CN109214585A - Customer consumption prediction technique, device, electronic equipment and storage medium - Google Patents
Customer consumption prediction technique, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109214585A CN109214585A CN201811119739.9A CN201811119739A CN109214585A CN 109214585 A CN109214585 A CN 109214585A CN 201811119739 A CN201811119739 A CN 201811119739A CN 109214585 A CN109214585 A CN 109214585A
- Authority
- CN
- China
- Prior art keywords
- consumption
- user
- predicted
- amount
- registered users
- 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
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment provides a kind of customer consumption prediction technique, device, electronic equipment and storage mediums, are related to field of artificial intelligence.This method comprises: the user information for obtaining registered users and the consumption history information in multiple marketing activities；The user characteristics and consumption feature of registered users are extracted from the user information and the consumption history information；Consumption prediction model is trained based on the user characteristics and the consumption feature；User to be predicted is predicted in the amount of consumption of the following predetermined amount of time in each marketing activity by consumption predictions model.The technical solution of the embodiment of the present invention use the intelligent predicting scheme based on artificial intelligence analysis, can automatically and accurately predict user the following predetermined amount of time each marketing activity the amount of consumption, so as to pointedly to user carry out precision marketing.
Description
Technical field
The present invention relates to field of artificial intelligence, in particular to a kind of customer consumption prediction technique, customer consumption
Prediction meanss, electronic equipment and computer readable storage medium.
Background technique
With the development of internet technology, the annual online a large amount of marketing activity of the various network platforms, increases registration user newly
Quantity also increasingly increase, how the consumption to new registration user in following a period of time carry out prediction become concern
Focus.
Currently, passing through user characteristics such as age, educational background, occupation of new registration user etc. pair in a kind of technical solution
New registration user predicts in consumption of the following a period of time in each marketing activity.However, in the technical solution
In, it is difficult to accurately predict consumption of the user in each marketing activity according only to user characteristics, it can not specific aim
Ground carries out precision marketing to user.
Accordingly, it is desirable to provide a kind of customer consumption prediction side for the one or more problems being able to solve in the above problem
Method, customer consumption prediction meanss, electronic equipment and computer readable storage medium.
It should be noted that information is only used for reinforcing the reason to background of the present invention disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The embodiment of the present invention is designed to provide a kind of customer consumption prediction technique, customer consumption prediction meanss, electronics
Equipment and computer readable storage medium, so overcome limitation and defect due to the relevant technologies at least to a certain extent and
One or more caused problem.
According to a first aspect of the embodiments of the present invention, a kind of customer consumption prediction technique is provided, comprising: obtain registered
The user information of user and the consumption history information in multiple marketing activities；It is gone through from the user information and the consumption
The user characteristics and consumption feature of the registered users are extracted in history information；Based on the user characteristics and the consumption
Feature is trained consumption prediction model；Existed to user to be predicted in the following predetermined amount of time by the consumption predictions model
The amount of consumption in each marketing activity is predicted.
In some embodiments of the invention, aforementioned schemes are based on, the user characteristics and the consumption feature are based on
Consumption prediction model is trained, comprising: the user characteristics and the consumption feature are divided into instruction according to predetermined ratio
Practice sample set and verifying sample set；The consumption predictions model is trained based on the training sample set, is tested based on described
Card sample set is adjusted the parameter of the consumption predictions model.
In some embodiments of the invention, aforementioned schemes are based on, obtain the user information of registered users and more
Consumption history information in a marketing activity, comprising: the identification information based on the user to be predicted obtains the use to be predicted
The registration month at family；It is determining corresponding with the following predetermined amount of time using the anti-pushing manipulation of time series based on the registration month
Time series；The user information of the registered users and disappearing in multiple marketing activities are obtained based on the time series
Take historical information.
In some embodiments of the invention, aforementioned schemes are based on, by the consumption predictions model to user to be predicted
It is predicted in the amount of consumption of the following predetermined amount of time in each marketing activity, comprising: pre- by the consumption predictions model
The registered users are surveyed in the amount of consumption of the registration month in each marketing activity of the user to be predicted；Based on it is described
The amount of consumption for registering user carries out user to be predicted in the amount of consumption of the following predetermined amount of time in each marketing activity
Prediction.
In some embodiments of the invention, aforementioned schemes are based on, are pushed away based on the registration month using time series is counter
The determining time series corresponding with the future predetermined amount of time of method, comprising: be monthly divided into the following predetermined amount of time
Multiple time serieses；Based on the registration month and the multiple time series using the anti-pushing manipulation of time series it is determining with it is described
The corresponding time series of following predetermined amount of time.
In some embodiments of the invention, aforementioned schemes are based on, the amount of consumption based on the registered users is treated pre-
It surveys user to predict in the amount of consumption of the following predetermined amount of time in each marketing activity, comprising: will be described to be predicted
The ratio of the registration amount of the registration amount and registered users of user is as the first weight coefficient；By the user's to be predicted
The ratio of Characteristics of age distribution and the Characteristics of age distribution of the registered users is as the second weight coefficient；Based on described first
Weight coefficient and second weight coefficient to the registered users the registration month of the user to be predicted the amount of consumption
It is adjusted；The amount of consumption based on registered users adjusted exists to the user to be predicted in the following predetermined amount of time
The amount of consumption in each marketing activity is predicted.
In some embodiments of the invention, aforementioned schemes are based on, the consumption predictions model is Logic Regression Models.
According to a second aspect of the embodiments of the present invention, a kind of customer consumption prediction meanss are provided, comprising: acquisition of information list
Member, the user information for obtaining registered users and the consumption history information in multiple marketing activities；Feature extraction list
Member, for extracting the user characteristics of the registered users from the user information and the consumption history information and disappearing
Take feature；Model training unit, for being instructed based on the user characteristics and the consumption feature to consumption prediction model
Practice；Predicting unit, for being lived in the following predetermined amount of time in each marketing by the consumption predictions model to user to be predicted
The amount of consumption on dynamic is predicted.
According to a third aspect of the embodiments of the present invention, a kind of electronic equipment is provided, comprising: processor；And memory,
It is stored with computer-readable instruction on the memory, is realized when the computer-readable instruction is executed by the processor as above
State customer consumption prediction technique described in first aspect.
According to a fourth aspect of the embodiments of the present invention, a kind of computer readable storage medium is provided, meter is stored thereon with
Calculation machine program realizes the customer consumption prediction side as described in above-mentioned first aspect when the computer program is executed by processor
Method.
In the technical solution provided by some embodiments of the present invention, using the intelligent predicting based on artificial intelligence analysis
Scheme, on the one hand, the user characteristics of registered users are extracted from the user information of registered users and consumption history information
And consumption feature, consumption prediction model is trained based on user characteristics and consumption feature, registered use can be combined
The user characteristics and consumption feature at family are trained model；On the other hand, by consumption predictions model to user to be predicted
It is predicted in the amount of consumption of the following predetermined amount of time in each marketing activity, can automatically and accurately predict user in future
Predetermined amount of time each marketing activity the amount of consumption, so as to pointedly to user carry out precision marketing.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
It can the limitation present invention.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets implementation of the invention
Example, and be used to explain the principle of the present invention together with specification.It should be evident that the accompanying drawings in the following description is only the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.In the accompanying drawings:
Fig. 1 shows the flow diagram of customer consumption prediction technique according to some embodiments of the present invention；
Fig. 2 shows the consumption for using the anti-pushing manipulation of time series to obtain registered users according to some embodiments of the present invention
The flow diagram of historical information；
Fig. 3 shows the schematic diagram of the anti-pushing manipulation of time series according to some embodiments of the present invention；
Fig. 4 shows the schematic block diagram of the customer consumption prediction meanss of an exemplary embodiment according to the present invention；
Fig. 5 shows the structural schematic diagram for being suitable for the computer system for the electronic equipment for being used to realize the embodiment of the present invention.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be real in a variety of forms
It applies, and is not understood as limited to embodiment set forth herein；On the contrary, thesing embodiments are provided so that the present invention will be comprehensively and complete
It is whole, and the design of example embodiment is comprehensively communicated to those skilled in the art.Identical appended drawing reference indicates in figure
Same or similar part, thus repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to the embodiment of the present invention.However,
It will be appreciated by persons skilled in the art that technical solution of the present invention can be practiced without one or more in specific detail,
Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known side
Method, device, realization or operation are to avoid fuzzy each aspect of the present invention.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuit
These functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,
It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can close
And or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
Fig. 1 shows the flow diagram of customer consumption prediction technique according to some embodiments of the present invention.Referring to Fig.1
Shown, which may comprise steps of:
In step s 110, the user information of registered users and the consumption history letter in multiple marketing activities are obtained
Breath；
In the step s 120, the registered users are extracted from the user information and the consumption history information
User characteristics and consumption feature；
In step s 130, consumption prediction model is trained based on the user characteristics and the consumption feature；
In step S140, by the consumption predictions model to user to be predicted in the following predetermined amount of time in each battalion
The amount of consumption in pin activity is predicted.
According to the customer consumption prediction technique in the example embodiment of Fig. 1, on the one hand, from the user information of registered users
And the user characteristics and consumption feature of registered users are extracted in consumption history information, it is special based on user characteristics and consumption
Sign is trained consumption prediction model, can instruct in conjunction with the user characteristics and consumption feature of registered users to model
Practice；On the other hand, by consumption predictions model to user to be predicted in the following predetermined amount of time disappearing in each marketing activity
Expense volume predicted, can automatically and accurately predict user the following predetermined amount of time each marketing activity the amount of consumption, from
And precision marketing pointedly can be carried out to user.
In the following, the customer consumption prediction technique in the example embodiment to Fig. 1 is described in detail.
In step s 110, the consumption history letter in the user information and multiple marketing activities of registered users is obtained
Breath.
In the exemplary embodiment, user information can wrap for the information that user registers in website platform, user information
Include the information such as age, gender, income level, occupation type, educational background, the assets of user.Multiple marketing activities may include: insurance
Class activity, financing class marketing activity, the marketing activity of fund class, the healthy marketing such as class marketing activity and life kind marketing activity are living
It is dynamic.The consumption history data of user may include historical information, the use of the account managing detailed catalogue of user, user's participation marketing activity
The historical information such as user that marketing activity product is bought at family buys the historical information of finance product, fund product, insurance products.
In the step s 120, the registered users are extracted from the user information and the consumption history information
User characteristics and consumption feature.
In the exemplary embodiment, age, the gender, income level, educational background, assets of user can be extracted from user information
Equal characteristic informations.The consumption preferences, consumption time and consumption type etc. that user is extracted from the consumption history information of user disappear
Take feature.
In step s 130, consumption prediction model is trained based on the user characteristics and the consumption feature.
In the exemplary embodiment, for consumption predictions model for predicting the amount of consumption of user, consumption predictions model can
Think Logic Regression Models, or neural network prediction model can also be other prediction models appropriate, the present invention couple
This is without particular determination.
In the exemplary embodiment, the user characteristics and the consumption feature can be divided into training according to predetermined ratio
Sample set and verifying sample set；The consumption predictions model is trained based on the training sample set, is based on the verifying
Sample set is adjusted the parameter of the consumption predictions model.Based on training sample concentrate registered users characteristic information with
Consumption history information calculates the parameter of consumption predictions model, characteristic information and message based on registered users in verifying sample set
Historical information is adjusted the parameter of consumption prediction model.
In step S140, by the consumption predictions model to user to be predicted in the following predetermined amount of time in each battalion
The amount of consumption in pin activity is predicted.
In the exemplary embodiment, user to be predicted can be the new user of current month registration, extract user's to be predicted
The characteristic information of user to be predicted is input to and disappears by the information such as characteristic information such as age, gender, income level, educational background, assets
Take prediction model, so that it may obtain user to be predicted the following predetermined amount of time each channel the amount of consumption.
Further, in the exemplary embodiment, by the note of the registration amount of the user to be predicted and the registered users
The ratio of volume amount is as the first weight coefficient；By the year of the Characteristics of age distribution of the user to be predicted and the registered users
The ratio of age distribution characteristics is as the second weight coefficient；Based on first weight coefficient and second weight coefficient to described
The amount of consumption of the registered users in the registration month of the user to be predicted is adjusted；Based on registered users adjusted
The amount of consumption predicts the user to be predicted in the amount of consumption of the following predetermined amount of time in each marketing activity.
First weight coefficient, that is, registration amount ratio can reflect the ratio of user's overall quantity, the second weight coefficient, that is, year
The ratio of age distribution characteristics can reflect the ratio in the number of users in all ages and classes stage, for example, existing in the second weight coefficient
When the ratio of 60 to 70 age brackets is larger, indicate registered users 60 to 70 age brackets distribution it is less i.e. user group compared with
It is few, in order to improve the accuracy of prediction, need to reduce the second weight coefficient.
Fig. 2 shows the consumption for using the anti-pushing manipulation of time series to obtain registered users according to some embodiments of the present invention
The flow diagram of historical information.
In Fig. 2, in step S210, the identification information based on the user to be predicted obtains the user's to be predicted
Register month.
In the exemplary embodiment, can the identification information based on user to be predicted use to be predicted is obtained from target database
The registration month at family, target database can be MySQL database or oracle database, or the data of other forms
Library.
In step S220, based on the registration month using the anti-pushing manipulation determination of time series and the following predetermined time
The corresponding time series of section.
In the exemplary embodiment, in user to be predicted when registering month as in May, 2017, in order to predict 2017 5
The user to be predicted of month registration is determined in the following 2 years amount of consumptions in each marketing activity by the anti-pushing manipulation of time series
Time series corresponding with the future predetermined amount of time, for example, when the following predetermined amount of time is monthly divided into multiple
Between sequence；It is determining pre- with the future using the anti-pushing manipulation of time series based on the registration month and the multiple time series
The corresponding time series of section of fixing time, the i.e. time series in May, 2017 in May, 2019 correspond in May, 2017 to 2015
The time series in May in year corresponds in May, 2017 i.e. in May, 2017, corresponds in April, 2017 in June, 2017,
In June, 2017 corresponds in March, 2017, and so on, in April, 2019 corresponds in June, 2015, in May, 2019
Part corresponds in May, 2015.
In step S230, the user information of the registered users is obtained based on the time series and in multiple battalion
Consumption history information in pin activity.
In the exemplary embodiment, it is in time series corresponding with the following predetermined time end in May, 2017 in May, 2019
When in May, 2017 in May, 2015, the user of user, in April, 2017 registration that available in May, 2017 registers, 2017
March registration user, and so on in May, 2015 register user respectively in the consumption history information in May, 2017.
Further, in some embodiments, by registered users described in consumption predictions model prediction described to pre-
Survey the amount of consumption of the registration month of user in each marketing activity；The amount of consumption based on the registered users is to use to be predicted
It is predicted in the amount of consumption of the following predetermined amount of time in each marketing activity at family.
Fig. 3 shows the schematic diagram of the anti-pushing manipulation of time series according to some embodiments of the present invention.
Referring to shown in Fig. 3, the amount of consumption for user to be predicted in May, 2017 can be registered by May, 2017
The amount of consumption of the user in May, 2017 is predicted；The amount of consumption for user to be predicted in June, 2017 can pass through
The amount of consumption of the user of in April, 2017 registration in May, 2017 is predicted；For user to be predicted disappearing in July, 2017
Take volume, can be predicted by the amount of consumption of the user that in March, 2017 registers in May, 2017；And so on, 2019 4
The amount of consumption of the user that month amount of consumption is registered by June, 2015 in May, 2017 predict, the amount of consumption in May, 2019
The amount of consumption of the user registered by May, 2015 in May, 2017 is predicted.
In addition, in an embodiment of the present invention, additionally providing a kind of customer consumption prediction meanss.Referring to shown in Fig. 4, the use
Family consumption predictions device 4 may include: information acquisition unit 410, feature extraction unit 420, model training unit 430 and pre-
Survey unit 440.Wherein, information acquisition unit 410 is for obtaining the user information of registered users and in multiple marketing activities
On consumption history information；Feature extraction unit 420 from the user information and the consumption history information for extracting
The user characteristics and consumption feature of the registered users；Model training unit 430 be used for based on the user characteristics and
The consumption feature is trained consumption prediction model；Predicting unit 440 is pre- for being treated by the consumption predictions model
User is surveyed to predict in the amount of consumption of the following predetermined amount of time in each marketing activity.
In some embodiments of the invention, aforementioned schemes are based on, model training unit 430 includes: sample division unit,
For the user characteristics and the consumption feature to be divided into training sample set and verifying sample set according to predetermined ratio；Parameter
Determination unit is based on the verifying sample set for being trained based on the training sample set to the consumption predictions model
The parameter of the consumption predictions model is adjusted.
In some embodiments of the invention, aforementioned schemes are based on, information acquisition unit 410 includes: to determine in registration month
Unit obtains the registration month of the user to be predicted for the identification information based on the user to be predicted；Time is counter to push away list
Member is used for based on the registration month using the determining time sequence corresponding with the future predetermined amount of time of the anti-pushing manipulation of time series
Column；Consumption information acquiring unit, for obtaining the user information of the registered users based on the time series and more
Consumption history information in a marketing activity.
In some embodiments of the invention, aforementioned schemes are based on, predicting unit 440 is configured as: by the consumption
Prediction model predicts the registered users in the amount of consumption of the registration month in each marketing activity of the user to be predicted；
The amount of consumption based on the registered users to user to be predicted in the following predetermined amount of time in each marketing activity
The amount of consumption is predicted.
In some embodiments of the invention, aforementioned schemes are based on, the time, the anti-unit that pushes away included: time division unit, was used
In the following predetermined amount of time is monthly divided into multiple time serieses；It is counter to push away unit, for based on the registration month with
And the multiple time series is using the determining time series corresponding with the future predetermined amount of time of the anti-pushing manipulation of time series.
In some embodiments of the invention, aforementioned schemes are based on, predicting unit 440 is configured as: will be described to be predicted
The ratio of the registration amount of the registration amount and registered users of user is as the first weight coefficient；By the user's to be predicted
The ratio of Characteristics of age distribution and the Characteristics of age distribution of the registered users is as the second weight coefficient；Based on described first
Weight coefficient and second weight coefficient to the registered users the registration month of the user to be predicted the amount of consumption
It is adjusted；The amount of consumption based on registered users adjusted exists to the user to be predicted in the following predetermined amount of time
The amount of consumption in each marketing activity is predicted.
In some embodiments of the invention, aforementioned schemes are based on, the consumption predictions model is Logic Regression Models.
Since each functional module of the customer consumption prediction meanss 400 of example embodiments of the present invention disappears with above-mentioned user
The step of taking the example embodiment of prediction technique is corresponding, therefore details are not described herein.
In an exemplary embodiment of the present invention, a kind of electronic equipment that can be realized the above method is additionally provided.
Below with reference to Fig. 5, it illustrates the computer systems 500 for the electronic equipment for being suitable for being used to realize the embodiment of the present invention
Structural schematic diagram.The computer system 500 of electronic equipment shown in Fig. 5 is only an example, should not be to the embodiment of the present invention
Function and use scope bring any restrictions.
As shown in figure 5, computer system 500 includes central processing unit (CPU) 501, it can be read-only according to being stored in
Program in memory (ROM) 502 or be loaded into the program in random access storage device (RAM) 503 from storage section 508 and
Execute various movements appropriate and processing.In RAM 503, it is also stored with various programs and data needed for system operatio.CPU
501, ROM 502 and RAM 503 is connected with each other by bus 504.Input/output (I/O) interface 505 is also connected to bus
504。
I/O interface 505 is connected to lower component: the importation 506 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 508 including hard disk etc.；
And the communications portion 509 of the network interface card including LAN card, modem etc..Communications portion 509 via such as because
The network of spy's net executes communication process.Driver 510 is also connected to I/O interface 505 as needed.Detachable media 511, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 510, in order to read from thereon
Computer program be mounted into storage section 508 as needed.
Particularly, according to an embodiment of the invention, may be implemented as computer above with reference to the process of flow chart description
Software program.For example, the embodiment of the present invention includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 509, and/or from detachable media
511 are mounted.When the computer program is executed by central processing unit (CPU) 501, executes and limited in the system of the application
Above-mentioned function.
It should be noted that computer-readable medium shown in the present invention can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the present invention, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In invention, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in unit involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part realizes that described unit also can be set in the processor.Wherein, the title of these units is in certain situation
Under do not constitute restriction to the unit itself.
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in electronic equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when the electronics is set by one for said one or multiple programs
When standby execution, so that the electronic equipment realizes such as above-mentioned customer consumption prediction technique as described in the examples.
For example, the electronic equipment may be implemented as shown in Figure 1: in step s 110, obtaining registered users
User information and the consumption history information in multiple marketing activities；In the step s 120, from the user information and institute
State the user characteristics and consumption feature that the registered users are extracted in consumption history information；In step s 130, it is based on institute
User characteristics and the consumption feature is stated to be trained consumption prediction model；It is pre- by the consumption in step S140
Model is surveyed to predict user to be predicted in the amount of consumption of the following predetermined amount of time in each marketing activity.
It should be noted that although being referred to several modules for acting the device executed in the above detailed description
Or unit, but this division is not enforceable.In fact, embodiment according to the present invention, above-described two
Or more the feature and function of module or unit can be embodied in a module or unit.Conversely, above-described
One module or the feature and function of unit can be to be embodied by multiple modules or unit with further division.
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the present invention
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, touch control terminal or network equipment etc.) executes embodiment according to the present invention
Method.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to of the invention its
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the invention, these modifications, purposes or
Person's adaptive change follows general principle of the invention and including the undocumented common knowledge in the art of the present invention
Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by following
Claim is pointed out.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is limited only by the attached claims.
Claims (10)
1. a kind of customer consumption prediction technique characterized by comprising
The user information for obtaining registered users and the consumption history information in multiple marketing activities；
User characteristics and the consumption of the registered users are extracted from the user information and the consumption history information
Feature；
Consumption prediction model is trained based on the user characteristics and the consumption feature；
The amount of consumption by the consumption predictions model to user to be predicted in the following predetermined amount of time in each marketing activity
It is predicted.
2. customer consumption prediction technique according to claim 1, which is characterized in that based on user characteristics and described
Consumption feature is trained consumption prediction model, comprising:
The user characteristics and the consumption feature are divided into training sample set and verifying sample set according to predetermined ratio；
The consumption predictions model is trained based on the training sample set, based on the verifying sample set to the consumption
The parameter of prediction model is adjusted.
3. customer consumption prediction technique according to claim 1, which is characterized in that obtain the user information of registered users
And the consumption history information in multiple marketing activities, comprising:
Identification information based on the user to be predicted obtains the registration month of the user to be predicted；
Based on the registration month using the determining time series corresponding with the future predetermined amount of time of the anti-pushing manipulation of time series；
The user information of the registered users is obtained based on the time series and the consumption in multiple marketing activities is gone through
History information.
4. customer consumption prediction technique according to claim 3, which is characterized in that treated by the consumption predictions model
Prediction user predicts in the amount of consumption of the following predetermined amount of time in each marketing activity, comprising:
By registered users described in the consumption predictions model prediction the user to be predicted registration month in each battalion
The amount of consumption in pin activity；
The amount of consumption based on the registered users is to user to be predicted in the following predetermined amount of time in each marketing activity
On the amount of consumption predicted.
5. customer consumption prediction technique according to claim 3, which is characterized in that use the time based on the registration month
The determining time series corresponding with the future predetermined amount of time of the anti-pushing manipulation of sequence, comprising:
The following predetermined amount of time is monthly divided into multiple time serieses；
It is determining predetermined with the future using the anti-pushing manipulation of time series based on the registration month and the multiple time series
Period corresponding time series.
6. customer consumption prediction technique according to claim 4, which is characterized in that the consumption based on the registered users
Volume predicts user to be predicted in the amount of consumption of the following predetermined amount of time in each marketing activity, comprising:
Using the ratio of the registration amount of the user to be predicted and the registration amount of the registered users as the first weight coefficient；
Using the ratio of the Characteristics of age distribution of the user to be predicted and the Characteristics of age distribution of the registered users as the
Two weight coefficients；
Based on first weight coefficient and second weight coefficient to the registered users the user's to be predicted
The amount of consumption in registration month is adjusted；
The amount of consumption based on registered users adjusted is to the user to be predicted in the following predetermined amount of time each
The amount of consumption in marketing activity is predicted.
7. customer consumption prediction technique according to claim 1, which is characterized in that the consumption predictions model returns for logic
Return model.
8. a kind of customer consumption prediction meanss characterized by comprising
Information acquisition unit, the consumption history letter for obtaining the user information of registered users and in multiple marketing activities
Breath；
Feature extraction unit, for extracting the registered users from the user information and the consumption history information
User characteristics and consumption feature；
Model training unit, for being trained based on the user characteristics and the consumption feature to consumption prediction model；
Predicting unit, for being lived in the following predetermined amount of time in each marketing by the consumption predictions model to user to be predicted
The amount of consumption on dynamic is predicted.
9. a kind of electronic equipment characterized by comprising
Processor；And
Memory is stored with computer-readable instruction on the memory, and the computer-readable instruction is held by the processor
The customer consumption prediction technique as described in any one of claims 1 to 7 is realized when row.
10. a kind of computer readable storage medium, is stored thereon with computer program, the computer program is executed by processor
Customer consumption prediction technique of the Shi Shixian as described in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811119739.9A CN109214585B (en) | 2018-09-25 | 2018-09-25 | User consumption prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811119739.9A CN109214585B (en) | 2018-09-25 | 2018-09-25 | User consumption prediction method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109214585A true CN109214585A (en) | 2019-01-15 |
| CN109214585B CN109214585B (en) | 2023-04-18 |
Family
ID=64981447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811119739.9A Active CN109214585B (en) | 2018-09-25 | 2018-09-25 | User consumption prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214585B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934623A (en) * | 2019-02-26 | 2019-06-25 | 中山大学 | Individual economy consuming capacity prediction technique based on user's APP usage behavior |
| CN110764902A (en) * | 2019-09-18 | 2020-02-07 | 平安银行股份有限公司 | Virtual resource allocation method and device based on AI (Artificial Intelligence), computer equipment and storage medium |
| CN112070534A (en) * | 2020-08-31 | 2020-12-11 | 深圳市铭数信息有限公司 | Consumption budget generation method and device, computer equipment and storage medium |
| CN112711711A (en) * | 2021-01-07 | 2021-04-27 | 泰康保险集团股份有限公司 | Knowledge base-based client marketing cue recommendation method and device |
| CN113065717A (en) * | 2021-04-22 | 2021-07-02 | 杭州同犀智能科技有限公司 | E-commerce data processing method, device, equipment and storage medium |
| CN113919585A (en) * | 2021-10-29 | 2022-01-11 | 中国联合网络通信集团有限公司 | Marketing time prediction method and device, electronic equipment and storage medium |
| 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 |
| CN116843377A (en) * | 2023-07-25 | 2023-10-03 | 河北鑫考科技股份有限公司 | Consumption behavior prediction method, device, equipment and medium based on big data |
| CN117291655A (en) * | 2023-11-27 | 2023-12-26 | 广州欧派创意家居设计有限公司 | Consumer life cycle operation analysis method based on entity and network collaborative mapping |
| WO2024199404A1 (en) * | 2023-03-31 | 2024-10-03 | 华为技术有限公司 | Consumption prediction method and related device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423442A (en) * | 2017-08-07 | 2017-12-01 | 火烈鸟网络(广州)股份有限公司 | Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis |
| CN107895213A (en) * | 2017-12-05 | 2018-04-10 | 北京三快在线科技有限公司 | Forecasting Methodology, device and the electronic equipment of spending limit |
| CN108280683A (en) * | 2018-01-18 | 2018-07-13 | 百度在线网络技术（北京）有限公司 | Discount coupon distribution method based on advertisement launching platform and device |
-
2018
- 2018-09-25 CN CN201811119739.9A patent/CN109214585B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423442A (en) * | 2017-08-07 | 2017-12-01 | 火烈鸟网络(广州)股份有限公司 | Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis |
| CN107895213A (en) * | 2017-12-05 | 2018-04-10 | 北京三快在线科技有限公司 | Forecasting Methodology, device and the electronic equipment of spending limit |
| CN108280683A (en) * | 2018-01-18 | 2018-07-13 | 百度在线网络技术（北京）有限公司 | Discount coupon distribution method based on advertisement launching platform and device |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934623A (en) * | 2019-02-26 | 2019-06-25 | 中山大学 | Individual economy consuming capacity prediction technique based on user's APP usage behavior |
| CN110764902A (en) * | 2019-09-18 | 2020-02-07 | 平安银行股份有限公司 | Virtual resource allocation method and device based on AI (Artificial Intelligence), computer equipment and storage medium |
| CN112070534A (en) * | 2020-08-31 | 2020-12-11 | 深圳市铭数信息有限公司 | Consumption budget generation method and device, computer equipment and storage medium |
| CN112711711A (en) * | 2021-01-07 | 2021-04-27 | 泰康保险集团股份有限公司 | Knowledge base-based client marketing cue recommendation method and device |
| CN113065717A (en) * | 2021-04-22 | 2021-07-02 | 杭州同犀智能科技有限公司 | E-commerce data processing method, device, equipment and storage medium |
| CN113919585A (en) * | 2021-10-29 | 2022-01-11 | 中国联合网络通信集团有限公司 | Marketing time prediction method and device, electronic equipment and storage medium |
| 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 |
| WO2024199404A1 (en) * | 2023-03-31 | 2024-10-03 | 华为技术有限公司 | Consumption prediction method and related device |
| CN116843377A (en) * | 2023-07-25 | 2023-10-03 | 河北鑫考科技股份有限公司 | Consumption behavior prediction method, device, equipment and medium based on big data |
| CN117291655A (en) * | 2023-11-27 | 2023-12-26 | 广州欧派创意家居设计有限公司 | Consumer life cycle operation analysis method based on entity and network collaborative mapping |
| CN117291655B (en) * | 2023-11-27 | 2024-01-23 | 广州欧派创意家居设计有限公司 | Consumer life cycle operation analysis method based on entity and network collaborative mapping |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109214585B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214585A (en) | Customer consumption prediction technique, device, electronic equipment and storage medium | |
| US11861464B2 (en) | Graph data structure for using inter-feature dependencies in machine-learning | |
| CN109919684A (en) | For generating method, electronic equipment and the computer readable storage medium of information prediction model | |
| CN109360012A (en) | The selection method and device, storage medium, electronic equipment of advertisement dispensing channel | |
| US20200234218A1 (en) | Systems and methods for entity performance and risk scoring | |
| CN109345368A (en) | Credit estimation method, device, electronic equipment and storage medium based on big data | |
| CN109190028A (en) | Activity recommendation method, apparatus, electronic equipment and storage medium based on big data | |
| CN109299356A (en) | Activity recommendation method, apparatus, electronic equipment and storage medium based on big data | |
| CN109242496A (en) | Prediction technique, device and the computer-readable medium of the means of payment | |
| CN109857431A (en) | Code revision method and device, computer-readable medium and electronic equipment | |
| CN109472632A (en) | Evaluate method, apparatus, medium and the electronic equipment of advertisement competition power | |
| JP7429102B2 (en) | Quiz-type question and answer service providing method and system | |
| CN109685537A (en) | Analysis method, device, medium and the electronic equipment of user behavior | |
| CN110335090A (en) | Replenishing method and system, electronic equipment based on Sales Volume of Commodity forecast of distribution | |
| CN110866625A (en) | Promotion index information generation method and device | |
| CN115578138A (en) | Marketing method, marketing device, marketing medium and computing equipment | |
| WO2020150597A1 (en) | Systems and methods for entity performance and risk scoring | |
| CN109460778A (en) | Active evaluation method, apparatus, electronic equipment and storage medium | |
| CN110717101A (en) | User classification method and device based on application behaviors and electronic equipment | |
| CN109472455A (en) | Active evaluation method, apparatus, electronic equipment and storage medium | |
| CN115879993A (en) | Site selection method and device for network points, electronic equipment and storage medium | |
| CN114218496A (en) | Object recommendation method, device and equipment, medium and product | |
| CN114817716A (en) | Method, device, equipment and medium for predicting user conversion behaviors and training model | |
| CN110163482B (en) | Method for determining safety scheme data of activity scheme, terminal equipment and server | |
| KR20220137521A (en) | Method, system and non-transitory computer-readable recording medium for recommending means of payment |
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 |