CN108154420A - Products Show method and device, storage medium, electronic equipment - Google Patents
Products Show method and device, storage medium, electronic equipment Download PDFInfo
- Publication number
- CN108154420A CN108154420A CN201711429283.1A CN201711429283A CN108154420A CN 108154420 A CN108154420 A CN 108154420A CN 201711429283 A CN201711429283 A CN 201711429283A CN 108154420 A CN108154420 A CN 108154420A
- Authority
- CN
- China
- Prior art keywords
- user
- product
- state information
- big data
- probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Abstract
The embodiment of the present invention is about a kind of Products Show method and device based on big data, belongs to technical field of data processing, which includes：Historical user's status data is obtained, and historical user's status data is predicted to obtain current user state information based on big data model；It is predicted to obtain the probability of the multiple products of user's purchase according to the current user state information；The probability size that each product is bought according to the user is followed successively by the corresponding product of user's recommendation.This method is followed successively by the corresponding product of user's recommendation by buying the probability size of each product according to user, the product for being more in line with requirement can be provided for client, the success rate for improving each Products Show improves user experience simultaneously.
Description
Technical field
The present embodiments relate to technical field of data processing, are pushed away in particular to a kind of product based on big data
Recommend method, Products Show device, computer readable storage medium and electronic equipment based on big data.
Background technology
As enterprise sets up the increase of time, the customer resources of enterprise also can be with increase.Certain company set up number every year with
Come, had accumulated tens million of declaration forms and client, the client of these declaration forms is a great riches for company, how right
Existing client, which carries out depth excavation, becomes further developing direction.
After client's declaration form is sold to, as time go on, physical condition, Income situation, employment status and the family of client
Front yard situation etc. is also in changing slowly；This means that the demand of client is also changing.On the one hand, the guarantor of initial purchase
List cannot may meet the needs of client, need to buy new insurance products；On the other hand, the declaration form of some clients has been
Failure or because other reasons surrender；Things have changed with the lapse of time, this portions of client may have a new demand, and these new demands
New value for company can be provided, therefore can be the newest insurance products of lead referral again.
But in existing suggested design, do not occur also temporarily recommending user for the above situation newest corresponding
The technical solution of insurance products, it is therefore desirable to which a kind of new Products Show method based on big data is provided.
It should be noted that the information in the invention of above-mentioned background technology part is only used for strengthening the reason to background of the invention
Solution, therefore can include not forming the information to the prior art known to persons of ordinary skill in the art.
Invention content
The purpose of the present invention is to provide a kind of Products Show method based on big data, the Products Shows based on big data
Device, computer readable storage medium and electronic equipment, and then the limit due to the relevant technologies is overcome at least to a certain extent
The problem of cannot new value being created by existing client caused by system and defect.
The embodiment of the present invention provides a kind of Products Show method based on big data, including：
Historical user's status data is obtained, and historical user's status data is measured in advance based on big data model
To current user state information；
It is predicted to obtain the probability of the multiple products of user's purchase according to the current user state information；
The probability size that each product is bought according to the user is followed successively by the corresponding product of user's recommendation.
Optionally, historical user's status data is predicted based on big data model to obtain current user state letter
Breath is specially：
Multiple attribute informations are extracted from historical user's status data；
The corresponding characteristic value of each attribute information is analyzed to obtain the current user state information.
Optionally, the corresponding characteristic value of each attribute information is carried out analyzing the current user state information specific
For：
Judge whether the corresponding characteristic value of each attribute information lacks；
When judging that the corresponding characteristic value of the attribute information lacks, the corresponding characteristic value of the attribute information is carried out pre-
Estimate to obtain the current user state information.
Optionally, the corresponding characteristic value of the attribute information is estimated specially：
The corresponding characteristic value of the attribute information is estimated using prediction model.
Optionally, the prediction model is obtained using linear regression algorithm or decision Tree algorithms.
Optionally, the probability size for each product being bought according to the user is followed successively by the corresponding production of user's recommendation
Product are specially：
The current user state information is randomly divided into training sample and test sample；
Machine learning is carried out to the training sample and obtains initial predicted model, and using the test sample to described first
Beginning prediction model is verified to obtain standard prediction；
The current user state information is predicted using the standard prediction to obtain the multiple productions of user's purchase
The probability of product.
Optionally, the current user state information is predicted using the standard prediction to obtain user's purchase
The probability of various product is specially：
The current user state information is inputted into the standard prediction, user is obtained and buys each product
Probability.
Optionally, the sum of probability for buying each product is 1.
Optionally, the probability size for each product being bought according to the user is followed successively by the corresponding production of user's recommendation
Product are specially：
The corresponding label of each product of user's purchase is marked and searched to product using label；
The probability size and the corresponding label of each product for each product bought according to the user are recommended for the user
Corresponding product.
The embodiment of the present invention provides a kind of Products Show device based on big data, including：
Current state information prediction module, for obtaining historical user's status data, and based on big data model to described
Historical user's status data is predicted to obtain current user state information；
Product probabilistic forecasting module, it is multiple for being predicted to obtain user's purchase according to the current user state information
The probability of product；
Products Show module, the probability size for buying each product according to the user are followed successively by the user and push away
Recommend corresponding product.
The embodiment of the present invention provides a kind of computer readable storage medium, is stored thereon with computer program, the calculating
Machine program realizes Products Show method of any one of them based on big data when being executed by processor.
The embodiment of the present invention provides a kind of electronic equipment, including：
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to perform any one of them based on big number via the executable instruction is performed
According to Products Show method.
A kind of Products Show method and device based on big data of the embodiment of the present invention uses history based on big data model
Family status data is predicted to obtain current user state information；It is predicted to obtain user further according to current user state information
Buy the probability of multiple products；The probability size that each product is finally bought according to user is followed successively by the corresponding product of user's recommendation；
On the one hand, by being predicted to obtain current user state information and according to current user state according to historical user's status data
Information prediction obtains the probability that user buys each product, and solving in prior art can not be to existing historic customer into one
Step is excavated and leads to the problem of value, improves the benefit of enterprise；On the other hand, pass through the probability according to each product of user's purchase
Size is followed successively by user and recommends corresponding product, and the product for being more in line with requirement can be provided for client, each product is improved and pushes away
The success rate recommended improves user experience simultaneously.
It should be understood that above general description and following detailed description are only exemplary and explanatory, not
It can the limitation present invention.
Description of the drawings
Attached drawing herein is incorporated into specification and forms the part of this specification, shows the implementation for meeting the present 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.
Fig. 1 schematically shows a kind of flow chart of the Products Show method based on big data.
Fig. 2, which is schematically shown, a kind of to be predicted historical user's status data to obtain the method for current user state information
Flow chart.
Fig. 3 schematically shows a kind of probability predicted to obtain user to current user state information and buy multiple products
Method flow diagram.
Fig. 4 schematically shows a kind of prediction model computational methods flow chart.
Fig. 5 schematically shows a kind of decision tree exemplary plot.
Fig. 6 schematically shows a kind of probability size that each product is bought according to user and is followed successively by the corresponding product of user's recommendation
Method flow diagram.
Fig. 7 schematically shows a kind of block diagram of the Products Show device based on big data.
Fig. 8 schematically shows a kind of electronic equipment for being used to implement the above-mentioned Products Show method based on big data.
Fig. 9 schematically shows a kind of computer-readable storage for being used to implement the above-mentioned Products Show method based on big data
Medium.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, these embodiments are provided so that the present invention will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be in any suitable manner incorporated in one or more embodiments.In the following description, it provides perhaps
More details fully understand embodiments of the present invention so as to provide.It it will be appreciated, however, by one skilled in the art that can
One or more in the specific detail are omitted to put into practice technical scheme of the present invention or others side may be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution to avoid a presumptuous guest usurps the role of the host and
So that each aspect of the present invention thickens.
In addition, attached drawing is only the schematic illustrations of the present invention, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note represents same or similar part, thus will omit repetition thereof.Attached some block diagrams shown in figure are work(
Can entity, not necessarily must be corresponding with physically or logically independent entity.Software form may be used to realize these work(
Entity or these functional entitys can be realized in one or more hardware modules or integrated circuit or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
Certain enterprise is it is intended that client provides the comprehensive life insurance insurance service of various aspects.Wherein, line of insurance can be with
Including from newborn's related insurance, health insurance, accident insurance, universal life insurance, endowment insurance up to commemorating ceremony park etc..For the enterprise
For user, buy the insurance products of the enterprise like all one's life, including from birth to juvenile, the young, middle age until old age etc.
Deng.In the route in this all one's life, in addition to the change at age is outside the pale of civilization, also some crucial life nodes, such as employment, marriage, life
Youngster educates female, buying car house-purchase, retirement etc..As soon as often by people's tight knot point, demand of the user to insurance products is varied from, therefore
It can meet customer need in each node insurance products new for lead referral.In addition, there is some users midway to move back
It protects or insures the failure etc. that expires, like the passenger to break the journey, the new situation offer that can be directed to such user is most suitable
These users are retrieved in insurance products, effort.
A kind of Products Show method based on big data is provided firstly in this example embodiment, this method can be run
In server, server cluster or Cloud Server etc.；Certainly, those skilled in the art can also transport in other platforms according to demand
The method of the row present invention, does not do this particular determination in the present exemplary embodiment.It refering to what is shown in Fig. 1, should the production based on big data
Product recommend method may comprise steps of：
Step S110. obtains historical user's status data, and based on big data model to historical user's status data
It is predicted to obtain current user state information.
Step S120. is predicted to obtain the probability of the multiple products of user's purchase according to the current user state information.
Step S130. according to the user buy each product probability size be followed successively by the user recommend it is corresponding
Product.
In the above-mentioned Products Show method based on big data, on the one hand, pre- by being carried out according to historical user's status data
Current user state information is measured, and the probability of each product of user's purchase, solution are obtained according to current user state information prediction
Existing historic customer can not further be excavated in prior art of having determined and lead to the problem of value, improve enterprise
Benefit；On the other hand, the corresponding product of user's recommendation, Ke Yiwei are followed successively by by buying the probability size of each product according to user
Client provides the product for being more in line with requirement, and the success rate for improving each Products Show improves user experience simultaneously.
In the following, Products Show method based on big data above-mentioned in this example embodiment will be carried out detailed explanation with
And explanation.
In step s 110, historical user's status data is obtained, and based on big data model to historical user's state
Data are predicted to obtain current user state information.
First, historical user's status data is explained and illustrated.Historical user's status data can include user
Purchasing history (detail of declaration form and the amount of money etc.), user attribute information (personal user or enterprise customer etc.) with
And product attribute information (personal insurance or property insurance etc.).
Secondly, step S110 is explained and illustrated based on above-mentioned historical user's status data.Wherein, with reference to figure 2
Shown, historical user's status data, which is predicted to obtain current user state information, can include step S210 and step
S220.Wherein：
In step S210, multiple attribute informations are extracted from historical user's status data.For example：
For this sentences personal user, the attribute information extracted from historical user's status data can include：Age believes
Breath, gender information whether there is child information, income information etc., can also include other information, for example, can be certificate address information,
Account information whether there is caravan etc., and there is no special restriction on this for this example.Further, the attribute information of user can refer to
Shown in the following table 1：
| Attribute information | Explanation | Whether change over time |
| Age | It at age when client insures, changes over time | It is |
| Gender | Client gender does not change over time | It is no |
| Place provinces and cities | Branch company | It is no |
| Zhong Zhi mechanisms | Zhong Zhi mechanisms, do not change over time | It is no |
| Registered permanent residence classification | Cities and towns or rural area, do not change over time | It is no |
| Whether VIP client is belonged to | Yes/no does not change over time | It is no |
| Marital status | Unmarried, married, divorce, the death of one's spouse etc.. | It is |
| It has no children | Have or nothing | It is |
| Occupational group | Professional risk grade | It is |
| Income | It is high, normal, basic | It is |
| Education | Education degree | It is no |
| The product bought before | Product category code | It is no |
| Claim times | 0,1,2 ... | It is |
Table 1
In step S220, the corresponding characteristic value of each attribute information is analyzed to obtain the current user state
Information.Wherein, the corresponding characteristic value of each attribute information is analyzed to obtain current user state information and can includes following step
Suddenly.Wherein：
First, it is determined that whether the corresponding characteristic value of each attribute information lacks.Specifically：
First, it is determined that whether the corresponding characteristic value of each attribute information lacks；For example, when age corresponding characteristic value is 31
When, can the age of user be obtained according to time of the declaration form date of user apart from current date, then may determine that as the age
Corresponding characteristic value does not lack；It, then can be according to the date of birth when age corresponding characteristic value is on January 1st, 1980
The age is calculated with the current date to obtain the age of user, then may determine that and do not lacked for age corresponding characteristic value
It loses；Further, it when age corresponding characteristic value is work 5 years, then may determine that as age corresponding characteristic value missing.
Secondly, when judging that the corresponding characteristic value of the attribute information lacks, characteristic value corresponding to the attribute information
It is estimated to obtain the current user state information.Specifically：
When judging attribute information corresponding characteristic value missing, can utilize prediction model to attribute information corresponding feature
Value is estimated to obtain current user state information；Wherein, prediction model can utilize linear regression algorithm or decision tree to calculate
Method obtains, and can also utilize other algorithms, such as can be that random forest or gradient promote decision tree etc., this example is to this
It does not do specifically limited.For example：
It, first can be according to the declaration form date of user apart from current when age corresponding characteristic value missing (work 5 years)
The time on date obtains the year that user works in total, prediction model is recycled to carry out the year that the user works in total pre-
Estimate to obtain the current state information (current age) of user；Further, can also be inferred to according to the current age of user
User has no children (current state information).Further, when the corresponding characteristic value of the attribute information of the presence or absence of user children
During missing, this feature value can be estimated；It specifically, can be according to the attribute information pair of the presence or absence of existing user children
The characteristic value answered estimates this feature value of missing in the case of not lacking, such as can be according to the age within 10 years old
Children parent's situation (including gender, place provinces and cities and Zhong Zhi mechanisms, existing residence, whether belong to VIP client, marital status,
Occupational group, income, education degree) (can also be decision data, the present invention is implemented to the age progress linear regression born child
There is no special restriction on this for example), whether then according to the latest development of existing customer, estimating has child etc..
In the following, in order to which be better understood from features described above value estimates process, above-mentioned linear regression algorithm is carried out simple
Explanation and explanation.
Linear regression algorithm is based on such a hypothesis：Output result (i.e. label) is linear group of input feature vector
It closes；For example, output have the corresponding characteristic value of childless attribute information can be age of user, whether marriage and education
Wait the linear combination of the corresponding characteristic value of attribute informations.Specifically, it can be indicated with following formula：
Wherein, h (x) represents output as a result, xiRepresent the corresponding feature of each attribute information
Value, θiRepresent the corresponding parameter of each attribute information.Further, the calculating process of above formula can include：For given one
Training data (attribute information+characteristic value) is criticized, θ is calculated and to predict the error (feature using training data feature calculation gone out
The error of value and actual characteristic value) it is minimum.For example：
Assuming that a user has the age of child and age of user and income linear correlation, then the feature of this model
It can be as shown in table 2 below：
| Attribute information | Characteristic value |
| Gender | Man, female |
| Income | Specific number |
Table 2
Further, training sample can be as shown in table 3 below：
| Gender | Income | There is the age of child |
| Man | 30000 | 31 |
| Female | 30000 | 29 |
| Man | 50000 | 32 |
| … | … | … |
Table 3
Therefore, x0 and x1 can be gender and income respectively, and target h (x) to be predicted is the age that client has child；Into
One step, target can train θ using training data1And θ2, then only need in practical applications to above-mentioned prediction model
The gender and income of middle input client, you can predicting client has the age of child.Further, θ is solved1And θ2Process can
To include：First, a loss function is determined, this loss function is the flat of all training sample predicted values and actual value error
Side and divided by 2, be meant that the quadratic sum divided by 2 of predicted value and the distance of each actual value, be exactly in embodiments of the present invention
It predicts the quadratic sum divided by 2 of age and real age difference, makes to be formulated as follows, for each feature, parameter changes
It is following (by taking j-th of parameter as an example) for calculation formula：
θj=θj+α(y(i)-hθ(x(i)))xj (i)
Wherein, α is the model learning speed artificially specified, and training sample Reusability above formula is iterated
It calculates, until the θ values of current θ values and back have almost no change, iterative calculation is completed.It is directly used in the embodiment of the present invention
The linear regression tool of scikit carries out model training.Further, by the way that training sample is input in prediction model constantly
Training, obtains a trained prediction model, you can in use, to input a test sample (attribute information),
It will obtain the corresponding characteristic value of the attribute information.Herein it should be added that, when a certain user attribute information lack
When losing large percentage, the historical state data of the user can be given up, such as：Age, have no children, whether marriage with
And occupational group can delete the historical state data of the user when the corresponding characteristic value of attribute informations lacks.
In the step s 120, it is predicted to obtain the general of the multiple products of user's purchase according to the current user state information
Rate.Wherein, refering to what is shown in Fig. 3, current user state information is predicted to obtain user buy the probability of multiple products can be with
Including step S310- steps S330.Wherein：
In step S310, the current user state information is randomly divided into training sample and test sample.In detail
For：
Current user state information is randomly divided into training sample and test sample, wherein, training sample and test
The ratio data of sample can be 4:1 or other ratios, such as can be 7:3 or 3:2 etc., this example is to this
It does not do specifically limited.
In step s 320, machine learning is carried out to the training sample and obtains initial predicted model, and utilize the survey
Sample this initial predicted model is verified to obtain standard prediction.Specifically：
First, machine learning is carried out to training sample and obtains an initial predicted model, then recycle test sample to first
Beginning prediction model is verified to obtain standard prediction；Further, when using test sample to initial predicted model carry out
When predicting that the result difference of obtained prediction result and script is larger, training sample can be trained again until prediction knot
When fruit and the difference of script result are less than preset value, above-mentioned standard prediction model can be just obtained.Specifically：
Refering to what is shown in Fig. 4, by the training to training sample 401, an initial predicted model 402 is obtained, it is then sharp again
Initial predicted model 402 is verified to obtain standard prediction 404 so that the standard prediction with test sample 403
The resultant error that 404 pairs of data are judged is low as possible.Wherein, model training is exactly by feature (user's current state information)
Differentiate label (classification of product).
Refering to what is shown in Fig. 5, the usual factor for most having judgement index is arranged on the root position of decision tree, the differentiation of each factor
Power can be sorted by entropy production.Wherein, entropy production formula can be as follows：
Wherein, S is training sample set；For information gains of the attribute A of Gain (S, A) with respect to sample set S；
Value (A) is the codomain of attribute A；Sv is that value is equal to the sample set of v on attribute A in S；Entropy (S) is former set S
Entropy；Desired value for the entropy after the S that classified with A.
In step S330, the current user state information is predicted using the standard prediction and is used
Buy the probability of multiple products in family.Wherein, current user state information is predicted to obtain the general of the multiple products of user's purchase
Rate can specifically include：The current user state information is inputted into the standard prediction, it is each to obtain user's purchase
The probability of the product.Specifically：
After above-mentioned standard prediction model is obtained, current user state information is inputted into the standard prediction, is obtained
The user buys the probability of each product；Such as：The current user state information inputted into standard prediction includes：User year
Age：35；Children's situation：There are children；Whether caravan is had：Have etc., then the recommendation probability that can obtain family insurance is 0.5；Vehicle
The recommendation probability of danger is 0.2；The recommendation probability of life insurance is 0.3 etc.；Can also other products be obtained according to other input information
Recommendation probability, there is no special restriction on this for this example.It should be added that, obtained herein according to input data each
The sum of recommendation probability of product can be 1.
In step s 130, the probability size for each product being bought according to the user is followed successively by user's recommendation pair
The product answered.Wherein, refering to what is shown in Fig. 6, the probability size that each product is bought according to user is followed successively by the corresponding production of user's recommendation
Product can include step S610 and step S620.Wherein：
In step S610, the corresponding label of each product of user's purchase is marked and searched to product using label.
Specifically：
First, product is marked using each label；Next, each production is bought when obtaining user according to standard prediction
After the probability of product, the corresponding label of each product is searched.For example, can the big classification of production sharing (such as can include 20
Class or other multiclass, there is no special restriction on this for this example), reuse number (can be 1~20 or its
He number or character, there is no special restriction on this for this example) various product is marked.Wherein, the standard of classification and
Specific division result can be referred to shown in the following table 4.
Table 4
Further, (such as can be family insurance, vehicle insurance when obtaining user to buy each product according to standard prediction
And life insurance etc.) probability after, family insurance, vehicle insurance and the corresponding mark of life insurance can be searched according to above-mentioned classification results
Label.It, can be to avoid following problem by using which：If using the product code of client's declaration form, but there are some again
Product has been suspended sale of or the product that has is suspended sale of rear and replaced new product code and the Product Similarity that has is very high etc.
The problem of causing further improves the accuracy rate of Products Show.
In step S620, the probability size and the corresponding label of each product of each product bought according to the user are
The user recommends corresponding product.Specifically：
After the probability and each product that obtain each product of user's purchase corresponding label, it can be bought according to user each
The probability size and the corresponding label of each product of product recommend corresponding product for user.For example, obtain pushing away for family insurance
It is 0.5 to recommend probability；The recommendation probability of vehicle insurance is 0.2；The recommendation probability of life insurance be 0.3 after, find family insurance, vehicle insurance and
Then the corresponding label of life insurance pushes away successively according to corresponding family insurance, vehicle insurance and the corresponding probability of life insurance and label for user
It recommends.
Further, by being recommended according to the corresponding label of each product, the name of product before avoiding is no longer suitable
With and the problem of cause, the title of product can be timely adjusted according to the fresh information of product in the category, is further carried
The accuracy rate recommended and the experience of user are risen.Herein it should be added that, when obtaining the recommendation probability of a certain product
When too low, can selectivity ignore without recommend, for example, the recommendation probability of annuity be 0.001, then can not be to this
Product is recommended.
The embodiment of the present invention also provides a kind of Products Show device based on big data.It refering to what is shown in Fig. 7, should be based on big number
According to Products Show device can be pushed away including current state information prediction module 710, product probabilistic forecasting module 720 and product
Recommend module 730.Wherein：
Current state information prediction module 710 can be used for obtaining historical user's status data, and based on big data model
Historical user's status data is predicted to obtain current user state information.
Product probabilistic forecasting module 720 can be used for being predicted to obtain user's purchase according to the current user state information
Buy the probability of multiple products.
Products Show module 730 can be used for according to being followed successively by the probability size of each product of user purchase
User recommends corresponding product.
The detail of each module is based on big data corresponding in the above-mentioned Products Show device based on big data
Products Show method in carried out wanting to describe, therefore details are not described herein again in detail.
It should be noted that although several modules or list for acting the equipment performed are referred in above-detailed
Member, but this division is not enforceable.In fact, according to the embodiment of the present invention, it is above-described two or more
The feature and function of module either unit can embody in a module or unit.A conversely, above-described mould
Either the feature and function of unit can be further divided into being embodied by multiple modules or unit block.
In addition, although describing each step of method in the present invention with particular order in the accompanying drawings, this does not really want
Asking or implying must could realize according to the particular order come the step for performing these steps or having to carry out shown in whole
Desired result.It is additional or alternative, it is convenient to omit certain steps, by multiple steps merge into a step perform and/
Or a step is decomposed into execution of multiple steps etc..
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 be realized by software, can also be realized in a manner that software is with reference to necessary hardware.Therefore, according to the present invention
The technical solution of embodiment can be embodied in the form of software product, the software product can be stored in one it is non-volatile
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions so that a calculating
Equipment (can be personal computer, server, mobile terminal or network equipment etc.) is performed according to embodiment of the present invention
Method.
In an exemplary embodiment of the present invention, a kind of electronic equipment that can realize the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be with specific implementation is as follows, i.e.,：It is complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as " circuit ", " module " or " system ".
The electronic equipment 600 of this embodiment according to the present invention is described referring to Fig. 8.The electronics that Fig. 8 is shown
Equipment 600 is only an example, should not bring any restrictions to the function and use scope of the embodiment of the present invention.
As shown in figure 8, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap
It includes but is not limited to：Above-mentioned at least one processing unit 610, above-mentioned at least one storage unit 620, connection different system component
The bus 630 of (including storage unit 620 and processing unit 610).
Wherein, the storage unit has program stored therein code, and said program code can be held by the processing unit 610
Row so that the processing unit 610 performs various according to the present invention described in above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 610 can perform step S110 as shown in fig. 1：Acquisition is gone through
History User Status data, and historical user's status data is predicted to obtain current user state based on big data model
Information；S120：It is predicted to obtain the probability of the multiple products of user's purchase according to the current user state information；Step
S130：The probability size that each product is bought according to the user is followed successively by the corresponding product of user's recommendation.
Storage unit 620 can include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
Storage unit 620 can also include program/utility with one group of (at least one) program module 6205
6204, such program module 6205 includes but not limited to：Operating system, one or more application program, other program moulds
Block and program data may include the realization of network environment in each or certain combination in these examples.
Bus 630 can be to represent one or more in a few class bus structures, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use the arbitrary bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, the equipment interacted with the electronic equipment 600 communication can be also enabled a user to one or more and/or with causing
Any equipment that the electronic equipment 600 can communicate with one or more of the other computing device (such as router, modulation /demodulation
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown in the figure, network adapter 660 is communicated by bus 630 with other modules of electronic equipment 600.
It should be understood that although not shown in the drawings, can combine electronic equipment 600 use other hardware and/or software module, including but not
It is limited to：Microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
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 be realized by software, can also be realized in a manner that software is with reference to necessary hardware.Therefore, according to the present invention
The technical solution of embodiment can be embodied in the form of software product, the software product can be stored in one it is non-volatile
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is performed according to embodiment of the present invention
Method.
In an exemplary embodiment of the present invention, a kind of computer readable storage medium is additionally provided, is stored thereon with energy
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product, including program code, when described program product is run on the terminal device, institute
State program code for make the terminal device perform described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
Refering to what is shown in Fig. 9, describe the program product for being used to implement the above method according to the embodiment of the present invention
800, portable compact disc read only memory (CD-ROM) may be used and including program code, and can in terminal device,
Such as it is run on PC.However, the program product of the present invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
Any tangible medium for including or storing program, the program can be commanded execution system, device either device use or
It is in connection.
The arbitrary combination of one or more readable mediums may be used in described program product.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor or arbitrary above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include：It is electrical connection, portable disc, hard disk, random access memory (RAM) with one or more conducting wires, read-only
Memory (ROM), erasable programmable read only memory (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.
Computer-readable signal media can include in a base band or as a carrier wave part propagation data-signal,
In carry readable program code.The data-signal of this propagation may be used diversified forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, which can send, propagate either transmit for used by instruction execution system, device or device or and its
The program of combined use.
The program code included on readable medium can be transmitted with any appropriate medium, including but not limited to wirelessly, be had
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
It can combine to write to perform the program that the present invention operates with the arbitrary of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It performs on computing device, partly perform on a user device, the software package independent as one performs, is partly calculated in user
Upper side point is performed or is performed in remote computing device or server completely on a remote computing.It is being related to far
In the situation of journey computing device, remote computing device can be by the network of any kind, including LAN (LAN) or wide area network
(WAN), be connected to user calculating equipment or, it may be connected to external computing device (such as utilizes ISP
To pass through Internet connection).
In addition, above-mentioned attached drawing is only the schematic theory of the processing included by method according to an exemplary embodiment of the present invention
Bright rather than limitation purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, being also easy to understand, these processing for example can be performed either synchronously or asynchronously in multiple modules.
Those skilled in the art will readily occur to the present invention its after considering specification and putting into practice the invention invented here
His embodiment.This application is intended to cover the present invention any variations, uses, or adaptations, these modifications, purposes or
Adaptive change follow the general principle of the present invention and including the of the invention common knowledge in the art do not invented or
Conventional techniques.Description and embodiments are considered only as illustratively, and true scope and spirit of the invention are by claim
It points out.
Claims (12)
- A kind of 1. Products Show method based on big data, which is characterized in that including：Historical user's status data is obtained, and historical user's status data is predicted based on big data model and is worked as Preceding user state information；It is predicted to obtain the probability of the multiple products of user's purchase according to the current user state information；The probability size that each product is bought according to the user is followed successively by the corresponding product of user's recommendation.
- 2. the Products Show method according to claim 1 based on big data, which is characterized in that based on big data model pair Historical user's status data is predicted to obtain current user state information：Multiple attribute informations are extracted from historical user's status data；The corresponding characteristic value of each attribute information is analyzed to obtain the current user state information.
- 3. the Products Show method according to claim 2 based on big data, which is characterized in that each attribute information Corresponding characteristic value carries out analyzing the current user state information：Judge whether the corresponding characteristic value of each attribute information lacks；When judging that the corresponding characteristic value of the attribute information lacks, the corresponding characteristic value of the attribute information estimate To the current user state information.
- 4. the Products Show method according to claim 3 based on big data, which is characterized in that the attribute information pair The characteristic value answered is estimated specially：The corresponding characteristic value of the attribute information is estimated using prediction model.
- 5. the Products Show method according to claim 4 based on big data, which is characterized in that utilize linear regression algorithm Or decision Tree algorithms obtain the prediction model.
- 6. the Products Show method according to claim 1 based on big data, which is characterized in that bought according to the user The probability size of each product is followed successively by the corresponding product of user's recommendation：The current user state information is randomly divided into training sample and test sample；Machine learning is carried out to the training sample and obtains initial predicted model, and using the test sample to described initial pre- Model is surveyed to be verified to obtain standard prediction；The current user state information is predicted using the standard prediction to obtain the multiple products of user's purchase Probability.
- 7. the Products Show method according to claim 6 based on big data, which is characterized in that utilize the normative forecast Model is predicted to obtain user and buys the probability of various product to the current user state information is specially：The current user state information is inputted into the standard prediction, user is obtained and buys the general of each product Rate.
- 8. the Products Show method according to claim 6 based on big data, which is characterized in that each product of purchase The sum of probability is 1.
- 9. the Products Show method according to claim 1 based on big data, which is characterized in that bought according to the user The probability size of each product is followed successively by the corresponding product of user's recommendation：Product is marked using label, and searches the corresponding label of each product of user's purchase；The probability size and the corresponding label of each product for each product bought according to the user recommend to correspond to for the user Product.
- 10. a kind of Products Show device based on big data, which is characterized in that including：Current state information prediction module, for obtaining historical user's status data, and based on big data model to the history User Status data are predicted to obtain current user state information；Product probabilistic forecasting module, for being predicted to obtain the multiple products of user's purchase according to the current user state information Probability；Products Show module, the probability size for buying each product according to the user are followed successively by user's recommendation pair The product answered.
- 11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program Products Show method of the claim 1-9 any one of them based on big data is realized when being executed by processor.
- 12. a kind of electronic equipment, which is characterized in that including：Processor；AndMemory, for storing the executable instruction of the processor；Wherein, the processor is configured to carry out perform claim requirement 1-9 any one of them via the execution executable instruction Products Show method based on big data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711429283.1A CN108154420A (en) | 2017-12-26 | 2017-12-26 | Products Show method and device, storage medium, electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711429283.1A CN108154420A (en) | 2017-12-26 | 2017-12-26 | Products Show method and device, storage medium, electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108154420A true CN108154420A (en) | 2018-06-12 |
Family
ID=62462862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711429283.1A Pending CN108154420A (en) | 2017-12-26 | 2017-12-26 | Products Show method and device, storage medium, electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108154420A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108711110A (en) * | 2018-08-14 | 2018-10-26 | 中国平安人寿保险股份有限公司 | Insurance products recommend method, apparatus, computer equipment and storage medium |
| CN109087124A (en) * | 2018-07-02 | 2018-12-25 | 麒麟合盛网络技术股份有限公司 | A kind of application program Value Prediction Methods and device |
| CN109165347A (en) * | 2018-08-20 | 2019-01-08 | 腾讯科技（深圳）有限公司 | Data push method and device, storage medium and electronic device |
| CN109242631A (en) * | 2018-09-17 | 2019-01-18 | 平安科技（深圳）有限公司 | Product intelligent recommended method, server and storage medium |
| CN109300054A (en) * | 2018-11-27 | 2019-02-01 | 泰康保险集团股份有限公司 | Insurance products recommended method, device, server and storage medium |
| CN110197295A (en) * | 2019-04-23 | 2019-09-03 | 深圳壹账通智能科技有限公司 | Prediction financial product buy in risk method and relevant apparatus |
| CN110570229A (en) * | 2019-07-30 | 2019-12-13 | 平安科技（深圳）有限公司 | User information processing method and device, computer equipment and storage medium |
| CN110659947A (en) * | 2019-10-11 | 2020-01-07 | 沈阳民航东北凯亚有限公司 | Commodity recommendation method and device |
| CN110781380A (en) * | 2019-09-09 | 2020-02-11 | 深圳壹账通智能科技有限公司 | Information pushing method and device, computer equipment and storage medium |
| WO2020063116A1 (en) * | 2018-09-29 | 2020-04-02 | 阿里巴巴集团控股有限公司 | Risk guarantee product pushing method and apparatus, and electronic device |
| CN111179011A (en) * | 2019-11-05 | 2020-05-19 | 泰康保险集团股份有限公司 | Insurance product recommendation method and device |
| CN111177564A (en) * | 2019-12-31 | 2020-05-19 | 北京顺丰同城科技有限公司 | Product recommendation method and device |
| CN111192108A (en) * | 2019-12-16 | 2020-05-22 | 北京淇瑀信息科技有限公司 | Sorting method and device for product recommendation and electronic equipment |
| CN111798273A (en) * | 2020-07-01 | 2020-10-20 | 中国建设银行股份有限公司 | Training method of purchase probability prediction model of product and purchase probability prediction method |
| CN112116397A (en) * | 2020-09-25 | 2020-12-22 | 贝壳技术有限公司 | User behavior characteristic real-time processing method and device, storage medium and electronic equipment |
| CN113129114A (en) * | 2021-05-13 | 2021-07-16 | 北京大米科技有限公司 | Service recommendation method and device, readable storage medium and electronic equipment |
| CN113191821A (en) * | 2021-05-20 | 2021-07-30 | 北京大米科技有限公司 | Data processing method and device |
| CN113656690A (en) * | 2021-08-16 | 2021-11-16 | 中国平安财产保险股份有限公司 | Product recommendation method and device, electronic equipment and readable storage medium |
| CN113807905A (en) * | 2020-11-05 | 2021-12-17 | 北京沃东天骏信息技术有限公司 | Article recommendation method and device, computer storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164447A (en) * | 2011-12-14 | 2013-06-19 | 阿里巴巴集团控股有限公司 | Method and device for searching target information |
| CN105808637A (en) * | 2016-02-23 | 2016-07-27 | 平安科技（深圳）有限公司 | Personalized recommendation method and device |
| CN106372961A (en) * | 2016-08-23 | 2017-02-01 | 北京小米移动软件有限公司 | Commodity recommendation method and device |
| CN107403358A (en) * | 2017-07-19 | 2017-11-28 | 无锡天脉聚源传媒科技有限公司 | A kind of information recommendation method and device |
-
2017
- 2017-12-26 CN CN201711429283.1A patent/CN108154420A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164447A (en) * | 2011-12-14 | 2013-06-19 | 阿里巴巴集团控股有限公司 | Method and device for searching target information |
| CN105808637A (en) * | 2016-02-23 | 2016-07-27 | 平安科技（深圳）有限公司 | Personalized recommendation method and device |
| CN106372961A (en) * | 2016-08-23 | 2017-02-01 | 北京小米移动软件有限公司 | Commodity recommendation method and device |
| CN107403358A (en) * | 2017-07-19 | 2017-11-28 | 无锡天脉聚源传媒科技有限公司 | A kind of information recommendation method and device |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109087124A (en) * | 2018-07-02 | 2018-12-25 | 麒麟合盛网络技术股份有限公司 | A kind of application program Value Prediction Methods and device |
| CN108711110B (en) * | 2018-08-14 | 2023-06-23 | 中国平安人寿保险股份有限公司 | Insurance product recommendation method, apparatus, computer device and storage medium |
| CN108711110A (en) * | 2018-08-14 | 2018-10-26 | 中国平安人寿保险股份有限公司 | Insurance products recommend method, apparatus, computer equipment and storage medium |
| CN109165347A (en) * | 2018-08-20 | 2019-01-08 | 腾讯科技（深圳）有限公司 | Data push method and device, storage medium and electronic device |
| CN109242631A (en) * | 2018-09-17 | 2019-01-18 | 平安科技（深圳）有限公司 | Product intelligent recommended method, server and storage medium |
| WO2020063116A1 (en) * | 2018-09-29 | 2020-04-02 | 阿里巴巴集团控股有限公司 | Risk guarantee product pushing method and apparatus, and electronic device |
| CN109300054A (en) * | 2018-11-27 | 2019-02-01 | 泰康保险集团股份有限公司 | Insurance products recommended method, device, server and storage medium |
| CN110197295A (en) * | 2019-04-23 | 2019-09-03 | 深圳壹账通智能科技有限公司 | Prediction financial product buy in risk method and relevant apparatus |
| CN110570229A (en) * | 2019-07-30 | 2019-12-13 | 平安科技（深圳）有限公司 | User information processing method and device, computer equipment and storage medium |
| CN110781380A (en) * | 2019-09-09 | 2020-02-11 | 深圳壹账通智能科技有限公司 | Information pushing method and device, computer equipment and storage medium |
| CN110659947A (en) * | 2019-10-11 | 2020-01-07 | 沈阳民航东北凯亚有限公司 | Commodity recommendation method and device |
| CN111179011A (en) * | 2019-11-05 | 2020-05-19 | 泰康保险集团股份有限公司 | Insurance product recommendation method and device |
| CN111192108A (en) * | 2019-12-16 | 2020-05-22 | 北京淇瑀信息科技有限公司 | Sorting method and device for product recommendation and electronic equipment |
| CN111177564B (en) * | 2019-12-31 | 2023-06-02 | 北京顺丰同城科技有限公司 | Product recommendation method and device |
| CN111177564A (en) * | 2019-12-31 | 2020-05-19 | 北京顺丰同城科技有限公司 | Product recommendation method and device |
| CN111798273A (en) * | 2020-07-01 | 2020-10-20 | 中国建设银行股份有限公司 | Training method of purchase probability prediction model of product and purchase probability prediction method |
| CN112116397A (en) * | 2020-09-25 | 2020-12-22 | 贝壳技术有限公司 | User behavior characteristic real-time processing method and device, storage medium and electronic equipment |
| CN113807905A (en) * | 2020-11-05 | 2021-12-17 | 北京沃东天骏信息技术有限公司 | Article recommendation method and device, computer storage medium and electronic equipment |
| CN113129114A (en) * | 2021-05-13 | 2021-07-16 | 北京大米科技有限公司 | Service recommendation method and device, readable storage medium and electronic equipment |
| CN113191821A (en) * | 2021-05-20 | 2021-07-30 | 北京大米科技有限公司 | Data processing method and device |
| CN113656690A (en) * | 2021-08-16 | 2021-11-16 | 中国平安财产保险股份有限公司 | Product recommendation method and device, electronic equipment and readable storage medium |
| CN113656690B (en) * | 2021-08-16 | 2023-06-02 | 中国平安财产保险股份有限公司 | Product recommendation method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108154420A (en) | Products Show method and device, storage medium, electronic equipment | |
| US11537719B2 (en) | Deep neural network system for similarity-based graph representations | |
| Yu et al. | Prediction of bus travel time using random forests based on near neighbors | |
| CN109064278B (en) | Target object recommendation method and device, electronic equipment and storage medium | |
| CN109242044A (en) | Training method, device, storage medium and the electronic equipment of vehicle and goods matching model | |
| Hillel et al. | Recreating passenger mode choice-sets for transport simulation: A case study of London, UK | |
| CN110222893B (en) | Method and device for recommending delivery places of shared traffic resources and electronic equipment | |
| CN111582559B (en) | Arrival time estimation method and device | |
| CN109784978A (en) | Advertisement competition power calculation method, device, medium and equipment based on big data | |
| CN111723292B (en) | Recommendation method, system, electronic equipment and storage medium based on graph neural network | |
| CN112508300A (en) | Method for establishing risk prediction model, regional risk prediction method and corresponding device | |
| CN110910180A (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN110457339A (en) | Data search method and device, electronic equipment, storage medium | |
| CN112884235A (en) | Travel recommendation method, and training method and device of travel recommendation model | |
| Liu et al. | Modeling the interaction coupling of multi-view spatiotemporal contexts for destination prediction | |
| Lai et al. | Understanding drivers' route choice behaviours in the urban network with machine learning models | |
| CN109034853A (en) | Similar users method, apparatus, medium and electronic equipment are found based on seed user | |
| Lim et al. | Determinants of household flood evacuation mode choice in a developing country | |
| CN115775059A (en) | Site planning method, device, equipment and storage medium | |
| CN115456266A (en) | Journey planning method, device, equipment and storage medium | |
| Kim et al. | Why do people move? Enhancing human mobility prediction using local functions based on public records and SNS data | |
| CN112686457B (en) | Route arrival time estimation method and device, electronic equipment and storage medium | |
| CN110348581A (en) | User characteristics optimization method, device, medium and electronic equipment in user characteristics group | |
| CN111274471A (en) | Information pushing method and device, server and readable storage medium | |
| Chebbi et al. | An elitist multi-objective genetic algorithm for minimizing vehicle numbers and energy consumption in the context of Personal Rapid Transit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180612 |
|
| RJ01 | Rejection of invention patent application after publication |