CN109410075A - Intelligence insurance recommended method and system based on Bayes - Google Patents
Intelligence insurance recommended method and system based on Bayes Download PDFInfo
- Publication number
- CN109410075A CN109410075A CN201811239289.7A CN201811239289A CN109410075A CN 109410075 A CN109410075 A CN 109410075A CN 201811239289 A CN201811239289 A CN 201811239289A CN 109410075 A CN109410075 A CN 109410075A
- Authority
- CN
- China
- Prior art keywords
- data
- insurance
- bayes
- probability
- recommended models
- 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
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Technology Law (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention relates to insurance information fields, are related to a kind of intelligence insurance recommended method based on Bayes, comprising: obtain initial data, carry out feature extraction processing；Using bayesian algorithm, to feature extraction, treated that data are trained, and establishes recommended models；Recommended models are imported in insurance products inline system, user characteristic data is inputted, the user for obtaining recommended models output buys the probability of insurance products as the recommendation results intelligently insured.The present invention also proposes a kind of intelligence insurance recommender system based on Bayes.The present invention passes through the analysis and processing to data, probability statistics calculating is carried out by historic sales data using Bayes' theorem, it trains corresponding insurance recommended models and applies in insurance system on line, realize the intelligent recommendation of insurance products, improve user experience.
Description
Technical field
The present invention relates to insurance information field, in particular to a kind of intelligence based on Bayes insures recommended method and is
System.
Background technique
Insurance, on law and economics meaning, is a kind of risk management mode, is mainly used for the risk of economic loss.
With the development of internet, it is sold in a manner of insurance is increasingly becoming a kind of mainstream by online mode.But on line in system, lack
The introduction and guidance to product of few business personnel is easy to appear and does not know which kind of insurance of selection, which kind of insurance and user itself feelings
Crowd's situation that condition or user prepare to insure more matches, and user is difficult to obtain preferable usage experience under such circumstances.
That is the appearance of information-based degree also fails to go to help user to obtain the preferable intelligence of experience in a manner of technological means
It can insurance recommendation.
Summary of the invention
Embodiments of the present invention aim to solve at least one of the technical problems existing in the prior art.For this purpose, of the invention
Embodiment need to provide a kind of intelligence insurance recommended method and system based on Bayes.
A kind of intelligence insurance recommended method based on Bayes of embodiment of the present invention characterized by comprising
Step 1, initial data is obtained, feature extraction processing is carried out；
Step 2, using bayesian algorithm, to feature extraction, treated that data are trained, and establishes recommended models；
Step 3, recommended models are imported in insurance products inline system, user characteristic data is inputted, obtained and recommend mould
The user of type output buys the probability of insurance products as the recommendation results intelligently insured.
In a kind of embodiment, this method further include:
Step 4, it is handled using recommendation results as training data according to the process of step 2 and step 3, completes to recommend mould
The data feedback of recommendation results in type, and then obtain new recommended models.
In a kind of embodiment, step 1 includes:
Step 11, the initial data including user characteristic data, insurance sales data, insurance products data is obtained；
Step 12, data cleansing processing is carried out to initial data；
Step 13, feature extraction processing is carried out to the cleaned data of data.
In a kind of embodiment, step 2 includes:
Step 21, feature extraction treated data are organized into respectively by preset ratio including training dataset and verifying
The data set of data set；
Step 22, it is calculated using training dataset as input according to Bayesian formula, it is general to obtain each insurance products purchase
Rate and every kind of feature correspond to the conditional probability of each product；
Step 23, it is calculated using validation data set as input according to Bayesian formula, obtains user and buy each insurance production
The Probability p of product, being considered as user if p is more than the probability threshold value of setting will buy and compare with actual conditions to verify recommendation mould
Recommended models are exported as PMML file when accuracy rate reaches preset requirement by the predictablity rate of type.
In a kind of embodiment, step 11 is specifically included: being taken out from the client management system of insurance and marketing system with ETL
The mode taken obtains the initial data including user characteristic data, insurance sales data, insurance products data.
The present invention also proposes a kind of intelligence insurance recommender system based on Bayes characterized by comprising
Data processing module carries out feature extraction processing for obtaining initial data；
Model building module, for using bayesian algorithm, to feature extraction, treated that data are trained, foundation is pushed away
Recommend model；
Insure recommending module, for importing recommended models in insurance products inline system, user characteristic data inputted,
The user for obtaining recommended models output buys the probability of insurance products as the recommendation results intelligently insured.
In a kind of embodiment, the system further include:
Data feedback module, for according to model building module and insuring recommending module for recommendation results as training data
Treatment process handled, complete the data feedback of recommendation results in recommended models, and then obtain new recommended models.
In a kind of embodiment, data processing module includes:
Data capture unit, for obtaining including user characteristic data, insurance sales data, insurance products data
Initial data；
Data cleansing unit, for carrying out data cleansing processing to initial data；
Feature extraction unit, for carrying out feature extraction processing to the cleaned data of data.
In a kind of embodiment, model building module includes:
Finishing unit, for being organized into feature extraction treated data respectively by preset ratio including training dataset
With the data set of validation data set；
Computing unit obtains each insurance products for calculating using training dataset as input according to Bayesian formula
Purchase probability and every kind of feature correspond to the conditional probability of each product；
It is each to obtain user's purchase for calculating using validation data set as input according to Bayesian formula for lead-out unit
The Probability p of insurance products, being considered as user if p is more than the probability threshold value of setting will buy and compare with actual conditions to verify
Recommended models are exported as PMML file when accuracy rate reaches preset requirement by the predictablity rate of recommended models.
In a kind of embodiment, data capture unit be specifically used for from the client management system of insurance and marketing system with
The mode that ETL is extracted obtains the initial data including user characteristic data, insurance sales data, insurance products data.
The intelligence insurance recommended method and system based on Bayes of embodiment of the present invention, by analysis to data with
Processing carries out probability statistics calculating by historic sales data using Bayes' theorem, trains corresponding insurance recommended models
And using in insurance system on line, realizes the intelligent recommendation of insurance products, improve user experience.
The advantages of additional aspect of the invention, will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
The above-mentioned and/or additional aspect and advantage of embodiments of the present invention are from combination following accompanying drawings to embodiment
It will be apparent and be readily appreciated that in description, in which:
Fig. 1 is the flow diagram of the intelligence insurance recommended method based on Bayes of embodiment of the present invention；
Fig. 2 is the composition schematic diagram of the intelligence insurance recommender system based on Bayes of embodiment of the present invention.
Specific embodiment
Embodiments of the present invention are described below in detail, the example of embodiment is shown in the accompanying drawings, wherein identical or class
As label indicate same or similar element or element with the same or similar functions from beginning to end.Below with reference to attached
The embodiment of figure description is exemplary, and can only be used to explain embodiments of the present invention, and should not be understood as to the present invention
Embodiment limitation.
Referring to Fig. 1, the intelligence insurance recommended method based on Bayes of embodiment of the present invention, comprising:
Step 1, initial data is obtained, feature extraction processing is carried out.
Step 2, using bayesian algorithm, to feature extraction, treated that data are trained, and establishes recommended models.
Step 3, recommended models are imported in insurance products inline system, user characteristic data is inputted, obtained and recommend mould
The user of type output buys the probability of insurance products as the recommendation results intelligently insured.
Referring to Fig. 2, the intelligence insurance recommender system based on Bayes of embodiment of the present invention, comprising:
Data processing module carries out feature extraction processing for obtaining initial data.
Model building module, for using bayesian algorithm, to feature extraction, treated that data are trained, foundation is pushed away
Recommend model.
Insure recommending module, for importing recommended models in insurance products inline system, user characteristic data inputted,
The user for obtaining recommended models output buys the probability of insurance products as the recommendation results intelligently insured.
In this embodiment, the intelligence insurance recommended method based on Bayes is recommended with the intelligence insurance based on Bayes
Execution object of the system as step, or the execution object using the module in system as step.Specifically, step 1 can be with
Execution object by data processing module as step, step 2 can execution object by model building module as step, step
Rapid 3 can execution object by insurance recommending module as step.
In step 1, it specifically includes:
Step 11, the initial data including user characteristic data, insurance sales data, insurance products data is obtained.
Step 12, data cleansing processing is carried out to initial data.
Step 13, feature extraction processing is carried out to the cleaned data of data.
Accordingly, data processing module includes: in the intelligence insurance recommender system based on Bayes
Data capture unit, for obtaining including user characteristic data, insurance sales data, insurance products data
Initial data.
Data cleansing unit, for carrying out data cleansing processing to initial data.
Feature extraction unit, for carrying out feature extraction processing to the cleaned data of data.
Step 11 to step 13 can execution object by data processing module as step, or with the unit in module
Execution object as step.Specifically, execution object of the step 11 by data capture unit as step, step 12 is by data
Execution object of the cleaning unit as step, execution object of the step 13 by feature extraction unit as step.
In step 11, data capture unit obtains the mode that can be manually entered of mode of initial data for user characteristics
Data, insurance sales data, the input of insurance products data carry out subsequent processing.Further, in order to improve the effect of input
Rate, data capture unit can obtain in such a way that ETL is extracted including use from the client management system of insurance and marketing system
Initial data including family characteristic, insurance sales data, insurance products data.
The abbreviation of ETL, Extraction-Transformation-Loading, i.e. data pick-up (Extract), conversion
(Transform), the process of (Load) is loaded, it is the important link for constructing data warehouse.Key link during ETL is just
It is data pick-up, data conversion and processing, data loading.Wherein, data pick-up is the process that data are extracted from data source.It is real
In the application of border, data source is more using relational database.Data are extracted from database generally following methods:
(1) full dose extracts
Full dose, which extracts, is similar to Data Migration or data duplication, it remains untouched the data of table or view in data source
Slave database in the format that can identify of the ETL tool that extracts, and be converted into oneself.Full dose extracts fairly simple.
(2) increment extraction
The data for having increased newly or having modified in the table to be extracted in database since increment extraction is only drawn from last time extraction.?
In ETL use process, increment extraction is wider compared with full dose extraction application.
It in step 12, after data pick-up comes, needs to be cleaned by data cleansing unit, such as to give up null value excessive
Data, discrete data carries out numeralization processing, such as insurance type includes travel accident insurance, and accident insurance etc., we can be processed into 0,1
Etc..
In step 13, data analysis is carried out according to business actual conditions, feature extraction unit extracts the feature of needs, than
It include gender, age, occupation etc. such as user's natural quality；Kinsfolk's situation, income level, history purchaser record etc..Then
The characteristic of extraction is organized into wide table, i.e., is arranged characteristic for following format: User ID, feature 1, feature 2 ...
Bayes decision theory is the basic skills of implementation decision under probabilistic framework.In all known situation of all dependent probabilities
Under, Bayes decision theory considers how to select optimal category label based on these probability and misclassification loss.
Bayes' theorem are as follows:
Wherein, P (A | B) refers to the probability that A occurs in the case where B occurs.
P (B | A) refer to the probability that B occurs in the case where A occurs.
P (A) is the probability that A occurs.
P (B) is the probability that B occurs.
Bayesian meaning is to derive the probability of unknown event by the probability of known event, to reach
To prediction, the purpose recommended.
Assuming that insurance products integrate as C, analyze and obtain from historic sales data, the user characteristics vector for buying insurance is X
(mutually indepedent between each feature, to be independent of each other), then being then equivalent to the problem of proposed algorithm: when the feature of our known users
Max { P (C=c is sought then which product is user's maximum possible can buy for xi| X=x) }.It, can according to Bayes' theorem
To obtain:
Due to mutually indepedent between each feature, then:
User is calculated for the purchase probability of each product according to above-mentioned formula, can be carried out by historic sales data general
Rate statistics calculates, and trains corresponding recommended models.
Specifically, step 2 includes:
Step 21, feature extraction treated data are organized into respectively by preset ratio including training dataset and verifying
The data set of data set.
Step 22, it is calculated using training dataset as input according to Bayesian formula, it is general to obtain each insurance products purchase
Rate and every kind of feature correspond to the conditional probability of each product.
Step 23, it is calculated using validation data set as input according to Bayesian formula, obtains user and buy each insurance production
The Probability p of product, being considered as user if p is more than the probability threshold value of setting will buy and compare with actual conditions to verify recommendation mould
Recommended models are exported as PMML file when accuracy rate reaches preset requirement by the predictablity rate of type.
Accordingly, model building module includes: in the intelligence insurance recommender system based on Bayes
Finishing unit, for being organized into feature extraction treated data respectively by preset ratio including training dataset
With the data set of validation data set.
Computing unit obtains each insurance products for calculating using training dataset as input according to Bayesian formula
Purchase probability and every kind of feature correspond to the conditional probability of each product.
It is each to obtain user's purchase for calculating using validation data set as input according to Bayesian formula for lead-out unit
The Probability p of insurance products, being considered as user if p is more than the probability threshold value of setting will buy and compare with actual conditions to verify
Recommended models are exported as PMML file when accuracy rate reaches preset requirement by the predictablity rate of recommended models.
Step 21 to step 23 can execution object by model building module as step, can also be by the module
Execution object of each unit as step.Specifically, step 21 can execution object by finishing unit as step, step
22 can execution object by computing unit as step, step 23 can execution object by lead-out unit as step.
In step 21, finishing unit is by the data after feature extraction: User ID, feature 1, feature 2 ..., the product bought
ID is divided into two parts according to the ratio of 3:7, and 70% data is used to use 30% data as verify data as training dataset
Collection, certainly, this programme can also use other preset ratios according to actual needs, such as 4:6 etc., it is not limited here.
Step 22, computing unit, according to the Bayesian formula introduced above, obtains each using training dataset as input
Insurance products purchase probability and every kind of feature correspond to the conditional probability of each product.
In step 23, lead-out unit first will verifying collection data preparation are as follows: feature 1, feature 2 ..., and according to Bayesian formula,
The Probability p that the user buys each product is calculated, if Probability p is more than the threshold value of setting, then it is assumed that can buy, by the result
It is compared with actual conditions, PMML can be exported as recommended models by verifying model prediction accuracy rate if accuracy rate reaches requirement
File.The requirement of accuracy rate can be set according to the actual demand of recommended models, such as reached 90% and be can be used as judgement
Threshold value, when accuracy rate is more than 90% to be considered as and reach requirement.PMML full name oracle model markup language (Predictive Model
Markup Language), it is the standard received by W3C using XML description and storing data mining model.
After the above process is set up recommended models and exported, which is imported into the guarantor on line by insurance recommending module
In dangerous operation system, user characteristic data is inputted, can be obtained the probability that user buys product.
Further, in actual insurance business system in use, the accuracy rate that recommended models are recommended may be with training
Result when verifying is deviated, so, the intelligence insurance recommended method based on Bayes further include:
Step 4, it is handled using recommendation results as training data according to the process of step 2 and step 3, completes to recommend mould
The data feedback of recommendation results in type, and then obtain new recommended models.
Accordingly, the intelligence insurance recommender system based on Bayes further include:
Data feedback module, for according to model building module and insuring recommending module for recommendation results as training data
Treatment process handled, complete the data feedback of recommendation results in recommended models, and then obtain new recommended models.
Wherein, step 4 can be by execution object of the intelligence insurance recommender system as step based on Bayes, can also be with
Execution object by data feedback module as step.
I.e. by the data feedback of recommendation results, model training is repeated, newly generated data are obtained as instruction using this
Practice data, and then obtains more structurally sound new recommended models.
From Bayesian formula as can be seen that the calculating of bayesian algorithm is all some simple probability statistics, calculate complicated
It spends lower, model training can be rapidly completed, and then be applied in real-time recommendation system.Embodiment of the present invention based on pattra leaves
This intelligence insurance recommended method and system passes through historical sales using Bayes' theorem by the analysis and processing to data
Data carry out probability statistics calculating, train corresponding insurance recommended models and application is on line in insurance system, realize insurance
The intelligent recommendation of product, improves user experience.
In the description of this specification, reference term " embodiment ", " some embodiments ", " schematically implementation
The description of mode ", " example ", specific examples or " some examples " etc. means the tool described in conjunction with the embodiment or example
Body characteristics, structure, material or feature are contained at least one embodiment or example of the invention.In the present specification,
Schematic expression of the above terms are not necessarily referring to identical embodiment or example.Moreover, the specific features of description, knot
Structure, material or feature can be combined in any suitable manner in any one or more embodiments or example.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processing module or other can be from instruction
Execute system, device or equipment instruction fetch and the system that executes instruction) use, or combine these instruction execution systems, device or
Equipment and use.For the purpose of this specification, " computer-readable medium " can be it is any may include, store, communicating, propagating or
Transfer program uses for instruction execution system, device or equipment or in conjunction with these instruction execution systems, device or equipment
Device.The more specific example (non-exhaustive list) of computer-readable medium include the following: there are one or more wirings
Electrical connection section (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can then be edited, be interpreted or when necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of embodiments of the present invention can be with hardware, software, firmware or their combination come real
It is existing.In the above-described embodiment, multiple steps or method can be with storages in memory and by suitable instruction execution system
The software or firmware of execution is realized.For example, if realized with hardware, in another embodiment, ability can be used
Any one of following technology or their combination well known to domain is realized: being had for realizing logic function to data-signal
The discrete logic of logic gates, the specific integrated circuit with suitable combinational logic gate circuit, programmable gate array
(PGA), field programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.In addition, in each implementation of the invention
Each functional unit in example can integrate in a processing module, is also possible to each unit and physically exists alone, can also be with
Two or more units are integrated in a module.Above-mentioned integrated module both can take the form of hardware realization,
It can be realized in the form of software function module.If the integrated module is realized and is made in the form of software function module
It is independent product when selling or using, also can store in a computer readable storage medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of intelligence insurance recommended method based on Bayes characterized by comprising
Step 1, initial data is obtained, feature extraction processing is carried out；
Step 2, using bayesian algorithm, to feature extraction, treated that data are trained, and establishes recommended models；
Step 3, recommended models are imported in insurance products inline system, user characteristic data is inputted, it is defeated to obtain recommended models
User out buys the probability of insurance products as the recommendation results intelligently insured.
2. the intelligence insurance recommended method based on Bayes as described in claim 1, which is characterized in that this method further include:
Step 4, it handles, completes in recommended models according to the process of step 2 and step 3 using recommendation results as training data
The data feedback of recommendation results, and then obtain new recommended models.
3. the intelligence insurance recommended method based on Bayes as claimed in claim 2, which is characterized in that step 1 includes:
Step 11, the initial data including user characteristic data, insurance sales data, insurance products data is obtained；
Step 12, data cleansing processing is carried out to initial data；
Step 13, feature extraction processing is carried out to the cleaned data of data.
4. the intelligence insurance recommended method based on Bayes as claimed in claim 3, which is characterized in that step 2 includes:
Step 21, feature extraction treated data are organized into respectively by preset ratio including training dataset and verify data
The data set of collection；
Step 22, calculate using training dataset as input according to Bayesian formula, obtain each insurance products purchase probability and
Every kind of feature corresponds to the conditional probability of each product；
Step 23, it is calculated using validation data set as input according to Bayesian formula, obtains user and buy each insurance products
Probability p, being considered as user if p is more than the probability threshold value of setting will buy and compare with actual conditions to verify recommended models
Recommended models are exported as PMML file when accuracy rate reaches preset requirement by predictablity rate.
5. the intelligence insurance recommended method based on Bayes as claimed in claim 3, which is characterized in that step 11 specifically includes:
It is obtained in such a way that ETL is extracted including user characteristic data, insurance sales from the client management system of insurance and marketing system
Initial data including data, insurance products data.
6. a kind of intelligence insurance recommender system based on Bayes characterized by comprising
Data processing module carries out feature extraction processing for obtaining initial data；
Model building module is established and recommends mould for treated that data are trained to feature extraction using bayesian algorithm
Type；
Insure recommending module, for importing recommended models in insurance products inline system, user characteristic data is inputted, is obtained
The user of recommended models output buys the probability of insurance products as the recommendation results intelligently insured.
7. the intelligence insurance recommender system based on Bayes as claimed in claim 6, which is characterized in that the system further include:
Data feedback module, for using recommendation results as training data according to model building module and insurance recommending module place
Reason process is handled, and completes the data feedback of recommendation results in recommended models, and then obtain new recommended models.
8. the intelligence insurance recommender system based on Bayes as claimed in claim 7, which is characterized in that data processing module packet
It includes:
Data capture unit, it is original including user characteristic data, insurance sales data, insurance products data for obtaining
Data；
Data cleansing unit, for carrying out data cleansing processing to initial data；
Feature extraction unit, for carrying out feature extraction processing to the cleaned data of data.
9. the intelligence insurance recommender system based on Bayes as claimed in claim 8, which is characterized in that model building module packet
It includes:
Finishing unit, for feature extraction treated data to be organized into respectively including training dataset and tested by preset ratio
Demonstrate,prove the data set of data set；
Computing unit obtains each insurance products purchase for calculating using training dataset as input according to Bayesian formula
Probability and every kind of feature correspond to the conditional probability of each product；
Lead-out unit is obtained user and buys each insurance for being calculated using validation data set as input according to Bayesian formula
The Probability p of product, being considered as user if p is more than the probability threshold value of setting will buy and compare with actual conditions to verify and recommend
Recommended models are exported as PMML file when accuracy rate reaches preset requirement by the predictablity rate of model.
10. the intelligence insurance recommender system based on Bayes as claimed in claim 8, which is characterized in that data capture unit tool
Body is used to from the client management system of insurance and marketing system obtained in such a way that ETL is extracted including user characteristic data, protect
Initial data including dangerous sales data, insurance products data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811239289.7A CN109410075A (en) | 2018-10-23 | 2018-10-23 | Intelligence insurance recommended method and system based on Bayes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811239289.7A CN109410075A (en) | 2018-10-23 | 2018-10-23 | Intelligence insurance recommended method and system based on Bayes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109410075A true CN109410075A (en) | 2019-03-01 |
Family
ID=65469414
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811239289.7A Pending CN109410075A (en) | 2018-10-23 | 2018-10-23 | Intelligence insurance recommended method and system based on Bayes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109410075A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363582A (en) * | 2019-06-29 | 2019-10-22 | 上海淇馥信息技术有限公司 | Financial service favor information promotion method, device and electronic equipment based on user intention |
| CN111179041A (en) * | 2020-01-22 | 2020-05-19 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Riding insurance product recommendation method and device |
| CN111833078A (en) * | 2019-04-15 | 2020-10-27 | 泰康保险集团股份有限公司 | Block chain based recommendation method, device, medium and electronic equipment |
| CN113139079A (en) * | 2021-04-15 | 2021-07-20 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Music recommendation method and system |
| CN113158039A (en) * | 2021-04-06 | 2021-07-23 | 深圳先进技术研究院 | Application recommendation method, system, terminal and storage medium |
| CN113822743A (en) * | 2021-09-23 | 2021-12-21 | 秦桂珍 | Big data insurance recommendation method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110082712A1 (en) * | 2009-10-01 | 2011-04-07 | DecisionQ Corporation | Application of bayesian networks to patient screening and treatment |
| CN106600369A (en) * | 2016-12-09 | 2017-04-26 | 广东奡风科技股份有限公司 | Real-time recommendation system and method of financial products of banks based on Naive Bayesian classification |
| CN107240005A (en) * | 2017-06-13 | 2017-10-10 | 携程旅游网络技术（上海）有限公司 | The commending system and method for air ticket addition product |
| CN107507068A (en) * | 2017-09-02 | 2017-12-22 | 广东奡风科技股份有限公司 | A kind of financial product real-time recommendation method based on random forests algorithm |
-
2018
- 2018-10-23 CN CN201811239289.7A patent/CN109410075A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110082712A1 (en) * | 2009-10-01 | 2011-04-07 | DecisionQ Corporation | Application of bayesian networks to patient screening and treatment |
| CN106600369A (en) * | 2016-12-09 | 2017-04-26 | 广东奡风科技股份有限公司 | Real-time recommendation system and method of financial products of banks based on Naive Bayesian classification |
| CN107240005A (en) * | 2017-06-13 | 2017-10-10 | 携程旅游网络技术（上海）有限公司 | The commending system and method for air ticket addition product |
| CN107507068A (en) * | 2017-09-02 | 2017-12-22 | 广东奡风科技股份有限公司 | A kind of financial product real-time recommendation method based on random forests algorithm |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111833078A (en) * | 2019-04-15 | 2020-10-27 | 泰康保险集团股份有限公司 | Block chain based recommendation method, device, medium and electronic equipment |
| CN110363582A (en) * | 2019-06-29 | 2019-10-22 | 上海淇馥信息技术有限公司 | Financial service favor information promotion method, device and electronic equipment based on user intention |
| CN111179041A (en) * | 2020-01-22 | 2020-05-19 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Riding insurance product recommendation method and device |
| CN113158039A (en) * | 2021-04-06 | 2021-07-23 | 深圳先进技术研究院 | Application recommendation method, system, terminal and storage medium |
| CN113139079A (en) * | 2021-04-15 | 2021-07-20 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Music recommendation method and system |
| CN113822743A (en) * | 2021-09-23 | 2021-12-21 | 秦桂珍 | Big data insurance recommendation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109410075A (en) | Intelligence insurance recommended method and system based on Bayes | |
| Ahani et al. | Market segmentation and travel choice prediction in Spa hotels through TripAdvisor’s online reviews | |
| CN111553759A (en) | Product information pushing method, device, equipment and storage medium | |
| CN108491377A (en) | A kind of electric business product comprehensive score method based on multi-dimension information fusion | |
| Clemens et al. | Earmarks and subcommittee government in the US Congress | |
| US20180218427A1 (en) | Recommendation integrated online digital sales service chat system | |
| CN111275524A (en) | Insurance product recommendation method and system | |
| WO2018165580A1 (en) | Analytic and learning framework for quantifying value in value based care | |
| Wu et al. | Nonadditive robust ordinal regression with nonadditivity index and multiple goal linear programming | |
| CN110348919A (en) | Item recommendation method, device and computer readable storage medium | |
| Akgül et al. | An application of fuzzy linguistic summarization and fuzzy association rule mining to Kansei Engineering: a case study on cradle design | |
| Li et al. | Evolutive preference analysis with online consumer ratings | |
| Wang et al. | Toward dual roles of users in recommender systems | |
| Bali et al. | R machine learning by example | |
| Ahamed et al. | A recommender system based on deep neural network and matrix factorization for collaborative filtering | |
| US20210374545A1 (en) | Method and apparatus of increasing knowledge based on uncertainty in neural networks | |
| Cao et al. | Personalized next-best action recommendation with multi-party interaction learning for automated decision-making | |
| Lefort et al. | Interpretation of approximate numerical expressions: Computational model and empirical study | |
| CN117235264A (en) | Text processing method, apparatus, device and computer readable storage medium | |
| Shanti et al. | Machine Learning-Powered Mobile App for Predicting Used Car Prices | |
| Knoll et al. | Applying recommender approaches to the real estate e-commerce market | |
| US20230244990A1 (en) | Semantic graphing of heterogeneous documents for automated decision making and resource allocation using reinforcement learning | |
| CN115511582A (en) | Artificial intelligence based Commodity recommendation system and method | |
| Mahmood et al. | An Intelligent Multi-agent Recommender System | |
| KR102161828B1 (en) | Method and apparatus for controlling merchant management |
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: 20190301 |
|
| RJ01 | Rejection of invention patent application after publication |