of these subproblems, usually may be used
The solution of all subproblems solved is recorded so that a two-dimensional array can be used.Specific solution procedure can pass through program example
As the function in C++, java is realized.
Further, in this example embodiment, using dynamic programming algorithm calculate the current order address information with
The common characters string of multiple History Order address informations in preset duration may include:
Obtain all History Order address informations in preset duration similar with the current order address information；
The current order address information and each History Order address information are calculated using maximum common sequence algorithm
Longest common characters string.
In this example, all History Orders in N number of hour similar with current order address information can be obtained first
Address information.Specifically, obtaining all History Order address informations similar with the current order address information
May include:
It inquires in the buffer and obtains all institutes identical with the presupposed information in the current order request address information
State History Order address information.
In this example, History Order address information can be stored in redis caching or distributed caching, as long as this is slow
Deposit the requirement that can satisfy online processing duration with very high handling capacity and access efficiency.Presupposed information can be with
Including the address informations such as province, city, area and commodity SKU.It for example, herein can be by buying the identical of same commodity SKU
Similar historical order is screened in province, city, area, similar historical order can also be screened by identical province, city, county, town, specifically
The method for selecting similar address information can be configured according to different address naming methods.Filter out all symbols in the time
The History Order address information of conjunction condition can more accurately carry out address similitude judgement, without will cause leakage identification.Example
Such as, current order address information " Beijing, Haidian District, No. 5 buildings Guang Yun in W. 3rd Ring North Road Building A Room 906 " is ordered in screening history
Dan Shi selects next to select address in these History Orders with the History Order of commodity SKU with current order purchase first
It include the History Order of " Beijing, Haidian District " in information.
Longest common characters string may include multiple, but it must be continuous for requiring character string, such as give two words
Symbol string is respectively " abab ", " baba ", then the longest common characters string between the two character strings can " aba ", " bab " it is specific
For, the current order address can be calculated by longest common sequence algorithm (Longest Common Substring) and believed
The longest common characters string of breath and each History Order address information, the longest common characters string can describe two characters
" similarity " between string, therefore can more accurately identify similar address information.For example, current order address information " Beijing
City, Haidian District, No. 5 buildings Guang Yun in W. 3rd Ring North Road Building A Room 906 ", the address information of a certain History Order are " Beijing Haidian
Area, No. 5 buildings Guang Yun, W. 3rd Ring North Road Building A ", ignores the influence of spcial character, and the longest common characters string of the two is " Beijing
No. 5 buildings Guang Yun in Haidian District W. 3rd Ring North Road Building A ".
Specifically, it is assumed that there are two character string S and U, C [i-1, j-1]=LCS (S [1 ... i-1], U [1 ... j-1]) is
The longest common characters string of two character string S [1 ... i-1] and U [1 ... j-1], recurrence formula are shown below:
Two-dimensional array is finally traversed, the longest common characters string that the maximum character string of length is two character strings is found out.
Specifically process can be realized by function or program.
In step S330, an order identification model is constructed and according to the order identification model and the common characters string
The current order is predicted and identified.
In the present exemplary embodiment, an order can be constructed according to the address information of current order and History Order first
Then identification model carries out off-line training to the order identification model, and then according to trained order identification model and above-mentioned
The longest common characters string of the address information obtained in step predicts current order judge whether current order is potential
Whether malice order is malice order.When the address information of current order meets order identification model, then can predict
The order is potential malice order.Meet order identification model it is to be understood that in preset time current order address information with
The number that the identical longest common characters string of History Order address information occurs is more than preset times, such as 10 times.
Specifically, carrying out prediction in this example embodiment to the current order and identification may include:
Off-line training is carried out to the order identification model using random forests algorithm；
On-line prediction and identification are carried out to the current order according to the order identification model after off-line training.
In the present exemplary embodiment, it can be carried out first using order identification model of the random forests algorithm to building offline
Training.Such as it may include setting target variable, selected characteristic data and can be reasonably arranged according to forest algorithm at any time
Parameter.Random forests algorithm can be provided by the machine algorithm packet of Spark frame, can pass through bootstrap (bootstrap) weight
Sampling technique is concentrated with from original training sample and repeats to randomly select n sample and generate new training sample with putting back to；From all
K feature is randomly choosed in feature, decision tree is established using these features to the sample selected, and then generates m by above step
Decision tree forms random forest.It, to a certain extent can be to avoid due to each tree all selected section sample and Partial Feature
Over-fitting；And each tree randomly chooses sample and randomly chooses feature, resists well so that the Random Forest model of fitting has
It makes an uproar ability.
Order identification model obtains an optimal order identification model after carrying out off-line training.It can incite somebody to action at this time
Longest common characters string between the address information of the current order obtained in above-mentioned steps and the address information of History Order, in conjunction with
On-line prediction is carried out to current order by the order identification model after off-line training, is ordered in current order address information with history
When the longest common characters string of multiple address informations in list is identical, it can be determined that current order is potential malice order.
Further, in this example embodiment, the order identification model is carried out using random forests algorithm offline
Training may include:
Training data corresponding with the order identification model and test data are obtained, and the determining and order identifies mould
The corresponding characteristic of type；
The training data based on each History Order carries out the characteristic of the order identification model offline
Training；
The test data based on each History Order hands over the order identification model after off-line training
Fork verifying, and export the order identification model.
In the present exemplary embodiment, when carrying out off-line training to the order identification model using random forests algorithm,
Training pattern can be read first needs training data to be used and test data, and wherein training data is mainly used for data mining
The data of model construction, test data is only used in model testing, for the accuracy rate of assessment models, training data and test
Data can randomly select, and be possibly stored in Spark memory.
It next can and order identification model feature pair determining according to each feature and target feature of high importance
The characteristic answered.For example, descending arrangement can be carried out according to importance to the characteristic variable that random forest is arranged, by importance
It for example can be 0.7 History Order greater than preset value to be saved, by more important several characteristic values as final mask
Training, further improves the precision of model.Characteristic for example can be the mansion address information Zhong XX or the street XX
Etc..
In this example, it is assumed that there are 1000 address information recordings, it can be using 70% sample data as training data to mould
Type is trained, using remaining 30% sample data as test data.Model after training can be verified to obtain
To more complete model, then trained model verified based on test data, it is highest to choose verifying rate
Once as final order identification model, then model output is saved in Spark.
K parts identical, the choosing that data can be divided by cross validation (cross-validation) by quantity in this example
A copy of it is selected as the test data for carrying out off-line training to order identification model, remaining k-1 parts is training data, is repeated
K times, each part of data is just made all to be used for a test data and for k-1 training data.It can be in this example
Make data as much as possible as training data by cross validation, and then keeps trained order identification model more accurate.
Further, in this example embodiment, using random forests algorithm to the order identification model carry out from
Before line training, the method can also include:
The wide table of feature is generated according to the dimensional information of the common characters string and the History Order.
In the present exemplary embodiment, the current order address information and the History Order address information are being determined most
After long common characters string, one can also be generated according to the dimensional information of determining common characters string and the History Order
The wide table of feature.The dimensional information of History Order may include such as unit time user order volume, Successful Transaction order volume, unit
Time turnover, sales volume and goods return and replacement rate, the information such as user rating.The wide table of feature can be will be relevant to order identification
The database table of index, dimension, Attribute Association together may include the common characters string extracted in the wide table of this feature,
The efficiency iterated to calculate during model training can be improved by the wide table of this feature.
It should be noted that the malice order recognition methods provided in this example, can be based on current order address information
The longest common characters string of commodity SKU History Order address information identical as in preset duration, accurate and quick identification are latent
In malice order, to improve the quality of order.
This example embodiment additionally provides a kind of malice order identification device.Refering to what is shown in Fig. 5, the malice order identifies
Device device 500 may include that address information obtains module 501, common characters string computing module 502 and order identification module
503.Wherein:
Address information obtains module 501, can be used for when receiving current order request, with obtaining the current order
Location information and multiple History Order address informations；
Common characters string computing module 502 can be used for calculating the current order address information and multiple history
The common characters string of Order Address information；
Order identification module 503 can be used for constructing an order identification model and according to the order identification model and institute
It states common characters string and the current order is predicted and identified.
The detail of each module is in corresponding malice order recognition methods in above-mentioned malice order identification device
It is described in detail, therefore details are not described herein again.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/
Or a step is decomposed into execution of multiple steps etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, mobile terminal or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 600 of this embodiment according to the present invention is described referring to Fig. 6.The electronics that Fig. 6 is shown
Equipment 600 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in fig. 6, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 610, at least one above-mentioned storage unit 620, the different system components of connection
The bus 630 of (including storage unit 620 and processing unit 610).
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 610
Row, so that various according to the present invention described in the execution of the processing unit 610 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 610 can execute step as shown in Figure 3: step S310.
When receiving current order request, the current order address information and multiple History Order address informations are obtained；Step
S320. the common characters string of the current order address information Yu multiple History Order address informations is calculated；Step S330.
It constructs an order identification model and the current order is carried out according to the order identification model and the common characters string pre-
It surveys and identifies.
Storage unit 620 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
Storage unit 620 can also include program/utility with one group of (at least one) program module 6205
6204, such program module 6205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 630 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 600 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 600 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 660 is communicated by bus 630 with other modules of electronic equipment 600.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 600, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
Refering to what is shown in Fig. 7, describing the program product for realizing the above method of embodiment according to the present invention
800, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
Claims (10)
1. a kind of malice order recognition methods characterized by comprising
When receiving current order request, the current order address information and multiple History Order address informations are obtained；
Calculate the common characters string of the current order address information Yu multiple History Order address informations；
Construct an order identification model and according to the order identification model and the common characters string to the current order into
Row prediction and identification.
2. malice order recognition methods according to claim 1, which is characterized in that calculate the current order address information
Common characters string with multiple History Order address informations includes:
With calculating multiple History Orders in the current order address information and preset duration using dynamic programming algorithm
The common characters string of location information.
3. malice order recognition methods according to claim 2, which is characterized in that using described in dynamic programming algorithm calculating
Current order address information and the common characters string of multiple History Order address informations in preset duration include:
Obtain all History Order address informations in preset duration similar with the current order address information；
The current order address information and each History Order address information are calculated most using maximum common sequence algorithm
Long common characters string.
4. malice order recognition methods according to claim 1, which is characterized in that the current order carry out prediction and
Identification includes:
Off-line training is carried out to the order identification model using random forests algorithm；
On-line prediction and identification are carried out to the current order according to the order identification model after off-line training.
5. malice order recognition methods according to claim 4, which is characterized in that ordered using random forests algorithm to described
Single identification model carries out off-line training
Training data corresponding with the order identification model and test data are obtained, and is generated special with the order identification model
Levy corresponding characteristic；
The training data based on each History Order carries out off-line training to the characteristic of the order identification model；
The test data based on each History Order intersect to the order identification model after off-line training and be tested
Card, and export the order identification model.
6. malice order recognition methods according to claim 4, which is characterized in that in use random forests algorithm to described
Before order identification model carries out off-line training, the method also includes:
The wide table of data characteristics is generated according to the dimensional information of the common characters string and the History Order.
7. malice order recognition methods according to claim 3, which is characterized in that obtain and believe with the current order address
All History Order address informations include: as manner of breathing
It inquires in the buffer and obtains all described go through identical with the presupposed information in the current order request address information
History Order Address information.
8. a kind of malice order identification device characterized by comprising
Address information obtain module, for receive current order request when, obtain the current order address information and
Multiple History Order address informations；
Common characters string computing module, for calculating the current order address information and multiple History Order address informations
Common characters string；
Order identification module, for constructing an order identification model and according to the order identification model and the common characters string
The current order is predicted and identified.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program quilt
Claim 1-7 described in any item malice order recognition methods are realized when processor executes.
10. a kind of electronic equipment characterized by comprising
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to require 1-7 described in any item via executing the executable instruction and carry out perform claim
Malice order recognition methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710833495.XA CN109509048B (en) | 2017-09-15 | 2017-09-15 | Malicious order identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710833495.XA CN109509048B (en) | 2017-09-15 | 2017-09-15 | Malicious order identification method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109509048A true CN109509048A (en) | 2019-03-22 |
| CN109509048B CN109509048B (en) | 2020-09-29 |
Family
ID=65744894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710833495.XA Active CN109509048B (en) | 2017-09-15 | 2017-09-15 | Malicious order identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109509048B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110784435A (en) * | 2019-04-15 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Abnormal service identification method and device, electronic equipment and storage medium |
| CN111126629A (en) * | 2019-12-25 | 2020-05-08 | 上海携程国际旅行社有限公司 | Model generation method, system, device and medium for identifying brushing behavior |
| CN111461815A (en) * | 2020-03-17 | 2020-07-28 | 上海携程国际旅行社有限公司 | Order recognition model generation method, recognition method, system, device and medium |
| WO2020232902A1 (en) * | 2019-05-23 | 2020-11-26 | 平安科技（深圳）有限公司 | Abnormal object identification method and apparatus, computing device, and storage medium |
| CN112116284A (en) * | 2020-03-27 | 2020-12-22 | 上海寻梦信息技术有限公司 | False waybill identification method, false waybill identification system, electronic equipment and storage medium |
| CN112529509A (en) * | 2020-12-29 | 2021-03-19 | 安徽运通达物流科技有限公司 | Method for identifying malicious freight notes in transportation platform |
| CN115641177A (en) * | 2022-10-20 | 2023-01-24 | 北京力尊信通科技股份有限公司 | Prevent second and kill prejudgement system based on machine learning |
| CN117035945A (en) * | 2023-09-08 | 2023-11-10 | 广东海洋大学 | Electronic information management method based on deep learning and related equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520851A (en) * | 2008-02-29 | 2009-09-02 | 富士通株式会社 | Character information identification device and method |
| US8364694B2 (en) * | 2007-10-26 | 2013-01-29 | Apple Inc. | Search assistant for digital media assets |
| CN103678708A (en) * | 2013-12-30 | 2014-03-26 | 小米科技有限责任公司 | Method and device for recognizing preset addresses |
| CN104219230A (en) * | 2014-08-21 | 2014-12-17 | 腾讯科技（深圳）有限公司 | Method and device for identifying malicious websites |
| CN104809589A (en) * | 2015-05-08 | 2015-07-29 | 北京嘀嘀无限科技发展有限公司 | Order processing method and device |
| CN105468742A (en) * | 2015-11-25 | 2016-04-06 | 小米科技有限责任公司 | Malicious order recognition method and device |
| JP2016526212A (en) * | 2013-05-24 | 2016-09-01 | ベイジン ジンドン シャンケ インフォメーション テクノロジー カンパニー リミテッド | Method and apparatus for determining information processing goals |
| CN106251202A (en) * | 2016-07-29 | 2016-12-21 | 北京小米移动软件有限公司 | Maliciously order recognition methods and device |
| CN106779899A (en) * | 2016-08-29 | 2017-05-31 | 北京小米移动软件有限公司 | The recognition methods of malice order and device |
| CN107133645A (en) * | 2017-05-03 | 2017-09-05 | 百度在线网络技术（北京）有限公司 | Passenger is estimated to cancel an order method, equipment and the storage medium of behavior |
-
2017
- 2017-09-15 CN CN201710833495.XA patent/CN109509048B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8364694B2 (en) * | 2007-10-26 | 2013-01-29 | Apple Inc. | Search assistant for digital media assets |
| CN101520851A (en) * | 2008-02-29 | 2009-09-02 | 富士通株式会社 | Character information identification device and method |
| JP2016526212A (en) * | 2013-05-24 | 2016-09-01 | ベイジン ジンドン シャンケ インフォメーション テクノロジー カンパニー リミテッド | Method and apparatus for determining information processing goals |
| CN103678708A (en) * | 2013-12-30 | 2014-03-26 | 小米科技有限责任公司 | Method and device for recognizing preset addresses |
| CN104219230A (en) * | 2014-08-21 | 2014-12-17 | 腾讯科技（深圳）有限公司 | Method and device for identifying malicious websites |
| CN104809589A (en) * | 2015-05-08 | 2015-07-29 | 北京嘀嘀无限科技发展有限公司 | Order processing method and device |
| CN105468742A (en) * | 2015-11-25 | 2016-04-06 | 小米科技有限责任公司 | Malicious order recognition method and device |
| CN106251202A (en) * | 2016-07-29 | 2016-12-21 | 北京小米移动软件有限公司 | Maliciously order recognition methods and device |
| CN106779899A (en) * | 2016-08-29 | 2017-05-31 | 北京小米移动软件有限公司 | The recognition methods of malice order and device |
| CN107133645A (en) * | 2017-05-03 | 2017-09-05 | 百度在线网络技术（北京）有限公司 | Passenger is estimated to cancel an order method, equipment and the storage medium of behavior |
Non-Patent Citations (2)
| Title |
|---|
| 张华忠: "基于贝叶斯集成分类器的自动图像标注", 《中国优秀硕士学位论文全文数据库·信息科技辑》 * |
| 牛永洁 等: "多种字符串相似度算法的比较研究", 《计算机与数字工程》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110784435A (en) * | 2019-04-15 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Abnormal service identification method and device, electronic equipment and storage medium |
| WO2020232902A1 (en) * | 2019-05-23 | 2020-11-26 | 平安科技（深圳）有限公司 | Abnormal object identification method and apparatus, computing device, and storage medium |
| CN111126629A (en) * | 2019-12-25 | 2020-05-08 | 上海携程国际旅行社有限公司 | Model generation method, system, device and medium for identifying brushing behavior |
| CN111126629B (en) * | 2019-12-25 | 2023-09-19 | 上海携程国际旅行社有限公司 | Model generation method, brush list identification method, system, equipment and medium |
| CN111461815A (en) * | 2020-03-17 | 2020-07-28 | 上海携程国际旅行社有限公司 | Order recognition model generation method, recognition method, system, device and medium |
| CN111461815B (en) * | 2020-03-17 | 2023-04-28 | 上海携程国际旅行社有限公司 | Order recognition model generation method, recognition method, system, equipment and medium |
| CN112116284A (en) * | 2020-03-27 | 2020-12-22 | 上海寻梦信息技术有限公司 | False waybill identification method, false waybill identification system, electronic equipment and storage medium |
| CN112116284B (en) * | 2020-03-27 | 2021-04-13 | 上海寻梦信息技术有限公司 | False waybill identification method, false waybill identification system, electronic equipment and storage medium |
| CN112529509A (en) * | 2020-12-29 | 2021-03-19 | 安徽运通达物流科技有限公司 | Method for identifying malicious freight notes in transportation platform |
| CN115641177A (en) * | 2022-10-20 | 2023-01-24 | 北京力尊信通科技股份有限公司 | Prevent second and kill prejudgement system based on machine learning |
| CN117035945A (en) * | 2023-09-08 | 2023-11-10 | 广东海洋大学 | Electronic information management method based on deep learning and related equipment |
| CN117035945B (en) * | 2023-09-08 | 2024-05-14 | 广东海洋大学 | Electronic information management method based on deep learning and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109509048B (en) | 2020-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109509048A (en) | The recognition methods of malice order, device, electronic equipment and storage medium | |
| US11442804B2 (en) | Anomaly detection in data object text using natural language processing (NLP) | |
| US20190354881A1 (en) | Computer environment infrastructure compliance audit result prediction | |
| CN105719001A (en) | Large-Scale Classification In Neural Networks Using Hashing | |
| JP2023514465A (en) | machine learning platform | |
| CN109766479A (en) | Data processing method, device, electronic equipment and storage medium | |
| US11983105B2 (en) | Systems and methods for generating and executing a test case plan for a software product | |
| US20200234218A1 (en) | Systems and methods for entity performance and risk scoring | |
| US20160350690A1 (en) | Just in time learning driven by point of sale or other data and metrics | |
| CN112017059A (en) | Hierarchical optimization risk control method and device and electronic equipment | |
| US11972382B2 (en) | Root cause identification and analysis | |
| US20210042291A1 (en) | Annotation Assessment and Ground Truth Construction | |
| CN110162518A (en) | Data grouping method, apparatus, electronic equipment and storage medium | |
| US11714855B2 (en) | Virtual dialog system performance assessment and enrichment | |
| CN110348581A (en) | User characteristics optimization method, device, medium and electronic equipment in user characteristics group | |
| WO2020150597A1 (en) | Systems and methods for entity performance and risk scoring | |
| CN108683749A (en) | A kind of judgment method, equipment and the medium of random email address | |
| KR102467194B1 (en) | System and method for product inspection using artificial intelligence and computer program for the same | |
| CN110070383A (en) | Abnormal user recognition methods and device based on big data analysis | |
| CN115408263A (en) | Utilizing and training artificial intelligence models for control identification | |
| CN115809891A (en) | Multi-product combined demand prediction method and device based on substitution and correlation effects | |
| CN115829159A (en) | Social media fan newly-increased prediction method, device, equipment and storage medium | |
| CN113935802A (en) | Information processing method, device, equipment and storage medium | |
| CN109800933A (en) | Methods of risk assessment and device, storage medium, electronic equipment | |
| CN115204931A (en) | User service policy determination method and device and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |