CN109858952A - Data processing method and device under service scenarios - Google Patents
Data processing method and device under service scenarios Download PDFInfo
- Publication number
- CN109858952A CN109858952A CN201910001961.7A CN201910001961A CN109858952A CN 109858952 A CN109858952 A CN 109858952A CN 201910001961 A CN201910001961 A CN 201910001961A CN 109858952 A CN109858952 A CN 109858952A
- Authority
- CN
- China
- Prior art keywords
- red packet
- user
- money
- rate
- amount
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This specification embodiment provides the data processing method and device under a kind of service scenarios, target user is divided into multiple user groups, and calculate separately the red packet amount of money that red packet is provided to each user group, simplify the pricing problem of red packet, automation price is realized, while the user's La Xin rate for realizing service platform maximizes.
Description
Technical field
This specification is related to the data processing method and device under technical field of data processing more particularly to service scenarios.
Background technique
In order to guide user to download the corresponding application program of activation service platform, service platform can usually give certain gold
Volume subsidy, induces it to become the new user of service platform.Wherein, providing red packet is a kind of important means for realizing above-mentioned purpose.
Red packet can be used as a kind of subsidy form when being consumed on service platform, therefore also have and user is promoted to exist
It is consumed on service platform, to experience the effect of the core function of service platform.Therefore, it is necessary to provide service platform red
The mode of packet improves.
Summary of the invention
Based on this, present description provides the data processing method and device under service scenarios.
According to this specification embodiment in a first aspect, a kind of data processing method under providing service scenarios, the side
Method includes:
Obtain the user characteristics of the target user of red packet to be provided on service platform；
The target user is divided into several user groups according to the user characteristics, and calculates separately each user group
Corresponding red packet checks and writes off rate model, the red packet check and write off rate model for characterize user group to the red packet check and write off rate with it is described
Corresponding relationship between the red packet amount of money of red packet；
Rate model is checked and write off according to the corresponding red packet of each user group respectively to determine to the red packet for corresponding to user group granting red packet
The amount of money, so that user's La Xin rate maximizes when the service platform corresponds to the red packet of the red packet amount of money to each user group granting, institute
It states the sum that user's La Xin rate is the user checked and write off in each user group to red packet and provides red packet with the service platform
The ratio between master budget amount of money.
Optionally, the step of target user being divided into several user groups according to the user characteristics include:
The decision-tree model that the user characteristics input of each target user is trained in advance respectively, obtains corresponding target user
User tag；
The target user is divided into several user groups according to the user tag.
Optionally, the method also includes:
Obtain the history red packet amount of money of each red packet of the introversive user group granting of historical time section；
It calculates separately history red packet of the user group under each history red packet amount of money and checks and writes off rate；
Rate is checked and write off according to the history red packet amount of money and history red packet rate model is checked and write off to the red packet be trained.
Optionally, it is linear regression model (LRM) that the red packet, which checks and writes off rate model,.
Optionally, the red packet checks and writes off rate model are as follows:
In formula,For weight vectors, p (c) is that the corresponding red packet of red packet amount of money c checks and writes off rate, and b is constant.
Optionally, rate model is checked and write off according to the corresponding red packet of each user group respectively to determine to corresponding user group granting red packet
The red packet amount of money the step of include:
Obtain the subsidy amount of money per capita of the target user；
Red packet, which is calculated, according to the amount of money of subsidy per capita checks and writes off rate constant；
Check and write off rate constant according to the red packet, and respectively according to the corresponding red packet of each user group check and write off rate model determine to
Corresponding user group provides the red packet amount of money of red packet.
Optionally, rate constant is checked and write off according to the red packet, and rate mould is checked and write off according to the corresponding red packet of each user group respectively
Type determines that the step of providing the red packet amount of money of red packet to corresponding user group includes:
The red packet amount of money that red packet is provided to corresponding user group is determined according to the following formula:
In formula, cobFor the red packet amount of money for providing red packet to corresponding user group；λ is that red packet checks and writes off rate constant；pijIt is used for registration
Family i is in given red packet amount of money cjUnder be converted into the probability of consumption user；cjFor each possible candidate red packet amount of money.
According to the second aspect of this specification embodiment, the data processing equipment under a kind of service scenarios, the dress are provided
It sets and includes:
Module is obtained, for obtaining the user characteristics of the target user of red packet to be provided on service platform；
Computing module, for the target user to be divided into several user groups according to the user characteristics, and respectively
It calculates the corresponding red packet of each user group and checks and writes off rate model, the red packet checks and writes off rate model for characterizing user group to the red packet
The corresponding relationship checked and write off between rate and the red packet amount of money of the red packet；
Red packet provides module, determines for checking and writing off rate model according to the corresponding red packet of each user group respectively to corresponding user
The red packet amount of money of red packet is put in mass-sending, so that user when the service platform corresponds to the red packet of the red packet amount of money to each user group granting
New rate is drawn to maximize, the user La Xin rate is the total and service of the user checked and write off in each user group to red packet
The ratio between the master budget amount of money of platform granting red packet.
According to the third aspect of this specification embodiment, a kind of computer readable storage medium is provided, is stored thereon with meter
Calculation machine program realizes method described in any embodiment when the program is executed by processor.
According to the fourth aspect of this specification embodiment, a kind of computer equipment is provided, including memory, processor and deposit
The computer program that can be run on a memory and on a processor is stored up, the processor realizes any reality when executing described program
Apply method described in example.
Using this specification example scheme, target user is divided into multiple user groups, and is calculated separately to each use
The red packet amount of money for putting red packet is mass-sended at family, simplifies the pricing problem of red packet, realizes automation price, while it is flat to realize service
User's La Xin rate of platform maximizes.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
This specification can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the reality for meeting this specification
Example is applied, and is used to explain the principle of this specification together with specification.
Fig. 1 is the schematic diagram of the application scenarios of this specification one embodiment.
Fig. 2 is the flow chart of the data processing method under the service scenarios of this specification one embodiment.
Fig. 3 (a) and Fig. 3 (b) be respectively the group 1 and group 5 of this specification one embodiment the red packet amount of money with check and write off
The schematic diagram of the fitting result of rate relationship.
Fig. 4 is that the red packet of this specification one embodiment checks and writes off rate constant and draws the relation schematic diagram of new cost.
Fig. 5 is the red packet amount of money pricing scheme schematic diagram of this specification one embodiment.
Fig. 6 is the block diagram of the data processing equipment under the service scenarios of this specification one embodiment.
Fig. 7 is the structural representation of the computer equipment for implementing this specification method of this specification one embodiment
Figure.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with this specification.On the contrary, they are only and such as institute
The example of the consistent device and method of some aspects be described in detail in attached claims, this specification.
It is only to be not intended to be limiting this explanation merely for for the purpose of describing particular embodiments in the term that this specification uses
Book.The "an" of used singular, " described " and "the" are also intended to packet in this specification and in the appended claims
Most forms are included, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein is
Refer to and includes that one or more associated any or all of project listed may combine.
It will be appreciated that though various information may be described using term first, second, third, etc. in this specification, but
These information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not taking off
In the case where this specification range, the first information can also be referred to as the second information, and similarly, the second information can also be claimed
For the first information.Depending on context, word as used in this " if " can be construed to " ... when " or
" when ... " or " in response to determination ".
As shown in Figure 1, being the schematic diagram of the application scenarios of this specification one embodiment.It may include consumption in the scene
Side, service provider and service platform.Wherein, service provider can service platform (such as: public praise net, go where net, capital
East, Taobao etc.) on publication have certain values service, the service of publication may include but be not limited to garment marketing, vegetable sell
Deng services such as services, or the sale card of game points.Consumer can pay certain assets in service platform and be provided with enjoying service
The service of Fang Fabu, the assets of payment include but is not limited to all kinds of currency or the resources such as RMB, bit coin, game tokens.
Consumer and service provider can be by the corresponding application programs of respective client log-in service platform, to realize respective function
Energy.The interactive process of one embodiment may include following procedure:
Step 102: service provider issuing service information on service platform, information on services may include service name, class
Not, the information such as price, size, service content picture.
Step 104: service platform issues red packet information on this platform, and red packet refers to a kind of amount of money subsidy, and user is consuming
When red packet can be used to reducing or remitting the corresponding amount of money, red packet can be the forms such as cash red packet or coupons red packet
Red packet, red packet information may include the amount of money of red packet, using threshold (for example, how much spending amount is full can be used red packet), use
The information such as period (for example, December 20 20 days to 2018 November in 2018 is available).In general, it is issued on service platform
Red packet usually can be used for consumer's use when consuming on service platform.
Step 106: consumer browses information on services and red packet information on service platform.
Step 108: consumer gets red packet from service platform.
Step 110: consumer buys from service provider and services, and red packet can be used to be paid when purchase.
Step 112: after red packet use, carrying out red packet to service platform from service provider and check and write off.
Certainly, the sequence for each step that tripartite executes in interactive process in above-mentioned scene may not need in strict accordance with upper
Process is stated, for example, the sequence of step 1 and step 2 can be interchanged.In addition, may also further include other steps between each step,
Depending on the demand of practical application scene.It should be noted that the application scenarios of this specification embodiment are not limited to the above institute
It states, above-described application scenarios are a kind of citing.
It can be seen that by above-mentioned application scenarios by providing red packet, user can be induced to become the new use of service platform
Family, meanwhile, red packet can be used as a kind of subsidy form when being consumed on service platform, therefore also had and promoted
It is consumed on service platform into user, to experience the effect of the core function of service platform.
Based on this, this specification embodiment provides the data processing method under a kind of service scenarios, as shown in Fig. 2, described
Method can include:
Step 202: obtaining the user characteristics of the target user of red packet to be provided on service platform；
Step 204: the target user being divided into several user groups according to the user characteristics, and is calculated separately each
The corresponding red packet of a user group checks and writes off rate model, and the red packet is checked and write off rate model and checked and write off for characterizing user group to the red packet
Corresponding relationship between rate and the red packet amount of money of the red packet；
Step 206: it is determining red to corresponding user group granting that rate model being checked and write off according to the corresponding red packet of each user group respectively
The red packet amount of money of packet, so that user La Xin rate is most when the service platform corresponds to the red packet of the red packet amount of money to each user group granting
Bigization, the user La Xin rate are the total and service platform granting of the user checked and write off in each user group to red packet
The ratio between master budget amount of money of red packet.
In step 202, service platform can be online service platform, such as: public praise net, go where net, Jingdone district, Taobao
Deng, it is also possible to service platform under line, such as: market, supermarket etc..Target user is the consumer of service platform, can be by taking
Being engaged in, platform is Yu Xianxuanding, and service platform can send the red packet of certain amount of money to each target user, also, use to different target
The red packet amount of money for the red packet that family is sent may be the same or different.It is put down in practical application, target user can be in service
The user of new registration on platform, that is, time interval between registion time and current time is less than the user of preset duration, can also be with
It is user that is registered on service platform but carrying out consumption not on service platform within a preset period of time.Wherein, it presets
Period can be registion time to the current time corresponding period, when being also possible to from current time forward nearest one section
Between (for example, nearest 1 month, nearest half a year etc.).It is of course also possible to according to other pre-set service logics of service platform come
Determine target user.
The user characteristics of target user may include scene characteristic, customer acceptance degree feature and amount of money sensitivity characteristics, go back
It may include other features, such as: gender, age of consumer etc..Wherein, scene characteristic is used to indicate current service scene,
Service scenarios may include user consumed in service platform consumption time (such as: the morning, noon, afternoon), consumption place
(such as: company nearby, near residence) and the infrastructure (such as: whether free WiFi is provided) in consumption place etc..
For characterizing user to the degree of recognition of service platform, customer acceptance degree feature can service customer acceptance degree feature according to user
Behavior on platform determines that above-mentioned behavior includes: search, click, browsing, transaction, the comment etc. executed in service platform.Gold
Volume sensitivity characteristics, that is, user checks and writes off situation to the history of red packet, executed including red packet of the user to which amount of money and checks and writes off behaviour
Make, and number for checking and writing off operation etc..
In step 204, the target user can be divided into several user groups according to user characteristics.Specifically,
The decision-tree model that can respectively train the user characteristics input of each target user in advance, obtains the use of corresponding target user
Family label；The target user is divided into several user groups according to the user tag.Herein, several can be chosen
Whether user's sample checks and writes off user's sample to red packet as sample label, and obtains the corresponding use of each user's sample
Then family feature trains decision-tree model, and is used for above-mentioned user partition process.
The user characteristics of one embodiment and grouping result are as shown in the table.The embodiment be can be seen that by target user
It divides for 7 user groups, each user group has different user characteristics, for example, the user characteristics of group 1 are as follows: there is transaction
Service was bought in behavior.In another example the user characteristics of group 5 are as follows: no deal behavior, gender female are not currently in peak period use
Meal.
Red packet checks and writes off rate for characterizing ratio shared by the user checked and write off in target user to red packet.Different user group
Red packet check and write off rate may be different, therefore, it is necessary to calculate separately the corresponding red packet of each user group to check and write off rate, that is, the user group
In in the user occupancy family group that is checked and write off to red packet total number of users ratio.
Red packet is checked and write off rate model and can be obtained according to following manner: obtaining each of the introversive user group granting of historical time section
The history red packet amount of money of a red packet；It calculates separately history red packet of the user group under each history red packet amount of money and checks and writes off rate；
Rate is checked and write off according to the history red packet amount of money and history red packet rate model is checked and write off to the red packet be trained.
For example, to the history red packet amount of money of each red packet of user group granting in available nearest one month, it is assumed that point
It Wei not be 5 yuan, 10 yuan and 20 yuan.It is then possible to which calculating separately the corresponding history red packet of 5 yuan of red packets checks and writes off rate, that is, into user group
When each user provides 5 yuan of red packets, the red packet was executed in the quantity and user group for check and write off the user of operation in user group and was used
The ratio of family sum.Similarly, 10 yuan can be calculated and the corresponding history red packet of 20 yuan of red packets checks and writes off rate.Then, according to each history
The red packet amount of money and its corresponding history red packet, which check and write off rate and check and write off rate model to the red packet, to be trained.
Optionally, it is linear regression model (LRM) that the red packet, which checks and writes off rate model,.In one embodiment, it is assumed that y is red packet core
Pin rate, x are 4 dimensions being derived by the red packet amount of money, are red packet amount of money c, square c of the red packet amount of money respectively2, evolution
Logarithm log (c).The data for choosing group 1 and group 5 above in table are fitted, and the specific red packet amount of money and check and write off rate
The fitting result (for data desensitization, deleting reference axis scale) of relationship respectively as shown in Fig. 3 (a) and Fig. 3 (b), check and write off by red packet
Rate model form is as follows:
In formula,For weight vectors, p (c) is that the corresponding red packet of red packet amount of money c checks and writes off rate, and b is constant.
In step 206, can respectively by the corresponding red packet of each user group check and write off rate model substitute into it is predetermined red
The pricing formula of volume covered with gold leaf, and calculate separately the corresponding red packet amount of money of each user group when formula takes maximum.At this point, each use
Red packet of the family group under the corresponding red packet amount of money, which checks and writes off the ratio between the master budget that the sum of number provides red packet with service platform, to be obtained
Maximum value.
In one embodiment, the subsidy amount of money per capita of the target user can also be obtained；It is subsidized per capita according to described
The amount of money calculates red packet and checks and writes off rate constant；Rate constant is checked and write off according to the red packet, and respectively according to the corresponding red packet of each user group
It checks and writes off rate model and determines the red packet amount of money for providing red packet to corresponding user group.
It is directly related that red packet, which checks and writes off rate constant with the subsidy amount of money per capita,.It is bigger that red packet checks and writes off rate constant, subsidizes per capita
Cost is lower, and vice versa.The red packet of one embodiment checks and writes off rate constant and the relationship of the subsidy amount of money per capita is as shown in Figure 4.Cause
This can predefine according to business need and subsidize the amount of money per capita, determine that red packet checks and writes off rate constant further according to the subsidy amount of money per capita.
Specifically, it can first choose red packet and check and write off rate constant initial value, the amount of money be subsidized according to the calculation of initial value per capita, and will calculate
The amount of money of subsidy per capita with it is predetermined per capita subsidy amount of money setting value be compared, rate is checked and write off to red packet according to comparison result
Constant initial value is adjusted, if the calculated amount of money of subsidy per capita is greater than is subsidized amount of money setting value per capita, increases red packet
Check and write off rate constant initial value；Conversely, then reducing red packet checks and writes off rate constant initial value.Then it repeats the above process, until calculating
The amount of money of subsidy per capita and per capita subsidize amount of money setting value difference be less than preset value.
In one embodiment, the target of red packet algorithm is to solve following optimization problem:
Wherein, cj, j ∈ 1,2 ..., and k } it is each possible candidate red packet amount of money；K is total of the candidate red packet amount of money
Number；pijIndicate user i (in the case where certain context) to given red packet amount of money cjConversion ratio, i.e. user i using red packet gold
Volume is cjRed packet probability；gijIndicate user i in given red packet amount of money cjUnder expected revenus.xij∈ { 0,1 } is decision change
Amount, xijIndicate that it is c that the amount of money is sent to user i when=1jRed packet, C be service platform provide red packet master budget.
Lagrangian is constructed, former optimization problem is equivalent to:
Its problem isThere is the minimum value of x in LagrangianL, and if only if
-gij+λpijcj+ui>=0,
That is ui≥gij-λpijcj (1)
Also, because L will be minimized x, for any i, work as xijWhen=1, there is ui=gij-λpijcj(A)。
At this point, problem reduction isIt is maximized i.e. to uiIt is minimized.By formula (1) it is found that uiIt answers
Take its lower bound:
For any user i, it is assumed that give bonus amount of money c to itjIt is Income Maximum, that is, needs to take xij=1, at this moment by tying
By (A) and formula (2) it is found that gij-λpijcjIts upper bound is taken, i.e.,
Above-mentioned formula is the pricing formula of the red packet amount of money.For drawing fresh target, income is that red packet checks and writes off rate.Cause
This, can determine the red packet amount of money that red packet is provided to corresponding user group according to the following formula:
In formula, cobFor the red packet amount of money for providing red packet to corresponding user group；λ is that red packet checks and writes off rate constant；pijIt is used for registration
Family i is in given red packet amount of money cjUnder be converted into the probability of consumption user；cjFor each possible candidate red packet amount of money.One implementation
The red packet amount of money pricing scheme of example is as shown in Figure 5, it can be seen that service platform can be mass-sended to different user and put the different amount of money
Red packet, wherein the red packet amount of money for the red packet provided to each user inside each user group is identical.
Using this specification example scheme, target user is divided into multiple user groups, and is calculated separately to each use
The red packet amount of money for putting red packet is mass-sended at family, simplifies the pricing problem of red packet, realizes automation price, while it is flat to realize service
User's La Xin rate of platform maximizes.
Various technical characteristics in above embodiments can be arbitrarily combined, as long as there is no punchings for the combination between feature
Prominent or contradiction, but as space is limited, is not described one by one, thus the various technical characteristics in above embodiment it is any into
Row combination also belongs to the range of this disclosure.
As shown in fig. 6, be this specification one embodiment service scenarios under data processing equipment block diagram, the dress
It sets can include:
Module 602 is obtained, for obtaining the user characteristics of the target user of red packet to be provided on service platform；
Computing module 604 for the target user to be divided into several user groups according to the user characteristics, and divides
Each user group not being calculated, rate being checked and write off to the red packet of the red packet of the given amount of money, the red packet is checked and write off rate and used for characterizing the target
Ratio shared by the user checked and write off in family to the red packet；
Red packet provides module 606, determines for checking and writing off rate according to the corresponding red packet of each user group respectively to corresponding user
The red packet amount of money of red packet is put in mass-sending, so that user's La Xin rate of the service platform maximizes, the user La Xin rate is each
The sum of the user checked and write off in user group to red packet provides the ratio between the master budget amount of money of red packet with the service platform.
The specific details of the realization process of the function of modules and effect, which are shown in, in above-mentioned apparatus corresponds to step in the above method
Realization process, details are not described herein.
For device embodiment, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The module of explanation may or may not be physically separated, and the component shown as module can be or can also be with
It is not physical module, it can it is in one place, or may be distributed on multiple network modules.It can be according to actual
The purpose for needing to select some or all of the modules therein to realize this specification scheme.Those of ordinary skill in the art are not
In the case where making the creative labor, it can understand and implement.
The embodiment of this specification device can be applied on a computing device, such as server or intelligent terminal.Device
Embodiment can also be realized by software realization by way of hardware or software and hardware combining.Taking software implementation as an example,
As the device on a logical meaning, being will be corresponding in nonvolatile memory by the processor of file process where it
Computer program instructions are read into memory what operation was formed.For hardware view, as shown in fig. 7, being this specification device
A kind of hardware structure diagram of place computer equipment, in addition to processor 702 shown in Fig. 7, memory 704, network interface 706, with
And except nonvolatile memory 708, server or electronic equipment in embodiment where device are set generally according to the computer
Standby actual functional capability can also include other hardware, repeat no more to this.
Correspondingly, this specification embodiment also provides a kind of computer storage medium, is stored with journey in the storage medium
Sequence realizes the method in any of the above-described embodiment when described program is executed by processor.
Correspondingly, this specification embodiment also provides a kind of intelligent terminal, including memory, processor and is stored in storage
On device and the computer program that can run on a processor, the processor realize any of the above-described embodiment when executing described program
In method.
This specification embodiment can be used one or more wherein include the storage medium of program code (including but not
Be limited to magnetic disk storage, CD-ROM, optical memory etc.) on the form of computer program product implemented.Computer is available to be deposited
Storage media includes permanent and non-permanent, removable and non-removable media, can be accomplished by any method or technique letter
Breath storage.Information can be computer readable instructions, data structure, the module of program or other data.The storage of computer is situated between
The example of matter includes but is not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory
Device (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), the read-only storage of electrically erasable
Device (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM), digital versatile disc
(DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices or any other non-biography
Defeated medium, can be used for storage can be accessed by a computing device information.
Those skilled in the art will readily occur to the disclosure after considering specification and practicing specification disclosed herein
Other embodiments.The disclosure is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes
Or adaptive change follow the general principles of this disclosure and including the disclosure it is undocumented in the art known in often
Knowledge or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim point out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
The foregoing is merely the preferred embodiments of the disclosure, not to limit the disclosure, all essences in the disclosure
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of disclosure protection.
Claims (10)
1. the data processing method under a kind of service scenarios, which comprises
Obtain the user characteristics of the target user of red packet to be provided on service platform；
The target user is divided into several user groups according to the user characteristics, and it is corresponding to calculate separately each user group
Red packet check and write off rate model, the red packet checks and writes off rate model and checks and writes off rate and the red packet to the red packet for characterizing user group
The red packet amount of money between corresponding relationship；
Rate model is checked and write off according to the corresponding red packet of each user group respectively to determine to the red packet amount of money for corresponding to user group granting red packet,
So that user's La Xin rate maximizes when the service platform corresponds to the red packet of the red packet amount of money to each user group granting, the user
Drawing new rate is that the sum of the user checked and write off in each user group to red packet provides the master budget of red packet with the service platform
The ratio between amount of money.
2. according to the method described in claim 1, the target user is divided into several users according to the user characteristics
Group the step of include:
The decision-tree model that the user characteristics input of each target user is trained in advance respectively, obtains the use of corresponding target user
Family label；
The target user is divided into several user groups according to the user tag.
3. according to the method described in claim 1, the method also includes:
Obtain the history red packet amount of money of each red packet of the introversive user group granting of historical time section；
It calculates separately history red packet of the user group under each history red packet amount of money and checks and writes off rate；
Rate is checked and write off according to the history red packet amount of money and history red packet rate model is checked and write off to the red packet be trained.
4. according to the method described in claim 3, it is linear regression model (LRM) that the red packet, which checks and writes off rate model,.
5. according to the method described in claim 4, the red packet checks and writes off rate model are as follows:
In formula,For weight vectors, p (c) is that the corresponding red packet of red packet amount of money c checks and writes off rate, and b is constant.
6. checking and writing off rate mould according to the corresponding red packet of each user group respectively to method described in 5 any one according to claim 1
Type determines that the step of providing the red packet amount of money of red packet to corresponding user group includes:
Obtain the subsidy amount of money per capita of the target user；
Red packet, which is calculated, according to the amount of money of subsidy per capita checks and writes off rate constant；
Rate constant is checked and write off according to the red packet, and rate model is checked and write off according to the corresponding red packet of each user group respectively and is determined to correspondence
The red packet amount of money of user group granting red packet.
7. according to the method described in claim 6, checking and writing off rate constant according to the red packet, and corresponding according to each user group respectively
Red packet check and write off rate model and determine that the step of providing the red packet amount of money of red packet to corresponding user group includes:
The red packet amount of money that red packet is provided to corresponding user group is determined according to the following formula:
In formula, cobFor the red packet amount of money for providing red packet to corresponding user group；λ is that red packet checks and writes off rate constant；pijExist for registration user i
Given red packet amount of money cjUnder be converted into the probability of consumption user；cjFor each possible candidate red packet amount of money.
8. the data processing equipment under a kind of service scenarios, described device include:
Module is obtained, for obtaining the user characteristics of the target user of red packet to be provided on service platform；
Computing module for the target user to be divided into several user groups according to the user characteristics, and calculates separately
The corresponding red packet of each user group checks and writes off rate model, and the red packet checks and writes off rate model for characterizing user group to the core of the red packet
Corresponding relationship between pin rate and the red packet amount of money of the red packet；
Red packet provides module, determines for checking and writing off rate model according to the corresponding red packet of each user group respectively to corresponding user's mass-sending
The red packet amount of money of red packet is put, so that user La Xin when the service platform corresponds to the red packet of the red packet amount of money to each user group granting
Rate maximizes, and the user La Xin rate is the sum and the service platform of the user checked and write off in each user group to red packet
Provide the ratio between the master budget amount of money of red packet.
9. a kind of computer readable storage medium, is stored thereon with computer program, power is realized when which is executed by processor
Benefit requires method described in 1 to 7 any one.
10. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, the processor realize method described in claim 1 to 7 any one when executing described program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910001961.7A CN109858952A (en) | 2019-01-02 | 2019-01-02 | Data processing method and device under service scenarios |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910001961.7A CN109858952A (en) | 2019-01-02 | 2019-01-02 | Data processing method and device under service scenarios |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109858952A true CN109858952A (en) | 2019-06-07 |
Family
ID=66893644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910001961.7A Pending CN109858952A (en) | 2019-01-02 | 2019-01-02 | Data processing method and device under service scenarios |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109858952A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443636A (en) * | 2019-07-15 | 2019-11-12 | 阿里巴巴集团控股有限公司 | Resource is distributed between user to regulate and control the method and apparatus of its e-payment behavior |
| CN113724454A (en) * | 2021-08-25 | 2021-11-30 | 上海擎朗智能科技有限公司 | Interaction method of mobile equipment, device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140104620A (en) * | 2013-02-20 | 2014-08-29 | 이태호 | A mobile discount coupon system and the service providing method using the same |
| CN107578281A (en) * | 2017-08-31 | 2018-01-12 | 湖南大学 | User preferential certificate behavior prediction method and model building method under e-commerce environment |
| CN108154288A (en) * | 2017-12-07 | 2018-06-12 | 北京三快在线科技有限公司 | New user subsidizes computational methods, device, electronic equipment and the storage medium of strategy |
| CN108416614A (en) * | 2018-01-31 | 2018-08-17 | 北京三快在线科技有限公司 | Sending method, device, electronic equipment and the storage medium of virtual objects |
| CN108520443A (en) * | 2018-04-11 | 2018-09-11 | 口碑(上海)信息技术有限公司 | The distribution method of intelligent certificate, device and check and write off method, apparatus using intelligent certificate |
-
2019
- 2019-01-02 CN CN201910001961.7A patent/CN109858952A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140104620A (en) * | 2013-02-20 | 2014-08-29 | 이태호 | A mobile discount coupon system and the service providing method using the same |
| CN107578281A (en) * | 2017-08-31 | 2018-01-12 | 湖南大学 | User preferential certificate behavior prediction method and model building method under e-commerce environment |
| CN108154288A (en) * | 2017-12-07 | 2018-06-12 | 北京三快在线科技有限公司 | New user subsidizes computational methods, device, electronic equipment and the storage medium of strategy |
| CN108416614A (en) * | 2018-01-31 | 2018-08-17 | 北京三快在线科技有限公司 | Sending method, device, electronic equipment and the storage medium of virtual objects |
| CN108520443A (en) * | 2018-04-11 | 2018-09-11 | 口碑(上海)信息技术有限公司 | The distribution method of intelligent certificate, device and check and write off method, apparatus using intelligent certificate |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443636A (en) * | 2019-07-15 | 2019-11-12 | 阿里巴巴集团控股有限公司 | Resource is distributed between user to regulate and control the method and apparatus of its e-payment behavior |
| CN113724454A (en) * | 2021-08-25 | 2021-11-30 | 上海擎朗智能科技有限公司 | Interaction method of mobile equipment, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10936986B2 (en) | Generation of engagement and support recommendations for content creators | |
| US20110137994A1 (en) | System and method of a purchasing information platform | |
| CN101379522A (en) | Ad publisher performance and mitigation of click fraud | |
| JP2004534313A (en) | Method and system for determining market demand based on consumer donations | |
| CN111586162A (en) | Information pushing method and system | |
| CN102132285A (en) | Method and system of automatically setting and changing price for online content selling | |
| CN103460235A (en) | Offering social deals based on activities of connections in a social networking system | |
| CN108416616A (en) | The sort method and device of complaints and denunciation classification | |
| CN108777701A (en) | A kind of method and device of determining receiver | |
| CN110033120A (en) | For providing the method and device that risk profile energizes service for trade company | |
| CN112215448A (en) | Method and device for distributing customer service | |
| CN108416684A (en) | A kind of credibility appraisal procedure, device and the server of account main body | |
| JP6679648B2 (en) | Information processing device, information processing method, information processing program, determination device, determination method, and determination program | |
| CN111465953B (en) | Device and method for deriving social relationship between accounts based on transaction ledger | |
| CN112132634A (en) | Virtual gift resource distribution method and device, computer equipment and storage medium | |
| CN109858952A (en) | Data processing method and device under service scenarios | |
| CN112767046B (en) | Method and device for constructing non-standardized service product | |
| CN104751234B (en) | A kind of prediction technique and device of user's assets | |
| KR20220153899A (en) | A providing method for providing a reward providing service based on a purchase contribution of review content and a system implementing the same | |
| CN108769208A (en) | Specific user's identification and information-pushing method and device | |
| CN116361542A (en) | Product recommendation method, device, computer equipment and storage medium | |
| CN111259242B (en) | Data processing method, device, storage medium and equipment | |
| CN113191570A (en) | Fund planning recommendation method, device and equipment based on deep learning | |
| CA3098792A1 (en) | Systems and methods for customization of reviews | |
| CN112330373A (en) | User behavior analysis method and device and computer readable storage medium |
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: 20190607 |
|
| RJ01 | Rejection of invention patent application after publication |