CN107492021A - Order source analysis method and device - Google Patents
Order source analysis method and device Download PDFInfo
- Publication number
- CN107492021A CN107492021A CN201710752505.7A CN201710752505A CN107492021A CN 107492021 A CN107492021 A CN 107492021A CN 201710752505 A CN201710752505 A CN 201710752505A CN 107492021 A CN107492021 A CN 107492021A
- Authority
- CN
- China
- Prior art keywords
- order
- information
- sequence information
- similarity
- orders
- 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
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]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- 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]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
- G06Q30/0629—Directed, with specific intent or strategy for generating comparisons
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
The present invention provides a kind of order source analysis method and device, belongs to field of computer technology.This method includes：For any order in order set, using any order as the first order, the similarity between the sequence information of the first order and the sequence information of each order in other orders is determined, other orders are order of the order set in addition to the first order；When the similarity between the sequence information and the sequence information of the first order that order in other orders be present is more than predetermined threshold value, the order for the condition that meets and the first order are classified as to the order of same source.For any order in order set, when the present invention is more than predetermined threshold value by the similarity existed in other orders between the sequence information of order and the sequence information of the first order, the order for the condition that meets and the first order are classified as to the order of same source.Due to the order of same source can be filtered out, so as to can detect that malice brushes single behavior.
Description
Technical field
The present invention relates to field of computer technology, more particularly, to a kind of order source analysis method and device.
Background technology
The people of shopping online at present is more and more, and electric business platform is in order to promote customer consumption, and in order to improve platform
Exposure, it will usually carry out corresponding preferential activity.In preferential activity, the very high commodity of preferential dynamics are typically had.For
These commodity, often may be useful for family malice brush it is single by way of rush to purchase and store goods, subsequently to be sold higher than the price of specially preferential price.
Again and for example, for the businessman moved into electric business platform, progress malice competition between businessman is often had.For example, A businessmans pass through note
Volume user account, by maliciously brush it is single in a manner of buy the commodity of B businessmans, directly returned goods after commodity are received, to reduce B businessmans'
Credit worthiness.For above-mentioned malice brush single act, it is badly in need of a kind of order source analysis method at present.
The content of the invention
In order to solve the above problems, the present invention provides one kind and overcomes above mentioned problem or solve the above problems at least in part
Order source analysis method and device.
According to the first aspect of the invention, there is provided a kind of order source analysis method, this method include：
For any order in order set, using any order as the first order, determine that the order of the first order is believed
Similarity in breath and other orders between the sequence information of each order, other orders are order set in addition to the first order
Order；
When the similarity between the sequence information and the sequence information of the first order that order in other orders be present is more than in advance
If during threshold value, the order for the condition that meets and the first order are classified as to the order of same source.
Method provided in an embodiment of the present invention, for any order in order set, ordered any order as first
It is single, determine the similarity between the sequence information of the first order and the sequence information of each order in other orders, other orders
For order of the order set in addition to the first order.When the sequence information that order in other orders be present and the order of the first order
When similarity between information is more than predetermined threshold value, the order for the condition that meets and the first order are classified as ordering for same source
It is single.Due to the order of same source according to the similarity between order, can be filtered out, so as to analyze coming for each order
Source, and then can detect that malice brushes single behavior.
With reference to the first possible implementation of first aspect, in second of possible implementation, first is determined
Before similarity in the sequence information of order and other orders between the sequence information of each order, in addition to：
The order received in preset time period is obtained, and is used as order set.
With reference to the first possible implementation of first aspect, in the third possible implementation, sequence information
Including at least any one in following three information, three information are user's registration information, consignee's address and placed an order below
Information.
With reference to the third possible implementation of first aspect, in the 4th kind of possible implementation, first is determined
Similarity in the sequence information of order and other orders between the sequence information of each order, including：
For any order in other orders, using any order in other orders as the second order, first is determined
The sequence information of order and information identical item number in the sequence information of the second order, believe item number as the order of the first order
Similarity between breath and the sequence information of the second order.
With reference to the third possible implementation of first aspect, in the 5th kind of possible implementation, first is determined
Similarity in the sequence information of order and other orders between the sequence information of each order, including：
For any order in other orders, using any order in other orders as the second order, first is determined
Similarity scoring in the sequence information of order and the sequence information of the second order between each single item information；
Based on the similarity scoring between each single item information, determine that the sequence information of the first order is believed with the order of the second order
Similarity between breath.
With reference to the 5th kind of possible implementation of first aspect, in the 6th kind of possible implementation, for order
Consignee's address in information, determine in the sequence information of the first order and the sequence information of the second order between each single item information
Similarity scoring, including：
Determine distance between the consignee's address of the first order and the consignee's address of the second order；
The similarity scoring between the consignee's address of the first order and the consignee's address of the second order is determined based on distance.
With reference to the 5th kind of possible implementation of first aspect, in the 7th kind of possible implementation, for order
User's registration information in information, determine in the sequence information of the first order and the sequence information of the second order each single item information it
Between similarity scoring, including：
Determine that hour of log-on is corresponding with the user's registration information of the second order corresponding to the user's registration information of the first order
Hour of log-on between time difference；
Determine the information similarity degree between the user's registration information of the first order and the user's registration information of the second order；
Based on time difference and information similarity degree, determine that user's registration information is corresponding with the second order corresponding to the first order
User's registration information between similarity scoring.
With reference to the 5th kind of possible implementation of first aspect, in the 8th kind of possible implementation, for order
Order placement information in information, order placement information comprise at least lower single time, determine the sequence information and the second order of the first order
Similarity scoring in sequence information between each single item information, including：
Determine the time difference between lower single time of the first order and lower single time of the second order；
Based on the time difference, the similarity scoring between the order placement information of the first order and the order placement information of the second order is determined.
With reference to the 5th kind of possible implementation of first aspect, in the 9th kind of possible implementation, bar will be met
The order of part and the first order are classified as after the order of same source, in addition to：
The consignee's address of the first order is obtained, using the consignee's address of the first order receiving as same source order
People address.
According to the second aspect of the invention, there is provided a kind of order source analysis device, including：
Determining module, for for any order in order set, using any order as the first order, determining first
Similarity in the sequence information of order and other orders between the sequence information of each order, other orders are that order set removes
Order outside first order；
Classifying module, for when between the sequence information and the sequence information of the first order that order in other orders be present
When similarity is more than predetermined threshold value, the order for the condition that meets and the first order are classified as same class order.
It should be appreciated that the general description and following detailed description of the above are exemplary and explanatory, can not
The limitation present invention.
Brief description of the drawings
Fig. 1 is a kind of schematic flow sheet of order source analysis method of the embodiment of the present invention；
Fig. 2 is a kind of schematic flow sheet of order source analysis method of the embodiment of the present invention；
Fig. 3 is a kind of structural representation of order source analysis device of the embodiment of the present invention；
Fig. 4 is a kind of block diagram of order source analysis equipment of the embodiment of the present invention.
Embodiment
With reference to the accompanying drawings and examples, the embodiment of the present invention is described in further detail.Implement below
Example is used to illustrate the present invention, but is not limited to the scope of the present invention.
The people of shopping online at present is more and more, and electric business platform is in order to promote customer consumption, and in order to improve platform
Exposure, it will usually carry out corresponding preferential activity.In preferential activity, the very high commodity of preferential dynamics are typically had.For
These commodity, often may be useful for family malice brush it is single by way of rush to purchase and store goods, subsequently to be sold higher than the price of specially preferential price.
Again and for example, for the businessman moved into electric business platform, progress malice competition between businessman is often had.For example, A businessmans pass through note
Volume user account, by maliciously brush it is single in a manner of buy the commodity of B businessmans, directly returned goods after commodity are received, to reduce B businessmans'
Credit worthiness.
In view of the above-mentioned problems, the embodiments of the invention provide a kind of order source analysis method.This method can be applied to take
Business device, i.e., the order source of order is sent by server analysis various terminals, be probably that malice brushes list so as to which which be filtered out
Behavior.With reference to figure 1, this method includes：101st, for any order in order set, using any order as the first order,
Determine the similarity between the sequence information of the first order and the sequence information of each order in other orders, other orders is order
Order of single set in addition to the first order；102nd, when the sequence information that order in other orders be present and the order of the first order
When similarity between information is more than predetermined threshold value, the order for the condition that meets and the first order are classified as ordering for same source
It is single.
Wherein, order collection is combined into a series of orders that server receives, and similarity is used to represent several orders to dislike
The possibility of meaning brush single act.Same source order refers to the order that a batch malice brush single act is generated, such as same
User a period of time malice brush it is single produced by into order.
Method provided in an embodiment of the present invention, for any order in order set, ordered any order as first
It is single, determine the similarity between the sequence information of the first order and the sequence information of each order in other orders, other orders
For order of the order set in addition to the first order.When the sequence information that order in other orders be present and the order of the first order
When similarity between information is more than predetermined threshold value, the order for the condition that meets and the first order are classified as ordering for same source
It is single.Due to the order of same source according to the similarity between order, can be filtered out, so as to analyze coming for each order
Source, and then can detect that malice brushes single behavior.
As a kind of alternative embodiment, determine that the sequence information of the first order is believed with the order of each order in other orders
Before similarity between breath, in addition to：
The order received in preset time period is obtained, and is used as order set.
As a kind of alternative embodiment, sequence information comprise at least following three information in any one, three below
Information is user's registration information, consignee's address and order placement information.
As a kind of alternative embodiment, determine that the sequence information of the first order is believed with the order of each order in other orders
Similarity between breath, including：
For any order in other orders, using any order in other orders as the second order, first is determined
The sequence information of order and information identical item number in the sequence information of the second order, believe item number as the order of the first order
Similarity between breath and the sequence information of the second order.
As a kind of alternative embodiment, determine that the sequence information of the first order is believed with the order of each order in other orders
Similarity between breath, including：
For any order in other orders, using any order in other orders as the second order, first is determined
Similarity scoring in the sequence information of order and the sequence information of the second order between each single item information；
Based on the similarity scoring between each single item information, determine that the sequence information of the first order is believed with the order of the second order
Similarity between breath.
As a kind of alternative embodiment, for the consignee's address in sequence information, the sequence information of the first order is determined
With the similarity scoring between each single item information in the sequence information of the second order, including：
Determine distance between the consignee's address of the first order and the consignee's address of the second order；
The similarity scoring between the consignee's address of the first order and the consignee's address of the second order is determined based on distance.
As a kind of alternative embodiment, for the user's registration information in sequence information, determine that the order of the first order is believed
Similarity scoring in the sequence information of breath and the second order between each single item information, including：
Determine that hour of log-on is corresponding with the user's registration information of the second order corresponding to the user's registration information of the first order
Hour of log-on between time difference；
Determine the information similarity degree between the user's registration information of the first order and the user's registration information of the second order；
Based on time difference and information similarity degree, determine that user's registration information is corresponding with the second order corresponding to the first order
User's registration information between similarity scoring.
As a kind of alternative embodiment, for the order placement information in sequence information, order placement information comprises at least lower single time,
The similarity scoring between each single item information in the sequence information of the first order and the sequence information of the second order is determined, including：
Determine the time difference between lower single time of the first order and lower single time of the second order；
Based on the time difference, the similarity scoring between the order placement information of the first order and the order placement information of the second order is determined.
As a kind of alternative embodiment, by the order for the condition that meets and the first order be classified as same source order it
Afterwards, in addition to：
The consignee's address of the first order is obtained, using the consignee's address of the first order receiving as same source order
People address.
Above-mentioned all optional technical schemes, any combination can be used to form the alternative embodiment of the present invention, herein no longer
Repeat one by one.
Content based on above-described embodiment, the embodiments of the invention provide a kind of order source analysis method.Referring to Fig. 2,
This method includes：201st, the order received in preset time period is obtained, and is used as order set；202nd, in order set
Any order, using any order as the first order, determine the sequence information of the first order and each order in other orders
Sequence information between similarity, other orders are order of the order set in addition to the first order；203rd, when other orders
When similarity between the middle sequence information that order be present and the sequence information of the first order is more than predetermined threshold value, condition will be met
Order and the first order be classified as the order of same source.
Wherein, 201 the order received in preset time period, is obtained, and is used as order set.
In this step, order set is mainly determined, so as to which subsequent step can analyze the source of order in order set.
Because the single act of malice brush generally has timeliness, so as to obtain the order received in preset time period, to determine order
Set.Specifically, the preferential activity of electric business platform would generally open time point, when this time point is follow-up of short duration
Between in section, for preferential commodity, server inherently receives many orders, so as to using the period as preset time
Section, using the order received in the period as order set.For example, if preferential activity starts for 9 points in the morning, at 9 points
To 9 points 5 minutes, server can receive for preferential commodity panic buying a large amount of orders, so as to be ordered what is received in this 5 minutes
Nonoculture is order set.
Wherein, 202, for any order in order set, using any order as the first order, the first order is determined
Sequence information and other orders in each order sequence information between similarity, other orders be order set remove first
Order outside order.
By above-mentioned steps after going to determine object to be analyzed, the order source in order set can be analyzed.Due to ordering
Single information can reflect the source of order to a certain extent, so as to this step can be determined based on sequence information it is similar between order
Degree.Wherein, sequence information can comprise at least any one in following three information, and three information are believed for user's registration below
Breath, consignee's address and order placement information, the embodiment of the present invention are not especially limited to this.
User's registration information is the user profile when user to place an order registers in electric business platform, under consignee's address is
The address for the reception commodity that order user is filled in, order placement information may include the correspondent party filled in lower single time of user, user
Formula etc., the embodiment of the present invention is not especially limited to this.
Based on the above, the embodiment of the present invention does not determine that the sequence information of the first order is ordered with each in other orders pair
The mode of similarity between single sequence information specifically limits, and includes but is not limited to：Ordered for any in other orders
It is single, using any order in other orders as the second order, determine the sequence information of the first order and the order of the second order
Information identical item number in information, using item number as the phase between the sequence information of the first order and the sequence information of the second order
Like degree.
For example, if the first order is identical with the user's registration information of the second order, the first order is received with the second order
People address is identical, and the first order is identical with the order placement information of the second order, then can determine that the sequence information and second of the first order
Information identical item number is 3 in the sequence information of order.If the first order is identical with the user's registration information of the second order, first
Order is different from the consignee's address of the second order, and the first order is identical with the order placement information of the second order, then can determine that first
The sequence information of order is 2 with information identical item number in the sequence information of the second order.
Brushing single user in view of malice may not use identical information to implement malice brush single act, such as use
Identical contact method, consignee's name, address etc..And partial information would generally be changed, to prevent from being detected malice
Brush single act, such as change consignee's name, placed an order according to several addresses of an address near its circumference.For above-mentioned row
The embodiments of the invention provide the validation testing of another similarity, to specifically include：Ordered for any in other orders
It is single, using any order in other orders as the second order, determine the sequence information of the first order and the order of the second order
Similarity scoring in information between each single item information；Based on the similarity scoring between each single item information, ordering for the first order is determined
Similarity between single information and the sequence information of the second order.
Wherein, similarity scoring is used to represent between order in sequence information the degree of approximation of each single item information or corresponding disliked
The possibility of meaning brush single act.
As shown in the above, sequence information may include in user's registration information, consignee's address and order placement information extremely
One item missing information.Different items of information are now directed to, the determination mode of similarity scoring is illustrated.For receiving in sequence information
People address, the embodiment of the present invention do not determine each single item information in the sequence information of the first order and the sequence information of the second order pair
Between the mode of similarity scoring specifically limit, include but is not limited to：The consignee's address and second for determining the first order are ordered
Distance between single consignee's address；The consignee's address and the consignee's address of the second order of the first order are determined based on distance
Between similarity scoring.
One it is determined that during similarity scoring, can pre-set apart from section, determining the consignee's address of the first order and the
Distance is in the position fallen into section between the consignee's address of two orders, so as to obtain similarity scoring.If for example, in advance
What is set arrives 1km apart from section for 0.If distance is between the consignee's address of the first order and the consignee's address of the second order
10m, so as to can determine that similarity scoring is 1km/10m=100.If the consignee's address of the first order and the consignee of the second order
Distance is 100m between address, so as to can determine that similarity scoring is 1km/100m=10.Certainly, for corresponding to consignee's address
Similarity scoring, in addition to the determination mode in above-mentioned example, it is also based on the single user of malice brush and is filling in ship-to
When behavioral expectations, choose corresponding determination mode, the embodiment of the present invention is not especially limited to this.
For the user's registration information in sequence information, the embodiment of the present invention pair do not determine the sequence information of the first order with
The mode of similarity scoring in the sequence information of second order between each single item information specifically limits, and includes but is not limited to：Really
Hour of log-on hour of log-on corresponding with the user's registration information of the second order corresponding to the user's registration information of fixed first order
Between time difference；Determine that the information between the user's registration information of the first order and the user's registration information of the second order is similar
Degree；Based on time difference and information similarity degree, determine that user's registration information is corresponding with the second order corresponding to the first order
Similarity scoring between user's registration information.
Because malice brushes single user to avoid the limitation of user account number, as each user account number in preferential activity can only
It is single three times under at most, it will usually multiple user account numbers of applying for the registration of.For the ease of implementing malice brush single act, malicious user is usual
Registered user's account number can be concentrated in certain time period, so as to hour of log-on can be used as analyze one of malice brush single act according to
According to.Similarly, user's log-on message for being filled in when a batch registers account number, may have in some degree it is identical, such as user
Location message, user's sex, user's date of birth etc..Therefore, it is determined that phase between the user's registration information of different orders
During like score value, it can be determined according to above-mentioned two factor.It is, of course, also possible to similar point is determined using any of which factor
Value, the embodiment of the present invention are not especially limited to this.
Such as, however, it is determined that hour of log-on corresponding to the user's registration information of the first order is at 9 points in the morning, and the second order
Hour of log-on corresponding to user's registration information is 1 minute morning 9 point on the same day, it may be determined that the time difference between the two is 1 minute.This
When, if other information exists identical, illustrate the first order and the second order is likely to be order under same malicious user.
It is determined that the similar journey of information between the user's registration information and the user's registration information of the second order of the first order
When spending, information identical item number in user's registration information can be based on, it is determined that information similarity degree between the two.If for example, first
Order is identical with user's location message corresponding to the second order, and the first order is identical with user's sex corresponding to the second order,
First order is identical with user's date of birth corresponding to the second order, then can determine that both information similarity degrees is 3.If first
Order is different from user's location message corresponding to the second order, and the first order is identical with user's sex corresponding to the second order,
First order is identical with user's date of birth corresponding to the second order, then can determine that both information similarity degrees is 2.
It is determined that after time difference and information similarity degree, it may be determined that user's registration information and second corresponding to the first order
Similarity scoring between user's registration information corresponding to order.Specifically, different orders can be determined in the way of weighted sum
User's registration information between similarity scoring.For example, the information between the user's registration information of the first order and the second order
Similarity degree is 2, and the information item number in user's registration information is 3, then can determine that corresponding score value is 2 × 100/3.And for
Time difference equally can be in the way of the corresponding score value of above-mentioned determination distance, and the time threshold section that is fallen into according to the time determines pair
The score value answered, such as 60.If weight corresponding to the time difference be 0.6, and weight corresponding to user's registration information be 0.4, so as to by
According to the mode of weighted sum, to calculate similarity scoring be 0.6 × 60+0.4 × 2 × 100/3.
For the order placement information in sequence information, lower single time can be comprised at least in order placement information.The embodiment of the present invention is not
Pair determine the mode of the similarity scoring in the sequence information of the first order and the sequence information of the second order between each single item information
Make specific restriction, include but is not limited to：Determine the time between lower single time of the first order and lower single time of the second order
Difference；Based on the time difference, the similarity scoring between the order placement information of the first order and the order placement information of the second order is determined.
For example, lower single time of the first order is at 5 points in afternoon, lower single time of the second order is afternoon 5: 2 on the same day
Point, it may be determined that the time difference between the two is 1 minute.Now, duplicated if other information is present, illustrate that the first order is ordered with second
It is likely to be singly the order under same malicious user.When determining similarity scoring based on the time difference, equally can according to according to when
Between the time threshold section that is fallen into determine corresponding to score value.Detailed process refers to the above, and here is omitted.
By the above-mentioned means, it is determined that after similarity scoring between each single item information, can be based between each single item information
Similarity scoring, determine the similarity between the sequence information of the first order and the sequence information of the second order.Specifically, equally may be used
Weight is set for each single item information, obtains similarity according to weighted sum, here is omitted.
It should be noted that above-mentioned steps mainly choose first order from order set, remaining other
Second order is chosen in order, determines the similarity between the first order and the second order.For every in other orders
One order, can aforesaid way be used to determine the similarity between the second order, here is omitted.
Wherein, 203 it is, similar between the sequence information of order and the sequence information of the first order when existing in other orders
When degree is more than predetermined threshold value, the order for the condition that meets and the first order are classified as to the order of same source.
By above-mentioned steps it is determined that after similarity between each order and the first order in other orders, when other
When the similarity between order and the first order in order be present and being more than predetermined threshold value, then the order for the condition that meets and first are ordered
Singly it is classified as the order of same source.Wherein, because the similarity in above-mentioned steps is specific score value, so as to which predetermined threshold value also may be used
To be arranged to score value as desired, the embodiment of the present invention is not especially limited to this.
Due to an above-mentioned steps mainly optional order from order set, whether remaining order and the order are analyzed
For the order of same source, and order remaining after the order for shooting off the same source in order set, may also can
In the presence of order caused by malice brush list, hence for remaining order, can still be divided using above-mentioned steps 201 to step 203
The order of corresponding same source is analysed, here is omitted.
It should be noted that for the order of same source, that is, determine order caused by malice brush list, it usually needs
Reduced using certain measure and lost caused by malice brush list.For example, a user has singly descended 10 orders by malice brush,
The consignee's address of this 10 orders is different address, but address corresponding to different districts near being.Sent if sending respectively
Send 10 times, then can increase many express fees with manpower burden.Based on this, sort out by the order for the condition that meets and the first order
After the order of same source, can also obtain the consignee's address of the first order, using the consignee's address of the first order as
The consignee's address of same source order.Same address can be uniformly delivered to by the process, during follow-up delivery, to reduce express fee
With and manpower bear.Certainly, can also be by closing down account, order failure, warning in addition to which tackles malice brush list
Deng, the embodiment of the present invention not to after malice brush list is judged corresponding processing mode make specific limit.
Method provided in an embodiment of the present invention, the order received in preset time period is obtained, and be used as order set.It is right
Any order in order set, using any order as the first order, determine that the sequence information of the first order is ordered with other
Similarity in list between the sequence information of each order, other orders are order of the order set in addition to the first order.When
, will when the similarity between the sequence information of order and the sequence information of the first order in other orders be present and being more than predetermined threshold value
Meet that the order of condition and the first order are classified as the order of same source.Due to can be screened according to the similarity between order
Go out the order of same source, so as to analyze the source of each order, and then can detect that malice brushes single behavior.
Secondly as order set is mainly to obtain the order in preset time period, and the order in preset time period is more
It is possible to as produced by malicious user time of concentration malice brush list, so as to analyze order based on the malice brush list in preset time period
Source, improve the accuracy of order source analysis.
Again, due to being to determine sequence information between order according to the similarity scoring between each information in sequence information
Similarity, and each information may indicate that the possibility of malice brush single act, and can subsequently combine the phase between each information
Like score value synthetic determination order source, so as to improve the accuracy of order source analysis.
Finally, due to after order source is analyzed, the order of same source can be arranged to same consignee's address,
It can be delivered when subsequently delivering according to same consignee's address, so as to reduce, express fee is used and manpower is born.
The order source analysis method provided based on above-described embodiment, the embodiments of the invention provide a kind of order source
Analytical equipment.Referring to Fig. 3, the device includes：
Determining module 301, for for any order in order set, using any order as the first order, it is determined that
Similarity in the sequence information of first order and other orders between the sequence information of each order, other orders are order collection
Close the order in addition to the first order；
Classifying module 302, for when the sequence information that order in other orders be present and the first order sequence information it
Between similarity when being more than predetermined threshold value, the order for the condition that meets and the first order are classified as same class order.
As a kind of alternative embodiment, the device also includes：
First acquisition module, for obtaining the order received in preset time period, and it is used as order set.
As a kind of alternative embodiment, sequence information comprise at least following three information in any one, three below
Information is user's registration information, consignee's address and order placement information.
As a kind of alternative embodiment, determining module 301, for for any order in other orders, being ordered other
Any order in list determines information phase in the sequence information of the first order and the sequence information of the second order as the second order
Same item number, using item number as the similarity between the sequence information of the first order and the sequence information of the second order.
As a kind of alternative embodiment, determining module 301, including：
First determining unit, for for any order in other orders, using any order in other orders as
Second order, determine similar point between the sequence information of the first order and each single item information in the sequence information of the second order
Value；
Second determining unit, for based on the similarity scoring between each single item information, determining the sequence information of the first order
Similarity between the sequence information of the second order.
As a kind of alternative embodiment, for the consignee's address in sequence information, the first determining unit, for determining the
Distance between the consignee's address of one order and the consignee's address of the second order；The consignee of the first order is determined based on distance
Similarity scoring between the consignee's address of address and the second order.
As a kind of alternative embodiment, for the user's registration information in sequence information, the first determining unit, for determining
The hour of log-on corresponding with the user's registration information of the second order of hour of log-on corresponding to the user's registration information of first order it
Between time difference；Determine the similar journey of information between the user's registration information of the first order and the user's registration information of the second order
Degree；Based on time difference and information similarity degree, determine that user's registration information corresponding to the first order is corresponding with the second order and use
Similarity scoring between the log-on message of family.
As a kind of alternative embodiment, for the order placement information in sequence information, the first determining unit, for determining first
Time difference between lower single time of order and lower single time of the second order；Based on the time difference, placing an order for the first order is determined
Similarity scoring between information and the order placement information of the second order.
As a kind of alternative embodiment, the device also includes：
Second acquisition module, for obtain the first order consignee's address, using the consignee's address of the first order as
The consignee's address of same source order.
Device provided in an embodiment of the present invention, for any order in order set, ordered any order as first
It is single, determine the similarity between the sequence information of the first order and the sequence information of each order in other orders, other orders
For order of the order set in addition to the first order.When the sequence information that order in other orders be present and the order of the first order
When similarity between information is more than predetermined threshold value, the order for the condition that meets and the first order are classified as ordering for same source
It is single.Due to the order of same source according to the similarity between order, can be filtered out, so as to analyze coming for each order
Source, and then can detect that malice brushes single behavior.
Secondly as order set is mainly to obtain the order in preset time period, and the order in preset time period is more
It is possible to as produced by malicious user time of concentration malice brush list, so as to analyze order based on the malice brush list in preset time period
Source, improve the accuracy of order source analysis.
Again, due to being to determine sequence information between order according to the similarity scoring between each information in sequence information
Similarity, and each information may indicate that the possibility of malice brush single act, and can subsequently combine the phase between each information
Like score value synthetic determination order source, so as to improve the accuracy of order source analysis.
Finally, due to after order source is analyzed, the order of same source can be arranged to same consignee's address,
It can be delivered when subsequently delivering according to same consignee's address, so as to reduce, express fee is used and manpower is born.
The embodiments of the invention provide a kind of order source analysis equipment.Referring to Fig. 4, the order source analysis equipment bag
Include：Processor (processor) 401, memory (memory) 402 and bus 403；
Wherein, processor 401 and memory 402 complete mutual communication by bus 403 respectively；
Processor 401 is used to call the programmed instruction in memory 402, and the order provided with performing above-described embodiment comes
Source analysis method, such as including：For any order in order set, using any order as the first order, first is determined
Similarity in the sequence information of order and other orders between the sequence information of each order, other orders are that order set removes
Order outside first order；Phase between sequence information of the sequence information that order in other orders be present with the first order
When being more than predetermined threshold value like degree, the order for the condition that meets and the first order are classified as to the order of same source.
The present invention provides a kind of non-transient computer readable storage medium storing program for executing, non-transient computer readable storage medium storing program for executing storage
Computer instruction, the computer instruction makes computer perform the order source analysis method that above-described embodiment is provided, such as wraps
Include：For any order in order set, using any order as the first order, determine the first order sequence information and its
Similarity in its order between the sequence information of each order, other orders are order set ordering in addition to the first order
It is single；When the similarity between the sequence information and the sequence information of the first order that order in other orders be present is more than predetermined threshold value
When, the order for the condition that meets and the first order are classified as to the order of same source.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above method embodiment can pass through
Programmed instruction related hardware is completed, and foregoing program can be stored in a computer read/write memory medium, the program
Upon execution, the step of execution includes above method embodiment；And foregoing storage medium includes：ROM, RAM, magnetic disc or light
Disk etc. is various can be with the medium of store program codes.
The embodiments such as information exchange equipment described above are only schematical, wherein illustrate as separating component
Unit can be or may not be physically separate, can be as the part that unit is shown or may not be thing
Manage unit, you can with positioned at a place, or can also be distributed on multiple NEs.It can select according to the actual needs
Some or all of module therein is selected to realize the purpose of this embodiment scheme.Those of ordinary skill in the art are not paying wound
In the case of the work for the property made, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
Realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on such understanding, on
The part that technical scheme substantially in other words contributes to prior art is stated to embody in the form of software product, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including some fingers
Make to cause a computer equipment (can be personal computer, server, or network equipment etc.) to perform each implementation
Some Part Methods of example or embodiment.
Finally, the present processes are only preferable embodiment, are not intended to limit the scope of the present invention.It is all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvements made etc., the protection of the present invention should be included in
Within the scope of.
Claims (10)
- A kind of 1. order source analysis method, it is characterised in that including：For any order in order set, using any order as the first order, ordering for first order is determined Similarity in single information and other orders between the sequence information of each order, other orders are that the order set removes Order outside first order；When the similarity between the sequence information and the sequence information of first order that order in other orders be present is big When predetermined threshold value, the order for the condition that meets and first order are classified as to the order of same source.
- 2. according to the method for claim 1, it is characterised in that the sequence information for determining first order with it is other Before similarity in order between the sequence information of each order, in addition to：The order received in preset time period is obtained, and is used as the order set.
- 3. according to the method for claim 1, it is characterised in that the sequence information is comprised at least in following three information Any one, following three information are user's registration information, consignee's address and order placement information.
- 4. according to the method for claim 3, it is characterised in that the sequence information for determining first order with it is other Similarity in order between the sequence information of each order, including：For any order in other orders, using any order in other orders as the second order, it is determined that Information identical item number in the sequence information of the sequence information of first order and second order, using the item number as Similarity between the sequence information of first order and the sequence information of second order.
- 5. according to the method for claim 3, it is characterised in that the sequence information for determining first order with it is other Similarity in order between the sequence information of each order, including：For any order in other orders, using any order in other orders as the second order, it is determined that Similarity scoring in the sequence information of first order and the sequence information of second order between each single item information；Based on the similarity scoring between each single item information, the sequence information of first order and ordering for second order are determined Similarity between single information.
- 6. according to the method for claim 5, it is characterised in that for the consignee's address in sequence information, the determination Similarity scoring in the sequence information of first order and the sequence information of second order between each single item information, bag Include：Determine distance between the consignee's address of first order and the consignee's address of second order；Determined based on the distance between the consignee's address of first order and the consignee's address of second order Similarity scoring.
- 7. according to the method for claim 5, it is characterised in that described true for the user's registration information in sequence information Similarity scoring in the sequence information of fixed first order and the sequence information of second order between each single item information, bag Include：Determine the user's registration information of hour of log-on corresponding to the user's registration information of first order and second order Time difference between corresponding hour of log-on；Determine that the information between the user's registration information of first order and the user's registration information of second order is similar Degree；Based on the time difference and described information similarity degree, determine user's registration information corresponding to first order with it is described Similarity scoring between user's registration information corresponding to second order.
- 8. according to the method for claim 5, it is characterised in that for the order placement information in sequence information, the letter that places an order Cease and comprise at least lower single time, it is every in the sequence information of the sequence information for determining first order and second order Similarity scoring between one information, including：Determine the time difference between lower single time of first order and lower single time of second order；Based on the time difference, the phase between the order placement information of first order and the order placement information of second order is determined Like score value.
- 9. according to the method for claim 1, it is characterised in that the order by the condition that meets is returned with first order After class is the order of same source, in addition to：The consignee's address of first order is obtained, the consignee's address of first order is ordered as the same source Single consignee's address.
- A kind of 10. order source analysis device, it is characterised in that including：Determining module, for for any order in order set, using any order as the first order, it is determined that described Similarity in the sequence information of first order and other orders between the sequence information of each order, other orders are institute State order of the order set in addition to first order；Classifying module, for when the sequence information that order in other orders be present and first order sequence information it Between similarity when being more than predetermined threshold value, the order for the condition that meets and first order are classified as same class order.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710752505.7A CN107492021A (en) | 2017-08-28 | 2017-08-28 | Order source analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710752505.7A CN107492021A (en) | 2017-08-28 | 2017-08-28 | Order source analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107492021A true CN107492021A (en) | 2017-12-19 |
Family
ID=60646670
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710752505.7A Pending CN107492021A (en) | 2017-08-28 | 2017-08-28 | Order source analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107492021A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647801A (en) * | 2018-03-23 | 2018-10-12 | 阿里巴巴集团控股有限公司 | Predict the method and device of account hot spot |
| CN108900609A (en) * | 2018-06-29 | 2018-11-27 | 重庆小雨点小额贷款有限公司 | A kind of business approval method, server, client and storage medium |
| CN109165906A (en) * | 2018-06-29 | 2019-01-08 | 重庆小雨点小额贷款有限公司 | A kind of business approval method, server and client |
| CN110298673A (en) * | 2019-06-14 | 2019-10-01 | 达疆网络科技(上海)有限公司 | A kind of shops participates in the monitoring method of brush list |
| CN110555589A (en) * | 2019-07-31 | 2019-12-10 | 苏宁云计算有限公司 | Risk order identification method and device |
| CN110955890A (en) * | 2018-09-26 | 2020-04-03 | 瑞数信息技术（上海）有限公司 | Method and device for detecting malicious batch access behaviors and computer storage medium |
| CN112214731A (en) * | 2019-07-11 | 2021-01-12 | 北京京东振世信息技术有限公司 | Method and device for determining target set |
| CN113469789A (en) * | 2021-07-01 | 2021-10-01 | 易纳购科技(北京)有限公司 | Abnormal order detection method and device and computer equipment |
| CN113837617A (en) * | 2021-09-26 | 2021-12-24 | 广州新丝路信息科技有限公司 | Anti-bill-swiping risk management method and device |
| 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 (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4861965B2 (en) * | 2007-11-14 | 2012-01-25 | 株式会社日立製作所 | Information distribution system |
| CN104573017A (en) * | 2015-01-09 | 2015-04-29 | 北京网智天元科技股份有限公司 | Network water army group identifying method and system |
| 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 |
| CN106569994A (en) * | 2015-10-10 | 2017-04-19 | 阿里巴巴集团控股有限公司 | Elevator remote control device |
| CN107092997A (en) * | 2016-07-29 | 2017-08-25 | 北京小度信息科技有限公司 | A kind of Logistic Scheduling method and device |
-
2017
- 2017-08-28 CN CN201710752505.7A patent/CN107492021A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4861965B2 (en) * | 2007-11-14 | 2012-01-25 | 株式会社日立製作所 | Information distribution system |
| CN104573017A (en) * | 2015-01-09 | 2015-04-29 | 北京网智天元科技股份有限公司 | Network water army group identifying method and system |
| CN106569994A (en) * | 2015-10-10 | 2017-04-19 | 阿里巴巴集团控股有限公司 | Elevator remote control 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 |
| CN107092997A (en) * | 2016-07-29 | 2017-08-25 | 北京小度信息科技有限公司 | A kind of Logistic Scheduling method and device |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647801B (en) * | 2018-03-23 | 2020-04-14 | 阿里巴巴集团控股有限公司 | Method and device for predicting financial hotspot |
| WO2019179236A1 (en) * | 2018-03-23 | 2019-09-26 | 阿里巴巴集团控股有限公司 | Accounting hotspot prediction method and apparatus |
| CN108647801A (en) * | 2018-03-23 | 2018-10-12 | 阿里巴巴集团控股有限公司 | Predict the method and device of account hot spot |
| CN108900609B (en) * | 2018-06-29 | 2019-06-21 | 重庆小雨点小额贷款有限公司 | A kind of business approval method, server, client and storage medium |
| CN108900609A (en) * | 2018-06-29 | 2018-11-27 | 重庆小雨点小额贷款有限公司 | A kind of business approval method, server, client and storage medium |
| CN109165906B (en) * | 2018-06-29 | 2021-07-09 | 重庆小雨点小额贷款有限公司 | Business approval method, server and client |
| CN109165906A (en) * | 2018-06-29 | 2019-01-08 | 重庆小雨点小额贷款有限公司 | A kind of business approval method, server and client |
| CN110955890B (en) * | 2018-09-26 | 2021-08-17 | 瑞数信息技术（上海）有限公司 | Method and device for detecting malicious batch access behaviors and computer storage medium |
| CN110955890A (en) * | 2018-09-26 | 2020-04-03 | 瑞数信息技术（上海）有限公司 | Method and device for detecting malicious batch access behaviors and computer storage medium |
| CN110298673A (en) * | 2019-06-14 | 2019-10-01 | 达疆网络科技(上海)有限公司 | A kind of shops participates in the monitoring method of brush list |
| CN112214731A (en) * | 2019-07-11 | 2021-01-12 | 北京京东振世信息技术有限公司 | Method and device for determining target set |
| CN112214731B (en) * | 2019-07-11 | 2024-04-09 | 北京京东振世信息技术有限公司 | Method and device for determining target set |
| CN110555589A (en) * | 2019-07-31 | 2019-12-10 | 苏宁云计算有限公司 | Risk order identification method and device |
| CN113469789A (en) * | 2021-07-01 | 2021-10-01 | 易纳购科技(北京)有限公司 | Abnormal order detection method and device and computer equipment |
| CN113837617A (en) * | 2021-09-26 | 2021-12-24 | 广州新丝路信息科技有限公司 | Anti-bill-swiping risk management method and device |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107492021A (en) | Order source analysis method and device | |
| CN108038696B (en) | Method and system for detecting bill swiping based on equipment identification code and social group information | |
| CN106127505A (en) | The single recognition methods of a kind of brush and device | |
| CN110807657B (en) | Order processing method, device, equipment and computer readable storage medium | |
| US10636100B2 (en) | System and method for prediction of value added tax reclaim success | |
| CN109064279A (en) | A kind of order processing method and device | |
| CN108876545A (en) | Order recognition methods, device and readable storage medium storing program for executing | |
| CN107944002A (en) | Reward voucher checks and writes off method, apparatus and electronic equipment | |
| JP7516249B2 (en) | Apparatus and method for preventing fraud | |
| CN107369026A (en) | Method for distributing business and device | |
| CN108197851A (en) | A kind of e-commerce mostly single flow distribution method with address | |
| CN110197408B (en) | Pricing early warning method and system for premium commodities | |
| CN107437216A (en) | Purchase method, platform, device, computer-readable storage medium and computer equipment | |
| CN112784039A (en) | Method, device and storage medium for distributing online customer service | |
| CN110414902B (en) | E-commerce platform system based on internet | |
| CN108648005A (en) | Data processing method and system | |
| CN107392614A (en) | The implementation method and device of off-line transaction | |
| CN110060413A (en) | Method for selling and device, the storage medium and electronic device of article | |
| US8533074B1 (en) | Lost and damaged items in a fulfillment network | |
| CN108182587A (en) | A kind of electric business platform brush single act detection method and system | |
| CN108415970A (en) | Retrieval result sort method, device, electronic equipment and storage medium | |
| CN110009511A (en) | Arbitrage behavior recognition methods, arbitrage behavior identification model training method and system | |
| CN112435059A (en) | Method and device for evaluating value of article in real time, electronic equipment and storage medium | |
| CN106157045A (en) | Method based on logistics data identification wash sale, device and server | |
| CN107622408A (en) | Purchase the predictor method and estimating device of fare rope transaction conversion |
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: 20171219 |
|
| RJ01 | Rejection of invention patent application after publication |