CN108647811A - Predict that user buys method, apparatus, equipment and the storage medium of equity commodity - Google Patents
Predict that user buys method, apparatus, equipment and the storage medium of equity commodity Download PDFInfo
- Publication number
- CN108647811A CN108647811A CN201810384346.4A CN201810384346A CN108647811A CN 108647811 A CN108647811 A CN 108647811A CN 201810384346 A CN201810384346 A CN 201810384346A CN 108647811 A CN108647811 A CN 108647811A
- Authority
- CN
- China
- Prior art keywords
- commodity
- equity
- user
- information
- user information
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present invention provides a kind of prediction user method, apparatus, equipment and the storage medium of buying equity commodity, wherein this method includes：Obtain the first user information of target user；Purchase prediction model based on first user information and preset equity commodity determines that the target user buys the probability of the equity commodity；If the probability that the target user buys the equity commodity is more than the first predetermined threshold value, the marketing message of the equity commodity is pushed to the target user.For the embodiment of the present invention by predicting that user buys the probability of equity commodity, the user that the first predetermined threshold value is more than to purchase probability pushes the marketing message of the equity commodity, can improve client's conversion ratio of equity commodity, improves customer experience.
Description
Technical field
The present embodiments relate to the sides that field of computer technology more particularly to a kind of prediction user buy equity commodity
Method, device, equipment and storage medium.
Background technology
Equity commodity refer to that operator provides to certain customers, with the preferential commodity sold less than the market price, such as
Say the film ticket for being less than market price sale and third party's discount coupon etc..In general this equity commodity is all that operator is
What higher ranked user provided, still, this equity commodity can be bought by being not each high ranked user.
The marketing mode of existing equity commodity is marketed for satisfactory total user, is not sought targetedly
Pin strategy, client's conversion ratio is relatively low, and for the user of not purchase intention, and this marketing will influence user to operator
Service experience.
Invention content
The embodiment of the present invention provides a kind of method, apparatus, equipment and the storage medium of prediction user purchase equity commodity, uses
To improve client's conversion ratio of equity commodity, the specific aim of equity goods marketing message push is improved, improves user experience.
First aspect of the embodiment of the present invention provides a kind of method that prediction user buys equity commodity, including：
Obtain the first user information of target user；
Purchase prediction model based on first user information and preset equity commodity determines target user's purchase
Buy the probability of the equity commodity；
If the probability that the target user buys the equity commodity is more than the first predetermined threshold value, to the target user
Push the marketing message of the equity commodity.
Optionally, the purchase prediction model based on first user information and preset equity commodity, determines institute
The probability that target user buys the equity commodity is stated, including：
First user information is inputted in preset Lasso models, the target information of the target user, institute are obtained
It states target information and correlation degree that whether target user buys between the equity commodity is more than the second predetermined threshold value；
Purchase prediction model based on the target information and preset equity commodity determines that the target user buys institute
State the probability of equity commodity.
Optionally, the purchase prediction model includes multiple disaggregated models, and the disaggregated model can be used for believing based on user
Breath prediction user buys the probability of the equity commodity；
The purchase prediction model based on first user information and preset equity commodity determines that the target is used
The probability of the equity commodity is bought at family, including：
First user information is inputted in the multiple disaggregated model, the output data based on each disaggregated model adds
Weights calculate and obtain the probability that the target user buys the equity commodity.
Optionally, described to input first user information in the multiple disaggregated model, it is defeated based on each disaggregated model
Go out the weighted value of data, before the calculating acquisition target user buys the probability of the equity commodity, the method includes：
It obtains the second user information of the users of multiple purchases equity commodity and multiple does not buy the equity quotient
The third user information of the user of product；
The multiple second user information and the multiple third user information are inputted in the multiple disaggregated model, base
In the prediction result of each disaggregated model, the corresponding weighted value of each disaggregated model is determined.
Second aspect of the embodiment of the present invention provides a kind of prediction meanss, including：
First acquisition module, the first user information for obtaining target user；
First determining module is used for the purchase prediction model based on first user information and preset equity commodity,
Determine that the target user buys the probability of the equity commodity；
Pushing module, when the probability for buying the equity commodity in the target user is more than the first predetermined threshold value,
The marketing message of the equity commodity is pushed to the target user.
Optionally, first determining module, including：
Information sifting submodule obtains the target for first user information to be inputted preset Lasso models
The correlation degree whether target information of user, the target information and the target user buy between the equity commodity is big
In the second predetermined threshold value；
Determination sub-module is used for the purchase prediction model based on the target information and preset equity commodity, determines institute
State the probability that target user buys the equity commodity.
Optionally, the purchase prediction model includes multiple disaggregated models, and the disaggregated model can be used for believing based on user
Breath prediction user buys the probability of the equity commodity；
First determining module, including：
Computational submodule is based on each classification mould for inputting first user information in the multiple disaggregated model
The weighted value of type output data calculates and obtains the probability that the target user buys the equity commodity.
Optionally, described device further includes：
Second acquisition module, the second user information of the user for obtaining multiple purchase equity commodity, Yi Jiduo
The third user information of a user for not buying the equity commodity；
Second determining module, for will the multiple second user information and the multiple third user information input described in
In multiple disaggregated models, based on the prediction result of each disaggregated model, the corresponding weighted value of each disaggregated model is determined.
The third aspect of the embodiment of the present invention provides a kind of server, including：
Processor；
Memory for storing the processor-executable instruction；
When the processor executes the executable instruction, method that above-mentioned first aspect can be executed.
Fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, including instruction, when described instruction exists
When being run on the computer, method that the computer can execute above-mentioned first aspect.
The embodiment of the present invention, by obtaining the first user information of target user, based on the first user information and preset
The purchase prediction model of equity commodity determines that target user buys the probability of equity commodity, if target user buys equity commodity
Probability be more than the first predetermined threshold value, then the marketing message of the equity commodity is pushed to target user, to improve equity quotient
Client's conversion ratio of product improves the specific aim of equity goods marketing message push, avoids to not interested purchase equity quotient
The user of product pushes marketing message, improves user experience.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without having to pay creative labor, may be used also for those of ordinary skill in the art
With obtain other attached drawings according to these attached drawings.
Fig. 1 is the flow chart for the method that a kind of prediction user provided in an embodiment of the present invention buys equity commodity；
Fig. 2 is the flow chart for the method that a kind of prediction user provided in an embodiment of the present invention buys equity commodity；
Fig. 3 is the flow chart for the method that a kind of prediction user provided in an embodiment of the present invention buys equity commodity；
Fig. 4 is a kind of structural schematic diagram of prediction meanss 40 provided in an embodiment of the present invention；
Fig. 5 is the structural schematic diagram of the first determining module 42 provided in an embodiment of the present invention；
Fig. 6 is a kind of structural schematic diagram of first determining module 42 provided in an embodiment of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The term " comprising " and " having " of description and claims of this specification and their any deformation, it is intended that
Be to cover it is non-exclusive include, for example, the device of the process or structure that contain series of steps is not necessarily limited to clearly arrange
Those of go out structure or step but may include not listing clearly or for the intrinsic other steps of these processes or device
Rapid or structure.
The embodiment of the present invention provides a kind of method that prediction user buys equity commodity.This method can be filled by a kind of prediction
It sets to execute, which can be specially the server positioned at network-side.Referring to Fig. 1,
Fig. 1 is the flow chart for the method that a kind of prediction user provided in an embodiment of the present invention buys equity commodity, such as Fig. 1 institutes
Show, this method comprises the following steps：
Step 101, the first user information for obtaining target user.
So-called target user refers to the user for meeting purchase equity commodity condition in the present embodiment.
In actual scene, prediction meanss can filter out target user based on preset screening strategy from total user,
The first user information that target user is obtained from database, wherein the name of the first user information is only used for being different from other use
The user information at family, without having other meanings.
By taking common carrier as an example, for common carrier, usually will average moon spending amount preset cost it
On user be divided into advanced level user, the equity commodity to be sold less than market price would generally be provided for operator of advanced level user,
Such as film ticket, coupons etc..So, for operation, target user i.e. averagely moon spending amount is on preset cost
User, then can will average moon spending amount as screening conditions, from the group of subscribers of operator, it is golden to filter out moon consumption
User of the volume between combining the amount of money is as target user, and first of the data acquisition target user from storage user information
User information.Alternatively, on the basis of can be with above-mentioned screening conditions, the information of equity commodity to be marketed be based further on to sieve
Select target user, for example equity commodity to be marketed are low price air tickets, then it can also be by user month on the basis of above-mentioned condition
The frequency on discrepancy airport is as screening conditions, if user is averaged, moon spending amount is more than preset cost, the frequency on the airport that comes in and goes out the moon
More than preset times, it is determined that user is target user, and obtains the first user information of target user from database.Its
In, the frequency on user month discrepancy airport can be determined based on user terminal and the link information of near airports base station.
User information in the present embodiment includes following one or more：User gender information, user gradation information, purchase
The use information of area information, duration of call information, mobile network's flow where the information of call option benefit commodity, user.
Step 102, the purchase prediction model based on first user information and preset equity commodity, determine the mesh
Mark user buys the probability of the equity commodity.
Purchase prediction model in the present embodiment is to train what is obtained to can be used according to user information prediction user in advance
Buy the probability of equity commodity.
In the training purchase prediction model, the second user of multiple users for buying the equity commodity can be first obtained
Information and the third user information of multiple users for not buying the equity commodity, by multiple second user information and more
A third user information inputs in preset model, to which training obtains the purchase prediction model of the equity commodity.
If the probability that step 103, the target user buy the equity commodity is more than the first predetermined threshold value, to described
Target user pushes the marketing message of the equity commodity.
The first predetermined threshold value in the present embodiment can be set as needed, and the present embodiment is not specifically limited.
When the probability that target user buys equity commodity is more than the first predetermined threshold value, then it is assumed that user has higher purchase
Wish is bought, then pushes the marketing message of the equity commodity to user, to improve being directed to for equity goods marketing message push
Property, improve client's conversion ratio of equity commodity.
The present embodiment is based on the first user information and preset equity by obtaining the first user information of target user
The purchase prediction model of commodity determines that target user buys the probability of equity commodity, if target user buys the general of equity commodity
Rate is more than the first predetermined threshold value, then the marketing message of the equity commodity is pushed to target user, to improve equity commodity
Client's conversion ratio improves the specific aim of equity goods marketing message push, avoids to not interested purchase equity commodity
User pushes marketing message, improves user experience.
Below in conjunction with the accompanying drawings, it is extended and optimizes on the basis of the above embodiments：
Fig. 2 is the flow chart for the method that a kind of prediction user provided in an embodiment of the present invention buys equity commodity, such as Fig. 2 institutes
Show, on the basis of Fig. 1 embodiments, this method includes：
Step 201, the first user information for obtaining target user.
Step 202 inputs first user information in preset Lasso models, obtains the mesh of the target user
Information is marked, it is pre- more than second whether the target information and the target user buy the correlation degree between the equity commodity
If threshold value.
Since the first user information includes the information of each various aspects of user, and some information are for user in these information
Whether buying equity commodity may not have much influence, then this partial information is removed from the first user information, reservation pair
User, which buys equity commodity, influences big information, can save the workload of following predicted operation, therefore, the present embodiment is obtaining
After taking the first user information of target user, needs first to input the first user information in trained Lasso models in advance, lead to
It crosses Lasso models and is filtered out from the first user information and the information that is affected of equity commodity is bought as target letter to user
Breath.
Step 203, the purchase prediction model based on the target information and preset equity commodity determine that the target is used
Buy the probability of the equity commodity in family.
If the probability that step 204, the target user buy the equity commodity is more than the first predetermined threshold value, to described
Target user pushes the marketing message of the equity commodity.
The present embodiment, after obtaining the first user information, by the way that the first user information is inputted preset Lasso moulds
Type obtains in the first user information and buys the information that is affected of equity commodity as target information, then based on target to user
The purchase prediction model of information and preset equity commodity determines that the target user buys the probability of the equity commodity, energy
Enough calculation amounts for reducing purchase prediction model, improve the forecasting efficiency of purchase prediction model, improve forecasting accuracy.
Fig. 3 is the flow chart for the method that a kind of prediction user provided in an embodiment of the present invention buys equity commodity, in Fig. 3 realities
It includes multiple disaggregated models to apply and buy prediction model in example, and the disaggregated model can be used for based on user information prediction user's purchase
The probability of the equity commodity, as shown in figure 3, on the basis of Fig. 1 embodiments, this method includes：
Step 301, the first user information for obtaining target user.
Step 302 inputs first user information in the multiple disaggregated model, the output based on each disaggregated model
The weighted value of data calculates and obtains the probability that the target user buys the equity commodity.
As an example it is assumed that purchase prediction model is respectively including four parts of disaggregated models：K nearest neighbour classifications algorithm (KNN)
Model, Adaboost models, iteration decision Tree algorithms (Gradient Boosting Decision Tree, GBDT) model,
Support vector machines (Support Vector Machine, SVM) model.Four models are trained in advance, be can be used for
The probability of equity commodity is bought based on user information prediction user.Wherein, the corresponding weighted value of each disaggregated model can be advance
Setting, can also be to be obtained based on multiple user information training for demarcating purchase situation.For example, can be first from database
It is middle to obtain multiple user's second user information for having purchased equity commodity and multiple users for not buying the equity commodity
Third user information；Multiple second user information and multiple third user informations are inputted in above-mentioned 4 disaggregated models again, to
Prediction result based on the corresponding purchase situation of the good each user information in advance Baoding and each disaggregated model, determines each point
The corresponding weighted value of class model.As an example it is assumed that getting a collection of user's (being denoted as User_Vali (including K user))
User information, it is known that its buy whether the case where, by the user information of this crowd of user be input to it is trained it is above-mentioned 4 classification moulds
In type, the probability of output purchase equity.Output valve is compared into true purchase situation.If user really buys the corresponding value of situation
For Real, predicted value is respectively predict_1~predict_4, if predict_i is more than or equal to 0, and is less than 0.5, wherein
I is the integer for being less than or equal to 4 more than or equal to 1, then it is assumed that user is partial to buy, if predict_i is more than or equal to
0.5, then it is assumed that user is more likely to purchase.
The user information of each user in User_Vali is traversed, if the result and Real phases of predict_i predictions
Meet, record the value of predict_i, if on the contrary, if to record this value be 0, after completing traversal, a K row can be generated, 4 row
Two-dimensional array.Every a line of this 2-D data is traversed, if say that the value that Real is Isosorbide-5-Nitrae row is respectively 0,0.6,0.6,0.56,
So generate four weighted value w_1 to w_4, wherein w_1 0, because it is respectively 0.6/ that corresponding numerical value, which is 0, w_2 to w_4,
(0.6+0.6+0.56), 0.6/ (0.6+0.6+0.56) and 0.56/ (0.6+0.6+0.56).Each line number of this 2-D data
According to can all export 4 weighted values, symbiosis is at K rows.For the corresponding weighted value of every column data, executes K rows and adds up and average,
4 average weighted values are finally exported, this 4 average weighted values do not correspond to the final weighted value of above-mentioned each disaggregated model.
Certainly it above are only and illustrate rather than uniquely limit.
If the probability that step 303, the target user buy the equity commodity is more than the first predetermined threshold value, to described
Target user pushes the marketing message of the equity commodity.
Purchase prediction model is constituted by the way that multiple trained disaggregated models combine in the present embodiment, and based on each
The weighted value of the output data of disaggregated model calculates and obtains the probability that target user buys equity commodity, can improve prediction
Accuracy.
Fig. 4 is a kind of structural schematic diagram of prediction meanss 40 provided in an embodiment of the present invention, as shown in figure 4, device 40 wraps
It includes：
First acquisition module 41, the first user information for obtaining target user；
First determining module 42 predicts mould for the purchase based on first user information and preset equity commodity
Type determines that the target user buys the probability of the equity commodity；
Pushing module 43, the probability for buying the equity commodity in the target user are more than the first predetermined threshold value
When, the marketing message of the equity commodity is pushed to the target user.
Device 40 provided in this embodiment can be used in the method for executing Fig. 1 embodiments, executive mode and advantageous effect
It is similar, it repeats no more herein.
Fig. 5 is the structural schematic diagram of the first determining module 42 provided in an embodiment of the present invention, as shown in figure 5, implementing in Fig. 4
On the basis of example, the first determining module 42, including：
Information sifting submodule 421, for will the preset Lasso models of first user information input, described in acquisition
The target information of target user, the target information whether buy the equity commodity with the target user between be associated with journey
Degree is more than the second predetermined threshold value；
Determination sub-module 422 is used for the purchase prediction model based on the target information and preset equity commodity, determines
The target user buys the probability of the equity commodity.
Prediction meanss provided in this embodiment can be used in the method for executing Fig. 2 embodiments, executive mode and beneficial effect
Fruit seemingly, repeats no more herein.
Fig. 6 is a kind of structural schematic diagram of first determining module 42 provided in an embodiment of the present invention, as shown in fig. 6, in Fig. 5
On the basis of embodiment, the purchase prediction model includes multiple disaggregated models, and the disaggregated model can be used for believing based on user
Breath prediction user buys the probability of the equity commodity；First determining module 42, including：
Computational submodule 423 is based on each classification for inputting first user information in the multiple disaggregated model
The weighted value of model output data calculates and obtains the probability that the target user buys the equity commodity.
Optionally, described device 40 can also include：
Second acquisition module, the second user information of the user for obtaining multiple purchase equity commodity, Yi Jiduo
The third user information of a user for not buying the equity commodity；
Second determining module, for will the multiple second user information and the multiple third user information input described in
In multiple disaggregated models, based on the prediction result of each disaggregated model, the corresponding weighted value of each disaggregated model is determined.
Prediction meanss provided in this embodiment can be used in the method for executing Fig. 3 embodiments, executive mode and beneficial effect
Fruit seemingly, repeats no more herein.
The embodiment of the present invention also provides a kind of server, including：
Processor；
Memory for storing the processor-executable instruction；
When the processor executes the executable instruction, the technical solution of above-mentioned Fig. 1-Fig. 3 embodiments can be executed.
The embodiment of the present invention also provides a kind of computer readable storage medium, including instruction, when described instruction is in the meter
When being run on calculation machine, the computer can execute the technical solution of above-mentioned Fig. 1-Fig. 3 embodiments.
Finally, it should be noted that one of ordinary skill in the art will appreciate that whole in above-described embodiment method or
Part flow is that relevant hardware can be instructed to complete by computer program, and the program can be stored in a computer
In readable storage medium storing program for executing, the program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described to deposit
Storage media can be disk, CD, read-only memory (ROM) or random access memory (RAM) etc..
Each functional unit in the embodiment of the present invention can be integrated in a processing module, can also be each unit
Individually be physically present, can also two or more units be integrated in a module.Above-mentioned integrated module both can be with
It is realized, can also be realized in the form of software function module in the form of hardware.If the integrated module is with software
The form of function module realizes, and when sold or used as an independent product, can also be stored in one and computer-readable deposit
In storage media.Storage medium mentioned above can be read-only memory, disk or CD etc..
The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；Although with reference to aforementioned each reality
Applying example, invention is explained in detail, it will be understood by those of ordinary skill in the art that：It still can be to aforementioned each
Technical solution recorded in embodiment is modified, and either carries out equivalent replacement to which part or all technical features；And
These modifications or replacements, the range for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of method that prediction user buys equity commodity, which is characterized in that including：
Obtain the first user information of target user；
Purchase prediction model based on first user information and preset equity commodity determines that the target user buys institute
State the probability of equity commodity；
If the probability that the target user buys the equity commodity is more than the first predetermined threshold value, pushed to the target user
The marketing message of the equity commodity.
2. according to the method described in claim 1, it is characterized in that, described be based on first user information and preset equity
The purchase prediction model of commodity determines that the target user buys the probability of the equity commodity, including：
First user information is inputted in preset Lasso models, the target information of the target user, the mesh are obtained
Whether mark information and the target user, which buy the correlation degree between the equity commodity, is more than the second predetermined threshold value；
Purchase prediction model based on the target information and preset equity commodity determines that the target user buys the power
The probability of beneficial commodity.
3. according to the method described in claim 1, it is characterized in that, the purchase prediction model includes multiple disaggregated models, institute
State the probability that disaggregated model can be used for buying the equity commodity based on user information prediction user；
The purchase prediction model based on first user information and preset equity commodity determines target user's purchase
The probability of the equity commodity is bought, including：
First user information is inputted in the multiple disaggregated model, the weighting of the output data based on each disaggregated model
Value calculates and obtains the probability that the target user buys the equity commodity.
4. according to the method described in claim 3, it is characterized in that, described input the multiple point by first user information
In class model, based on the weighted value of each disaggregated model output data, calculates and obtain target user's purchase equity commodity
Probability before, the method includes：
It obtains the second user information of the users of multiple purchases equity commodity and multiple does not buy the equity commodity
The third user information of user；
The multiple second user information and the multiple third user information are inputted in the multiple disaggregated model, based on each
The prediction result of disaggregated model determines the corresponding weighted value of each disaggregated model.
5. a kind of prediction meanss, which is characterized in that including：
First acquisition module, the first user information for obtaining target user；
First determining module is used for the purchase prediction model based on first user information and preset equity commodity, determines
The target user buys the probability of the equity commodity；
Pushing module, when the probability for buying the equity commodity in the target user is more than the first predetermined threshold value, to institute
State the marketing message that target user pushes the equity commodity.
6. device according to claim 5, which is characterized in that first determining module, including：
Information sifting submodule obtains the target user for first user information to be inputted preset Lasso models
Target information, whether the target information and the target user, which buy the correlation degree between the equity commodity, is more than the
Two predetermined threshold values；
Determination sub-module is used for the purchase prediction model based on the target information and preset equity commodity, determines the mesh
Mark user buys the probability of the equity commodity.
7. device according to claim 5, which is characterized in that the purchase prediction model includes multiple disaggregated models, institute
State the probability that disaggregated model can be used for buying the equity commodity based on user information prediction user；
First determining module, including：
Computational submodule, it is defeated based on each disaggregated model for inputting first user information in the multiple disaggregated model
Go out the weighted value of data, calculates and obtain the probability that the target user buys the equity commodity.
8. device according to claim 7, which is characterized in that described device further includes：
Second acquisition module, the second user information of the users for obtaining multiple purchases equity commodity and it is multiple not
Buy the third user information of the user of the equity commodity；
Second determining module, for the multiple second user information and the input of the multiple third user information is the multiple
In disaggregated model, based on the prediction result of each disaggregated model, the corresponding weighted value of each disaggregated model is determined.
9. a kind of server, which is characterized in that including：
Processor；
Memory for storing the processor-executable instruction；
When the processor executes the executable instruction, the side described in any one of the claims 1-4 can be executed
Method.
10. a kind of computer readable storage medium, including instruction, when described instruction is run on the computer, the meter
Calculation machine can execute the method described in any one of the claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810384346.4A CN108647811A (en) | 2018-04-26 | 2018-04-26 | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810384346.4A CN108647811A (en) | 2018-04-26 | 2018-04-26 | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108647811A true CN108647811A (en) | 2018-10-12 |
Family
ID=63747575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810384346.4A Pending CN108647811A (en) | 2018-04-26 | 2018-04-26 | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108647811A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598542A (en) * | 2018-11-20 | 2019-04-09 | 阿里巴巴集团控股有限公司 | A kind of put-on method, device and the electronic equipment of equity of marketing |
| CN109816441A (en) * | 2018-12-29 | 2019-05-28 | 江苏云天励飞技术有限公司 | Tactful method for pushing, system and relevant apparatus |
| CN110020887A (en) * | 2019-03-07 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of data processing method, equipment, medium and device |
| CN111091416A (en) * | 2019-12-10 | 2020-05-01 | 北京云迹科技有限公司 | Method and device for predicting probability of hotel purchase robot |
| CN111105281A (en) * | 2018-10-26 | 2020-05-05 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and electronic equipment |
| CN111586162A (en) * | 2020-05-06 | 2020-08-25 | 支付宝(杭州)信息技术有限公司 | Information pushing method and system |
| CN111598632A (en) * | 2020-07-17 | 2020-08-28 | 支付宝(杭州)信息技术有限公司 | Method and device for determining equity shares and equity share sequence |
| CN111756837A (en) * | 2020-06-23 | 2020-10-09 | 京东数字科技控股有限公司 | Information pushing method, device, equipment and computer readable storage medium |
| CN112116393A (en) * | 2020-09-23 | 2020-12-22 | 贝壳技术有限公司 | Method, device and equipment for realizing event user maintenance |
| CN112214675A (en) * | 2020-10-19 | 2021-01-12 | 中国移动通信集团江苏有限公司 | Method, device and equipment for determining user machine purchasing and computer storage medium |
| CN112243021A (en) * | 2020-05-25 | 2021-01-19 | 北京沃东天骏信息技术有限公司 | Information pushing method, device, equipment and computer readable storage medium |
| CN112465594A (en) * | 2020-11-27 | 2021-03-09 | 康键信息技术（深圳）有限公司 | Live broadcast interaction method, device, equipment and storage medium |
| CN112580686A (en) * | 2020-11-19 | 2021-03-30 | 青岛檬豆网络科技有限公司 | Aluminum electrolytic capacitor purchase prediction method based on Markov distance KNN algorithm |
| CN112837079A (en) * | 2019-11-22 | 2021-05-25 | 上海哔哩哔哩科技有限公司 | Commodity sales prediction method and device and computer equipment |
| CN113643068A (en) * | 2021-08-18 | 2021-11-12 | 北京小米移动软件有限公司 | Commodity purchase intention determining method and device, storage medium and electronic equipment |
| CN114549066A (en) * | 2022-02-15 | 2022-05-27 | 上海钧正网络科技有限公司 | Marketing mode determining method and device and computer storage medium |
| CN114549071A (en) * | 2022-02-18 | 2022-05-27 | 上海钧正网络科技有限公司 | Marketing strategy determination method and device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150332414A1 (en) * | 2014-05-13 | 2015-11-19 | Mastercard International Incorporated | System and method for predicting items purchased based on transaction data |
| CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
| CN107330744A (en) * | 2017-07-21 | 2017-11-07 | 携程旅游网络技术（上海）有限公司 | The recommendation method and system of air ticket derived product |
| CN107330741A (en) * | 2017-07-07 | 2017-11-07 | 北京京东尚科信息技术有限公司 | Graded electron-like certificate uses Forecasting Methodology, device and electronic equipment |
| CN107909433A (en) * | 2017-11-14 | 2018-04-13 | 重庆邮电大学 | A kind of Method of Commodity Recommendation based on big data mobile e-business |
-
2018
- 2018-04-26 CN CN201810384346.4A patent/CN108647811A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150332414A1 (en) * | 2014-05-13 | 2015-11-19 | Mastercard International Incorporated | System and method for predicting items purchased based on transaction data |
| CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
| CN107330741A (en) * | 2017-07-07 | 2017-11-07 | 北京京东尚科信息技术有限公司 | Graded electron-like certificate uses Forecasting Methodology, device and electronic equipment |
| CN107330744A (en) * | 2017-07-21 | 2017-11-07 | 携程旅游网络技术（上海）有限公司 | The recommendation method and system of air ticket derived product |
| CN107909433A (en) * | 2017-11-14 | 2018-04-13 | 重庆邮电大学 | A kind of Method of Commodity Recommendation based on big data mobile e-business |
Non-Patent Citations (2)
| Title |
|---|
| 乔纳森 R 沃尔帕乌: "《脑-机接口-原理与实践》", 31 May 2017 * |
| 方霞: "《R软件与金融数据分析》", 31 August 2017, 中国金融出版社 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111105281A (en) * | 2018-10-26 | 2020-05-05 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and electronic equipment |
| CN111105281B (en) * | 2018-10-26 | 2024-03-01 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and electronic equipment |
| CN109598542A (en) * | 2018-11-20 | 2019-04-09 | 阿里巴巴集团控股有限公司 | A kind of put-on method, device and the electronic equipment of equity of marketing |
| CN109598542B (en) * | 2018-11-20 | 2023-10-27 | 创新先进技术有限公司 | Marketing equity throwing method and device and electronic equipment |
| CN109816441A (en) * | 2018-12-29 | 2019-05-28 | 江苏云天励飞技术有限公司 | Tactful method for pushing, system and relevant apparatus |
| CN109816441B (en) * | 2018-12-29 | 2021-05-11 | 江苏云天励飞技术有限公司 | Policy pushing method, system and related device |
| CN110020887A (en) * | 2019-03-07 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of data processing method, equipment, medium and device |
| CN112837079B (en) * | 2019-11-22 | 2023-06-09 | 上海哔哩哔哩科技有限公司 | Commodity sales predicting method, commodity sales predicting device and computer equipment |
| CN112837079A (en) * | 2019-11-22 | 2021-05-25 | 上海哔哩哔哩科技有限公司 | Commodity sales prediction method and device and computer equipment |
| CN111091416A (en) * | 2019-12-10 | 2020-05-01 | 北京云迹科技有限公司 | Method and device for predicting probability of hotel purchase robot |
| CN111586162A (en) * | 2020-05-06 | 2020-08-25 | 支付宝(杭州)信息技术有限公司 | Information pushing method and system |
| CN112243021A (en) * | 2020-05-25 | 2021-01-19 | 北京沃东天骏信息技术有限公司 | Information pushing method, device, equipment and computer readable storage medium |
| CN111756837A (en) * | 2020-06-23 | 2020-10-09 | 京东数字科技控股有限公司 | Information pushing method, device, equipment and computer readable storage medium |
| CN111598632B (en) * | 2020-07-17 | 2020-10-27 | 支付宝(杭州)信息技术有限公司 | Method and device for determining equity shares and equity share sequence |
| CN111598632A (en) * | 2020-07-17 | 2020-08-28 | 支付宝(杭州)信息技术有限公司 | Method and device for determining equity shares and equity share sequence |
| CN112116393A (en) * | 2020-09-23 | 2020-12-22 | 贝壳技术有限公司 | Method, device and equipment for realizing event user maintenance |
| CN112116393B (en) * | 2020-09-23 | 2022-03-15 | 贝壳找房(北京)科技有限公司 | Method, device and equipment for realizing event user maintenance |
| CN112214675A (en) * | 2020-10-19 | 2021-01-12 | 中国移动通信集团江苏有限公司 | Method, device and equipment for determining user machine purchasing and computer storage medium |
| CN112214675B (en) * | 2020-10-19 | 2024-04-09 | 中国移动通信集团江苏有限公司 | Method, device, equipment and computer storage medium for determining user purchasing machine |
| CN112580686A (en) * | 2020-11-19 | 2021-03-30 | 青岛檬豆网络科技有限公司 | Aluminum electrolytic capacitor purchase prediction method based on Markov distance KNN algorithm |
| CN112580686B (en) * | 2020-11-19 | 2023-05-02 | 青岛檬豆网络科技有限公司 | KNN algorithm aluminum electrolytic capacitor purchase prediction method based on Mahalanobis distance |
| CN112465594A (en) * | 2020-11-27 | 2021-03-09 | 康键信息技术（深圳）有限公司 | Live broadcast interaction method, device, equipment and storage medium |
| CN113643068A (en) * | 2021-08-18 | 2021-11-12 | 北京小米移动软件有限公司 | Commodity purchase intention determining method and device, storage medium and electronic equipment |
| CN114549066A (en) * | 2022-02-15 | 2022-05-27 | 上海钧正网络科技有限公司 | Marketing mode determining method and device and computer storage medium |
| CN114549071A (en) * | 2022-02-18 | 2022-05-27 | 上海钧正网络科技有限公司 | Marketing strategy determination method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108647811A (en) | Predict that user buys method, apparatus, equipment and the storage medium of equity commodity | |
| CN110033314B (en) | Advertisement data processing method and device | |
| Li et al. | Offensive pricing strategies for online platforms | |
| Deng et al. | Integrated product line design and supplier selection: A multi-objective optimization paradigm | |
| US20210264448A1 (en) | Privacy preserving ai derived simulated world | |
| Saha et al. | The ramification of dynamic investment on the promotion and preservation technology for inventory management through a modified flower pollination algorithm | |
| US20160379244A1 (en) | Method and system for forecasting a campaign performance using predictive modeling | |
| CN106991598A (en) | Data push method and its system | |
| US20160323151A1 (en) | Predicting an effect of performing an action on a node of a geographical network | |
| CN111626767B (en) | Resource data issuing method, device and equipment | |
| CN110348947A (en) | Object recommendation method and device | |
| CN107688901B (en) | Data adjusting method and device | |
| Azadnia et al. | Integration model of Fuzzy C means clustering algorithm and TOPSIS Method for Customer Lifetime Value Assessment | |
| KR102564359B1 (en) | Method for determining selling price of product for sale in online market | |
| Bernat et al. | Modelling customer lifetime value in a continuous, non-contractual time setting | |
| CN113516492A (en) | Data processing method and device | |
| Ulkhaq et al. | Predicting customer churn: A comparison of eight machine learning techniques: A case study in an indonesian telecommunication company | |
| CN116128562A (en) | Crowd transformation prediction method and device, electronic equipment and storage medium | |
| CN111724176A (en) | Shop traffic adjusting method, device, equipment and computer readable storage medium | |
| Fasanghari et al. | Customer churn prediction using local linear model tree for iranian telecommunication companies | |
| Elreedy et al. | A framework for an agent-based dynamic pricing for broadband wireless price rate plans | |
| Cetinkaya et al. | New product launch decisions with robust optimization | |
| Hervert-Escobar et al. | Optimal pricing model based on reduction dimension: A case of study for convenience stores | |
| Jahan et al. | An Improved Machine Learning Based Customer Churn Prediction for Insight and Recommendation in E-commerce | |
| CN110264250A (en) | Determine product peers amount in the method and device of the distributed data of multiple regions |
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: 20181012 |
|
| RJ01 | Rejection of invention patent application after publication |