CN110111090A - A kind of distribution method and device of electronics red packet - Google Patents
A kind of distribution method and device of electronics red packet Download PDFInfo
- Publication number
- CN110111090A CN110111090A CN201910232926.6A CN201910232926A CN110111090A CN 110111090 A CN110111090 A CN 110111090A CN 201910232926 A CN201910232926 A CN 201910232926A CN 110111090 A CN110111090 A CN 110111090A
- Authority
- CN
- China
- Prior art keywords
- red packet
- electronics red
- target user
- sample
- conversion
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/04—Payment circuits
- G06Q20/06—Private payment circuits, e.g. involving electronic currency used among participants of a common payment scheme
- G06Q20/065—Private payment circuits, e.g. involving electronic currency used among participants of a common payment scheme using e-cash
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
This application discloses the distribution methods and device of a kind of electronics red packet, it is related to electronic information technical field, user can be exported based on the Conversion Model of building using the conversion ratio of electronics red packet with the relationship between the amount of money variation for providing electronics red packet, so that user obtains the optimum subsidy amount of money, and theoretically guarantee that the return rate of electronics red packet maximizes.The described method includes: obtaining multiple dimensional characteristics of target user；Multiple dimensional characteristics of the target user are input to the Conversion Model constructed in advance, obtain the anticipation function expression formula suitable for target user；According to the anticipation function expression formula suitable for target user, the corresponding amount of money for providing electronics red packet of the target user is determined；The electronics red packet of the amount of money is provided to the target user.
Description
Technical field
This application involves electronic information technical fields, more particularly to the distribution method and device of a kind of electronics red packet.
Background technique
In the mobile interchange epoch, with the rapid development of e-commerce technology, the network platform has become that people are daily to disappear
The important tool taken.In order to promote to consume, businessman often by way of providing electronics red packet to user, is given certain
The amount of money subsidy, attract new user be added to platform consumption.Customer is attracted by using electronics red packet, reach stimulation user into
The purpose of row consumption has become businessman's marketing methods important at present.User is based on when being consumed using electronics red packet
It on the basis of goods amount, is handled by electronics red packet of the staff to user, and it is additional to inform that user needs to pay
The amount of money completes the payment process of commodity.
In the related technology, businessman can use some operation rules to do determining for electronics red packet when providing electronics red packet
Valence is logged in lower than 2 times for one month for example, being fixed a price based on the frequency that user logs in platform as rule for electronics red packet
User is low frequent user, and logging within one month more than 10 times is high frequency user, and low frequent user subsidizes a little amount of money more, and high frequency user is few
Subsidize a little amount of money.
In the implementation of the present invention, inventor find the relevant technologies the prior art has at least the following problems:
The purpose of merchant issued electronics red packet is that user can use electronics red packet during buying commodity, promotes to use
Family consumption.After the electronics red packet after artificial price is issued to target user, whether user is consumed using electronics red packet
And user the case where being consumed using electronics red packet can be influenced user to a certain extent and provide electronics red packet again
The amount of money, if user does not use or is rarely employed electronics red packet and consumes, even if the electronics red packet amount of money manually fixed a price
It is high again, the conversion ratio that user uses electronics red packet can not be also promoted, since the price of the provided electronics red packet of different user is people
Work experience is determined, so that the price of electronics red packet is unreasonable, can not theoretically guarantee that the return rate of electronics red packet maximizes.
Summary of the invention
In view of this, main purpose is to solve existing this application provides the distribution method and device of a kind of electronics red packet
There is the price of electronics red packet in technology unreasonable, cannot theoretically guarantee the maximized problem of the return rate of electronics red packet.
On one side according to the application, a kind of distribution method of electronics red packet is provided, this method comprises:
Obtain multiple dimensional characteristics of target user；
Multiple dimensional characteristics of the target user are input to the Conversion Model constructed in advance, obtain being suitable for target
The anticipation function expression formula of user, wherein the Conversion Model exports anticipation function table based on multiple dimensional characteristics of input
Up to formula, the anticipation function expression formula is used to describe user using the conversion ratio of electronics red packet as the granting electronics red packet amount of money becomes
Relationship between change；
According to the anticipation function expression formula suitable for target user, determine that the corresponding granting electronics of the target user is red
The amount of money of packet；
The electronics red packet of the amount of money is provided to the target user.
Further, in the conversion ratio mould for being input to multiple dimensional characteristics of the target user and constructing in advance
Type, before obtaining the anticipation function expression formula suitable for target user, the method also includes:
Obtain multiple dimensional characteristics of sample of users；
It is identified based on the sample of users marked in advance using the conversion of electronics red packet, by multiple dimensions of the sample of users
Feature is input in default learning model and is trained, and constructs Conversion Model.
Further, described to be identified based on the sample of users marked in advance using the conversion of electronics red packet, by the sample
Multiple dimensional characteristics of user, which are input in default learning model, to be trained, and building Conversion Model includes:
It is identified based on the sample of users marked in advance using the conversion of electronics red packet, discrete spy is carried out to conversion mark
Value indicative coding, obtains the encoded radio of sample of users；
Using each dimensional characteristics of the sample of users as a characteristic component, each characteristic component is introduced and is assisted
Vector；
Bring the encoded radio of the sample of users and the auxiliary vector into default learning model corresponding objective function
In be trained, construct Conversion Model.
Further, described to be identified based on the sample of users marked in advance using the conversion of electronics red packet, to the conversion
Mark carries out Discrete Eigenvalue coding, and the encoded radio for obtaining sample of users includes:
If sample of users is identified as positive sample using the conversion of electronics red packet, Discrete Eigenvalue is carried out to the positive sample
Coding, obtains the first encoded radio of sample of users；
If sample of users is identified as negative sample using the conversion of electronics red packet, Discrete Eigenvalue is carried out to the negative sample
Coding, obtains the second encoded radio of sample of users.
Further, described to bring the encoded radio of the sample of users and the auxiliary vector into default learning model pair
It is trained in the objective function answered, building Conversion Model includes:
Using the auxiliary vector as the input feature vector of the corresponding objective function of the default learning model, according to described defeated
Enter feature and generates predicted value；
Using the encoded radio of the sample of users as the output feature of the corresponding objective function of the default learning model, root
Actual value is generated according to the output feature；
According to the predicted value and the actual value, iteration updates the weight parameter of the objective function, building
Conversion Model.
Further, the anticipation function expression formula for being suitable for target user according to, determines the target user
The corresponding amount of money for providing electronics red packet includes:
The historical information that target user provides electronics red packet is obtained, record has history to provide electronics red in the historical information
The amount of money of packet；
According to the anticipation function expression formula suitable for target user, the amount of money institute for searching history granting electronics red packet is right
Target user is answered to use the conversion ratio of electronics red packet；
Based on history provide electronics red packet the amount of money corresponding to target user use electronics red packet conversion ratio, determine described in
The corresponding amount of money for providing electronics red packet of target user.
On the other hand according to the application, a kind of dispensing apparatus of electronics red packet is provided, which includes:
First acquisition unit, for obtaining multiple dimensional characteristics of target user；
Predicting unit, for multiple dimensional characteristics of the target user to be input to the Conversion Model constructed in advance,
Obtain the anticipation function expression formula suitable for target user, wherein multiple dimensional characteristics of the Conversion Model based on input
Anticipation function expression formula is exported, the anticipation function expression formula is used to describe user using the conversion ratio of electronics red packet with granting
Relationship between the variation of the electronics red packet amount of money；
Determination unit, for determining the target user according to the anticipation function expression formula for being suitable for target user
The corresponding amount of money for providing electronics red packet；
Issuing unit, for providing the electronics red packet of the amount of money to the target user.
Further, described device further include:
Second acquisition unit, for multiple dimensional characteristics of the target user to be input to turn constructed in advance described
Rate model obtains multiple dimensional characteristics of sample of users before obtaining the anticipation function expression formula suitable for target user；
Construction unit, for being identified based on the sample of users marked in advance using the conversion of electronics red packet, by the sample
Multiple dimensional characteristics of user, which are input in default learning model, to be trained, and Conversion Model is constructed.
Further, the construction unit includes:
Coding module, for being identified based on the sample of users marked in advance using the conversion of electronics red packet, to the conversion
Mark carries out Discrete Eigenvalue coding, obtains the encoded radio of sample of users；
Module is introduced, for using each dimensional characteristics of the sample of users as a characteristic component, to each spy
It levies component and introduces auxiliary vector；
Module is constructed, for bringing the encoded radio of the sample of users and the auxiliary vector into default learning model pair
It is trained in the objective function answered, constructs Conversion Model.
Further, the coding module, if be positive specifically for sample of users using the conversion mark of electronics red packet
Sample carries out Discrete Eigenvalue coding to the positive sample, obtains the first encoded radio of sample of users；
The coding module is identified as negative sample using the conversion of electronics red packet if being specifically also used to sample of users, right
The negative sample carries out Discrete Eigenvalue coding, obtains the second encoded radio of sample of users.
Further, the building module is specifically used for corresponding using the auxiliary vector as the default learning model
Objective function input feature vector, according to the input feature vector generate predicted value；
The building module is specifically also used to corresponding using the encoded radio of the sample of users as the default learning model
Objective function output feature, according to the output feature generate actual value；
The building module is specifically also used to according to the predicted value and the actual value, described in iteration updates
The weight parameter of objective function constructs Conversion Model.
Further, the determination unit includes:
Module is obtained, the historical information of electronics red packet is provided for obtaining target user, recording in the historical information has
The amount of money of history granting electronics red packet；
Searching module, for searching history and providing electronics according to the anticipation function expression formula for being suitable for target user
Target user corresponding to the amount of money of red packet uses the conversion ratio of electronics red packet；
Determining module is turned for being provided target user corresponding to the amount of money of electronics red packet based on history using electronics red packet
Rate determines the corresponding amount of money for providing electronics red packet of the target user.
According to the application another aspect, a kind of storage equipment is provided, computer program, described program are stored thereon with
The distribution method of above-mentioned electronics red packet is realized when being executed by processor.
According to the application another aspect, a kind of dispensing apparatus of electronics red packet, including storage equipment, processor are provided
And the computer program that can be run on a storage device and on a processor is stored, the processor is realized when executing described program
The distribution method of above-mentioned electronics red packet.
By above-mentioned technical proposal, a kind of distribution method, device and the equipment of electronics red packet provided by the present application are and current
The price of electronics red packet is compared by the releasing mode of the fixed electronics red packet of artificial experience, and the application is in view of target user's
Multiple dimensional characteristics can export anticipation function table based on the different dimensions feature of input by the Conversion Model constructed in advance
Up to formula, which is used to describe user using the conversion ratio of electronics red packet as the amount of money for providing electronics red packet becomes
Relationship between change, and by the corresponding amount of money for providing electronics red packet of target user that anticipation function expression formula determines, the electronics
The amount of money of red packet can guarantee that target user is maximized using the conversion ratio of electronics red packet, so that target user obtains optimum subsidy
The amount of money so that user be promoted to consume using red packet, and theoretically improves the return rate of electronics red packet.
Above description is only the general introduction of technical scheme, in order to better understand the technological means of the application,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects, features and advantages of the application can
It is clearer and more comprehensible, below the special specific embodiment for lifting the application.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the application
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows a kind of flow diagram of the distribution method of electronics red packet provided by the embodiments of the present application；
Fig. 2 shows the flow diagrams of the distribution method of another electronics red packet provided by the embodiments of the present application；
Fig. 3 shows a kind of structural schematic diagram of the dispensing apparatus of electronics red packet provided by the embodiments of the present application；
Fig. 4 shows the apparatus structure schematic diagram of the granting of another electronics red packet provided by the embodiments of the present application.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Currently based on the releasing mode of existing electronics red packet, usual high frequency user can subsidize a little amount of money less, and low frequent user is more
A little amount of money are subsidized, however, the essence for providing electronics red packet is that user is promoted to consume using electronics red packet, due to different user
The price of provided electronics red packet is that artificial experience is determined, so that the price of electronics red packet is unreasonable, can not theoretically be protected
The return rate for demonstrate,proving electronics red packet maximizes, that is to say, that if user does not use or be rarely employed electronics red packet, even if manually
The electronics red packet amount of money of price is high again, can not also promote the conversion ratio that user uses electronics red packet.
In order to solve this problem, the distribution method for present embodiments providing a kind of electronics red packet, as shown in Figure 1, this method
Include the following steps:
101, multiple dimensional characteristics of target user are obtained.
Wherein, multiple dimensional characteristics of target user may include but be not limited to target user's essential information, target is used
Family uses electronics to the degree of recognition of electronics red packet granting platform, target user to the susceptibility of the electronics red packet amount of money, target user
The scene of red packet and target user provide the amount of money etc. of electronics red packet, and target user's essential information can be the property of target user
Not, age, occupation, consumption, the locating age level etc. for providing in electronics red packet platform, can specifically log in conjunction with user
The account information that electronics red packet provides platform is determined, and target user can be target user couple to the susceptibility of electronics red packet
To be issued to the service condition of the electronics red packet of user account, specifically electronics red packet or purchase can be got with combining target user
The case where electronics red packet, target user carry out payment times etc. using electronics red packet and are determined, and target user is to electronics red packet
The degree of recognition for providing platform can provide for target user electronics red packet evaluation, the use habit etc. of platform, can specifically tie
It closes target user to be determined using the historical trading number of platform, transaction evaluation, recommendation click condition etc., target user uses
The scene of electronics red packet can pay the social scene such as scene for application platform on scene of doing shopping under line, line, can specifically combine
Locating network state when time of the target user using electronics red packet, the place using electronics red packet and use photoelectron red packet
It is determined, the amount of money that target user provides electronics red packet is the amount of money being issued in target user's logon account.
In this step, target user is the user of unknown electronics red packet service condition, due to multiple dimensions of target user
Whether degree feature uses electronics red packet to have predictive effect target user, approves for example, providing platform for electronics red packet
It is high using the probability of electronics red packet to spend the high target user target user low compared to degree of recognition, for the mesh of electronics red packet sensitivity
It is high using the probability of electronics red packet compared to the target user insensitive for electronics red packet to mark user, so using by obtaining target
Multiple dimensional characteristics at family are equivalent to subsequent prediction target user using the preparation of the conversion ratio of electronics red packet, thus by pre-
Measure the basis for pricing that target user provide using the conversion ratio of electronics red packet the electronics red packet amount of money.
102, multiple dimensional characteristics of the target user are input to the Conversion Model constructed in advance, are suitable for
The anticipation function expression formula of target user.
In this step, multiple dimensional characteristics output anticipation function expression of the Conversion Model constructed in advance based on input
Formula, the anticipation function expression formula are used to describe user using the conversion ratio of electronics red packet as the granting electronics red packet amount of money changes it
Between relationship, for different target users, the multiple dimensional characteristics acquired are not also identical, thus output be suitable for target
The anticipation function expression formula of user is not also identical.
103, it according to the anticipation function expression formula for being suitable for target user, determines that the target user is corresponding and provides electricity
The amount of money of sub- red packet.
It in this step, is multiple dimensional characteristics for target user suitable for the anticipation function expression formula of target user
Obtain be used to describe target user using electronics red packet conversion ratio with provide the electronics red packet amount of money variation between relationship,
Since target user is higher using the conversion ratio of electronics red packet, user is bigger using the probability of red packet, can choose conversion ratio most
The amount of money that electronics red packet is provided at high point is set as the corresponding amount of money for providing electronics red packet of target user, if target user certainly
Using electronics red packet conversion ratio highest point when to provide the amount of money of electronics red packet be more than budget, can also be directly by electronics red packet gold
Volume budget peak is set as the corresponding amount of money for providing electronics red packet of target user, and it is red using electronics to be also based on target user
Packet conversion ratio promotes situation the corresponding amount of money for providing electronics red packet of target user is arranged, specifically can be with here without limiting
The case where providing electronics red packet according to target user is configured.
It should be noted that being examined by the corresponding amount of money for providing electronics red packet of target user determined by anticipation function expression formula
The characteristic dimension for considering target user, for using the lower target user of electronics red packet frequency, not using electronics red packet
Conversion ratio is higher, provides the higher target user of the electronics red packet amount of money for some instead, is got over using the conversion ratio of electronics red packet
It is high.
104, Xiang Suoshu target user provides the electronics red packet of the amount of money.
Since electronics red packet is equivalent to a kind of amount of money subsidy that platform provides to target user, target user consumption when
Red packet can be used to reduce or remit the corresponding amount of money in time, and the form for providing electronics red packet to target user may include but not limit to
In discount coupon, completely subtract the forms such as certificate, red packet.
A kind of distribution method of electronics red packet provided by the present application, the price with current electronics red packet are by artificial experience institute
The releasing mode of fixed electronics red packet is compared, and the application considers multiple dimensional characteristics of target user, can pass through preparatory structure
The Conversion Model built exports anticipation function expression formula based on the different dimensions feature of input, and the anticipation function expression formula is for retouching
User is stated using the conversion ratio of electronics red packet with the relationship between the amount of money variation for providing electronics red packet, and passes through anticipation function
The corresponding amount of money for providing electronics red packet of the target user that expression formula determines, the amount of money of the electronics red packet can guarantee that target user makes
It is maximized with the conversion ratio of electronics red packet, so that target user obtains the optimum subsidy amount of money, so that user be promoted to disappear using red packet
Take, and theoretically improves the return rate of electronics red packet.
Further, as the refinement and extension of above-described embodiment specific embodiment, in order to completely illustrate the present embodiment
Specific implementation process, as shown in Fig. 2, the embodiment of the present application provides the distribution method of another electronics red packet, this method packet
Include following steps:
201, multiple dimensional characteristics of sample of users are obtained.
In this step, sample of users is the user of known electronic red packet service condition, and multiple dimensions of sample of users are special
The specific descriptions of sign are referred to multiple dimensional characteristics of target user in step 101, and details are herein without repeating.
It is understood that sample of users known electronic red packet service condition specifically can use electronics based on sample of users
The conversion of red packet identifies to determine, for example, each electronics red packet to be provided to the sample of users mark for having got electronics red packet in platform
It is denoted as and gets mark, after the sample of users for getting electronics red packet is consumed using electronics red packet, mix the sample with getting for family
Mark is updated to conversion mark, shows that sample of users has used electronics red packet, and the sample of users for getting electronics red packet is not
Using electronics red packet, sample of users people, which remains as, gets mark, can also provide in platform each electronics red packet and get electricity
The conversion mark of the sample of users of sub- red packet and unused electronics red packet is labeled as negative sample, and electronics red packet is provided in platform
It gets and using the conversion of the sample of users of electronics red packet mark labeled as positive sample, here without limiting.
202, it is identified based on the sample of users marked in advance using the conversion of electronics red packet, by the multiple of the sample of users
Dimensional characteristics are input in default learning model and are trained, and construct Conversion Model.
It is understood that the service condition based on known electronic red packet, mixes the sample with multiple dimensional characteristics conducts at family
Training sample, the training sample inputted by continuous iteration export anticipation function expression formula, and the function expression is for retouching
User is stated using the conversion ratio of electronics red packet with the relationship provided between the variation of the electronics red packet amount of money.
In this step, on the one hand the process specifically trained uses electronics red packet based on the sample of users marked in advance
Conversion mark, identifies conversion and carries out Discrete Eigenvalue coding, obtain the encoded radio of sample of users, which is equivalent to sample
User uses the expression of electronics red packet situation, on the other hand using each dimensional characteristics of sample of users as a characteristic component,
Auxiliary vector is introduced to each characteristic component, which is equivalent to the interaction coefficent between characteristic component, and by sample
The encoded radio and auxiliary vector of user is brought into the corresponding objective function of default learning model and is trained, and conversion ratio mould is constructed
Type.
It is above-mentioned to be identified based on the sample of users marked in advance using the conversion of electronics red packet, conversion mark is carried out discrete
During Coding pattern features, since the sample of users marked in advance can show that target is used using the conversion mark of electronics red packet
Family uses the case where electronics red packet, if sample of users is identified as positive sample using the conversion of electronics red packet, illustrates that user gets
And electronics red packet is used, Discrete Eigenvalue coding further is carried out to positive sample, obtains the first encoded radio of sample of users；Instead
It illustrates that user gets and electronics red packet is not used if sample of users is identified as negative sample using the conversion of electronics red packet, into
One step carries out Discrete Eigenvalue coding to negative sample, obtains the second encoded radio of sample of users.Here the first encoded radio and
Two encoded radios are with the different coding value for distinguishing effect, for example, the first encoded radio is 001, the second encoded radio is 100, here
To the particular content of encoded radio without limiting.
In this step, preset learning model select can for include but is not limited to FM model, LR model, CO-FM
Model etc. has the model of learning effect, here without limiting.
It is above-mentioned to be brought into the corresponding objective function of default learning model in the encoded radio for mixing the sample with family and auxiliary vector
It is trained, during constructing Conversion Model, the objective function as used in difference default learning model is different,
After the multiple dimensional characteristics for mixing the sample with family are input to default learning model, using the auxiliary vector of introducing as default study mould
The input feature vector of the corresponding objective function of type generates predicted value according to input feature vector, which is equivalent to the defeated of objective function
It is worth out；And output feature of the encoded radio at family as the default corresponding objective function of learning model is mixed the sample with, and according to described
It exports feature and generates actual value, which is equivalent to the input value of objective function；According to predicted value and actual value, repetition changes
In generation, updates the weight parameter of objective function, constructs Conversion Model.
It should be noted that being learned since the default corresponding objective function of learning model of difference is different using difference is default
It is also not identical to practise the Conversion Model that model finally constructs, for example, the conversion ratio finally constructed for FM model and LR model
Change smoother, such as DT model of the model based on tree using electronics red packet conversion ratio with the variation of the electronics red packet amount of money in model
And changed with the variation of the electronics red packet amount of money using electronics red packet conversion ratio in the Conversion Model of the final framework of GBDT model
Be serrated variation or non-monotonic variation, in order to more exchange premium electronics red packet application scenarios expection business, it is preferable to use FM model,
Here the objective function of FM model are as follows:
Wherein, xiFor the multiple dimensional characteristics for inputting target user, υiFor each dimensional characteristics x with target useriIt is corresponding
Auxiliary vector, and each auxiliary vector include several Expressive Features the factor, ωiFor the weight parameter of objective function.
It should be noted that although FM model can reflect to a certain extent as the variation of the electronics red packet amount of money uses electronics
The case where red packet conversion ratio smooth change, but FM model does not account for cross characteristic more than two times, is substantially a line
Property model, can not capture the characteristic effect of high-order nonlinear.
203, multiple dimensional characteristics of target user are obtained.
In this step, the specific descriptions of multiple dimensional characteristics of target user are identical as step 101, herein without superfluous
It states.
It should be noted that in order to increase the ability to express that target user provides electronics red packet amount of money feature, in subsequent instruction
Practice Conversion Model during, the derivative feature of the red packet amount of money can be added, for example, the red packet amount of money square, the red packet amount of money
Logarithm etc..
204, multiple dimensional characteristics of the target user are input to the Conversion Model constructed in advance, are suitable for
The anticipation function expression formula of target user.
Specifically, the learning algorithm as used by the Conversion Model of building is different, so that being based on Conversion Model institute
The anticipation function expression formula of output may be different, for example, anticipation function expression formula may be the gold with electronics red packet
Volume increases and the smooth curve of conversion ratio increase, it is also possible to which with the amount of money increase of electronics red packet, conversion ratio is not dull
Jagged equity curve, it is also possible to as the amount of money of electronics red packet increases and the curve etc. of conversion ratio first increases and then decreases, into one
Multiple dimensional characteristics based on input different target user are walked, the anticipation function expression formula suitable for target user is obtained.
205, the historical information that target user provides electronics red packet is obtained.
Wherein, target user provides the historical information of electronics red packet and may include but be not limited to target user's history and get
The time of electronics red packet, history provide the amount of money of electronics red packet, target user uses time, place and the use of electronics red packet
The number etc. of electronics red packet, for example, user A got 20 red packets that subtract 5 January 1, and January 2 in Meituan platform using should
Electronics red packet.
206, according to the anticipation function expression formula for being suitable for target user, the amount of money that history provides electronics red packet is searched
Corresponding target user uses the conversion ratio of electronics red packet.
In this step, make under the amount of money for having each electronics red packet suitable for the anticipation function expression formula record of target user
It certainly also include being turned under the amount of money of target user's history granting electronics red packet using electronics red packet with the conversion ratio of electronics red packet
Rate further searches for history and provides the conversion ratio that target user corresponding to the amount of money of electronics red packet uses electronics red packet, this is gone through
History provides target user corresponding to the amount of money of electronics red packet can be from reflection target to a certain degree using the conversion ratio of electronics red packet
User uses the case where electronics red packet, and conversion ratio is higher, illustrates that user is higher using the probability of electronics red packet.
207, the conversion ratio that target user corresponding to the amount of money of electronics red packet uses electronics red packet is provided based on history, is determined
The corresponding amount of money for providing electronics red packet of the target user.
In this step, no matter user using the frequency of electronics red packet is how many, by all may be used in anticipation function expression formula
The conversion ratio that target user corresponding to the amount of money of electronics red packet uses electronics red packet is provided to find each history, if with
Family is lower using the frequency of electronics red packet, then searching to obtain target user uses the conversion ratio quantity of electronics red packet relatively
It is few, if user is higher using the amount of money of electronics red packet, search to obtain the conversion ratio that target user uses electronics red packet
Relatively more, each history here provides the conversion ratio that target user corresponding to the amount of money of electronics red packet uses electronics red packet
It all can serve as the reference frame of the corresponding amount of money for providing electronics red packet of subsequent determining target user.
For example, user A is higher than user B using the frequency of electronics red packet, user A is when providing the electronics red packet amount of money is 1 yuan
Conversion ratio using electronics red packet is 3.1, and user A is 5.0 using the conversion ratio of electronics red packet when providing 2 yuan, and user B exists
It is 1.0 using the conversion ratio of electronics red packet that the electronics red packet amount of money, which is provided, when being 1 yuan, and user B uses electronics red packet when providing 2 yuan
Conversion ratio be 2.0, so, user A compared to user B using electronics red packet conversion ratio promoted it is very fast, based on target use
Family determines the amount of money for providing electronics red packet using the conversion ratio size of electronics red packet, and correspondence is mentioned raised using red packet conversion ratio
Target user should keep or give more red packet amount of money, to improve the return rate of electronics red packet.
208, Xiang Suoshu target user provides the electronics red packet of the amount of money.
It is understood that making during providing the electronics red packet of the amount of money to target user in order to improve target user
With the conversion ratio of electronics red packet, the granting form of electronics red packet can also be set, for example, for lower using electronics red packet frequency
User provide the electronics red packet quantity of the amount of money and be more than the electronics red packet for providing the amount of money using the higher user of electronics red packet frequency
Quantity, and then promote to go using the lower user of electronics red packet frequency using electronics red packet.
Further, the specific implementation as Fig. 1 the method, the embodiment of the present application provide a kind of hair of electronics red packet
Device is put, as shown in figure 3, described device includes: first acquisition unit 31, predicting unit 32, determination unit 33, issuing unit
34。
First acquisition unit 31 can be used for obtaining multiple dimensional characteristics of target user；
Predicting unit 32 can be used for multiple dimensional characteristics of the target user being input to the conversion ratio constructed in advance
Model obtains the anticipation function expression formula suitable for target user, wherein multiple dimensions of the Conversion Model based on input
Feature export anticipation function expression formula, the anticipation function expression formula be used for describe user using electronics red packet conversion ratio with
Provide the relationship between the variation of the electronics red packet amount of money；
Determination unit 33 can be used for determining the mesh according to the anticipation function expression formula for being suitable for target user
Mark the corresponding amount of money for providing electronics red packet of user；
Issuing unit 34 can be used for providing the electronics red packet of the amount of money to the target user.
The dispensing apparatus of electronics red packet provided by the embodiments of the present application, the price with current electronics red packet is by artificial experience
The releasing mode of fixed electronics red packet compare, the application considers multiple dimensional characteristics of target user, can be by preparatory
The Conversion Model of building exports anticipation function expression formula based on the different dimensions feature of input, which is used for
User is described using the conversion ratio of electronics red packet with the relationship between the amount of money variation for providing electronics red packet, and by prediction letter
The corresponding amount of money for providing electronics red packet of the target user that number expression formula determines, the amount of money of the electronics red packet can guarantee target user
It is maximized using the conversion ratio of electronics red packet, so that target user obtains the optimum subsidy amount of money, so that user be promoted to use red packet
Consumption, and theoretically improve the return rate of electronics red packet.
In specific application scenarios, as shown in figure 4, described device further include:
Second acquisition unit 35 can be used for that multiple dimensional characteristics of the target user are input to preparatory structure described
The Conversion Model built obtains multiple dimensions of sample of users before obtaining the anticipation function expression formula suitable for target user
Feature；
Construction unit 36 can be used for identifying based on the sample of users marked in advance using the conversion of electronics red packet, by institute
The multiple dimensional characteristics for stating sample of users, which are input in default learning model, to be trained, and Conversion Model is constructed.
Further, the construction unit 36 includes:
Coding module 361 can be used for identifying based on the sample of users marked in advance using the conversion of electronics red packet, to institute
It states conversion mark and carries out Discrete Eigenvalue coding, obtain the encoded radio of sample of users；
Module 362 is introduced, can be used for using each dimensional characteristics of the sample of users as a characteristic component, to every
One characteristic component introduces auxiliary vector；
Module 363 is constructed, can be used for bringing the encoded radio of the sample of users and the auxiliary vector into default
It practises and being trained in the corresponding objective function of model, construct Conversion Model.
Further, the coding module 361, if specifically can be used for the conversion mark that sample of users uses electronics red packet
Knowing is positive sample, carries out Discrete Eigenvalue coding to the positive sample, obtains the first encoded radio of sample of users；
The coding module 361 is negative if specifically can be also used for sample of users using the conversion mark of electronics red packet
Sample carries out Discrete Eigenvalue coding to the negative sample, obtains the second encoded radio of sample of users.
Further, the building module 363 specifically can be used for using the auxiliary vector as the default study mould
The input feature vector of the corresponding objective function of type generates predicted value according to the input feature vector；
The building module 363, specifically can be also used for using the encoded radio of the sample of users as the default study
The output feature of the corresponding objective function of model generates actual value according to the output feature；
The building module 363, specifically can be also used for according to the predicted value and the actual value, iteration is more
The weight parameter of the new objective function, constructs Conversion Model.
Further, the determination unit 33 includes:
Module 331 is obtained, can be used for obtaining the historical information that target user provides electronics red packet, in the historical information
The amount of money that record has history to provide electronics red packet；
Searching module 332 can be used for searching history hair according to the anticipation function expression formula for being suitable for target user
The target user corresponding to the amount of money of sub- red packet that discharges uses the conversion ratio of electronics red packet；
Determining module 333 can be used for target user corresponding to the amount of money based on history granting electronics red packet and use electronics
The conversion ratio of red packet determines the corresponding amount of money for providing electronics red packet of the target user.
It should be noted that its of each functional unit involved by a kind of dispensing apparatus of electronics red packet provided in this embodiment
He accordingly describes, can be with reference to the corresponding description in Fig. 1 and Fig. 2, and details are not described herein.
It is deposited thereon based on above-mentioned method as depicted in figs. 1 and 2 correspondingly, the present embodiment additionally provides a kind of storage medium
Computer program is contained, which realizes the issuer of above-mentioned electronics red packet as depicted in figs. 1 and 2 when being executed by processor
Method.
Based on this understanding, the technical solution of the application can be embodied in the form of software products, which produces
Product can store in a non-volatile memory medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), including some instructions
With so that computer equipment (can be personal computer, server or the network equipment an etc.) execution the application is each
Method described in implement scene.
Based on above-mentioned method and Fig. 3 as depicted in figs. 1 and 2 and virtual bench embodiment shown in Fig. 4, for reality
Existing above-mentioned purpose, the embodiment of the present application also provides a kind of computer equipments, are specifically as follows personal computer, server, net
Network equipment etc., the entity device include storage medium and processor；Storage medium, for storing computer program；Processor is used
The distribution method of above-mentioned electronics red packet as depicted in figs. 1 and 2 is realized in execution computer program.
Optionally, which can also include user interface, network interface, camera, radio frequency (Radio
Frequency, RF) circuit, sensor, voicefrequency circuit, WI-FI module etc..User interface may include display screen
(Display), input unit such as keyboard (Keyboard) etc., optional user interface can also connect including USB interface, card reader
Mouthful etc..Network interface optionally may include standard wireline interface and wireless interface (such as blue tooth interface, WI-FI interface).
It will be understood by those skilled in the art that the entity device structure of the granting of electronics red packet provided in this embodiment is not
The restriction to the entity device is constituted, may include more or fewer components, perhaps combines certain components or different portions
Part arrangement.
It can also include operating system, network communication module in storage medium.Operating system is that the above-mentioned computer of management is set
The program of standby hardware and software resource, supports the operation of message handling program and other softwares and/or program.Network communication mould
Block leads to for realizing the communication between each component in storage medium inside, and between other hardware and softwares in the entity device
Letter.
Through the above description of the embodiments, those skilled in the art can be understood that the application can borrow
It helps software that the mode of necessary general hardware platform is added to realize, hardware realization can also be passed through.Pass through the skill of application the application
Art scheme corresponds to by the target user that anticipation function expression formula determines compared with currently available technology and provides electronics red packet
The amount of money, the amount of money of the electronics red packet can guarantee that target user is maximized using the conversion ratio of electronics red packet, so that target user
The optimum subsidy amount of money is obtained, so that user be promoted to consume using red packet, and theoretically improves the return rate of electronics red packet.
It will be appreciated by those skilled in the art that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, module in attached drawing or
Process is not necessarily implemented necessary to the application.It will be appreciated by those skilled in the art that the mould in device in implement scene
Block can according to implement scene describe be distributed in the device of implement scene, can also carry out corresponding change be located at be different from
In one or more devices of this implement scene.The module of above-mentioned implement scene can be merged into a module, can also be into one
Step splits into multiple submodule.
Above-mentioned the application serial number is for illustration only, does not represent the superiority and inferiority of implement scene.Disclosed above is only the application
Several specific implementation scenes, still, the application is not limited to this, and the changes that any person skilled in the art can think of is all
The protection scope of the application should be fallen into.
Claims (10)
1. a kind of distribution method of electronics red packet characterized by comprising
Obtain multiple dimensional characteristics of target user；
Multiple dimensional characteristics of the target user are input to the Conversion Model constructed in advance, obtain being suitable for target user
Anticipation function expression formula, wherein the Conversion Model based on input multiple dimensional characteristics export anticipation function expression formula,
The anticipation function expression formula is used to describe user using the conversion ratio of electronics red packet as the granting electronics red packet amount of money changes it
Between relationship；
According to the anticipation function expression formula suitable for target user, the corresponding granting electronics red packet of the target user is determined
The amount of money；
The electronics red packet of the amount of money is provided to the target user.
2. the method according to claim 1, wherein defeated in multiple dimensional characteristics by the target user
Enter before obtaining the anticipation function expression formula suitable for target user to the Conversion Model constructed in advance, the method is also wrapped
It includes:
Obtain multiple dimensional characteristics of sample of users；
It is identified based on the sample of users marked in advance using the conversion of electronics red packet, by multiple dimensional characteristics of the sample of users
It is input in default learning model and is trained, construct Conversion Model.
3. according to the method described in claim 2, it is characterized in that, described red using electronics based on the sample of users marked in advance
The conversion of packet identifies, and multiple dimensional characteristics of the sample of users are input in default learning model and are trained, and building turns
Rate model includes:
It is identified based on the sample of users marked in advance using the conversion of electronics red packet, the conversion is identified and carries out Discrete Eigenvalue
Coding, obtains the encoded radio of sample of users；
Using each dimensional characteristics of the sample of users as a characteristic component, to each characteristic component introduce auxiliary to
Amount；
By the encoded radio of the sample of users and the auxiliary vector bring into the corresponding objective function of default learning model into
Row training, constructs Conversion Model.
4. according to the method described in claim 3, it is characterized in that, described red using electronics based on the sample of users marked in advance
The conversion of packet identifies, and identifies to the conversion and carries out Discrete Eigenvalue coding, and the encoded radio for obtaining sample of users includes:
If sample of users is identified as positive sample using the conversion of electronics red packet, Discrete Eigenvalue volume is carried out to the positive sample
Code, obtains the first encoded radio of sample of users；
If sample of users is identified as negative sample using the conversion of electronics red packet, Discrete Eigenvalue volume is carried out to the negative sample
Code, obtains the second encoded radio of sample of users.
5. according to the method described in claim 3, it is characterized in that, described by the encoded radio of the sample of users and described auxiliary
It helps vector to bring into the corresponding objective function of default learning model to be trained, building Conversion Model includes:
It is special according to the input using the auxiliary vector as the input feature vector of the corresponding objective function of the default learning model
Sign generates predicted value；
Using the encoded radio of the sample of users as the output feature of the corresponding objective function of the default learning model, according to institute
It states output feature and generates actual value；
According to the predicted value and the actual value, iteration updates the weight parameter of the objective function, building conversion
Rate model.
6. the method according to claim 1, wherein the anticipation function for being suitable for target user according to
Expression formula determines that the corresponding amount of money for providing electronics red packet of the target user includes:
The historical information that target user provides electronics red packet is obtained, record has history to provide electronics red packet in the historical information
The amount of money；
According to the anticipation function expression formula suitable for target user, searches history and provide mesh corresponding to the amount of money of electronics red packet
Mark the conversion ratio that user uses electronics red packet；
The conversion ratio that target user corresponding to the amount of money of electronics red packet uses electronics red packet is provided based on history, determines the target
The corresponding amount of money for providing electronics red packet of user.
7. a kind of dispensing apparatus of electronics red packet characterized by comprising
First acquisition unit, for obtaining multiple dimensional characteristics of target user；
Predicting unit is obtained for multiple dimensional characteristics of the target user to be input to the Conversion Model constructed in advance
Anticipation function expression formula suitable for target user, wherein the Conversion Model is exported based on multiple dimensional characteristics of input
Anticipation function expression formula, the anticipation function expression formula are used to describe user using the conversion ratio of electronics red packet with granting electronics
Relationship between the variation of the red packet amount of money；
Determination unit, for determining that the target user is corresponding according to the anticipation function expression formula for being suitable for target user
Provide the amount of money of electronics red packet；
Issuing unit, for providing the electronics red packet of the amount of money to the target user.
8. device according to claim 7, which is characterized in that described device further include:
Second acquisition unit, for multiple dimensional characteristics of the target user to be input to the conversion ratio constructed in advance described
Model obtains multiple dimensional characteristics of sample of users before obtaining the anticipation function expression formula suitable for target user；
Construction unit, for being identified based on the sample of users marked in advance using the conversion of electronics red packet, by the sample of users
Multiple dimensional characteristics be input in default learning model and be trained, construct Conversion Model.
9. a kind of computer equipment, including memory and processor, it is stored with computer program in the memory, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer storage medium, is stored thereon with computer program, which is characterized in that the computer program is located
The step of reason device realizes method described in any one of claims 1 to 6 when executing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910232926.6A CN110111090A (en) | 2019-03-26 | 2019-03-26 | A kind of distribution method and device of electronics red packet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910232926.6A CN110111090A (en) | 2019-03-26 | 2019-03-26 | A kind of distribution method and device of electronics red packet |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110111090A true CN110111090A (en) | 2019-08-09 |
Family
ID=67484645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910232926.6A Pending CN110111090A (en) | 2019-03-26 | 2019-03-26 | A kind of distribution method and device of electronics red packet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110111090A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766441A (en) * | 2019-09-05 | 2020-02-07 | 口碑(上海)信息技术有限公司 | Resource object processing method and device, storage medium and computer equipment |
| CN110782277A (en) * | 2019-10-12 | 2020-02-11 | 上海陆家嘴国际金融资产交易市场股份有限公司 | Resource processing method, resource processing device, computer equipment and storage medium |
| CN111626767A (en) * | 2020-04-29 | 2020-09-04 | 拉扎斯网络科技（上海）有限公司 | Resource data distribution method, device and equipment |
| CN111833102A (en) * | 2020-06-30 | 2020-10-27 | 拉扎斯网络科技（上海）有限公司 | Data display method and device |
| CN111899067A (en) * | 2020-07-02 | 2020-11-06 | 拉扎斯网络科技（上海）有限公司 | Resource transfer mode display method and device, computer equipment and storage medium |
| CN112819497A (en) * | 2019-11-18 | 2021-05-18 | 百度在线网络技术（北京）有限公司 | Conversion rate prediction method, device, equipment and storage medium |
| CN113554385A (en) * | 2021-05-27 | 2021-10-26 | 北京每日优鲜电子商务有限公司 | Distribution robot control method, distribution robot control device, electronic equipment and computer readable medium |
| TWI792413B (en) * | 2020-07-22 | 2023-02-11 | 日商樂天集團股份有限公司 | Information processing device, information processing method and program product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN108305102A (en) * | 2018-01-30 | 2018-07-20 | 阿里巴巴集团控股有限公司 | Electronics red packet distribution method, device and client |
| CN108416624A (en) * | 2018-02-27 | 2018-08-17 | 深圳乐信软件技术有限公司 | A kind of discount coupon method for pushing, device, storage medium and intelligent terminal |
| KR20180108553A (en) * | 2018-09-27 | 2018-10-04 | 박경수 | How to use scores in self-service systems |
| CN109389431A (en) * | 2018-09-30 | 2019-02-26 | 北京三快在线科技有限公司 | Distribution method, device, electronic equipment and the readable storage medium storing program for executing of discount coupon |
-
2019
- 2019-03-26 CN CN201910232926.6A patent/CN110111090A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN108305102A (en) * | 2018-01-30 | 2018-07-20 | 阿里巴巴集团控股有限公司 | Electronics red packet distribution method, device and client |
| CN108416624A (en) * | 2018-02-27 | 2018-08-17 | 深圳乐信软件技术有限公司 | A kind of discount coupon method for pushing, device, storage medium and intelligent terminal |
| KR20180108553A (en) * | 2018-09-27 | 2018-10-04 | 박경수 | How to use scores in self-service systems |
| CN109389431A (en) * | 2018-09-30 | 2019-02-26 | 北京三快在线科技有限公司 | Distribution method, device, electronic equipment and the readable storage medium storing program for executing of discount coupon |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766441A (en) * | 2019-09-05 | 2020-02-07 | 口碑(上海)信息技术有限公司 | Resource object processing method and device, storage medium and computer equipment |
| CN110782277A (en) * | 2019-10-12 | 2020-02-11 | 上海陆家嘴国际金融资产交易市场股份有限公司 | Resource processing method, resource processing device, computer equipment and storage medium |
| CN112819497A (en) * | 2019-11-18 | 2021-05-18 | 百度在线网络技术（北京）有限公司 | Conversion rate prediction method, device, equipment and storage medium |
| CN112819497B (en) * | 2019-11-18 | 2023-10-10 | 百度在线网络技术（北京）有限公司 | Conversion rate prediction method, conversion rate prediction device, conversion rate prediction apparatus, and storage medium |
| CN111626767A (en) * | 2020-04-29 | 2020-09-04 | 拉扎斯网络科技（上海）有限公司 | Resource data distribution method, device and equipment |
| CN111626767B (en) * | 2020-04-29 | 2023-09-08 | 拉扎斯网络科技（上海）有限公司 | Resource data issuing method, device and equipment |
| CN111833102A (en) * | 2020-06-30 | 2020-10-27 | 拉扎斯网络科技（上海）有限公司 | Data display method and device |
| CN111899067A (en) * | 2020-07-02 | 2020-11-06 | 拉扎斯网络科技（上海）有限公司 | Resource transfer mode display method and device, computer equipment and storage medium |
| TWI792413B (en) * | 2020-07-22 | 2023-02-11 | 日商樂天集團股份有限公司 | Information processing device, information processing method and program product |
| CN113554385A (en) * | 2021-05-27 | 2021-10-26 | 北京每日优鲜电子商务有限公司 | Distribution robot control method, distribution robot control device, electronic equipment and computer readable medium |
| CN113554385B (en) * | 2021-05-27 | 2024-01-05 | 广东中顺信息科技有限公司 | Distribution robot control method, distribution robot control device, electronic equipment and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110111090A (en) | A kind of distribution method and device of electronics red packet | |
| CN108416624A (en) | A kind of discount coupon method for pushing, device, storage medium and intelligent terminal | |
| CN107330741A (en) | Graded electron-like certificate uses Forecasting Methodology, device and electronic equipment | |
| CN107622394A (en) | A kind of method of payment processes, medium, device and computing device | |
| KR100583181B1 (en) | System and method for providing partial payment in the electronic commerce | |
| KR101958773B1 (en) | Method, apparatus and computer-readable medium for making product detail page based on web-toon story | |
| CN108537460A (en) | Consumer's risk prediction technique and system | |
| CN107992500A (en) | A kind of information processing method and server | |
| CN111626767B (en) | Resource data issuing method, device and equipment | |
| CN109711859A (en) | Prediction technique and device, storage medium, the computer equipment of mixed railway | |
| CN109493075A (en) | For determining the method and apparatus of virtual resource object | |
| CN108898431A (en) | Consume interlock method, device and server | |
| JP7059160B2 (en) | Providing equipment, providing method and providing program | |
| CN109064180A (en) | Comment on method, apparatus and terminal device | |
| CN110232581A (en) | It is a kind of to provide the method and apparatus of discount coupon for user | |
| CN116308505A (en) | Resource allocation method, device, storage medium and computer equipment | |
| CN110163585B (en) | Method and device for issuing electronic red packet | |
| CN113298555B (en) | Promotion strategy generation method and device and electronic equipment | |
| CN111932319B (en) | Rights and interests configuration method and device, storage medium and computer equipment | |
| US9633357B2 (en) | Net utility determination based on product replacement and service plan coverage decisions | |
| CN109714381B (en) | Consumption tracking based information pushing method, equipment, storage medium and device | |
| CN112435066A (en) | Electronic certificate issuing method, device, terminal and storage medium | |
| CN114818843A (en) | Data analysis method and device and computing equipment | |
| CN112907699A (en) | Object processing method and device | |
| Cho et al. | Evaluating the efficiency of mobile content companies using data envelopment analysis and principal component analysis |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190809 |