CN108492194A - Products Show method, apparatus and storage medium - Google Patents
Products Show method, apparatus and storage medium Download PDFInfo
- Publication number
- CN108492194A CN108492194A CN201810183372.0A CN201810183372A CN108492194A CN 108492194 A CN108492194 A CN 108492194A CN 201810183372 A CN201810183372 A CN 201810183372A CN 108492194 A CN108492194 A CN 108492194A
- Authority
- CN
- China
- Prior art keywords
- customer
- target
- target customer
- sample
- preset
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 85
- 239000000047 product Substances 0.000 claims description 111
- 238000012549 training Methods 0.000 claims description 37
- 230000015654 memory Effects 0.000 claims description 17
- 239000006185 dispersion Substances 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 230000003014 reinforcing effect Effects 0.000 claims 2
- 230000006870 function Effects 0.000 description 14
- 239000010749 BS 2869 Class C1 Substances 0.000 description 8
- 239000010750 BS 2869 Class C2 Substances 0.000 description 8
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000009471 action Effects 0.000 description 6
- 239000003795 chemical substances by application Substances 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000002123 temporal effect Effects 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000000547 structure data Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 1
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention proposes a kind of Products Show method, including:Characteristic of the target customer in the first preset time is obtained, this feature data include assets, medical treatment, work and life information;According to this feature data and preset analysis rule, the customer class belonging to the target customer is analyzed;The characteristic is input in the corresponding analysis model trained in advance of the customer class, prediction, which obtains the target customer, there may be the product of purchase intention;And recommend the product to the target customer.The present invention also proposes a kind of electronic device and storage medium.Using the present invention, according to the characteristic of target customer, analysis predicts that the target customer may have the product of purchase intention, improves Products Show accuracy rate.
Description
Technical field
It can the present invention relates to a kind of field of computer technology more particularly to Products Show method, electronic device and computer
Read storage medium.
Background technology
In traditional insurance business, in order to improve the accuracy of Products Show, it usually needs use Products Show algorithm
For different user recommended products.However, traditional Products Show algorithm is used to be easy error, recommended products for lead referral product
Accuracy cannot be satisfied actual needs.
Therefore, the accuracy for how improving Products Show has become a technical problem urgently to be resolved hurrily.
Invention content
A kind of Products Show method of present invention offer, electronic device and computer readable storage medium, main purpose exist
In the product that the characteristic according to target customer, analysis and suggestion are recommended to target customer, the recommendation accuracy rate of product is improved.
To achieve the above object, the present invention provides a kind of electronic device, which includes memory, processor, described to deposit
It is stored with the Products Show program that can be run on the processor on reservoir, is realized such as when which is executed by the processor
Lower step:
Obtain characteristic of the target customer in the first preset time, this feature data include assets, medical treatment, work and
Life information;
According to this feature data and preset analysis rule, the customer class belonging to the target customer is analyzed;
The characteristic is input in the corresponding analysis model trained in advance of the customer class, prediction obtains the target
Client may have the product of purchase intention;And
Recommend the product to the target customer.
In addition, to achieve the above object, the present invention also provides a kind of Products Show method, this method includes:
Obtain characteristic of the target customer in the first preset time, this feature data include assets, medical treatment, work and
Life information;
According to this feature data and preset analysis rule, the customer class belonging to the target customer is analyzed;
The characteristic is input in the corresponding analysis model trained in advance of the customer class, prediction obtains the target
Client may have the product of purchase intention;And
Recommend the product to the target customer.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Products Show program is stored on storage medium, which realizes Products Show method as described above when being executed by processor
Arbitrary steps.
Compared to the prior art, Products Show method, electronic device and computer readable storage medium proposed by the present invention,
According to the characteristic of target customer, the customer class belonging to target customer is determined, corresponded to using the customer class belonging to target customer
Analysis model, analyze the product that suggestion is recommended to target customer, and recommend the product to it, the recommendation for improving product is accurate
True rate, and then improve buying rate of the target customer to product.
Description of the drawings
Fig. 1 is the schematic diagram of electronic device preferred embodiment of the present invention;
Fig. 2 is the operation mechanism schematic diagram of analysis model;
Fig. 3 is the program module schematic diagram of Products Show program in Fig. 1;
Fig. 4 is the flow chart of Products Show method preferred embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present invention provides a kind of Products Show method, and this method is applied to a kind of electronic device 1.Shown in referring to Fig.1, for this
The schematic diagram of 1 preferred embodiment of invention electronic device.
In the present embodiment, electronic device 1 can be server, smart mobile phone, tablet computer, pocket computer, on table
Type computer etc. has the terminal device of data processing function, and the server can be rack-mount server, blade type service
Device, tower server or Cabinet-type server.
The electronic device 1 includes memory 11, processor 12, communication bus 13 and network interface 14.
Wherein, memory 11 include at least a type of readable storage medium storing program for executing, the readable storage medium storing program for executing include flash memory,
Hard disk, multimedia card, card-type memory (for example, SD or DX memories etc.), magnetic storage, disk, CD etc..Memory 11
Can be the internal storage unit of the electronic device 1, such as the hard disk of the electronic device 1 in some embodiments.Memory
11 can also be the External memory equipment of the electronic device 1 in further embodiments, such as be equipped on the electronic device 1
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, memory 11 can also both include the internal storage unit of the electronic device 1 or wrap
Include External memory equipment.Memory 11 can be not only used for the application software and Various types of data that storage is installed on the electronic device 1,
Such as Products Show program 10, preset analysis rule, predetermined analysis model etc., it can be also used for temporarily storing
Data through exporting or will export.
Processor 12 can be in some embodiments a central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips, the program for being stored in run memory 11
Code or processing data, such as Products Show program 10 etc..
Communication bus 13 is for realizing the connection communication between these components.
Network interface 14 may include optionally standard wireline interface and wireless interface (such as WI-FI interface), be commonly used in
Communication connection is established between the electronic device 1 and other electronic equipments.Preferably, electronic device 1 is visited by network interface 14
Ask service server, for example, bank server, medical server, insurance server etc., to obtain relevant business datum.
Fig. 1 illustrates only the electronic device 1 with component 11-14, it should be understood that being not required for implementing all show
The component gone out, the implementation that can be substituted is more or less component.
Optionally, the electronic device 1 can also include user interface, user interface may include display (Display),
Input unit such as keyboard (Keyboard), optional user interface can also include standard wireline interface and wireless interface.
Optionally, in some embodiments, display can be that light-emitting diode display, liquid crystal display, touch control type LCD are shown
Device and Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) touch device etc..Wherein, display
It is properly termed as display screen or display unit, for showing the information handled in the electronic apparatus 1 and for showing visually
User interface.
In device embodiment shown in Fig. 1, Products Show program 10 is stored in memory 11.The execution of processor 12 is deposited
Following steps are realized when the Products Show program 10 stored in reservoir 11:
Obtain characteristic of the target customer in the first preset time, this feature data include assets, medical treatment, work and
Life information;
According to this feature data and preset analysis rule, the customer class belonging to the target customer is analyzed;
The characteristic is input in the corresponding analysis model trained in advance of the customer class, prediction obtains the target
Client may have the product of purchase intention;And
Recommend the product to the target customer.
In the present embodiment, this programme is illustrated by taking the insurance products of certain mechanism as an example, but is not limited only to insurance production
The recommendation of product.When needing to a predetermined lead referral insurance products, (do not marked in figure from customer database first
Know) in obtain the client properties data of target customer, for example, passport NO., alternatively, name, cell-phone number and passport NO., according to
The client properties data of target customer extract the various of target customer from different service servers (not identified in figure) respectively
Characteristic.For example, service server can be bank server, medical server, insurance server, instant messaging service
Device, game server, carryout service device and/or resume server etc.;Various characteristics can be bank loan amounts and go back
Money ask the information such as money, patient medical history information " for example, in preset time see a doctor number, illnesses type, each illness are held
Continuous time etc. ", insurance information " for example, the industry, gender, age, marital status, occupation etc. ", immediate communication tool account
Use information " for example, the information such as the daily landing time information of communication tool, daily online hours " etc., game information " example
Such as, daily game entry temporal information, the daily information such as game online hours " take out information of ordering " for example, point is taken out daily
Temporal information, put the take-away type etc. of take-away daily ", the information filled on job seeker resume " for example, hobby, personality,
The information such as work experience ".
It is understood that over time, the characteristic of target customer can have greatly changed, in order to make
The characteristic of acquisition more meets the current actual conditions of target customer, on time dimension to the characteristic of target customer into
Row screening, only retain target customer in the first preset time (for example, in 1 year away from current time) characteristic.
Recommend suitable insurance products for target customer, above all understanding the feature of target customer, i.e. target customer institute
Belong to customer class.After getting the various characteristics of target customer, is analyzed according to preset analysis rule, determine target
Customer class belonging to client.
As an implementation, preset analysis rule includes:According to the characteristic of the target customer, generate corresponding
Feature vector, calculate separately the Euclidean distance of itself and the target cluster centre of predetermined preset quantity, wherein each mesh
It marks cluster centre and corresponds to a customer class;And the Euclidean distance according to the target customer and the target cluster centre of preset quantity,
The corresponding target cluster centre of Euclidean distance minimum value is selected, type label is marked for the target customer, determines the target customer
Affiliated customer class.
For example, 500,000 client's sample set D of input, wherein D={ x1, x2 ..., xj ..., xm }, xj indicate each client
Characteristic corresponding feature vector of the sample in the second preset time (for example, 1 year);Corresponding kind of each client's sample
Class tally set B, wherein B={ t1, t2 ..., tj ... tm }, ti indicate the corresponding type label of each client's sample.It can manage
Solution, if being clustered for the first time, each client's sample is no type label, i.e. tj=-1;On the contrary, if not
It is once clustered, according to the structure that last time clusters, each client's sample can there are one type labels, as the first of this cluster
Beginning type label, i.e. tj=lable.
First, (for example, k) corresponding characteristic of client's sample of the preset quantity of dispersion is selected from client's sample set
According to corresponding feature vector initial cluster center collection M is determined as initial cluster center collection M, wherein M={ U1, U2 ..., Uk }
Corresponding type tally set MB, wherein MB={ Mt1, Mt2 ... Mtk }, Mtk indicate corresponding kind of some initial cluster center Uk
Class label.Similarly, if not being clustered for the first time, then the cluster centre for the preset quantity for directly clustering last time is made
For the initial cluster center of this cluster.
Next, according to the characteristic data xj of 500,000 client's samples in client's sample set D, calculate separately each
The Euclidean distance dij of client's sample and k cluster centre, wherein i are some cluster centre, and j is some client's sample, wherein i
∈ [1, k], j ∈ [1, m].It should be noted that if this cluster is not when clustering for the first time, then to need to consider each client's sample
This initial labels, specifically, for client's sample of type label tj ≠ -1, according to its corresponding type label, update meter
Euclidean distance dij ' is calculated, for example, when the type label of client's sample is not equal to -1 and equal to the type label of cluster centre, i.e. tj
=Mtk and when tj ≠ -1, dij '=dij-n*dij;When the type label of client's sample not equal to -1 and is not equal to cluster centre
Type label, i.e. when tj ≠ Mtk, tj ≠ -1, then dij '=dij+n*dij, wherein n refers to the study of preset clustering algorithm
Rate.
Then, according to the Euclidean distance dij ' of each client's sample and the initial cluster center of preset quantity, minimum is taken
It is worth corresponding initial cluster center, is the type label of each client's sample labeling initial cluster center, by client's sample
It is attributed in the cluster set Ui of the corresponding initial cluster center of type label, and to the poly- of the initial cluster center of preset quantity
Class set Ui is updated, and obtains Ui ', wherein Ui '=Ui+ { xj }.
Finally, after all client's samples are sorted out, according to the updated cluster of the initial cluster center of preset quantity
Set Ui ' recalculates the corresponding cluster centres of cluster set Ui ', obtains new cluster centre set M ', if after update
Cluster centre the corresponding feature vector of characteristic feature vector corresponding with the characteristic of initial cluster center between
Euclidean distance when meeting preset condition (for example, be less than predetermined threshold value Y), stop calculating, will be in the new cluster of preset quantity
The heart exports target cluster centre collection M ' and its corresponding type label B as target cluster centre, as finally determining k
Customer class, and determine the corresponding type label of each predetermined client's sample, i.e. customer class belonging to it.If after update
Cluster centre the corresponding feature vector of characteristic feature vector corresponding with the characteristic of initial cluster center between
Euclidean distance when being unsatisfactory for preset condition, flow is back to the initial cluster center for calculating each client's sample and preset quantity
Euclidean distance, and execute and follow-up calculate step.
After determining the corresponding target cluster centre of each customer class, the characteristic for extracting each target cluster centre corresponds to
Feature vector, the characteristic of target customer is obtained into corresponding feature vector;Calculate separately the feature of characterization target customer
Euclidean distance between the feature vector of data feature vector corresponding with the characteristic of target cluster centre of preset quantity;
The corresponding target cluster centre of Euclidean distance minimum value is selected, is that the target customer marks type according to its corresponding type label
Label determines the customer class belonging to the target customer.
After determining the customer class belonging to target customer, transfer that the customer class belonging to target customer is corresponding to be trained in advance
Analysis model, the corresponding feature vector of the characteristic of target customer is inputted into analysis model, obtains needing recommended to the user
Insurance products.
Specifically, before being trained to the corresponding analysis model of each customer class, (example in third preset time is obtained
Such as, in nearest 3 years, alternatively, in all historical times) to above-mentioned each predetermined client's sample (for example, 500,000 in advance
Determining client) insurance products recommended and each predetermined client's sample be to the purchase information of the insurance products of recommendation.
For example, the purchase information can be:On December 1st, 2017 to tri- insurance products of A lead referral X1, X2, X3, A client
Have purchased insurance products X1.
Then, the customer class of the corresponding preset quantity of target cluster centre of the preset quantity determined according to above-mentioned steps,
All client's samples under each customer class correspond to the purchase information of the insurance products of recommendation as each customer class respectively
Analysis model training sample data.For example, using above-mentioned steps by each predetermined client's sample be divided into C1, C2,
Tri- customer class of C3, using all client's samples under customer class C1 to the purchase information of the insurance products of recommendation as customer class C1
The training sample data of corresponding analysis model;By purchase of all client's samples to the insurance products of recommendation under customer class C2
Training sample data of the information as the corresponding analysis models of customer class C2;By all client's samples under customer class C3 to recommending
Insurance products training sample data of the purchase information as the corresponding analysis models of customer class C3.
After the training sample data for determining the corresponding analysis model of each customer class, it is utilized respectively each customer class and corresponds to
Training sample data train corresponding analysis model.For example, having tri- customer class of C1, C2, C3, the corresponding training of customer class C1
Sample data is for training the corresponding analysis models of customer class C1;The corresponding training sample data of customer class C2 are for training client
The corresponding analysis models of class C2;The corresponding training sample data of customer class C3 are for training the corresponding analysis models of customer class C3.
Specifically, the analysis model is intensified learning model, for example, Deep Q-Network (DQN) model, with reference to figure
It is the operation mechanism schematic diagram of analysis model shown in 2.The purpose of intensified learning is the tactful π learnt from ambient condition to behavior:
S → A so that the behavior of intelligent body selection can obtain the maximum award of environmental feedback so that external environment is to learning system
Evaluation (or runnability of whole system) under certain meaning is best.Wherein, intelligent body (Agent) is as study
System, obtains the current state information of external environment;Environment is characterized with preset structure data tuple, the preset structure number
According to tuple E=(X, A, P, R), wherein:X represents state space, and each state x ∈ X are the descriptions for the environment that machine perceives;A
Motion space is represented, the action that intellectual Agent can be taken constitutes motion space;P represents transfer function, and environment is from current shape
State is transferred to another shape probability of state;R represents reward functions, and when state shifts, environment can be according to reward functions to intelligent body
Mono- award of Agent;Deterministic policy a=π (x) may be used in tactful π:The action which be to be a at state x.
T step accumulation awards may be used in award calculation, wherein rtRepresent the t times award:
State-action value function may be used in Policy evaluation function, indicates that, from state x, the t times execution action is a
The accumulation award that tactful π is brought is reused afterwards:
Using the disaggregated model of the corresponding preset structure of the affiliated customer class of target customer, analyzes suggestion and pushed away to target customer
After the insurance products recommended, recommend the insurance products to target customer.In the present embodiment, the cell-phone number of target customer can be read,
Recommend corresponding insurance products to target customer in the form of short message.
In other embodiments, it in order to keep analysis model more acurrate, needs to be updated analysis model.Specifically, it obtains
Take in the 4th preset time (for example, after upper primary model training three months in) target customer to the insurance products of recommendation
New purchase information;The new purchase information of acquisition is instructed as the supplement of the corresponding analysis model of the customer class belonging to the target customer
Practice sample data, using the supplementary training sample data, the corresponding analysis model of customer class belonging to target customer is carried out strong
Change training, obtains updated analysis model.Subsequent analysis is insured to other lead referral of the affiliated customer class of target customer produces
It when product, is analyzed using corresponding updated analysis model, keeps analysis result more acurrate, improve user to insurance products
Buying rate.
The electronic device 1 that above-described embodiment proposes determines the visitor belonging to target customer according to the characteristic of target customer
Family class analyzes the product that suggestion is recommended to target customer using the corresponding analysis model of customer class belonging to target customer, and
Recommend the product to it, improve the recommendation accuracy rate of product, and then improves buying rate of the target customer to product.
Optionally, in other examples, Products Show program 10 can also be divided into one or more module,
One or more module is stored in memory 11, and by one or more processors (the present embodiment is processor 12) institute
It executes, to complete the present invention, the so-called module of the present invention is the series of computation machine program instruction for referring to complete specific function
Section.It is the program module schematic diagram of Products Show program 10 in Fig. 1 shown in Fig. 3, in the embodiment, Products Show
Program 10 can be divided into acquisition module 110, sort module 120, analysis module 130 and recommending module 140, the module
The functions or operations step that 110-140 is realized is similar as above, and and will not be described here in detail, illustratively, such as wherein:
Acquisition module 110, for obtaining characteristic of the target customer in the first preset time, this feature data include
Assets, medical treatment, work and life information;
Sort module 120, for according to this feature data and preset analysis rule, analyzing the visitor belonging to the target customer
Family class;
Analysis module 130, for the characteristic to be input to the corresponding analysis model trained in advance of the customer class
In, prediction, which obtains the target customer, may the product of purchase intention;And
Recommending module 140, for recommending the product to the target customer.
In addition, the present invention also provides a kind of Products Show methods.With reference to shown in Fig. 4, be Products Show method of the present invention compared with
The flow chart of good embodiment.This method can be executed by a device, which can be by software and or hardware realization.
In the present embodiment, Products Show method includes step S1-S4:
Step S1 obtains characteristic of the target customer in the first preset time, including:Assets, medical treatment, work and life
Information living;
Step S2 analyzes the customer class belonging to the target customer according to this feature data and preset analysis rule;
The characteristic is input in the corresponding analysis model trained in advance of the customer class, measures in advance by step S3
There may be the product of purchase intention to the target customer;And
Step S4 recommends the product to the target customer.
In the present embodiment, this programme is illustrated by taking the insurance products of certain mechanism as an example, but is not limited only to insurance production
The recommendation of product.When needing to a predetermined lead referral insurance products, (do not marked in figure from customer database first
Know) in obtain the client properties data of target customer, for example, passport NO., alternatively, name, cell-phone number and passport NO., according to
The client properties data of target customer extract the various of target customer from different service servers (not identified in figure) respectively
Characteristic.For example, service server can be bank server, medical server, insurance server, instant messaging service
Device, game server, carryout service device and/or resume server etc.;Various characteristics can be bank loan amounts and go back
Money ask the information such as money, patient medical history information " for example, in preset time see a doctor number, illnesses type, each illness are held
Continuous time etc. ", insurance information " for example, the industry, gender, age, marital status, occupation etc. ", immediate communication tool account
Use information " for example, the information such as the daily landing time information of communication tool, daily online hours " etc., game information " example
Such as, daily game entry temporal information, the daily information such as game online hours " take out information of ordering " for example, point is taken out daily
Temporal information, put the take-away type etc. of take-away daily ", the information filled on job seeker resume " for example, hobby, personality,
The information such as work experience ".
It is understood that over time, the characteristic of target customer can have greatly changed, in order to make
The characteristic of acquisition more meets the current actual conditions of target customer, on time dimension to the characteristic of target customer into
Row screening, only retain target customer in the first preset time (for example, in 1 year away from current time) characteristic.
Recommend suitable insurance products for target customer, above all understanding the feature of target customer, i.e. target customer institute
Belong to customer class.After getting the various characteristics of target customer, is analyzed according to preset analysis rule, determine target
Customer class belonging to client.
As an implementation, preset analysis rule includes:According to the characteristic of the target customer, generate corresponding
Feature vector, calculate separately the Euclidean distance of itself and the target cluster centre of predetermined preset quantity, wherein each mesh
It marks cluster centre and corresponds to a customer class;And the Euclidean distance according to the target customer and the target cluster centre of preset quantity,
The corresponding target cluster centre of Euclidean distance minimum value is selected, type label is marked for the target customer, determines the target customer
Affiliated customer class.
For example, 500,000 client's sample set D of input, wherein D={ x1, x2 ..., xj ..., xm }, xj indicate each client
Characteristic corresponding feature vector of the sample in the second preset time (for example, 1 year);Corresponding kind of each client's sample
Class tally set B, wherein B={ t1, t2 ..., tj ... tm }, ti indicate the corresponding type label of each client's sample.It can manage
Solution, if being clustered for the first time, each client's sample is no type label, i.e. tj=-1;On the contrary, if not
It is once clustered, according to the structure that last time clusters, each client's sample can there are one type labels, as the first of this cluster
Beginning type label, i.e. tj=lable.
First, (for example, k) corresponding characteristic of client's sample of the preset quantity of dispersion is selected from client's sample set
According to corresponding feature vector initial cluster center collection M is determined as initial cluster center collection M, wherein M={ U1, U2 ..., Uk }
Corresponding type tally set MB, wherein MB={ Mt1, Mt2 ... Mtk }, Mtk indicate corresponding kind of some initial cluster center Uk
Class label.Similarly, if not being clustered for the first time, then the cluster centre for the preset quantity for directly clustering last time is made
For the initial cluster center of this cluster.
Next, according to the characteristic data xj of 500,000 client's samples in client's sample set D, calculate separately each
The Euclidean distance dij of client's sample and k cluster centre, wherein i are some cluster centre, and j is some client's sample, wherein i
∈ [1, k], j ∈ [1, m].It should be noted that if this cluster is not when clustering for the first time, then to need to consider each client's sample
This initial labels, specifically, for client's sample of type label tj ≠ -1, according to its corresponding type label, update meter
Euclidean distance dij ' is calculated, for example, when the type label of client's sample is not equal to -1 and equal to the type label of cluster centre, i.e. tj
=Mtk and when tj ≠ -1, dij '=dij-n*dij;When the type label of client's sample not equal to -1 and is not equal to cluster centre
Type label, i.e. when tj ≠ Mtk, tj ≠ -1, then dij '=dij+n*dij, wherein n refers to the study of preset clustering algorithm
Rate.
Then, according to the Euclidean distance dij ' of each client's sample and the initial cluster center of preset quantity, minimum is taken
It is worth corresponding initial cluster center, is the type label of each client's sample labeling initial cluster center, by client's sample
It is attributed in the cluster set Ui of the corresponding initial cluster center of type label, and to the poly- of the initial cluster center of preset quantity
Class set Ui is updated, and obtains Ui ', wherein Ui '=Ui+ { xj }.
Finally, after all client's samples are sorted out, according to the updated cluster of the initial cluster center of preset quantity
Set Ui ' recalculates the corresponding cluster centres of cluster set Ui ', obtains new cluster centre set M ', if after update
Cluster centre the corresponding feature vector of characteristic feature vector corresponding with the characteristic of initial cluster center between
Euclidean distance when meeting preset condition (for example, be less than predetermined threshold value Y), stop calculating, will be in the new cluster of preset quantity
The heart exports target cluster centre collection M ' and its corresponding type label B as target cluster centre, as finally determining k
Customer class, and determine the corresponding type label of each predetermined client's sample, i.e. customer class belonging to it.If after update
Cluster centre the corresponding feature vector of characteristic feature vector corresponding with the characteristic of initial cluster center between
Euclidean distance when being unsatisfactory for preset condition, flow is back to the initial cluster center for calculating each client's sample and preset quantity
Euclidean distance, and execute and follow-up calculate step.
After determining the corresponding target cluster centre of each customer class, the characteristic for extracting each target cluster centre corresponds to
Feature vector, the characteristic of target customer is obtained into corresponding feature vector;Calculate separately the feature of characterization target customer
Euclidean distance between the feature vector of data feature vector corresponding with the characteristic of target cluster centre of preset quantity;
The corresponding target cluster centre of Euclidean distance minimum value is selected, is that the target customer marks type according to its corresponding type label
Label determines the customer class belonging to the target customer.
After determining the customer class belonging to target customer, transfer that the customer class belonging to target customer is corresponding to be trained in advance
Analysis model, the corresponding feature vector of the characteristic of target customer is inputted into analysis model, suggestion is obtained and recommends to user
Insurance products.
Specifically, before being trained to the corresponding analysis model of each customer class, (example in third preset time is obtained
Such as, in nearest 3 years, alternatively, in all historical times) to above-mentioned each predetermined client's sample (for example, 500,000 in advance
Determining client) insurance products recommended and each predetermined client's sample be to the purchase information of the insurance products of recommendation.
For example, the purchase information can be:On December 1st, 2017 to tri- insurance products of A lead referral X1, X2, X3, A client
Have purchased insurance products X1.
Then, the customer class of the corresponding preset quantity of target cluster centre of the preset quantity determined according to above-mentioned steps,
All client's samples under each customer class correspond to the purchase information of the insurance products of recommendation as each customer class respectively
Analysis model training sample data.For example, using above-mentioned steps by each predetermined client's sample be divided into C1, C2,
Tri- customer class of C3, using all client's samples under customer class C1 to the purchase information of the insurance products of recommendation as customer class C1
The training sample data of corresponding analysis model;By purchase of all client's samples to the insurance products of recommendation under customer class C2
Training sample data of the information as the corresponding analysis models of customer class C2;By all client's samples under customer class C3 to recommending
Insurance products training sample data of the purchase information as the corresponding analysis models of customer class C3.
After the training sample data for determining the corresponding analysis model of each customer class, it is utilized respectively each customer class and corresponds to
Training sample data train corresponding analysis model.For example, having tri- customer class of C1, C2, C3, the corresponding training of customer class C1
Sample data is for training the corresponding analysis models of customer class C1;The corresponding training sample data of customer class C2 are for training client
The corresponding analysis models of class C2;The corresponding training sample data of customer class C3 are for training the corresponding analysis models of customer class C3.
Specifically, the analysis model is intensified learning model, for example, Deep Q-Network (DQN) model, with reference to figure
It is the operation mechanism schematic diagram of analysis model shown in 2.The purpose of intensified learning is the tactful π learnt from ambient condition to behavior:
S → A so that the behavior of intelligent body selection can obtain the maximum award of environmental feedback so that external environment is to learning system
Evaluation (or runnability of whole system) under certain meaning is best.Wherein, intelligent body (Agent) is as study
System, obtains the current state information of external environment;Environment is characterized with preset structure data tuple, the preset structure number
According to tuple E=(X, A, P, R), wherein:X represents state space, and each state x ∈ X are the descriptions for the environment that machine perceives;A
Motion space is represented, the action that intellectual Agent can be taken constitutes motion space;P represents transfer function, and environment is from current shape
State is transferred to another shape probability of state;R represents reward functions, and when state shifts, environment can be according to reward functions to intelligent body
Mono- award of Agent;Deterministic policy a=π (x) may be used in tactful π:The action which be to be a at state x.
T step accumulation awards may be used in award calculation, wherein rtRepresent the t times award:
State-action value function may be used in Policy evaluation function, indicates that, from state x, the t times execution action is a
The accumulation award that tactful π is brought is reused afterwards:
Using the disaggregated model of the corresponding preset structure of the affiliated customer class of target customer, analyzes suggestion and pushed away to target customer
After the insurance products recommended, recommend the insurance products to target customer.In the present embodiment, the cell-phone number of target customer can be read,
Recommend corresponding insurance products to target customer in the form of short message.
In other embodiments, it in order to keep analysis model more acurrate, needs to be updated analysis model.Specifically, it obtains
Take in the 4th preset time (for example, after upper primary model training three months in) target customer to the insurance products of recommendation
New purchase information;The new purchase information of acquisition is instructed as the supplement of the corresponding analysis model of the customer class belonging to the target customer
Practice sample data, using the supplementary training sample data, the corresponding analysis model of customer class belonging to target customer is carried out strong
Change training, obtains updated analysis model.Subsequent analysis is insured to other lead referral of the affiliated customer class of target customer produces
It when product, is analyzed using corresponding updated analysis model, keeps analysis result more acurrate, improve user to insurance products
Buying rate.
The Products Show method that above-described embodiment proposes is determined according to the characteristic of target customer belonging to target customer
Customer class analyze the production that suggestion is recommended to target customer using the corresponding analysis model of customer class belonging to target customer
Product, and recommend the product to it, the recommendation accuracy rate of product is improved, and then improve buying rate of the target customer to product.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with Products Show program 10, following operation is realized when which is executed by processor:
Obtain characteristic of the target customer in the first preset time, this feature data include assets, medical treatment, work and
Life information;
According to this feature data and preset analysis rule, the customer class belonging to the target customer is analyzed;
The characteristic is input in the corresponding analysis model trained in advance of the customer class, prediction obtains the target
Client may have the product of purchase intention;And
Recommend the product to the target customer.
Computer readable storage medium specific implementation mode of the present invention recommends each embodiment of method basic with the said goods
It is identical, do not make tired state herein.
It should be noted that the embodiments of the present invention are for illustration only, can not represent the quality of embodiment.And
The terms "include", "comprise" herein or any other variant thereof is intended to cover non-exclusive inclusion, so that packet
Process, device, article or the method for including a series of elements include not only those elements, but also include being not explicitly listed
Other element, or further include for this process, device, article or the intrinsic element of method.Do not limiting more
In the case of, the element that is limited by sentence "including a ...", it is not excluded that in the process including the element, device, article
Or there is also other identical elements in method.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be expressed in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions use so that a station terminal equipment (can be mobile phone,
Computer, server or network equipment etc.) execute method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of Products Show method, it is applied to electronic device, which is characterized in that this method includes:
Characteristic of the target customer in the first preset time is obtained, this feature data include assets, medical treatment, work and life
Information;
According to this feature data and preset analysis rule, the customer class belonging to the target customer is analyzed;
The characteristic is input in the corresponding analysis model trained in advance of the customer class, prediction obtains the target customer
There may be the product of purchase intention;And
Recommend the product to the target customer.
2. Products Show method as described in claim 1, which is characterized in that the preset analysis rule is:
According to the characteristic of the target customer, the Europe of itself and predetermined one or more target cluster centres is calculated separately
Family name's distance, wherein each target cluster centre corresponds to a customer class;And
According to the type label of the corresponding target cluster centre of Euclidean distance minimum value, type label is marked for the target customer,
Determine the customer class belonging to the target customer.
3. Products Show method as claimed in claim 2, which is characterized in that affiliated predetermined one or more targets are poly-
The obtaining step at class center includes:
Sample data of the predetermined client's sample in the second preset time is obtained, including:Each predetermined client
The characteristic and type label of sample select the characteristic of client's sample of the preset quantity of dispersion from the sample data
Initial cluster center label is marked as initial cluster center, and for the initial cluster center;
According to the characteristic of each predetermined client's sample, calculates separately each predetermined client's sample and preset
The Euclidean distance of the initial cluster center of quantity;
According to the type label of each predetermined client's sample, update calculates each predetermined client's sample and presets
The new Euclidean distance of the initial cluster center of quantity;
It is each predetermined client's sample according to the type label of the new corresponding initial cluster center of Euclidean distance minimum value
This more New raxa label, and be attributed in the corresponding cluster set of type label;And
After all samples are sorted out, the new cluster centre of the cluster set of preset quantity is calculated, when new cluster centre
When meeting preset condition with the Euclidean distance of corresponding initial cluster center, using the new cluster centre of preset quantity as target
Cluster centre exports target cluster centre and its corresponding type label, determines belonging to each predetermined client's sample
Customer class.
4. Products Show method as claimed in claim 3, which is characterized in that the training step of the analysis model includes:
Obtain the product recommended to each predetermined client's sample in third preset time and each predetermined client
Sample is to the purchase information of the product of recommendation, respectively by all client's samples under preset each customer class to the product of recommendation
Training sample data of the purchase information as the corresponding analysis model of preset each customer class;And
It is utilized respectively the corresponding training sample data of each customer class, the corresponding analysis model of training.
5. Products Show method as claimed in claim 4, which is characterized in that this method further includes:
The target customer is obtained in the 4th preset time to the purchase information of the product of recommendation;And
Using the purchase information of acquisition as the supplementary training sample number of the corresponding analysis model of the customer class belonging to the target customer
According to using the supplementary training sample data, supplement reinforcing is carried out to the corresponding analysis model of customer class belonging to the target customer
Training.
6. Products Show method as described in claim 1, which is characterized in that the predetermined analysis model using
Nitrification enhancement.
7. a kind of electronic device, which is characterized in that the device includes:Memory, processor, being stored on the memory can be
The Products Show program run on the processor, the program realize following steps when being executed by the processor:
Characteristic of the target customer in the first preset time is obtained, this feature data include assets, medical treatment, work and life
Information;
According to this feature data and preset analysis rule, the customer class belonging to the target customer is analyzed;
The characteristic is input in the corresponding analysis model trained in advance of the customer class, prediction obtains the target customer
There may be the product of purchase intention;And
Recommend the product to the target customer.
8. electronic device as claimed in claim 7, which is characterized in that the preset analysis rule is:
According to the characteristic of the target customer, the Europe of itself and predetermined one or more target cluster centres is calculated separately
Family name's distance, wherein each target cluster centre corresponds to a customer class;And
According to the type label of the corresponding target cluster centre of Euclidean distance minimum value, type label is marked for the target customer,
Determine the customer class belonging to the target customer.
9. electronic device as claimed in claim 7, which is characterized in that the predetermined analysis model is using reinforcing
Learning algorithm.
10. a kind of computer readable storage medium, which is characterized in that be stored with product on the computer readable storage medium and push away
Program is recommended, the step such as Products Show method according to any one of claims 1 to 6 is realized when which is executed by processor
Suddenly.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810183372.0A CN108492194A (en) | 2018-03-06 | 2018-03-06 | Products Show method, apparatus and storage medium |
PCT/CN2018/089127 WO2019169756A1 (en) | 2018-03-06 | 2018-05-31 | Product recommendation method and apparatus, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810183372.0A CN108492194A (en) | 2018-03-06 | 2018-03-06 | Products Show method, apparatus and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108492194A true CN108492194A (en) | 2018-09-04 |
Family
ID=63341499
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810183372.0A Pending CN108492194A (en) | 2018-03-06 | 2018-03-06 | Products Show method, apparatus and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN108492194A (en) |
WO (1) | WO2019169756A1 (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109360072A (en) * | 2018-11-13 | 2019-02-19 | 平安科技(深圳)有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
CN109377388A (en) * | 2018-09-13 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Medical insurance is insured method, apparatus, computer equipment and storage medium |
CN109376306A (en) * | 2018-12-04 | 2019-02-22 | 挖财网络技术有限公司 | A kind of service recommendation method and system based on label panorama sketch |
CN109447728A (en) * | 2018-09-07 | 2019-03-08 | 平安科技(深圳)有限公司 | Financial product recommended method, device, computer equipment and storage medium |
CN109670896A (en) * | 2018-09-28 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Investment product recommended method, device, equipment and storage medium |
CN109711929A (en) * | 2018-12-13 | 2019-05-03 | 中国平安财产保险股份有限公司 | Business recommended method and device based on prediction model |
CN109767345A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, equipment and storage medium based on information matches |
CN109785000A (en) * | 2019-01-16 | 2019-05-21 | 深圳壹账通智能科技有限公司 | Customer resources distribution method, device, storage medium and terminal |
CN109816127A (en) * | 2019-01-11 | 2019-05-28 | 广州市骑鹅游信息技术咨询服务有限公司 | A kind of intelligence ticketing service recommended method and system |
CN109816534A (en) * | 2018-12-17 | 2019-05-28 | 平安国际融资租赁有限公司 | Financing lease Products Show method, apparatus, computer equipment and storage medium |
CN109903168A (en) * | 2019-01-18 | 2019-06-18 | 平安科技(深圳)有限公司 | The method and relevant device of recommendation insurance products based on machine learning |
CN109919093A (en) * | 2019-03-07 | 2019-06-21 | 苏州科达科技股份有限公司 | A kind of face identification method, device, equipment and readable storage medium storing program for executing |
CN110111158A (en) * | 2019-05-16 | 2019-08-09 | 创络(上海)数据科技有限公司 | The Marketing Design method, apparatus and storage medium of life cycle or Development phase |
CN110309379A (en) * | 2019-05-22 | 2019-10-08 | 中国平安人寿保险股份有限公司 | Products Show method, apparatus, equipment and computer readable storage medium |
CN110674391A (en) * | 2019-08-15 | 2020-01-10 | 中国平安财产保险股份有限公司 | Product data pushing method and system based on big data and computer equipment |
CN111383049A (en) * | 2020-02-21 | 2020-07-07 | 中国平安财产保险股份有限公司 | Product recommendation method, device and storage medium |
CN111401935A (en) * | 2020-02-21 | 2020-07-10 | 中国平安财产保险股份有限公司 | Resource allocation method, device and storage medium |
CN111951077A (en) * | 2020-08-13 | 2020-11-17 | 中国民航信息网络股份有限公司 | Ticket buying scheme display method and system |
CN111951044A (en) * | 2020-07-30 | 2020-11-17 | 中国工商银行股份有限公司 | Bank terminal interaction method and system |
CN112508074A (en) * | 2020-11-30 | 2021-03-16 | 深圳市飞泉云数据服务有限公司 | Visualization display method and system and readable storage medium |
CN112910953A (en) * | 2021-01-14 | 2021-06-04 | 中国工商银行股份有限公司 | Business data pushing method and device and server |
WO2022089190A1 (en) * | 2020-11-02 | 2022-05-05 | 深圳壹账通智能科技有限公司 | Product recommendation method and apparatus, and electronic device and readable storage medium |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107730389A (en) * | 2017-09-30 | 2018-02-23 | 平安科技(深圳)有限公司 | Electronic installation, insurance products recommend method and computer-readable recording medium |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100268661A1 (en) * | 2009-04-20 | 2010-10-21 | 4-Tell, Inc | Recommendation Systems |
CN107451832B (en) * | 2016-05-30 | 2023-09-05 | 北京京东尚科信息技术有限公司 | Method and device for pushing information |
CN107688995A (en) * | 2016-08-03 | 2018-02-13 | 湖南移商动力网络技术有限公司 | One kind is based on bank's big data application solution |
CN107689008A (en) * | 2017-06-09 | 2018-02-13 | 平安科技(深圳)有限公司 | A kind of user insures the method and device of behavior prediction |
CN107679946B (en) * | 2017-09-28 | 2021-09-10 | 平安科技(深圳)有限公司 | Fund product recommendation method and device, terminal equipment and storage medium |
-
2018
- 2018-03-06 CN CN201810183372.0A patent/CN108492194A/en active Pending
- 2018-05-31 WO PCT/CN2018/089127 patent/WO2019169756A1/en active Application Filing
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107730389A (en) * | 2017-09-30 | 2018-02-23 | 平安科技(深圳)有限公司 | Electronic installation, insurance products recommend method and computer-readable recording medium |
Non-Patent Citations (2)
Title |
---|
CSDN: "K-means算法详解", 《HTTPS://BLOG.CSDN.NET/ZHIHUA_OBA/ARTICLE/DETAILS/73832614》 * |
张旭辉: "基于大数据的代理保险业务分析", 《通信管理与技术》 * |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109447728A (en) * | 2018-09-07 | 2019-03-08 | 平安科技(深圳)有限公司 | Financial product recommended method, device, computer equipment and storage medium |
CN109377388A (en) * | 2018-09-13 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Medical insurance is insured method, apparatus, computer equipment and storage medium |
CN109377388B (en) * | 2018-09-13 | 2023-08-18 | 深圳平安医疗健康科技服务有限公司 | Medical insurance application method, medical insurance application device, computer equipment and storage medium |
CN109670896A (en) * | 2018-09-28 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Investment product recommended method, device, equipment and storage medium |
CN109360072A (en) * | 2018-11-13 | 2019-02-19 | 平安科技(深圳)有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
CN109360072B (en) * | 2018-11-13 | 2023-06-23 | 平安科技(深圳)有限公司 | Insurance product recommendation method and device, computer equipment and storage medium |
CN109376306A (en) * | 2018-12-04 | 2019-02-22 | 挖财网络技术有限公司 | A kind of service recommendation method and system based on label panorama sketch |
CN109376306B (en) * | 2018-12-04 | 2021-04-16 | 挖财网络技术有限公司 | Service recommendation method and system based on tag panorama |
CN109711929A (en) * | 2018-12-13 | 2019-05-03 | 中国平安财产保险股份有限公司 | Business recommended method and device based on prediction model |
CN109767345A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, equipment and storage medium based on information matches |
CN109816534A (en) * | 2018-12-17 | 2019-05-28 | 平安国际融资租赁有限公司 | Financing lease Products Show method, apparatus, computer equipment and storage medium |
CN109816127A (en) * | 2019-01-11 | 2019-05-28 | 广州市骑鹅游信息技术咨询服务有限公司 | A kind of intelligence ticketing service recommended method and system |
CN109816127B (en) * | 2019-01-11 | 2022-12-30 | 广州市骑鹅游信息技术咨询服务有限公司 | Intelligent ticket recommendation method and system |
CN109785000A (en) * | 2019-01-16 | 2019-05-21 | 深圳壹账通智能科技有限公司 | Customer resources distribution method, device, storage medium and terminal |
CN109903168A (en) * | 2019-01-18 | 2019-06-18 | 平安科技(深圳)有限公司 | The method and relevant device of recommendation insurance products based on machine learning |
CN109919093A (en) * | 2019-03-07 | 2019-06-21 | 苏州科达科技股份有限公司 | A kind of face identification method, device, equipment and readable storage medium storing program for executing |
CN110111158A (en) * | 2019-05-16 | 2019-08-09 | 创络(上海)数据科技有限公司 | The Marketing Design method, apparatus and storage medium of life cycle or Development phase |
CN110309379A (en) * | 2019-05-22 | 2019-10-08 | 中国平安人寿保险股份有限公司 | Products Show method, apparatus, equipment and computer readable storage medium |
CN110309379B (en) * | 2019-05-22 | 2023-07-25 | 中国平安人寿保险股份有限公司 | Product recommendation method, device, equipment and computer readable storage medium |
CN110674391A (en) * | 2019-08-15 | 2020-01-10 | 中国平安财产保险股份有限公司 | Product data pushing method and system based on big data and computer equipment |
CN110674391B (en) * | 2019-08-15 | 2024-05-03 | 中国平安财产保险股份有限公司 | Product data pushing method and system based on big data and computer equipment |
CN111401935B (en) * | 2020-02-21 | 2023-04-07 | 中国平安财产保险股份有限公司 | Resource allocation method, device and storage medium |
CN111401935A (en) * | 2020-02-21 | 2020-07-10 | 中国平安财产保险股份有限公司 | Resource allocation method, device and storage medium |
CN111383049A (en) * | 2020-02-21 | 2020-07-07 | 中国平安财产保险股份有限公司 | Product recommendation method, device and storage medium |
CN111951044A (en) * | 2020-07-30 | 2020-11-17 | 中国工商银行股份有限公司 | Bank terminal interaction method and system |
CN111951077A (en) * | 2020-08-13 | 2020-11-17 | 中国民航信息网络股份有限公司 | Ticket buying scheme display method and system |
WO2022089190A1 (en) * | 2020-11-02 | 2022-05-05 | 深圳壹账通智能科技有限公司 | Product recommendation method and apparatus, and electronic device and readable storage medium |
CN112508074A (en) * | 2020-11-30 | 2021-03-16 | 深圳市飞泉云数据服务有限公司 | Visualization display method and system and readable storage medium |
CN112508074B (en) * | 2020-11-30 | 2024-05-14 | 深圳市飞泉云数据服务有限公司 | Visual display method, system and readable storage medium |
CN112910953A (en) * | 2021-01-14 | 2021-06-04 | 中国工商银行股份有限公司 | Business data pushing method and device and server |
CN112910953B (en) * | 2021-01-14 | 2023-02-17 | 中国工商银行股份有限公司 | Business data pushing method and device and server |
Also Published As
Publication number | Publication date |
---|---|
WO2019169756A1 (en) | 2019-09-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108492194A (en) | Products Show method, apparatus and storage medium | |
CN110070391B (en) | Data processing method and device, computer readable medium and electronic equipment | |
US10902341B1 (en) | Machine learning based list recommendations | |
US20190102835A1 (en) | Artificial intelligence derived anonymous marketplace | |
EP2700049A2 (en) | Predictive modeling | |
KR20190021189A (en) | Model analysis method, apparatus and computer readable storage | |
CN107797989A (en) | Enterprise name recognition methods, electronic equipment and computer-readable recording medium | |
CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
CN108846687A (en) | Client segmentation method, apparatus and storage medium | |
CN113626606B (en) | Information classification method, device, electronic equipment and readable storage medium | |
US20220351004A1 (en) | Industry specific machine learning applications | |
Sun et al. | The dynamic financial distress prediction method of EBW-VSTW-SVM | |
CN110503453A (en) | Customer-action analysis method, apparatus, computer equipment and storage medium | |
CN110276382A (en) | Listener clustering method, apparatus and medium based on spectral clustering | |
CN113268665A (en) | Information recommendation method, device and equipment based on random forest and storage medium | |
CN113468338A (en) | Big data analysis method for digital cloud service and big data server | |
CN113688923A (en) | Intelligent order abnormity detection method and device, electronic equipment and storage medium | |
CN112288337A (en) | Behavior recommendation method, behavior recommendation device, behavior recommendation equipment and behavior recommendation medium | |
CN113313463A (en) | Data analysis method and data analysis server applied to big data cloud office | |
CN107679635A (en) | Client's follow-up method, system and readable storage medium storing program for executing based on priority | |
CN110874640B (en) | Distribution selection and simulation of intermittent data using machine learning (ML) | |
CN112269875A (en) | Text classification method and device, electronic equipment and storage medium | |
CN111046156A (en) | Method and device for determining reward data and server | |
US20220108246A1 (en) | Generating a forecast based on multiple time dimensions and machine learning techniques | |
CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180904 |