CN109325810A - Supplement improvement method, electronic equipment and the computer storage medium of conversion with money - Google Patents
Supplement improvement method, electronic equipment and the computer storage medium of conversion with money Download PDFInfo
- Publication number
- CN109325810A CN109325810A CN201811162216.2A CN201811162216A CN109325810A CN 109325810 A CN109325810 A CN 109325810A CN 201811162216 A CN201811162216 A CN 201811162216A CN 109325810 A CN109325810 A CN 109325810A
- Authority
- CN
- China
- Prior art keywords
- money
- gear
- target user
- target
- supplement
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- 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)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a kind of improvement method for supplementing conversion with money, electronic equipment and computer storage mediums, the case where supplementing conversion results with money of the page is supplemented with money for improving, wherein, this method comprises: the reading behavior feature according to target user, supplements intention with money using Intention Anticipation model prediction target user;Based on prediction supplement intention with money and the target of target user supplements gear with money, recommend to correspond to that target supplements gear with money supplements strategy with money for target user, wherein supplement with money strategy include set according to preset rules supplement the corresponding preferential mode of gear with money with target.The embodiment of the present invention solve the problems, such as the access of user in the prior art supplement with money the page to supplement conversion results with money bad, by provided for target user it is personalized supplement strategy with money in a manner of, improve target user actually supplements behavior with money, improve supplement the page with money supplement conversion ratio with money.
Description
Technical field
The present invention relates to field of computer technology, and in particular to a kind of improvement method for supplementing conversion with money, electronic equipment and meter
Calculation machine storage medium.
Background technique
Currently, with universal and E-book reader the development of the mobile terminals such as mobile phone, e-book is increasingly reviewed
Read the favor of user.As a kind of reading trend of modernization, the advantage of electronic reading is fairly obvious: low-carbon, convenient, at low cost
And amount of storage is big.
For electronic reading enterprise, deficiency existing for application product is found in time, and enterprise is helped to continuously improve application
Function promotes product competitiveness, improves efficiency of operation and user experience, is the substantial responsibility of enterprise.However, in the reading side of supplementing with money
Face still lacks the personalized payment way for being directed to user in the prior art, cause user actually to supplement conversion ratio with money not high.
Summary of the invention
In view of the above problems, it proposes on the present invention overcomes the above problem or at least be partially solved in order to provide one kind
State the improvement method for supplementing conversion with money, electronic equipment and the computer storage medium of problem.
According to an aspect of the invention, there is provided a kind of improvement method for supplementing conversion with money, which comprises according to mesh
The reading behavior feature for marking user, supplements intention with money using Intention Anticipation model prediction target user;Based on filling for the prediction
Value is intended to and the target of target user supplements gear with money, recommends to correspond to that target supplements gear with money supplements strategy with money for target user,
In, the strategy of supplementing with money includes supplementing the corresponding preferential mode of gear with money with target according to preset rules setting.
According to another aspect of the present invention, provide a kind of electronic equipment, comprising: processor, memory, communication interface and
Communication bus, the processor, the memory and the communication interface complete mutual communication by the communication bus;
The memory makes the processor execute following operation for storing an at least executable instruction, the executable instruction: according to
According to the reading behavior feature of target user, intention is supplemented with money using Intention Anticipation model prediction target user;Based on the prediction
Supplement intention with money and the target of target user supplements gear with money, recommend to correspond to that target supplements gear with money supplements plan with money for target user
Slightly, wherein it is described supplement with money strategy include set according to preset rules supplement the corresponding preferential mode of gear with money with target.
According to another aspect of the invention, a kind of computer storage medium is provided, at least one is stored in storage medium
Executable instruction, executable instruction make processor execute following operation: according to the reading behavior feature of target user, utilizing intention
Prediction model prediction target user's supplements intention with money;The target for supplementing intention and target user with money based on the prediction supplements shelves with money
Position, recommends to correspond to that target supplements gear with money supplements strategy with money for target user, wherein the strategy of supplementing with money includes according to default rule
What is then set supplements the corresponding preferential mode of gear with money with target.
The improvement method for supplementing conversion with money, electronic equipment and computer storage medium according to the present invention, by according to target
The reading behavior feature of user predicts that it supplements intention with money, and then combines to supplement with money and be intended to target user and recommend to correspond to its target fill
Value gear supplements strategy with money, solve the problems, such as the access of user in the prior art supplement with money the page to supplement conversion results with money bad, with
The personalized mode for supplementing strategy with money is provided for target user, improve target user actually supplements behavior with money, improves and supplements with money
The page supplements conversion ratio with money.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
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 present invention
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 chart of improvement method for supplementing conversion with money provided in an embodiment of the present invention;
Fig. 2 shows the flow charts that another kind provided in an embodiment of the present invention supplements the improvement method of conversion with money;
Fig. 3 shows the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
The exemplary embodiment that the present invention will be described in more detail below with reference to accompanying drawings.Although showing the present invention in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the present invention without should be by embodiments set forth here
It is limited.It is to be able to thoroughly understand the present invention on the contrary, providing these embodiments, and can be by the scope of the present invention
It is fully disclosed to those skilled in the art.
Fig. 1 shows a kind of flow chart of improvement method for supplementing conversion with money provided in an embodiment of the present invention, fills for improving
The case where supplementing conversion results with money of the value page, this method can be by supporting the electronic equipment of installation e-book reading application to execute.
As shown in Figure 1, method includes the following steps:
Step S101 utilizes filling for Intention Anticipation model prediction target user according to the reading behavior feature of target user
Value is intended to.
In the present embodiment the reading behavior feature of target user refer to and supplement with money behavior there are the behavioural characteristic of relevance, because
And input of the reading behavior feature for the target user that can be will acquire as Intention Anticipation model, predict filling for target user
Value is intended to.It supplements with money and is intended to indicate the probability that user is currently supplemented with money.For example, Intention Anticipation model table in the form of output probability
Show the intention of supplementing with money of user, the probability value of output is bigger, and the probability for indicating that user is currently supplemented with money is bigger.
Optionally, it is intended that prediction model is two disaggregated models, and training process includes:
Obtain the reading behavior feature of sample of users;
Reading behavior feature is distinguished, positive sample feature and negative sample feature are obtained, wherein positive sample feature, which refers to, reads
The feature successfully supplemented with money involved in behavioural characteristic is read, negative sample feature refers to the spy supplemented with money not successfully involved in reading behavior feature
Sign;
Two classifiers are obtained using positive sample feature and the training of negative sample feature, as Intention Anticipation model.
Sample of users is a large amount of reading users for training Intention Anticipation model and grabbing at random.Positive sample feature includes spy
Sample of users accesses for the first time or repeatedly in section of fixing time supplements the page with money and completes to supplement related behavior with money within a preset time
Feature, wherein preset time is arranged according to the factors adaptability such as page load time and payment plug-in unit load time is supplemented with money, example
Such as 60 seconds.Negative sample feature include in same time period user access supplement the page with money but supplement related row with money not successfully always
It is characterized.The reading behavior that family is mixed the sample with whether by according to successful recharging distinguishes, and is subsequently used for the training of model, can
Supplement the accuracy of intention with money with utility model prediction.
Specifically, the reading behavior feature of target user or sample of users includes that current reading behavior feature and history are read
Read behavioural characteristic.Current reading behavior feature and history reading behavior are characterized in distinguishing using the time on the same day as boundary, user
The reading behavior on the same day is attributed to current reading behavior, and the reading behavior feature in the certain period of time before the time on the same day sums up
For history reading behavior feature.For target user, the time on the same day described here executes and supplements working as Intention Anticipation with money
It;For sample of users, the time on the same day described here is the same day for implementing payment or payment being not carried out.It is exemplary
, current reading behavior feature include: in the time on the same day read books progress of user, download progress, paid cases, user work as
Preceding balance status and user is to the feature for supplementing the dimensions such as preferential attention rate with money;History reading behavior feature includes: the same day
Downloading, payment in preceding certain period of time, reading histories, supplement with money, preferential Generalization bounds it is preferential using situation and to supplementing with money
The feature of the dimensions such as attention rate.The storage location of current reading behavior feature and history reading behavior feature has differences, therefore,
It needs to transfer corresponding data from different storage locations.
Step S102, based on prediction supplement intention with money and the target of target user supplements gear with money, for target user recommend pair
Strategy should be supplemented with money in what target supplemented gear with money, wherein supplementing strategy with money includes supplementing gear with money with target according to preset rules setting
Corresponding preferential mode.
Target, which supplements gear with money, indicates that the current most probable if being supplemented with money of target user selected supplements amount with money, can pass through
Behavioural analysis is carried out to target user to determine.Optionally, this method further include: personal information and history according to target user are filled
Value information determines that the target of target user supplements gear with money.Target supplement with money gear may include history it is usual supplement with money gear or in the recent period
Supplement gear with money.For example, being obtained by analyzing target user's personal information within a preset period of time and history charging information
There is no variations for the purchasing power of target user out, and it is very high using the frequency that gear c is supplemented with money is supplemented with money, then can be with
Gear c will be supplemented with money it is determined as its target and supplement gear with money, and will supplement gear c with money at this time and belong to that history is usual to supplement gear with money;Alternatively, to mesh
During the personal information of mark user is analyzed, it is found that its identity information changes, such as engineer is become from student,
Show that its purchasing power is changed, it is higher using the frequency that gear z is supplemented with money is supplemented with money after identity variation, then it can will
It supplements gear z with money and is determined as its target and supplement gear with money, supplement gear z with money at this time and belong to and supplement gear with money in the recent period.
When predict probability that target user is currently supplemented with money it is smaller when, gear is supplemented with money according to its target, is recommended for it
It is preferential with stronger dynamics to supplement strategy with money;When predict probability that target user is currently supplemented with money it is larger when, then can be pushed away for it
Favour of recommending the excellent dynamics is lesser to supplement strategy with money.The purpose for supplementing strategy with money is recommended to be to improve the lesser use of probability currently supplemented with money
Behavior is actually supplemented at family with money, supplements conversion ratio with money with improve that user's access supplements the page with money, i.e. access is supplemented the page with money and successfully filled
The ratio between the total number of users amount of the page is supplemented in the number of users of value and access with money.
It supplements the preset rules in strategy with money to be formulated by reading application service provider, determines the specific preferential side for showing user
Formula, for example, give charging bills or supplement discounting with money etc..
Illustratively, it is x1 that the target of target user A, which supplements gear with money, and the probability for predicting that it is currently supplemented with money is smaller, then
Can under x1 gear, for its recommend discount it is biggish supplement with money it is preferential;It is x2 that the target of target user B, which supplements gear with money, predicts it
Currently the probability supplemented with money is larger, can recommend discount is lesser to supplement with money preferential for it under x2 gear, also can choose not
It is preferential for its recommendation.
Optionally, in the reading behavior feature according to target user, filling for Intention Anticipation model prediction target user is utilized
Before value is intended to, this method further include:
The current page for reading application is detected;
If current page is to supplement the page with money, the prediction for supplementing intention with money is executed.
That is the implementing precondition of the present embodiment is that the page is supplemented in target user's access with money, for example, target user is in read electronic
The page is supplemented in access with money during book, or is switched to according to the active link of push by current page and supplemented page etc. with money.When true
Determining current page is to supplement the page with money, just executes the prediction and subsequent operation for supplementing intention with money.Wherein, page detection can pass through
The detection modes such as page layout information and page control are realized.
The present embodiment technical solution is pre- using Intention Anticipation model by being first depending on the reading behavior feature of target user
Survey target user and supplement intentions with money, then, based on prediction supplement intention with money and the target of target user supplements gear with money, be target use
Family recommends to correspond to that target supplements gear with money supplements strategy with money, and solve that user's access in the prior art supplements the page with money supplements conversion with money
The problem of result badly, provided for target user it is personalized supplement strategy with money by way of, improve actually supplementing with money for user
Behavior, improve supplement the page with money supplement conversion ratio with money.
Fig. 2 shows the flow charts that another kind provided in an embodiment of the present invention supplements the improvement method of conversion with money, as above-mentioned
The refinement and extension of embodiment technical solution, in this implementation in the content of not detailed description can refer to retouching in above-described embodiment
It states.As shown in Fig. 2, method includes the following steps:
Step S201 utilizes filling for Intention Anticipation model prediction target user according to the reading behavior feature of target user
Value is intended to.
Step S202, the reading behavior feature based on target user, using gear prediction model prediction target user to filling
That each supplements gear on the value page with money supplements probability with money.
Illustratively, currently supplementing show on the page multiple with money and supplementing gear with money includes: k1, k2, k3, k4, k5 and k6, according to
The reading behavior feature of target user A predicts user and supplements probability with money to what k1 to k6 this 6 supplemented gear with money are as follows: 12%, 8%,
45%, 15%, 3%, 17%, supplement that probability is bigger with money, indicate user's selection supplement with money accordingly gear frequency it is bigger.Pass through utilization
Gear prediction model predict target user to supplement with money each supplement gear on the page with money supplement probability with money, it can be ensured that succeeding target fills
It is worth the accuracy that gear determines, helps to improve user to the use rate for supplementing strategy with money of recommendation.
Optionally, gear prediction model is more disaggregated models, and the training process of gear prediction model includes:
Obtain the reading behavior feature of sample of users, wherein reading behavior feature, which is included in difference, supplements gear with money and filled
Corresponding reading behavior feature when value;
Multi-categorizer is obtained using the training of reading behavior feature, as gear prediction model.
Step S203 supplements gear with money according to the target for supplementing determine the probability target user with money, wherein target supplements filling for gear with money
It is worth probability and is greater than or equal to probability threshold value.
Probability threshold value adaptability setting according to different users determines that supplementing with money for target user is general according to probability threshold value
Rate is maximum to supplement gear with money as target and supplements gear with money.Continue taking the above example as an example, if probability threshold value is set as 40%,
Determining that the target of target user supplements gear with money is k3;If probability threshold value is set as 15%, it can determine that target user's is standby
It includes k3, k5 and k6 that gear is supplemented in choosing, which with money, at this point it is possible to select to supplement this multiple alternatively supplements with money with money maximum probability supplement with money in gear
Gear is determined as target and supplements gear with money.
Step S204 supplements intention with money based on target user, recommends to supplement that gear is corresponding to be filled with money with target for target user
Value strategy.
It can be user in the case where target supplements gear with money if the probability that prediction target user is currently supplemented with money is smaller
Recommend preferential with stronger dynamics to supplement strategy with money.
The present embodiment technical solution is secondly sharp by supplementing intention with money first with Intention Anticipation model prediction target user
With gear prediction model prediction target user to supplement with money each supplement gear on the page with money supplement probability with money, determine the mesh of target user
Mark supplements gear with money;Intention is finally supplemented with money based on target user, recommends to supplement that gear is corresponding to supplement with money with money with target for target user
Strategy, solve the problems, such as the access of user in the prior art supplement with money the page to supplement conversion results with money bad, by for target user
The personalized mode for supplementing strategy with money is provided, including predicting that supplementing intention and personalized target with money supplements gear with money, further improves
User's actually supplements behavior with money, improve supplement the page with money supplement conversion ratio with money.
Fig. 3 shows the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention, the specific embodiment of the invention
The specific implementation of electronic equipment is not limited.
As shown in figure 3, the electronic equipment may include: processor (processor) 302, communication interface
(Communications Interface) 304, memory (memory) 306 and communication bus 308.
Wherein:
Processor 302, communication interface 304 and memory 306 complete mutual communication by communication bus 308.
Communication interface 304, for being communicated with the network element of other equipment such as client or other electronic equipments etc..
Processor 302 can specifically execute in the above-mentioned improvement method embodiment for supplementing conversion with money for executing program 310
Correlation step.
Specifically, program 310 may include program code, which includes computer operation instruction.
Processor 302 may be central processor CPU or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or be arranged to implement the integrated electricity of one or more of the embodiment of the present invention
Road.The one or more processors that electronic equipment includes can be same type of processor, such as one or more CPU;It can also
To be different types of processor, such as one or more CPU and one or more ASIC.
Memory 306, for storing program 310.Memory 306 may include high speed RAM memory, it is also possible to further include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Program 310 specifically can be used for so that processor 302 executes following operation:
According to the reading behavior feature of target user, intention is supplemented with money using Intention Anticipation model prediction target user;
The target for supplementing intention and target user with money based on the prediction supplements gear with money, recommends to correspond to mesh for target user
What mark supplemented gear with money supplements strategy with money, wherein the strategy of supplementing with money includes supplementing gear pair with money with target according to what preset rules were set
The preferential mode answered.
In a kind of optional mode, program 310 can be specifically also used to so that processor 302 executes following operation:
According to the personal information and history charging information of target user, determine that the target of target user supplements gear with money.
In a kind of optional mode, the Intention Anticipation model is two disaggregated models, and program 310 specifically can be also used for
So that processor 302 executes following operation:
Obtain the reading behavior feature of sample of users;
The reading behavior feature is distinguished, positive sample feature and negative sample feature are obtained, wherein the positive sample
Feature refers to that the feature successfully supplemented with money involved in the reading behavior feature, the negative sample feature refer in the reading behavior feature
It is related to the feature supplemented with money not successfully;
Two classifiers are obtained using the positive sample feature and the training of negative sample feature, as the Intention Anticipation model.
In a kind of optional mode, program 310 can specifically be further used for so that processor 302 executes following behaviour
Make:
Reading behavior feature based on target user, it is every on the page to supplementing with money using gear prediction model prediction target user
It is a supplement gear with money supplement probability with money;
Gear is supplemented with money according to the target for supplementing determine the probability target user with money, wherein it is general that target supplements supplementing with money for gear with money
Rate is greater than or equal to probability threshold value;
Intention is supplemented with money based on described, recommends to supplement that gear is corresponding to supplement strategy with money with money with target for target user.
In a kind of optional mode, the gear prediction model is more disaggregated models, and program 310 specifically can be also used for
So that processor 302 executes following operation:
Obtain sample of users reading behavior feature, wherein the reading behavior feature be included in difference supplement with money gear into
Row reading behavior feature corresponding when supplementing with money;
Multi-categorizer is obtained using reading behavior feature training, as the gear prediction model.
In a kind of optional mode, the reading behavior feature includes current reading behavior feature and history reading behavior
Feature.
In a kind of optional mode, program 310 specifically be can be also used for so that processor 302 executes following operation:
The current page for reading application is detected;
If the current page is to supplement the page with money, the prediction of intention is supplemented described in execution with money.
The embodiment of the invention also provides a kind of nonvolatile computer storage media, the computer storage medium storage
There is an at least executable instruction, which can be performed in above-mentioned any means embodiment and supplement mentioning for conversion with money
High method.
Executable instruction specifically can be used for so that processor executes following operation:
According to the reading behavior feature of target user, intention is supplemented with money using Intention Anticipation model prediction target user;
The target for supplementing intention and target user with money based on the prediction supplements gear with money, recommends to correspond to mesh for target user
What mark supplemented gear with money supplements strategy with money, wherein the strategy of supplementing with money includes supplementing gear pair with money with target according to what preset rules were set
The preferential mode answered.
In a kind of optional mode, the executable instruction also makes the processor execute following operation:
According to the personal information and history charging information of target user, determine that the target of target user supplements gear with money.
In a kind of optional mode, the Intention Anticipation model is two disaggregated models, and the executable instruction also makes institute
It states processor and executes following operation:
Obtain the reading behavior feature of sample of users;
The reading behavior feature is distinguished, positive sample feature and negative sample feature are obtained, wherein the positive sample
Feature refers to that the feature successfully supplemented with money involved in the reading behavior feature, the negative sample feature refer in the reading behavior feature
It is related to the feature supplemented with money not successfully;
Two classifiers are obtained using the positive sample feature and the training of negative sample feature, as the Intention Anticipation model.
In a kind of optional mode, the executable instruction further makes the processor execute following operation:
Reading behavior feature based on target user, it is every on the page to supplementing with money using gear prediction model prediction target user
It is a supplement gear with money supplement probability with money;
Gear is supplemented with money according to the target for supplementing determine the probability target user with money, wherein it is general that target supplements supplementing with money for gear with money
Rate is greater than or equal to probability threshold value;
Intention is supplemented with money based on described, recommends to supplement that gear is corresponding to supplement strategy with money with money with target for target user.
In a kind of optional mode, the gear prediction model is more disaggregated models, and the executable instruction also makes institute
It states processor and executes following operation:
Obtain sample of users reading behavior feature, wherein the reading behavior feature be included in difference supplement with money gear into
Row reading behavior feature corresponding when supplementing with money;
Multi-categorizer is obtained using reading behavior feature training, as the gear prediction model.
In a kind of optional mode, the reading behavior feature includes current reading behavior feature and history reading behavior
Feature.
In a kind of optional mode, the executable instruction also makes the processor execute following operation:
The current page for reading application is detected;
If the current page is to supplement the page with money, the prediction of intention is supplemented described in execution with money.
Further, the invention also discloses the following contents:
A1, a kind of improvement method for supplementing conversion with money, which comprises
According to the reading behavior feature of target user, intention is supplemented with money using Intention Anticipation model prediction target user;
The target for supplementing intention and target user with money based on the prediction supplements gear with money, recommends to correspond to mesh for target user
What mark supplemented gear with money supplements strategy with money, wherein the strategy of supplementing with money includes supplementing gear pair with money with target according to what preset rules were set
The preferential mode answered.
A2, the method according to a1, wherein the method also includes:
According to the personal information and history charging information of target user, determine that the target of target user supplements gear with money.
A3, the method according to a1, wherein the Intention Anticipation model is two disaggregated models, the Intention Anticipation mould
The training process of type includes:
Obtain the reading behavior feature of sample of users;
The reading behavior feature is distinguished, positive sample feature and negative sample feature are obtained, wherein the positive sample
Feature refers to that the feature successfully supplemented with money involved in the reading behavior feature, the negative sample feature refer in the reading behavior feature
It is related to the feature supplemented with money not successfully;
Two classifiers are obtained using the positive sample feature and the training of negative sample feature, as the Intention Anticipation model.
A4, the method according to a1, wherein the target for supplementing intention and target user with money based on the prediction is filled
It is worth gear, recommends to correspond to that target supplements gear with money supplements strategy with money for target user, comprising:
Reading behavior feature based on target user, it is every on the page to supplementing with money using gear prediction model prediction target user
It is a supplement gear with money supplement probability with money;
Gear is supplemented with money according to the target for supplementing determine the probability target user with money, wherein it is general that target supplements supplementing with money for gear with money
Rate is greater than or equal to probability threshold value;
Intention is supplemented with money based on described, recommends to supplement that gear is corresponding to supplement strategy with money with money with target for target user.
A5, the method according to a4, wherein the gear prediction model is more disaggregated models, and the gear predicts mould
The training process of type includes:
Obtain sample of users reading behavior feature, wherein the reading behavior feature be included in difference supplement with money gear into
Row reading behavior feature corresponding when supplementing with money;
Multi-categorizer is obtained using reading behavior feature training, as the gear prediction model.
A6, the method according to any in a1-a5, wherein the reading behavior feature includes that current reading behavior is special
History of seeking peace reading behavior feature.
A7, the method according to a6, wherein pre- using being intended in the reading behavior feature according to target user
Survey model prediction target user supplement intention with money before, the method also includes:
The current page for reading application is detected;
If the current page is to supplement the page with money, the prediction of intention is supplemented described in execution with money.
B8, a kind of electronic equipment, comprising: processor, memory, communication interface and communication bus, it is the processor, described
Memory and the communication interface complete mutual communication by the communication bus;
For the memory for storing an at least executable instruction, it is following that the executable instruction executes the processor
Operation:
According to the reading behavior feature of target user, intention is supplemented with money using Intention Anticipation model prediction target user;
The target for supplementing intention and target user with money based on the prediction supplements gear with money, recommends to correspond to mesh for target user
What mark supplemented gear with money supplements strategy with money, wherein the strategy of supplementing with money includes supplementing gear pair with money with target according to what preset rules were set
The preferential mode answered.
B9, the electronic equipment according to b8, the executable instruction also make the processor execute following operation:
According to the personal information and history charging information of target user, determine that the target of target user supplements gear with money.
B10, the electronic equipment according to b8, wherein the Intention Anticipation model is two disaggregated models, described executable
Instruction also makes the processor execute following operation:
Obtain the reading behavior feature of sample of users;
The reading behavior feature is distinguished, positive sample feature and negative sample feature are obtained, wherein the positive sample
Feature refers to that the feature successfully supplemented with money involved in the reading behavior feature, the negative sample feature refer in the reading behavior feature
It is related to the feature supplemented with money not successfully;
Two classifiers are obtained using the positive sample feature and the training of negative sample feature, as the Intention Anticipation model.
B11, the electronic equipment according to b8, the executable instruction further make the processor execute following behaviour
Make:
Reading behavior feature based on target user, it is every on the page to supplementing with money using gear prediction model prediction target user
It is a supplement gear with money supplement probability with money;
Gear is supplemented with money according to the target for supplementing determine the probability target user with money, wherein it is general that target supplements supplementing with money for gear with money
Rate is greater than or equal to probability threshold value;
Intention is supplemented with money based on described, recommends to supplement that gear is corresponding to supplement strategy with money with money with target for target user.
B12, the electronic equipment according to b11, wherein the gear prediction model is more disaggregated models, described to hold
Row instruction also makes the processor execute following operation:
Obtain sample of users reading behavior feature, wherein the reading behavior feature be included in difference supplement with money gear into
Row reading behavior feature corresponding when supplementing with money;
Multi-categorizer is obtained using reading behavior feature training, as the gear prediction model.
B13, the electronic equipment according to any in b8-b12, wherein the reading behavior feature includes current reads
Behavioural characteristic and history reading behavior feature.
B14, the electronic equipment according to b13, the executable instruction also make the processor execute following operation:
The current page for reading application is detected;
If the current page is to supplement the page with money, the prediction of intention is supplemented described in execution with money.
C15, a kind of computer storage medium are stored with an at least executable instruction in the storage medium, described to hold
Row instruction makes processor execute following operation:
According to the reading behavior feature of target user, intention is supplemented with money using Intention Anticipation model prediction target user;
The target for supplementing intention and target user with money based on the prediction supplements gear with money, recommends to correspond to mesh for target user
What mark supplemented gear with money supplements strategy with money, wherein the strategy of supplementing with money includes supplementing gear pair with money with target according to what preset rules were set
The preferential mode answered.
C16, the computer storage medium according to c15, it is following that the executable instruction also executes the processor
Operation:
According to the personal information and history charging information of target user, determine that the target of target user supplements gear with money.
C17, the computer storage medium according to c15, wherein the Intention Anticipation model is two disaggregated models, institute
Stating executable instruction also makes the processor execute following operation:
Obtain the reading behavior feature of sample of users;
The reading behavior feature is distinguished, positive sample feature and negative sample feature are obtained, wherein the positive sample
Feature refers to that the feature successfully supplemented with money involved in the reading behavior feature, the negative sample feature refer in the reading behavior feature
It is related to the feature supplemented with money not successfully;
Two classifiers are obtained using the positive sample feature and the training of negative sample feature, as the Intention Anticipation model.
C18, the computer storage medium according to c15, the executable instruction further execute the processor
It operates below:
Reading behavior feature based on target user, it is every on the page to supplementing with money using gear prediction model prediction target user
It is a supplement gear with money supplement probability with money;
Gear is supplemented with money according to the target for supplementing determine the probability target user with money, wherein it is general that target supplements supplementing with money for gear with money
Rate is greater than or equal to probability threshold value;
Intention is supplemented with money based on described, recommends to supplement that gear is corresponding to supplement strategy with money with money with target for target user.
C19, the computer storage medium according to c18, wherein the gear prediction model is more disaggregated models, institute
Stating executable instruction also makes the processor execute following operation:
Obtain sample of users reading behavior feature, wherein the reading behavior feature be included in difference supplement with money gear into
Row reading behavior feature corresponding when supplementing with money;
Multi-categorizer is obtained using reading behavior feature training, as the gear prediction model.
C20, the computer storage medium according to any in c15-c19, wherein the reading behavior feature includes working as
Preceding reading behavior feature and history reading behavior feature.
C21, the computer storage medium according to c20, it is following that the executable instruction also executes the processor
Operation:
The current page for reading application is detected;
If the current page is to supplement the page with money, the prediction of intention is supplemented described in execution with money.
Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein.
Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system
Structure be obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can use various
Programming language realizes summary of the invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of the various inventive aspects,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims features more more than feature expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
Meaning one of can in any combination mode come using.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.The use of word first, second, and third does not indicate any sequence.These words can be construed to title.
Claims (10)
1. a kind of improvement method for supplementing conversion with money, which comprises
According to the reading behavior feature of target user, intention is supplemented with money using Intention Anticipation model prediction target user;
The target for supplementing intention and target user with money based on the prediction supplements gear with money, recommends to fill corresponding to target for target user
Value gear supplements strategy with money, wherein it is described supplement with money strategy include according to preset rules setting to supplement gear with money with target corresponding
Preferential mode.
2. according to the method described in claim 1, wherein, the method also includes:
According to the personal information and history charging information of target user, determine that the target of target user supplements gear with money.
3. according to the method described in claim 1, wherein, the Intention Anticipation model is two disaggregated models, the Intention Anticipation
The training process of model includes:
Obtain the reading behavior feature of sample of users;
The reading behavior feature is distinguished, positive sample feature and negative sample feature are obtained, wherein the positive sample feature
Refer to that the feature successfully supplemented with money involved in the reading behavior feature, the negative sample feature refer to involved in the reading behavior feature
The feature supplemented with money not successfully;
Two classifiers are obtained using the positive sample feature and the training of negative sample feature, as the Intention Anticipation model.
4. described to supplement intention and the target of target user with money based on the prediction according to the method described in claim 1, wherein
It supplements gear with money, recommends to correspond to that target supplements gear with money supplements strategy with money for target user, comprising:
Reading behavior feature based on target user, using gear prediction model, prediction target user is each filled on the page to supplementing with money
Value gear supplements probability with money;
Supplement gear with money according to the target for supplementing determine the probability target user with money, wherein target supplement with money gear to supplement probability with money big
In or equal to probability threshold value;
Intention is supplemented with money based on described, recommends to supplement that gear is corresponding to supplement strategy with money with money with target for target user.
5. the gear is predicted according to the method described in claim 4, wherein, the gear prediction model is more disaggregated models
The training process of model includes:
Obtain the reading behavior feature of sample of users, wherein the reading behavior feature, which is included in difference, supplements gear with money and filled
Corresponding reading behavior feature when value;
Multi-categorizer is obtained using reading behavior feature training, as the gear prediction model.
6. any method in -5 according to claim 1, wherein the reading behavior feature includes that current reading behavior is special
History of seeking peace reading behavior feature.
7. according to the method described in claim 6, wherein, in the reading behavior feature according to target user, utilizing intention
Prediction model prediction target user supplement intention with money before, the method also includes:
The current page for reading application is detected;
If the current page is to supplement the page with money, the prediction of intention is supplemented described in execution with money.
8. a kind of electronic equipment, comprising: processor, memory, communication interface and communication bus, the processor, the storage
Device and the communication interface complete mutual communication by the communication bus;
The memory makes the processor execute following behaviour for storing an at least executable instruction, the executable instruction
Make:
According to the reading behavior feature of target user, intention is supplemented with money using Intention Anticipation model prediction target user;
The target for supplementing intention and target user with money based on the prediction supplements gear with money, recommends to fill corresponding to target for target user
Value gear supplements strategy with money, wherein it is described supplement with money strategy include according to preset rules setting to supplement gear with money with target corresponding
Preferential mode.
9. electronic equipment according to claim 8, the executable instruction also makes the processor execute following operation:
According to the personal information and history charging information of target user, determine that the target of target user supplements gear with money.
10. a kind of computer storage medium, an at least executable instruction, the executable instruction are stored in the storage medium
Processor is set to execute following operation:
According to the reading behavior feature of target user, intention is supplemented with money using Intention Anticipation model prediction target user;
The target for supplementing intention and target user with money based on the prediction supplements gear with money, recommends to fill corresponding to target for target user
Value gear supplements strategy with money, wherein it is described supplement with money strategy include according to preset rules setting to supplement gear with money with target corresponding
Preferential mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811162216.2A CN109325810B (en) | 2018-09-30 | 2018-09-30 | Recharge conversion improving method, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811162216.2A CN109325810B (en) | 2018-09-30 | 2018-09-30 | Recharge conversion improving method, electronic equipment and computer storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109325810A true CN109325810A (en) | 2019-02-12 |
CN109325810B CN109325810B (en) | 2020-08-21 |
Family
ID=65266535
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811162216.2A Active CN109325810B (en) | 2018-09-30 | 2018-09-30 | Recharge conversion improving method, electronic equipment and computer storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109325810B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112150177A (en) * | 2019-06-27 | 2020-12-29 | 百度在线网络技术(北京)有限公司 | Intention prediction method and device |
CN112307308A (en) * | 2019-07-26 | 2021-02-02 | 腾讯科技(深圳)有限公司 | Data processing method, device, equipment and medium |
CN114418593A (en) * | 2021-12-23 | 2022-04-29 | 中国电信股份有限公司 | Illegal behavior recognition method and device, electronic equipment and readable medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100198640A1 (en) * | 2003-06-11 | 2010-08-05 | Kabushiki Kaisha Toshiba | Electric-power-generating-facility operation management support system, electric-power-generating-facility operation management support method, and program for executing operation management support method on computer |
US20140278994A1 (en) * | 2013-03-14 | 2014-09-18 | Richard J. Greenwood | Interactive Mobile Engagement Recharging Terminal System and Device |
US20160072326A1 (en) * | 2014-09-08 | 2016-03-10 | Google Technology Holdings LLC | Battery cycle life through smart overnight charging |
CN106971321A (en) * | 2017-04-06 | 2017-07-21 | 百度在线网络技术(北京)有限公司 | Marketing message method for pushing, device, equipment and storage medium |
CN107862551A (en) * | 2017-11-06 | 2018-03-30 | 广州虎牙信息科技有限公司 | Forecasting Methodology, device and the terminal device of network application promotion effect |
CN108074084A (en) * | 2016-11-18 | 2018-05-25 | 腾讯科技(深圳)有限公司 | A kind of method, apparatus and server of delay disposal request |
CN108520048A (en) * | 2018-03-30 | 2018-09-11 | 掌阅科技股份有限公司 | Activity description method for pushing based on e-book and electronic equipment |
CN108536804A (en) * | 2018-03-30 | 2018-09-14 | 掌阅科技股份有限公司 | Information-pushing method, electronic equipment based on e-book and computer storage media |
CN110675215A (en) * | 2019-09-02 | 2020-01-10 | 深圳市链上深度科技有限公司 | Method, system and computer readable medium for managing membership card certificate |
-
2018
- 2018-09-30 CN CN201811162216.2A patent/CN109325810B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100198640A1 (en) * | 2003-06-11 | 2010-08-05 | Kabushiki Kaisha Toshiba | Electric-power-generating-facility operation management support system, electric-power-generating-facility operation management support method, and program for executing operation management support method on computer |
US20140278994A1 (en) * | 2013-03-14 | 2014-09-18 | Richard J. Greenwood | Interactive Mobile Engagement Recharging Terminal System and Device |
US20160072326A1 (en) * | 2014-09-08 | 2016-03-10 | Google Technology Holdings LLC | Battery cycle life through smart overnight charging |
CN108074084A (en) * | 2016-11-18 | 2018-05-25 | 腾讯科技(深圳)有限公司 | A kind of method, apparatus and server of delay disposal request |
CN106971321A (en) * | 2017-04-06 | 2017-07-21 | 百度在线网络技术(北京)有限公司 | Marketing message method for pushing, device, equipment and storage medium |
CN107862551A (en) * | 2017-11-06 | 2018-03-30 | 广州虎牙信息科技有限公司 | Forecasting Methodology, device and the terminal device of network application promotion effect |
CN108520048A (en) * | 2018-03-30 | 2018-09-11 | 掌阅科技股份有限公司 | Activity description method for pushing based on e-book and electronic equipment |
CN108536804A (en) * | 2018-03-30 | 2018-09-14 | 掌阅科技股份有限公司 | Information-pushing method, electronic equipment based on e-book and computer storage media |
CN110675215A (en) * | 2019-09-02 | 2020-01-10 | 深圳市链上深度科技有限公司 | Method, system and computer readable medium for managing membership card certificate |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112150177A (en) * | 2019-06-27 | 2020-12-29 | 百度在线网络技术(北京)有限公司 | Intention prediction method and device |
CN112307308A (en) * | 2019-07-26 | 2021-02-02 | 腾讯科技(深圳)有限公司 | Data processing method, device, equipment and medium |
CN114418593A (en) * | 2021-12-23 | 2022-04-29 | 中国电信股份有限公司 | Illegal behavior recognition method and device, electronic equipment and readable medium |
Also Published As
Publication number | Publication date |
---|---|
CN109325810B (en) | 2020-08-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106055379B (en) | Method and system for scheduling computing tasks | |
US20120117558A1 (en) | Mobile application migration service | |
TW201939379A (en) | Information conversion rate prediction method and apparatus, and information recommendation method and apparatus | |
CN104641363A (en) | Evaluating application compatibility | |
CN107408821A (en) | Isomery battery unit charges | |
CN106355391A (en) | Service processing method and device | |
CN108537568A (en) | A kind of information recommendation method and device | |
CN104731607B (en) | Terminal Lifelong Learning processing method, device and system | |
CN107622394A (en) | A kind of method of payment processes, medium, device and computing device | |
CN105183895A (en) | Virtual resource pushing method and device | |
US11861643B2 (en) | Reinforcement learning method for driver incentives: generative adversarial network for driver-system interactions | |
KR102282023B1 (en) | Apparatus for recommending user's privacy control and method for the same | |
CN110046986A (en) | The overdue customer grouping method and device of loaning bill based on big data | |
Behan et al. | Adaptive graphical user interface solution for modern user devices | |
CN111340240A (en) | Method and device for realizing automatic machine learning | |
CN111598494A (en) | Resource limit adjusting method and device and electronic equipment | |
CN109325810A (en) | Supplement improvement method, electronic equipment and the computer storage medium of conversion with money | |
CN109598526A (en) | The analysis method and device of media contribution | |
US9618995B2 (en) | System and method for displaying content on a computing device during an inactive or off-state | |
CN106598379A (en) | Method and device for managing application program | |
RU2616164C2 (en) | Methods and device for browser engine work | |
CN115048577A (en) | Model training method, device, equipment and storage medium | |
CN111199420A (en) | User invitation method and device and electronic equipment | |
US20190179894A1 (en) | Contextual automation of information technology change services | |
CN110363583B (en) | Method and device for creating user consumption behavior label based on position information and electronic equipment |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |