Specific embodiment
It is to make purpose, technical scheme and the advantage of the application clearer, specifically real below in conjunction with the application
Apply example and corresponding accompanying drawing is clearly and completely described to technical scheme.Obviously, it is described
Embodiment is only some embodiments of the present application, rather than the embodiment of whole.Based on the enforcement in the application
Example, the every other enforcement obtained under the premise of creative work is not made by those of ordinary skill in the art
Example, belongs to the scope of the application protection.
The related information of the business that Fig. 1 is provided for the embodiment of the present application estimates process, the process specifically include with
Lower step:
S101:In the historical time section of setting, each historical operational information of each user is obtained.
Just it has been observed that related information can be determined by business information, in order to more save calculation resources,
All historical operational informations of the different user within the phase of history time will be obtained in this application.
Explanation is needed exist for, after the business that user has used business provider to be provided, it will usually raw
Into corresponding business information.For example:After user stores certain file using network storage service, it is used for
The server (or data base) for providing the network storage service will generate storage service information, the storage industry
Can include in business information:The information such as storage time, shared storage size, file type.Again
For example:After user uses logistics business, service provider would generally generate logistics business information, wherein wrapping
Containing information such as freight charges, delivery address, ship-to.In actual applications, generation above-mentioned business information (with
And historical operational information) generally carry out being stored in itself server or data base by business provider.
So, in the embodiment of the present application, for above-mentioned steps S101, can be by service provider's
Server obtains historical operational information, it is also possible to provided by the third party's business dedicated for providing association service
The server of side, obtains above-mentioned historical operational information from business provider.Here do not constitute to this Shen
Restriction please.
The historical time section of the setting described in above-mentioned steps, specifically can be setting with such as hour, day,
The historical time section determined by the unit of time such as week, month, is not especially limited here.
S102:According to described each historical operational information of each user for getting, the association of each user is determined
Eigenvalue.
Described linked character value, including the value that can reflect corresponding to the feature related to association service.Prolong
Continuous aforementioned exemplary:In network storage service, its association service can be dilatation service, then, it is described
Linked character value can be the average storage size used by user, it is seen then that according to putting down that the user is used
Storage size, can provide a user with the dilatation service of respective volume;Again for example:In logistics business,
Its association service can be danger service of returning goods, then, described linked character value can be dangerous being in danger of returning goods
Rate, it is seen then that according to the rate of being in danger, the return of goods that can provide a user with different premiums are nearly serviced.
Linked character value is can be seen that from above-mentioned example with user in the past using shape during corresponding business
State is related, so as in the above-mentioned steps of the application, by the historical operational information according to different user come really
Fixed respective linked character value.
When here it is considered that in prior art business operation each time, it is required for being entered according to current business information
Row computing is more and less efficient come the computing resource consumed by the mode of estimating related information.So, it is
Effectively lifted and efficiency estimated to related information, can adopt unified related information estimate standard,
Easily to estimate to related information.That is, performing following step S103.
S103:The linked character value of each user is counted, and all linked character values that statistics is obtained are drawn
It is divided into some linked character value scopes.
During practical application, the linked character value of different user may be identical, it is also possible to larger difference occurs, that
, after the linked character value to a large number of users is counted, one just can be obtained by different size of pass
The scope constituted by connection eigenvalue.
After the scope for having obtained linked character value, just related information can be estimated.Need exist for
Illustrate, be gradually incremented by as linked character value is ascending, the quantized value of related information also can increase therewith
Plus, can be seen that from above-mentioned example:The average storage size used by user is bigger, then, dilatation
The there is provided capacity of service also will be bigger;Similarly, the rate of being in danger of user is higher, then, danger of returning goods services
Premium also will be higher.Obviously, the scope of the above-mentioned linked character value for obtaining, only reflects a kind of trend,
And generally require in actual applications to estimate its corresponding related information according to the linked character value of different values
Quantized value, therefore, be also accomplished by refining linked character value, that is, in this application will to close
Connection eigenvalue is divided, so as to form several linked character value scopes.Afterwards, just can be directed to each
It is individual to divide the linked character value scope for obtaining, its corresponding related information is estimated, that is, performing following step
S104。
S104:For dividing the linked character value scope for obtaining, each linked character value scope institute is estimated
Corresponding initial association information.
For the initial association information obtained in this step, can be estimated according to linked character value.
For example:During danger service premium of returning goods is estimated, can be estimated out not according to the difference of the rate of being in danger
Same premium, in this example, premium specifically can carry out passing for arithmetic progression formula according to the increase of the rate of being in danger
Increase, it is assumed that when rate of being in danger is 1%, premium is estimated for 1 yuan, when rate of being in danger is 2%, premium is to estimate 2 yuan ...
By that analogy.Certainly, calculating is estimated for the initial association information here, does not constitute to the application
Restriction.
Due to being initial association information corresponding to linked character value scope, and may bag in linked character value scope
Containing multiple different linked character values, so, initial association information here be substantially one kind have passed through it is flat
Related information after calculating.By above-mentioned example and content can be seen that through this step it is estimated
Related information is regarded as the related information that a kind of rough estimate is obtained, and in actual applications, related information can
Can be affected by other business information, and a certain degree of change is occurred, that is, the association letter of reality
Breath may be not as between above-mentioned initial association information and linked character value with fixed corresponding relation.Cause
This, in order to cause the related information estimated out to more conform to practical situation, in this application by under execution
State step S105.
S105:It is according to each historical operational information belonged in the range of different linked character values, special to different associations
Initial association information corresponding to value indicative scope is adjusted, and estimates the standard for generating each linked character value scope
Related information.
By taking the rate of being in danger in danger service of returning goods as an example, under different rates of being in danger, the quantity of corresponding logistics business is led to
Chang Butong:In the case of low rate of being in danger, more logistics business is often dispersed with, and be in danger rate in height
In the case of, the logistics business of distribution is less.So, in this application, also just can be according to logistics business
Distributed number is adjusted to initial association information resulting before, for example:So that being in low rate feelings of being in danger
Premium under condition is reduced, and the premium rising being in the case of high rate of being in danger.Here for initial association information
The example of regulation do not constitute the restriction to the application.
The mode being adjusted to initial association information, can cause finally to estimate the standard association information for obtaining
More fit actually used scene, also, standard association information that can be further to obtaining in the application is entered
Mobile state is adjusted, so as to be adapted to the situation of change of business in practical application.
By above-mentioned steps, for the user using same business, these users are obtained respectively in certain history
All historical operational informations in time, according to these historical operational informations for obtaining, it may be determined that go out each
The linked character value of user, then the linked character value of all users is counted, and statistical result is refined
Into several linked character value scopes, on this basis, each association is estimated out according to historical operational information
Initial association information corresponding to range of characteristic values, also, again initial association information is finely adjusted, so as to
Estimate out the standard association information corresponding to each linked character value scope.It is believed that adopt in such a way,
Related information has been divided into into different steppings intervals, when actually used, only business operation institute need to have been determined
Stepping belonging to corresponding linked character information is interval, you can easily estimates out related information, and no longer needs
Will be according to calculating corresponding related information each time using the situation of business, it is clear that such mode can pole
It is big to reduce shared calculation resources, effectively lifted and efficiency is estimated to related information, meanwhile, in the application
The related information estimated can be finely adjusted, the related information for being is more stable, reliable, practical situation of fitting.
In order to clearly illustrate the related information predictor method of business in the application, now with electronics
Under business model, seller user is that return of goods danger services, related information is the return of goods using logistics business, association service
The application scenarios of dangerous premium are described in detail.
In this scene, seller user can dispense its purchase to the buyer user that have purchased commodity using logistics business
The commodity (that is, delivery) bought, and work as user after it have received commodity, for a variety of reasons, exist
The phenomenon of the return of goods, and using logistics business carry out in return process produced by back freight may be by selling domestic
Family undertakes, and in order to reduce the expense that seller user undertakes, corresponding business provider can provide return of goods danger and service.
For different seller users, due to type, the return of goods for occurring in history of its commodity for providing
Situation is different, then, it is necessary to for different seller users, respective rate of being in danger is determined respectively
(that is, linked character value), so that premium (that is, related information) subsequently to seller user is carried out
Estimate.
Therefore, under the scene, according to described each historical operational information of each user for getting, it is determined that often
The linked character value of one user, specifically includes:Wrap in counting the history logistics business information of each seller user
The return of goods information for containing, and accounting of the return of goods information in the history logistics business information of the seller user,
The return of goods rate of the return of goods information, the accounting and default logistics target that are obtained according to statistics, it is determined that
The rate of being in danger of each seller user.Wherein, described logistics target refers to the commodity transported by logistics business.
Said process can specifically adopt following formula:
T=Logit (C+log (N+1) * a1+R1*a2+R2*a3)
Wherein, t represents the rate of being in danger;
N represents the return of goods number of times of seller user;
R1Represent the return of goods rate of seller user;
R2Represent that the industry of the logistics target is in danger rate;
a1、a2, a3 represent corresponding coefficient;
C is constant.
It should be noted that the history logistics business information by counting each seller user, it may be determined that go out
N and R1.For R2For, which represent this kind of commodity going out in all seller users in commodity website
Dangerous rate, R2Obtain in the global statistics data that commodity website can be passed through, do not constitute to the application's here
Limit.
According to the above, can be counted for each seller user, and determine
Rate, the rate of being in danger it is possible to further be obtained according to statistics are divided, and form the stepping of multiple rates of being in danger
Interval (that is, multiple rate scopes of being in danger), and estimate the different initial guarantors being in danger corresponding to rate stepping interval
Take, it is assumed that can specifically form corresponding relation as shown in table 1 below.
Table 1
It can be seen in table 1 that the upper limit of rate of being in danger is less than 30%, also, each rate stepping institute of being in danger is right
The initial premium answered, is gradually incremental according to the mode of arithmetic progression.In above-mentioned table 1, initial premium is
Estimated according to the change of the rate of being in danger, the needs of practical application in order that premium more can be fitted can
To be adjusted to initial premium on the basis of table 1.
In the embodiment of the present application, initial premium is adjusted specifically including in the following manner:
First kind of way
In this mode, it is contemplated that the different logistics number of times distributions being in danger included in rate stepping interval is each not
It is identical, then, also just initial premium can be entered according to the logistics number of times distribution being respectively in danger in rate stepping interval
Row is adjusted.Specifically, according to each historical operational information belonged in the range of different linked character values, to not
It is adjusted with the initial association information corresponding to linked character value scope, specifically may include:Statistics at least two
The quantity of each historical operational information in the range of individual rate of being in danger, according to the quantity that statistics is obtained, to statistics
The initial return of goods danger premium being in danger corresponding to rate scope be adjusted.
For example:In table 1, for " t≤1% " this stepping interval, it may be determined that source is in this point
All seller users in shelves interval, correspondingly, the summation of the logistics number of times used by these seller users,
Namely logistics number of times corresponding to stepping interval.Using same way, it is also possible to count " 1%<t≤
2% " the logistics number of times in this stepping interval.It is assumed that the logistics number of times in stepping interval " t≤1% " is
400, stepping interval " 1%<Logistics number of times in t≤2% " is 100, although stepping interval " 1%<T≤2% "
Be in danger rate of the rate higher than stepping interval " t≤1% " of being in danger, but, stepping interval " 1%<Thing in t≤2% "
The distribution of stream number of times is substantially less, it is thus possible to correspondingly adjust stepping interval " 1%<T≤2% " is corresponding
Initial premium, such as:Assuming will section stepping interval " 1%<Initial premium (that is, a2) corresponding to t≤2% "
It is adjusted to identical (that is, by a with the corresponding initial premium of stepping interval " t≤1% "2It is adjusted to a1).Certainly,
Here it is a kind of example to the regulative mode of initial premium, can enters according to actual needs in actual applications
Row is adjusted, such as:Two ratios of the rate stepping interval according to wherein logistics number of times of being in danger, adjust corresponding initial
Premium etc., this is not intended as the restriction to the application.
It is likewise possible to adopt the initial premium being in danger to difference corresponding to rate stepping interval in a like fashion enter
Row is adjusted, and ultimately forms standard premium as shown in table 2.
Table 2
As seen from Table 2, according to difference be in danger rate stepping interval in logistics number of times distribution, can be to initial
Premium is adjusted, and ultimately generates the standard premium for tallying with the actual situation.As described in aforementioned exemplary
Situation, in table 2 difference be in danger rate steppings interval corresponding to standard premiums, numerically may it is identical,
Herein for each interval each self-corresponding standard premium of rate stepping that is in danger clearly is indicated, so employing
A1~A30Variable format represent, do not constitute the restriction to the application here.
The second way
In this mode, the same logistics number of times being in danger included in rate stepping interval can also affect final mark
Certainly take, specifically, according to each historical operational information belonged in the range of different linked character values, to not
It is adjusted with the initial association information corresponding to linked character value scope, specifically includes:Statistics is arbitrary to be in danger
The quantity of each historical operational information in the range of rate, according to the business of default, the belonging rate scope of being in danger
Amount threshold, and the quantity for obtaining is counted, the initial return of goods being in danger corresponding to rate scope described in regulation
Dangerous premium.
For example:If for the seller user in a certain stepping in interval, if which is gone through in certain
The logistics number of times very many (transaction count for also turning out generation is very more) used in the history time period,
More than default number of services threshold value, then, the seller is when the service of return of goods danger is obtained, it is necessary to purchase
The dangerous quantity for servicing of returning goods is also more, it is thus possible to the amount of premium is reduced, is beneficial to seller user and obtains
Must return goods dangerous service, it is assumed that in table 1, the interval initial premium of " t≤1% " this stepping is a1=0.3 yuan,
If the logistics number of times used by certain the seller user in the stepping interval is larger (to assume that quantity exceedes
500) when, can by initial premium 0.3 yuan be adjusted downward to 0.15 yuan, form the standard premium under stepping interval
A1=0.15 (numerical value for being adjusted here is a kind of example, in actual applications can be according to actual needs
It is adjusted, is not intended as the restriction to the application).
It is likewise possible to adopt the initial premium being in danger to difference corresponding to rate stepping interval in a like fashion enter
Row is adjusted, and ultimately forms standard premium as shown in table 3.
Table 3
The third mode
Initial premium as shown in table 1, is according to each seller user generated in certain historical time section
Historical operational information carry out estimating what is obtained, and in actual applications, can all there be newly-generated industry every day
Business information, in other words, historical operational information is also in constantly more new change, then, in this mode, can
Initial premium with according to the historical operational information that changes, in the above-mentioned table of continuous dynamic regulation 1.
Regulative mode by more than, can estimate the standard premium for obtaining laminating practical situation, beneficial to seller
User obtains corresponding danger of returning goods and services.
Certainly, the above in the application, is applicable not only to dangerous service of returning goods, and applies also for aforementioned being carried
And network storage service, cloud calculation service, in the business such as VOD service.Here concrete limit is not made
It is fixed.
After standard association information has been obtained, just user can be made to obtain corresponding closing according to standard association information
Connection service, therefore, in the embodiment of the present application, a kind of using method of the related information of business is additionally provided,
As shown in Figure 2.
In fig. 2, the using method of the related information of the business, specifically includes following steps:
S201:When monitoring that user uses specified services, the linked character value of the user is determined.
Specified services described in the present embodiment, including the business with association service, for example:Logistics business
(its association service is serviced for danger of returning goods), network storage service (its association service is dilatation service) etc..
Described linked character value, is exactly the linked character value in preceding method.Association simultaneously for user is special
The determination process of value indicative, it is also identical with preceding method, therefore will not be described here.
S202:According to the corresponding standard association information of the linked character value estimated, it is determined that with the user
The standard association information that matched of linked character value, to provide association service according to the related information.
By preceding method, different stepping interval (that is, linked character value scope) institutes have been estimated out
Correspondence standard association information, then, once it is determined that the linked character value of user, be also assured that out should
Stepping belonging to linked character value is interval, so that it is determined that going out corresponding standard association information.
The related information predictor method of the business for providing for the embodiment of the present application above, based on same thinking,
The embodiment of the present application also provides a kind of related information estimating device of business, as shown in Figure 3.
In figure 3, the related information estimating device of the business includes:Acquisition module 301, determining module
302nd, statistical module 303, division module 304 and adjustment module 305, wherein,
Acquisition module 301, for, in the historical time section of setting, obtaining each history industry of each user respectively
Business information.
Determining module 302, for the described each historical operational information according to each user for getting, it is determined that often
The linked character value of one user.
Statistical module 303, for counting the linked character value of each user, and by statistics obtain it is all
Linked character value is divided into some linked character value scopes.
Division module 304, for for dividing the linked character value scope for obtaining, estimating each association
Initial association information corresponding to range of characteristic values.
Adjustment module 305, belongs to each historical operational information in the range of different linked character values for basis,
Initial association information corresponding to different linked character value scopes is adjusted, each linked character of generation is estimated
The standard association information of value scope.
In the embodiment of the present application, the user includes seller user;The linked character value includes the rate of being in danger;
The related information includes dangerous premium of returning goods.
Comprising in the case of return of goods information in each historical operational information, the determining module 302 has
The return of goods information that body is included in being used to count the history logistics business information of each seller user, and described move back
Accounting of the goods information in the history logistics business information of the seller user, according to the return of goods that statistics is obtained
The return of goods rate of information, the accounting and default logistics target, determines the rate of being in danger of each seller user.
Under a kind of mode in the embodiment of the present application, the adjustment module 305, specifically for statistics at least
The quantity of each historical operational information in the range of two rates of being in danger, according to the quantity that statistics is obtained, to system
The initial return of goods danger premium being in danger corresponding to rate scope of meter is adjusted.
Under another way in the embodiment of the present application, the adjustment module 305 is appointed specifically for statistics
One quantity for being in danger each historical operational information in the range of rate, is in danger rate scope according to default, belonging this
Number of services threshold value, and the quantity that obtains of statistics, adjust it is described be in danger corresponding to rate scope at the beginning of
Begin dangerous premium of returning goods.
The embodiment of the present application also provides a kind of related information use device of business, as shown in Figure 4.The dress
Put including:
Monitoring modular 401, for when monitoring that user uses specified services, determining the association of the user
Eigenvalue;
Determining module 402, for according to the corresponding standard association information of the linked character value estimated, really
The fixed standard association information matched with the linked character value of the user, to be carried according to the related information
For association service.
In a typical configuration, computing device includes one or more processors (CPU), input/defeated
Outgoing interface, network interface and internal memory.
Internal memory potentially includes the volatile memory in computer-readable medium, random access memory
And/or the form, such as read only memory (ROM) or flash memory (flash RAM) such as Nonvolatile memory (RAM).
Internal memory is the example of computer-readable medium.
Computer-readable medium include permanent and non-permanent, removable and non-removable media can by appoint
What method or technique is realizing information Store.Information can be computer-readable instruction, data structure, program
Module or other data.The example of the storage medium of computer include, but are not limited to phase transition internal memory (PRAM),
Static RAM (SRAM), dynamic random access memory (DRAM), it is other kinds of with
Machine access memorizer (RAM), read only memory (ROM), Electrically Erasable Read Only Memory
(EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read only memory (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, tape magnetic rigid disk are stored or which
His magnetic storage apparatus or any other non-transmission medium, can be used to store the letter that can be accessed by a computing device
Breath.Define according to herein, computer-readable medium does not include temporary computer readable media (transitory
Media), such as the data signal and carrier wave of modulation.
Also, it should be noted that term " including ", "comprising" or its any other variant are intended to non-row
His property is included, so that a series of process, method, commodity or equipment including key elements not only includes
Those key elements, but also including other key elements being not expressly set out, or also include for this process,
The intrinsic key element of method, commodity or equipment.In the absence of more restrictions, " included by sentence
One ... " key element that limits, it is not excluded that in the process including the key element, method, commodity or set
Also there is other identical element in standby.
It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer journey
Sequence product.Therefore, the application can using complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.And, the application can wherein include calculating using at one or more
Machine usable program code computer-usable storage medium (including but not limited to disk memory, CD-ROM,
Optical memory etc.) on the form of computer program implemented.
Embodiments herein is the foregoing is only, the application is not limited to.For this area skill
For art personnel, the application can have various modifications and variations.All institutes within spirit herein and principle
Any modification, equivalent substitution and improvements of work etc., within the scope of should be included in claims hereof.