CN109447689A - Consumer's risk portrait generation method, device, equipment and readable storage medium storing program for executing - Google Patents
Consumer's risk portrait generation method, device, equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109447689A CN109447689A CN201811135650.1A CN201811135650A CN109447689A CN 109447689 A CN109447689 A CN 109447689A CN 201811135650 A CN201811135650 A CN 201811135650A CN 109447689 A CN109447689 A CN 109447689A
- Authority
- CN
- China
- Prior art keywords
- poi
- risk
- probability
- user
- portrait
- 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 44
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 10
- 238000004891 communication Methods 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 abstract 1
- 230000036541 health Effects 0.000 description 20
- 238000012512 characterization method Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 230000008439 repair process Effects 0.000 description 4
- 230000001186 cumulative effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000001737 promoting effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000032696 parturition Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000009466 transformation Effects 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Abstract
The present invention discloses a kind of consumer's risk portrait generation method, device, equipment and readable storage medium storing program for executing, the described method includes: reading the POI probability that user removes each POI in predetermined period, and each POI probability is counted according to the POI type belonged to, determine that user removes the overall risk POI probability of all risk classifications POI;Judge whether overall risk POI probability is greater than preset value, if more than preset value, then each risk classifications POI attribute for carrying out insurance products is sorted out, and determine sub- risk POI probability of the user relative to all kinds of insurance products;It is added in default portrait template by each sub- risk POI probability and corresponding insurance products formation probability product pair, and by each probability product to user characteristics label is set as, the risk for generating user in predetermined period is drawn a portrait.Big data analysis of this programme based on user behavior generates consumer's risk portrait, to realize the accurate reflection to risk situation involved in the daily generation of user.
Description
Technical field
The invention mainly relates to information technology fields, specifically, being related to a kind of consumer's risk portrait generation method, dress
It sets, equipment and readable storage medium storing program for executing.
Background technique
Current each financial institution is when carrying out insurance products marketing, in order to realize precision marketing, usually combines the wind of user
Dangerous data carry out, and reflect user's risk that may be present by risk data, and recommend insurance products corresponding with risk to user
Information, to meet the needs of users.This meets the recommendation of the insurance product information of user demand, accurate with consumer's risk data
Property have very big correlation so that the accuracy of identified consumer's risk data accounts in insurance product information recommendation process
There is very important status.Identified consumer's risk data in the prior art, can not accurately embody in use
Risk possessed by user, and the insurance product information recommended according to risk is caused on the one hand not to be able to satisfy user demand, separately
The success rate for promoting financial institution's insurance products is low, and it is existing for how accurately embodying the specific risk of user institute
Technical problem urgently to be resolved in technology.
Summary of the invention
The main object of the present invention is to provide a kind of consumer's risk portrait generation method, device, equipment and readable storage medium
Matter, it is intended to solve the problems, such as accurately reflect the had risk of user in the prior art.
To achieve the above object, the present invention provides a kind of consumer's risk portrait generation method, and point of interest POI type includes wind
Dangerous type POI, consumer's risk portrait generation method the following steps are included:
The POI probability that user removes each POI in predetermined period is read, and to each POI probability according to the POI belonged to
Type is counted, and determines that user removes the overall risk POI probability of all risk classifications POI;
Judge whether the overall risk POI probability is greater than preset value, if more than the preset value, then to each risk class
The attribute that type POI carries out insurance products is sorted out, and determines sub- risk POI probability of the user relative to all kinds of insurance products;
It is produced by each sub- risk POI probability and corresponding insurance products formation probability product pair, and by each probability
Product are added in default portrait template to user characteristics label is set as, and the risk for generating user in the predetermined period is drawn a portrait.
Preferably, described that each POI probability is counted according to the POI type belonged to, determine that user goes to own
The step of overall risk POI probability of risk classifications POI includes:
Identifier entrained in each POI probability is read, and is filtered out from each identifier and is attributed to risk
The risk identification of type accords with;
It will add up with the POI probability that the risk identification accords with, obtain user and go all risk classifications POI's
Overall risk POI probability.
Preferably, the attribute for carrying out insurance products to each risk classifications POI is sorted out, and determine user relative to
The step of sub- risk POI probability of all kinds of insurance products includes:
Call the type attribute label of all kinds of insurance products, and by each risk identification symbol one by one with each class
The comparison of type attribute tags determines that each risk identification accords with corresponding target type attribute label;
Each risk classifications POI with the identical target type attribute label is sorted out, formed with it is all kinds of
The corresponding risk classifications POI set of the insurance products;
It adds up to the POI probability of each risk classifications POI in each risk classifications POI set, it is raw
Sub- risk POI probability at user relative to all kinds of insurance products.
Preferably, the generation user includes: after the step of risk of the predetermined period is drawn a portrait
Each sub- risk POI probability and the overall risk POI probability are done into ratio, generate user relative to all kinds of described
The risk accounting of insurance products;
Each risk accounting is compared, determines the maximum target risk accounting of numerical value, and the determining and target risk
The corresponding insurance product type of accounting;
Product information corresponding with the insurance product type is obtained, and the product information is transferred to user and is held
Terminal.
Preferably, the step of acquisition product information corresponding with the insurance product type includes:
User basic information is read, and reads the product attribute of each insurance products corresponding with the insurance product type;
According to the matching degree of the user basic information and each product attribute, target insurance products are determined, and will
The product information of the target insurance products is determined as product information corresponding with the insurance product type.
Preferably, include: before the step of reading user removes the POI probability of each POI in predetermined period
Each location information of the user in predetermined period is read, and is determined default centered on each location information
POI in range;
The POI quantity of the POI is counted, and according to the POI quantity, determines that user goes to each institute from each location information
The POI probability of POI is stated, the POI probability that user removes each POI in predetermined period is generated.
Preferably, described according to the POI quantity, determine that user goes the POI of each POI general from each location information
Rate, generating the step of user removes the POI probability of each POI in predetermined period includes:
According to the distance relation of each location information and the preset range, the preset range is divided into multiple remote
Near field;
It is general for each far and near region distribution region according to the distance relation in each far and near region and the location information
Rate;
Product is done with the reciprocal value of the POI quantity and the area probability, determines that user goes from each location information
The POI probability of POI described in each far and near region, generates the POI probability that user removes each POI in predetermined period.
In addition, to achieve the above object, the present invention also proposes a kind of consumer's risk portrait generating means, point of interest POI class
Type includes risk classifications POI, and the consumer's risk portrait generating means include:
Read module removes the POI probability of each POI for reading user in predetermined period, and presses to each POI probability
It is counted according to the POI type belonged to, determines that user removes the overall risk POI probability of all risk classifications POI;
Determining module, for judging whether the overall risk POI probability is greater than preset value, if more than the preset value, then
Each risk classifications POI attribute for carrying out insurance products is sorted out, and determines user relative to all kinds of insurance products
Sub- risk POI probability;
Generation module is used for each sub- risk POI probability and corresponding insurance products formation probability product pair, and will
Each probability product is added in default portrait template to user characteristics label is set as, and generates user in the predetermined period
Risk portrait.
In addition, to achieve the above object, the present invention also proposes a kind of consumer's risk portrait generating device, the consumer's risk
Portrait generating device includes: memory, processor, communication bus and the consumer's risk portrait life being stored on the memory
At program;
The communication bus is for realizing the connection communication between processor and memory;
The processor generates program for executing the consumer's risk portrait, to perform the steps of
The POI probability that user removes each POI in predetermined period is read, and to each POI probability according to the POI belonged to
Type is counted, and determines that user removes the overall risk POI probability of all risk classifications POI;
Judge whether the overall risk POI probability is greater than preset value, if more than the preset value, then to each risk class
The attribute that type POI carries out insurance products is sorted out, and determines sub- risk POI probability of the user relative to all kinds of insurance products;
It is produced by each sub- risk POI probability and corresponding insurance products formation probability product pair, and by each probability
Product are added in default portrait template to user characteristics label is set as, and the risk for generating user in the predetermined period is drawn a portrait.
In addition, to achieve the above object, the present invention also provides a kind of readable storage medium storing program for executing, the readable storage medium storing program for executing storage
Have one perhaps more than one program the one or more programs can be held by one or more than one processor
Row is to be used for:
The POI probability that user removes each POI in predetermined period is read, and to each POI probability according to the POI belonged to
Type is counted, and determines that user removes the overall risk POI probability of all risk classifications POI;
Judge whether the overall risk POI probability is greater than preset value, if more than the preset value, then to each risk class
The attribute that type POI carries out insurance products is sorted out, and determines sub- risk POI probability of the user relative to all kinds of insurance products;
It is produced by each sub- risk POI probability and corresponding insurance products formation probability product pair, and by each probability
Product are added in default portrait template to user characteristics label is set as, and the risk for generating user in the predetermined period is drawn a portrait.
The consumer's risk portrait generation method of the present embodiment, first goes the POI of each POI general according to user in predetermined period
Rate determines that user removes the overall risk POI probability of all risk classifications POI;This overall risk POI probability reflects user's daily life
In involved risk situation, wherein overall risk POI probability is bigger, illustrates that risk involved in user's daily life is got over
It is high;When judging that this overall risk POI probability is greater than preset value, illustrate that risk involved in user's daily life is higher,
The success rate for promoting insurance products to this user according to involved risk classifications is higher;To further to each risk classifications
The attribute that POI carries out insurance products is sorted out, and determines sub- risk POI probability of the user relative to all kinds of insurance products, this sub- risk
POI probability shows user to the conditions of demand of all kinds of insurance products;And then the corresponding insurance of each sub- risk POI probability is produced
Product form multiple probability products pair, which is added in default portrait template to user characteristics label is set as, raw
It draws a portrait at user in the risk of predetermined period.Because each sub- risk POI probability is by the risk classifications with identical insurance products attribute
The POI determine the probability of POI, and each risk classifications POI embodies various risks involved in user's daily life, so that sub
Risk POI probability is related to the various risks of user;So that consumer's risk portrait generated, can accurately reflect user daily
Involved risk situation in life;It avoids reflecting risk possessed by user using simple consumer's risk data, it is real
Show and has had risky accurate reflection to user.
Detailed description of the invention
Fig. 1 is the flow diagram of consumer's risk portrait generation method first embodiment of the invention;
Fig. 2 is the flow diagram of consumer's risk portrait generation method second embodiment of the invention;
Fig. 3 is the functional block diagram of consumer's risk portrait generating means first embodiment of the invention;
Fig. 4 is the device structure schematic diagram for the hardware running environment that present invention method is related to.
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 embodiment
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 consumer's risk portrait generation method.
Fig. 1 is please referred to, Fig. 1 is the flow diagram of consumer's risk of the present invention portrait generation method first embodiment.At this
In embodiment, point of interest POI type includes risk classifications POI, and the consumer's risk portrait generation method includes:
Step S10 reads the POI probability that user removes each POI in predetermined period, and to each POI probability according to institute
The POI type of ownership is counted, and determines that user removes the overall risk POI probability of all risk classifications POI;
Consumer's risk portrait generation method of the invention is applied to server, is suitable for generating characterization user by server
May have risky risk portrait in daily life.Specifically, pre-generating in server has user in predetermined period
The POI probability of each POI (Point of Interest, point of interest) is removed, POI is the geographic object that can be abstracted as a little, especially
It is some closely related geographical entity, such as school, bank, restaurant, gas station, hospital and supermarkets of living with people.User
It goes different POI to reflect the different demands of user, wherein going certain POI that can reflect risk possessed by user, such as goes horsemanship
The more users of POI number such as field, rock-climbing field, airport, may emergency risk with higher;And hospital, clinic, medical treatment is gone to protect
The more users of POI number such as strong shop, may health risk with higher;And the POI number such as go to car repair shop, gas station
More user, may vehicle danger with higher;And demand size and possessed risk size of the user to each POI
The POI probability of each POI can be removed by user, and the POI probability of POI related to risk is gone to determine.Server is to user default
Location information detection in period, determines possessed POI around location information, and then generates user and go in predetermined period respectively
The POI probability of a POI;Wherein go the POI probability of certain POIs related to risk bigger, risk possessed by user is bigger.
It should be noted that, because the time that user is gone in predetermined period is different, corresponding to this for the same POI
The different time needs to generate different POI probability;Such as a certain POI, user's certain day morning in predetermined period respectively
This POI is gone to afternoon, then the time point for the morning and afternoon is needed to generate two POI probability respectively;I.e. each POI's
POI probability does not have additivity, and related to the different time gone in predetermined period.Wherein predetermined period is according to demand institute
Pre-set a period of time range, such as day, week, the moon, year, the time of predetermined period is longer, and the POI probability of generation is got over can be quasi-
True reflection user demand, this implementation preferably " year " are used as predetermined period, are illustrated by taking " year " as an example;I.e. herein using year as
The location information of real-time detection user in the time range of predetermined period is generated by each location information of user in 1 year
Reflect each POI probability of user demand, and reflects the risk size of user by the POI probability of POI related to risk.
Generate reflection the user preset period in the POI probability of each POI demand after, because each POI may belong to together
The POI of one type, it is also possible to belong to different types of POI;It is as same type of in belonged to if being located at the Liang Ge bank of different location
POI, and be located at the gymnasium of different location and fight with club and then belong to different types of POI;User to each POI demand not
While the same, the demand to different type POI is also different, and the POI probability for making user remove all kinds of POI is not of uniform size
Sample;The POI type high for user demand, possible user goes have the number of the position of such POI more, generated such
POI probability is larger.Will POI related to risk as risk classifications POI, POI probability is related to user demand accordingly, wherein
Risk classifications POI is the characterizations such as horsemanship field, rock-climbing field, airport, hospital, clinic, health care shop, car repair shop, gas station
The POI of risk present in user is possible.In order to characterize consumer's risk size, gone in predetermined period respectively generating user
It after the POI probability of a POI, needs from the POI probability of this each POI, determines all POI probability for belonging to risk classifications POI,
And then risk size of the user in risk classifications POI is determined according to this all POI probability.Specifically, user preset is first read
The POI probability of each POI is removed in period, then this each POI probability is counted according to the POI type belonged to, that is, is counted
It is attributed to the POI probability of risk classifications POI, the overall risk POI of all risk classifications POI is removed to determine user in predetermined period
Probability characterizes user's possessed risk size in predetermined period.Specifically, to each POI probability according to the POI class belonged to
Type is counted, and determines that the step of user removes the overall risk POI probability of all risk classifications POI includes:
Step S11 reads identifier entrained in each POI probability, and filters out and return from each identifier
Belong to and being accorded with for the risk identification of risk classifications;
It is preparatory to different type POI in order to be distinguished to different type POI in view of POI numerous types on the market
Different identifiers is set, such as identifier f1 is arranged to library, park common type POI, to the landscape class such as mountains and rivers, river
Identifier f2 is arranged in type POI, and identifier f3 is arranged to the risk classifications such as hospital, airport, car repair shop POI.Generating user
When removing the POI probability of each POI, according to the type of each POI, identifier corresponding with type is added for its POI probability, is such as worked as
POI probability of the user in the library predetermined period Nei Qu is a, then adds identifier f1 to this POI probability a.Reading user
After removing the POI probability of each POI in predetermined period, entrained identifier is further read in each probability, then from each mark
Know and filters out the risk identification symbol for being attributed to risk classifications in symbol.Because the risk identification symbol of characterization risk classifications is to preset
, by the identifier of reading and this preset risk identification symbol comparison, judge whether the two is consistent;If the two is consistent,
Illustrate that the identifier read accords with for risk identification, and it is screened from each identifier;If the two is inconsistent, illustrate to read
The identifier taken is not risk identification symbol, and is filtered this out.Sentenced with risk identification symbol in the identifier of all readings
It has no progeny, the identifier screened is the risk identification symbol that risk classifications are belonged in identifier.
Step S12 will add up with the POI probability that the risk identification accords with, and obtains user and goes to institute risky
The overall risk POI probability of type POI.
Understandably, the POI probability of the risk classifications identifier screened is carried, as user is in predetermined period
Inside remove the probability of risk classifications POI;To carry out accumulation operations to the POI probability with this risk classifications identifier, add up institute
Obtained result is the overall risk POI probability that user removes all risk classifications POI in predetermined period.
Step S20, judges whether the overall risk POI probability is greater than preset value, if more than the preset value, then to each institute
It states risk classifications POI and carries out the attribute classification of insurance products, and determine sub- risk of the user relative to all kinds of insurance products
POI probability;
Further, the big of the overall risk POI probability of all risk classifications POI is gone in order to characterize user in predetermined period
It is small, it is previously provided with preset value, this preset value is to be set according to historical data, as total as multiple users in historical data
When risk POI probability is greater than a certain value, specific gravity risk classifications POI shared in this multiple user's life is larger, this multiple use
Risk possessed by family is larger;And it regard this certain value as preset value, in order to determine other users subsequently through preset value
Risk size.Passing through Accumulating generation user after the overall risk POI probability of predetermined period, by this overall risk POI probability and in advance
If value comparison, judges whether overall risk POI probability is greater than this preset value;If judging, overall risk POI probability is default no more than this
Value, then illustrate that risk possessed by user is little;If generating the risk situation for characterizing consumer's risk for this user, and
It is drawn a portrait for each financial institution according to risk and carries out insurance product information popularization;Because of risk possessed by user itself, so that risk
The reference significance of portrait is little, will lead to the invalid popularization of financial institution;To not be less than or equal to for overall risk POI probability
The user of preset value generates risk portrait.And compared when by overall risk POI probability and preset value, judge that overall risk POI probability is big
When preset value, then illustrate that user has biggish risk, and generates risk portrait for it.
Understandably, risk classifications corresponding to different risk classifications POI are different, such as horsemanship field, rock-climbing field, airport
Equal POI are corresponding with emergency risk;And the POI such as hospital, clinic, health care shop are corresponding with health risk;And car repair shop, plus
The POI such as petrol station are corresponding with vehicle danger.And different types of risk corresponds to different types of insurance products, as emergency risk is corresponding
Insurance product type be accident insurance, the corresponding insurance product type of health risk is health insurance and vehicle nearly corresponding insurance
Product type is vehicle insurance.This different types of insurance products has different type attributes, to characterize the risk class that it is applicable in
Type characterizes it and is suitable for the risk in terms of health if the type attribute of health insurance is health.In order to determine user each
Risk size in type risk carries out the category of insurance products to user in each risk classifications POI that predetermined period is gone to
Property sort out, each risk classifications POI is belonged in the insurance products with each type attribute.Because having different type attribute
Insurance products and different risk classifications it is corresponding, so that user is gone risk class corresponding with same type attribute insurance products
Type POI is classified as one kind;Clinic and medical institutions are such as gone to, because clinic is corresponding with the insurance products that type attribute is health, and it is medical
Mechanism is also corresponding with the insurance products that type attribute is health;The type attribute of insurance products corresponding to the two is identical, and will examine
Institute and medical institutions are classified as a kind of risk classifications POI.POI by each risk classifications POI in each classification risk classifications POI is general
Rate, it may be determined that risk size of the user in such risk classifications POI.Insurance products are being carried out to each risk classifications POI
Attribute is sorted out, by each risk classifications POI be classified as with have the insurance products of all types of attributes it is corresponding after, need further true
Determine sub- risk POI probability of the user relative to all kinds of insurance products;Because all types of insurance products are applicable in different risk classifications, make
Risk size of each sub- risk POI probability tables requisition family in each type risk is obtained, can be used each classification risk classifications POI's
The sum of POI probability indicates.Specifically, to each risk classifications POI carry out insurance products attribute sort out, and determine user relative to
The step of sub- risk POI probability of all kinds of insurance products includes:
Step S21, calls the type attribute label of all kinds of insurance products, and will each risk identification symbol one by one with
Each type attribute label comparison, determines that each risk identification accords with corresponding target type attribute label;
Further, its risk classifications being applicable in is indicated with type attribute because of all kinds of insurance products, in order to all kinds of guarantors
The risk classifications that dangerous product is applicable in distinguish, i.e., type attribute distinguishes;In advance for different type insurance products
Type attribute is provided with different type attribute labels, such as the insurance products that type attribute is health, the risk class being applicable in
Type is health risk, and corresponding type attribute label is g3.When carrying out attribute classification to each risk classifications POI, first call each
The type attribute label of insurance products, then by it is each characterize be attributed to risk classifications risk identification symbol one by one with this all types of category
Property label compares.Although carrying this risk mark it should be noted that risk identification symbol is read from POI probability
The POI probability for knowing symbol is had by risk classifications POI, and POI probability, risk classifications POI, risk classifications identifier, which have, to be corresponded to
Property, the specific risk classifications of characterization risk classifications POI can be accorded with by risk identification.Specifically, it can accord in risk identification and increase below
Add the mode of kinds of characters to characterize the specific risk classifications of risk classifications POI, such as identifier for characterizing risk classifications POI
F3, risk identification symbol are f3, can increase different characters behind this f3 come come the specific risk class that characterizes risk classifications POI
Type;Hospital, health care shop such as are characterized with f3-31, to illustrate that the risk classifications POI's with risk identification symbol f3-31 is specific
Risk classifications are health risk;With f3-32 characterization horse-racing ground, rock-climbing field, there is the risk class of risk identification symbol f3-32 with explanation
The specific risk classifications of type POI are emergency risk.
In order to characterize the consistency of risk classifications, there is corresponding relationship, such as between type attribute label and risk identification symbol
The g3 and f3-31 of above-mentioned characterization health risk;Thus when comparing each risk identification symbol with all types of attribute tags one by one, when
When judging that the risk identification currently compared symbol and a certain type attribute label have corresponding relationship, then it can determine that this type
Attribute tags are corresponding with current risk identification symbol;Using this type attribute tags as target type attribute label, characterization has
The specific risk classifications of the risk classifications POI of current risk identifier, with the insurance products with this target type attribute label
The risk classifications being applicable in are consistent, can be by all risk classes having with the consistent risk identification symbol of this target type attribute label
Type POI is classified as same class.
Step S22 sorts out each risk classifications POI with the identical target type attribute label, shape
Gather at risk classifications POI corresponding with all kinds of insurance products;
Further, it after all risk identifications symbol is completed and all types of attribute tags compare, that is, can determine each
The corresponding target type attribute label of risk identification symbol;And then according to this target type attribute label, to each risk classifications POI
Sorted out, each risk classifications POI with same target type attribute label is sorted out.It should be noted that because of class
Type attribute tags and risk identification symbol have corresponding relationship, and target type attribute label is type category corresponding with risk identification symbol
Property label so that risk identification entrained by risk classifications POI symbol can use corresponding target type attribute tag characterization.Work as wind
Dangerous type POI carries a certain risk identification symbol, and this risk identification symbol is corresponding with a certain target type attribute label, and can use this
Entrained risk classifications mark in target type attribute tag characterization risk classifications POI can be described as this risk classifications POI tool
There is this target type attribute label.Each risk classifications POI with same target type attribute label is sorted out, is formed
Risk classifications POI set corresponding with all kinds of insurance products, and the corresponding relationship with all kinds of insurance products, by each target type category
Property label and insurance products corresponding relationship determine.M1, M2, M3 such as are respectively included for the risk classifications POI of user, M4 and
M5, wherein target type attribute label possessed by M1, M2 and M4 is that target type attribute label possessed by g2, M3 and M5 is
g3;To sort out to M1, M2, M4, the risk classifications POI set of [M1, M2, M4] is formed;M3 and M5 are sorted out, shape
Gather at the risk classifications POI of [M3, M5];Because g2 is corresponding with the product of accident insurance type, and the product of g3 and health insurance type
It is corresponding, and make [M1, M2, M4] corresponding with accident insurance product, [M3, M5] is corresponding with health insurance product.
Step S23 carries out the POI probability of each risk classifications POI in each risk classifications POI set
It is cumulative, generate sub- risk POI probability of the user relative to all kinds of insurance products.
Understandably, it is related to multiple risk classifications with same type risk in different risk classifications POI set
POI, and each risk classifications POI has different POI probability;All wind that will include in this each risk classifications POI set
The POI probability of dangerous type POI adds up one by one, after the completion of all risk classifications POI set is cumulative, obtained result
Gather possessed entirety POI probability for each risk classifications POI, characterizes risk size of the user in various types risk.
Because different types of risk corresponds to different types of insurance products, this each entirety POI probability its be substantially user relative to each
The sub- risk probability of class insurance products characterizes demand size of the user to all kinds of insurance products;As some risk classifications of user POI
When the sub- risk POI probability of set is larger, show user such risk classifications POI gather the risk of characterized type risk compared with
Greatly, and then show that demand of the user to the insurance products of such risk are suitable for is larger;It is produced by user relative to all kinds of insurances
The sub- risk POI probability of product, determines user to the conditions of demand of all kinds of insurance products.
Step S30, by each sub- risk POI probability and corresponding insurance products formation probability product pair, and by each institute
It states probability product and is added in default portrait template to user characteristics label is set as, generate user in the risk of the predetermined period
Portrait.
Further, it in the risk for determining each type of the user involved by predetermined period, and is produced with each insurance
Product characterize all types of risks, and after characterizing with sub- risk POI probability the size of all types of risks, by each sub- risk POI probability
And corresponding insurance products formation probability product pair, it is big to risk of the reflection user in all types of risks by probability product
It is small, and insurance product type corresponding with this type risk.Specifically, it is previously provided with for generating the default of risk portrait
Portrait template, and each category feature possessed by all kinds of feature tag argument tables requisition family in default portrait template with user;It will
The each probability product formed is added in the default portrait template to as user characteristics label, replaces feature tag therein
Variable is drawn a portrait using the default portrait template after added replacement operation as user in the risk of predetermined period.It is drawn by risk
Picture intuitively shows the risk distribution situation of user in daily life, the recommendation foundation by risk portrait as insurance products,
So that the insurance products recommended more are bonded the actual conditions of user.
The consumer's risk portrait generation method of the present embodiment, first goes the POI of each POI general according to user in predetermined period
Rate determines that user removes the overall risk POI probability of all risk classifications POI;This overall risk POI probability reflects user's daily life
In involved risk situation, wherein overall risk POI probability is bigger, illustrates that risk involved in user's daily life is got over
It is high;When judging that this overall risk POI probability is greater than preset value, illustrate that risk involved in user's daily life is higher,
The success rate for promoting insurance products to this user according to involved risk classifications is higher;To further to each risk classifications
The attribute that POI carries out insurance products is sorted out, and determines sub- risk POI probability of the user relative to all kinds of insurance products, this sub- risk
POI probability shows user to the conditions of demand of all kinds of insurance products;And then the corresponding insurance of each sub- risk POI probability is produced
Product form multiple probability products pair, which is added in default portrait template to user characteristics label is set as, raw
It draws a portrait at user in the risk of predetermined period.Because each sub- risk POI probability is by the risk classifications with identical insurance products attribute
The POI determine the probability of POI, and each risk classifications POI embodies various risks involved in user's daily life, so that sub
Risk POI probability is related to the various risks of user;So that consumer's risk portrait generated, can accurately reflect user daily
Involved risk situation in life;It avoids reflecting risk possessed by user using simple consumer's risk data, it is real
Show and has had risky accurate reflection to user.
Further, referring to figure 2., it on the basis of consumer's risk of the present invention draws a portrait generation method first embodiment, mentions
Consumer's risk portrait generation method second embodiment of the present invention out, in a second embodiment, the generation user is described default
Include: after the step of risk portrait in period
Step S40 does ratio to each sub- risk POI probability and the overall risk POI probability, generate user relative to
The risk accounting of all kinds of insurance products;
Understandably, risk of the user in different type risk is in different size, and risk size can be with being sorted out
Accounting of the sum of the POI probability of each risk classifications POI in the overall risk POI probability of entire risk classifications POI embodies, i.e., each son
Accounting of the risk POI probability in overall risk POI probability embodies;Wherein overall risk POI probability tables take over family for use in predetermined period
Overall risk size, and the risk size of each sub- risk POI probability tables requisition family various risks in predetermined period;When a certain son
The accounting of risk POI probability is bigger, then illustrates that this sub- risk POI probability occupies biggish numerical value in overall risk POI probability, uses
Risk main source of the family in predetermined period risk classifications corresponding with this sub- risk POI probability.Specifically, by each sub- risk
POI probability does ratio with overall risk POI probability one by one, characterizes risk class corresponding to each sub- risk POI probability by ratio size
Type occupies the number of user's overall risk in daily life.Because the insurance product type that different types of risk is applicable in is different
Sample, corresponding risk classifications occupy user in daily life overall risk how much, demand of the user to all kinds of insurance products can be characterized
Size;When risk classifications occupy, overall risk in user's daily life is more, then illustrates user to the guarantor for being suitable for this risk classifications
The demand of dangerous product is larger.To the risk accounting using the numerical result of ratio as user relative to all kinds of insurance products, table
Family is taken over for use to the conditions of demand of all kinds of insurance products;When larger by sub- risk POI probability ratio numerical result generated, then phase
The risk accounting answered is larger, and the demand that user corresponds to insurance products that risk classifications are applicable in this sub- risk POI probability is larger.
Step S50 compares each risk accounting, determines the maximum target risk accounting of numerical value, and it is determining with it is described
The corresponding insurance product type of target risk accounting;
Further, user is being generated after the risk accounting in all kinds of insurance products, each risk accounting has difference
Numerical values recited, wherein numerical value is bigger, illustrates that user has in the type risk that this risk accounting source insurance products is applicable in
There is greater risk.In order to determine the type risk of the had greateset risk of user, i.e., the most important risk of user in daily life
Source;Each risk accounting is compared, determines the maximum risk accounting of numerical value, and using this risk accounting as target risk
Accounting;Because risk accounting belongs to Mr. Yu's class insurance products, and the insurance product type that target risk accounting is belonged to as
Insurance product type corresponding with target risk accounting, to characterize the insurance product type that user most possibly needs.
Step S60 obtains product information corresponding with the insurance product type, and the product information is transferred to use
The terminal that family is held.
Understandably, all kinds of insurance products are suitable for different types of risk, and different types of risk is with different
Characteristic;For this different characteristics, all kinds of insurance products have different product informations.Such as the health of healthy type risk
Danger, and for the accident insurance of unexpected type risk;Because of the feature difference of healthy type risk and unexpected type risk, so that
There are product information othernesses between health insurance and accident insurance.Determining insurance product type corresponding with target risk accounting,
When characterization user's most probable has demand to this insurance product type, because the product information correspondence of all kinds of insurance products is stored in gold
Melt in the storage unit of authority server, so as to read production corresponding with the insurance product type that this is determined from storage unit
Product information;Consistent identifier, which is distributed, to each insurance products and its product information reads this guarantor after determining insurance product type
The identifier of dangerous product type, and find corresponding product information according to identifier and be read out.The product letter that this is read
Breath is transferred to the terminal that user is held, facilitate user understand the risk classifications in its greateset risk source applicable insurance products
Product information;The terminal that user is held can be mobile phone, the tablet computer etc. that user uses, without limitation.
Further, in consumer's risk of the present invention portrait another embodiment of generation method, the acquisition and the insurance
The step of product type corresponding product information includes:
Step S61 reads user basic information, and reads the production of each insurance products corresponding with the insurance product type
Product attribute;
Understandably, although different user has similitude in each type risk, also have between each user a
The difference of body;If user K1 and K2 like outdoor sports, and the type risk of the two is made to be accident insurance, but the K1 age
Larger and K2 age is smaller, and K2 is made to have preferable physical strength, and preferable risk resolution ability;It is faced in the two
When same outdoor sports, the emergency risk of K2 is smaller relative to K1.For the individual difference being preferably bonded between each user
Demand, being directed in all kinds of insurance products of different type risk includes multiple insurance products;Multiple insurance products entirety institutes
For risk classifications it is identical, but between each insurance products because be suitable for different user this type risk, and have difference
Product attribute.Such as above-mentioned insurance products X1 and X2 for user K1 and K2 type risk, unexpected type risk is belonged to, but
For having differences between X1 and X2, X1 is applicable in age small user, and X2 is applicable in older user, so that X1 is suitable for using
Family K2, and X2 is suitable for user K1.After determining the insurance product type suitable for user, in order to true from insurance product type
Surely the insurance products of user's individual demand are bonded, need further to read user basic information, this user basic information includes using
Family gender, age, city of residence, job specification etc.;The production of each insurance products included in insurance product type is read simultaneously
Product attribute, this product attribute characterize the crowd that each insurance products are applicable in, such as applicable age bracket, city, monthly income.Pass through
The user basic information and product information of reading, it may be determined that with the matched product information of user basic information institute.
Step S62 determines that target insurance produces according to the matching degree of the user basic information and each product attribute
Product, and the product information of the target insurance products is determined as product information corresponding with the insurance product type.
Further, after the product attribute for reading user basic information and each insurance products, by essential information and
Product attribute compares one by one, determines the matching degree of user basic information and each product attribute;Wherein matching degree is user's base
This information meets the degree of each product attribute demand, if the age being applicable in product attribute is between 20 to 30 years old, and is applicable in
City be Shenzhen, and when user basic information is the age 45 years old, then user and this product attribute mismatch.When user believes substantially
Breath more meets the needs of product attribute, then matching degree between the two is higher, and the insurance products with this product attribute are more suitable
Share family.The determining and highest product attribute of user basic information matching degree, and will be with the insurance products of this product attribute
As target insurance products;This product information is determined as and insurance products class by the product information for reading this target insurance products
The corresponding product information of type, and this product information is transferred in the terminal that user is held and carries out pushing away for target insurance products
It recommends.Because of the matching degree highest of the product informations of target insurance products and user basic information recommended, it may make and recommended
Target insurance products possessed risk in user's daily life is ensured to the full extent, meet the need of user
It asks.
Further, in consumer's risk of the present invention portrait another embodiment of generation method, the reading user exists
Include: before the step of removing the POI probability of each POI in predetermined period
Step q1 reads each location information of the user in predetermined period, and determines with each location information and be
POI in the preset range of the heart;
Understandably, it is generated because of each POI probability according to each location information of the user in predetermined period, without
It is not identical with POI possessed around location information, and user is not identical in the position that different time is gone;To generate use
When each POI probability of the family in predetermined period, pass through GPS (Global Positioning System, global positioning system)
The each location information of positioning service or base station location service acquisition user in predetermined period, and determined according to identifier with each
The POI in preset range centered on a location information.Wherein reading position information and statistics POI operation can be in default week
Interim real-time operation is also possible to unified operation after the completion of predetermined period;For real-time operation, GPS or base station to
The location information at family is positioned in real time, and the location information positioned is stored;This is read in real time in predetermined period
The location information of positioning determines the POI in the preset range centered on this location information;For unified operation, then default
After the completion of the time in period, the unified location information for reading user and being gone in predetermined period determines with each position information and is
POI in the preset range of the heart.In view of although the POI around each position information is numerous, the POI that user is gone is limited, and
A possibility that POI remoter apart from each position information, user is gone, is smaller;To previously according to user in multiple historical datas with
The distance range of gone to POI sets this preset range centered on location information, so that preset range meets going out for most people
Row demand.POI in this preset range of each position information is determined, characterizes user from each position information corresponding position institute
The each POI that may be gone to.
Step q2 counts the POI quantity of the POI, and according to the POI quantity, determines that user believes from each position
Breath removes the POI probability of each POI, generates the POI probability that user removes each POI in predetermined period.
Further, for each POI within a preset range, user can go to its POI for needing to go according to demand, use
Family goes the probability of each POI identical, and the sum of total probability for removing each POI is 1.Hence for the POI probability of each POI, first
Cumulative statistics is carried out to the quantity of the had POI in preset range, the result counted is POI quantity, further according to this POI
Quantity determines that user removes the POI probability of each POI from each location information.Because user goes from each position information that each POI's is general
Rate is identical, and summation is 1;Possessed POI quantity can be divided equally with summation 1, i.e., with 1 divided by POI quantity, with POI number
The mode of the reciprocal value of amount characterizes user and goes the probability of each POI identical, and each probability is the reciprocal value of POI quantity, generates
User removes the POI probability of each POI in this location information preset range from certain location information of predetermined period.As certain position is believed
There are 5 POI in breath preset range, then removing the probability of each POI is 1/5.According to being gone in this way to user from each position information
The POI probability of each POI is calculated in preset range, until each POI's in the preset range of all location informations
POI probability is computed determination, by this calculate user from each position information go the POI probability of each POI in preset range into
Row storage, so as to the subsequent demand size for removing each POI according to this each POI determine the probability user.In addition, it is contemplated that default model
Enclose that interior difference the distance between POI and location information are different, and different distances removes the probability of each POI to user from location information
Have an impact;A possibility that wherein remoter POI of distance and position information, user is gone to, is smaller, so that reducing user removes this POI
Probability;So that user from location information go the POI probability of each POI in addition to POI quantity mutually outside the Pass, also with each POI and
The distance between location information correlation.Specifically, according to POI quantity, determine that user removes each POI from each location information
POI probability, generating user the step of POI probability of each POI is removed in predetermined period includes:
Step q21 divides the preset range according to the distance relation of each location information and the preset range
For multiple far and near regions;
Further, because user goes the distance between the probability of each POI and each POI and location information far and near related;From
And in the POI probability for determining each POI, first according to the distance relation of each position information and preset range, preset range is divided
For multiple far and near regions, different distance regions are not identical at a distance from location information.Specifically, the position characterized with location information
It sets as starting point, at interval of a certain distance length, preset range is divided into multiple far and near regions;Wherein distance length is pre-
The length of historical data setting is first passed through, multiple distance regions are in the area that different starting points are extended with this distance length
Domain.If current location is A, and preset range is 1000m circular scope outside centered on A, distance length 500m;Then will
It is the border circular areas of starting point 500m forward as a far and near region section using A, and with the boundary of circular interval, i.e. distance A
Boundary for 500m is starting point, using the circle ring area between 500m to 1000m as another far and near region.
Step q22, according to the region quantity in the far and near region, for each far and near region distribution region probability;
Understandably, the closer far and near region of distance and position information, the probability that user goes to this far and near region is relatively large,
And the probability for going to the farther away far and near region of distance and position information is relatively small;To according to far and near region and location information away from
From relationship, different area probabilities is distributed for each far and near region, and larger with far and near region distribution that location information is closer
Area probability, and then distribute lesser area probability apart from farther away far and near region with location information, each distance region
The sum of area probability is 1, and the possibility that user goes to each distance region in preset range is characterized by this variant area probability
Property size.
Step q23 does product with the reciprocal value of the POI quantity and the area probability, determines user from each institute's rheme
Confidence breath removes the POI probability of POI described in each far and near region, generates user and goes the POI of each POI general in predetermined period
Rate.
Further, it after the area probability distribution to each far and near region, herein on the basis of each area probability, determines and uses
The POI probability of each POI in preset range is removed at family.Specifically, the area probability possessed by far and near region and institute in preset range
The reciprocal value of POI quantity with POI is multiplied;The result of multiplication is user gone from location information it is each in each far and near region
The POI probability of POI, i.e. user remove the POI probability of each POI in preset range from location information;According in this way to user from
The POI probability that each position information goes to each POI in each distance region in preset range is calculated, until all location informations
Preset range in each POI probability be computed completion.By continuing to be subdivided into multiple far and near regions for pre- range, make really
Fixed POI probability is more accurate;After the completion of POI possessed in preset range is calculated, obtained each POI will be calculated
POI probability stored, generate user and remove the POI probability of each POI in predetermined period, so as to subsequent according to this each POI
Probability accurately reflects that user goes the demand size of each POI.
In addition, referring to figure 3., the present invention provides a kind of consumer's risk portrait generating means, and point of interest POI type includes wind
Dangerous type POI, in consumer's risk of the present invention portrait generating means first embodiment, the consumer's risk portrait generating means packet
It includes:
Read module 10 removes the POI probability of each POI for reading user in predetermined period, and to each POI probability
It is counted according to the POI type belonged to, determines that user removes the overall risk POI probability of all risk classifications POI;
Determining module 20, for judging whether the overall risk POI probability is greater than preset value, if more than the preset value,
Then each risk classifications POI attribute for carrying out insurance products is sorted out, and determines user relative to all kinds of insurance products
Sub- risk POI probability;
Generation module 30 is used for each sub- risk POI probability and corresponding insurance products formation probability product pair, and
Each probability product is added in default portrait template to user characteristics label is set as, generates user in the predetermined period
Risk portrait.
The consumer's risk portrait generating means of the present embodiment, are first gone in predetermined period by read module 10 according to user each
The POI probability of a POI determines that user removes the overall risk POI probability of all risk classifications POI;This overall risk POI probability reflects
Involved risk situation in user's daily life, wherein overall risk POI probability is bigger, illustrates involved in user's daily life
And the risk arrived is higher;When judging that this overall risk POI probability is greater than preset value by determining module 20, illustrate the daily life of user
Involved risk is higher in work, according to involved risk classifications to this user promote the success rates of insurance products compared with
It is high;To further sort out to each risk classifications POI attribute for carrying out insurance products, determine user relative to all kinds of insurance products
Sub- risk POI probability, this sub- risk POI probability shows user to the conditions of demand of all kinds of insurance products;And then by generation mould
The corresponding insurance products of each sub- risk POI probability are formed multiple probability products pair by block 30, by each probability product to setting
It is added in default portrait template for user characteristics label, the risk for generating user in predetermined period is drawn a portrait.Because of each sub- risk POI
Probability is by the POI determine the probability of the risk classifications POI with identical insurance products attribute, and each risk classifications POI embodies use
Involved various risks in the daily life of family, so that sub- risk POI probability is related to the various risks of user;So that giving birth to
At consumer's risk portrait, user's involved risk situation in daily life can be accurately reflected;It avoids using simple
Consumer's risk data reflect risk possessed by user, realize and have risky accurate reflection to user.
Further, in consumer's risk of the present invention portrait another embodiment of generating means, the read module includes:
Reading unit for reading identifier entrained in each POI probability, and is screened from each identifier
It is attributed to the risk identification symbol of risk classifications out;
Summing elements obtain user and go to own for will have the POI probability of the risk identification symbol to add up
The overall risk POI probability of risk classifications POI.
Further, in consumer's risk of the present invention portrait another embodiment of generating means, the determining module includes:
Call unit is accorded with for calling the type attribute label of all kinds of insurance products, and by each risk identification
It is compared one by one with each type attribute label, determines that each risk identification accords with corresponding target type attribute label;
Sort out unit, for returning to each risk classifications POI with the identical target type attribute label
Class forms risk classifications POI set corresponding with all kinds of insurance products;
Generation unit, it is general for the POI to each risk classifications POI in each risk classifications POI set
Rate adds up, and generates sub- risk POI probability of the user relative to all kinds of insurance products.
Further, in consumer's risk of the present invention portrait another embodiment of generating means, the consumer's risk portrait life
At device further include:
Ratio module generates user for each sub- risk POI probability and the overall risk POI probability to be done ratio
Risk accounting relative to all kinds of insurance products;
Contrast module, for will each risk accounting comparison, determine the maximum target risk accounting of numerical value, and determine and
The corresponding insurance product type of the target risk accounting;
Module is obtained, for obtaining product information corresponding with the insurance product type, and the product information is passed
The defeated terminal held to user.
Further, in consumer's risk of the present invention portrait another embodiment of generating means, the acquisition module is also used to:
User basic information is read, and reads the product attribute of each insurance products corresponding with the insurance product type;
According to the matching degree of the user basic information and each product attribute, target insurance products are determined, and will
The product information of the target insurance products is determined as product information corresponding with the insurance product type.
Further, in consumer's risk of the present invention portrait another embodiment of generating means, the consumer's risk portrait life
At device further include:
The read module is also used to read each location information of the user in predetermined period, and determines with each institute's rheme
The POI in preset range centered on confidence breath;
Statistical module determines user from each described for counting the POI quantity of the POI, and according to the POI quantity
Location information removes the POI probability of each POI, generates the POI probability that user removes each POI in predetermined period.
Further, in consumer's risk of the present invention portrait another embodiment of generating means, the statistical module is also used to:
According to the distance relation of each location information and the preset range, the preset range is divided into multiple remote
Near field;
It is general for each far and near region distribution region according to the distance relation in each far and near region and the location information
Rate;
Product is done with the reciprocal value of the POI quantity and the area probability, determines that user goes from each location information
The POI probability of POI described in each far and near region, generates the POI probability that user removes each POI in predetermined period.
Wherein, each virtual functions module of above-mentioned consumer's risk portrait generating means is stored in the picture of consumer's risk shown in Fig. 4
As generating device memory 1005 in, processor 1001 execute consumer's risk portrait generate program when, realize Fig. 3 shown in implement
The function of modules in example.
Referring to Fig. 4, Fig. 4 is the device structure schematic diagram for the hardware running environment that present invention method is related to.
Consumer's risk of embodiment of the present invention portrait generating device can be PC (personal computer, individual calculus
Machine), it is also possible to the terminal devices such as smart phone, tablet computer, E-book reader, portable computer.
As shown in figure 4, consumer's risk portrait generating device may include: processor 1001, such as CPU (Central
Processing Unit, central processing unit), memory 1005, communication bus 1002.Wherein, communication bus 1002 for realizing
Connection communication between processor 1001 and memory 1005.Memory 1005 can be high-speed RAM (random access
Memory, random access memory), it is also possible to stable memory (non-volatile memory), such as disk storage
Device.Memory 1005 optionally can also be the storage device independently of aforementioned processor 1001.
Optionally, consumer's risk portrait generating device can also include user interface, network interface, camera, RF
(Radio Frequency, radio frequency) circuit, sensor, voicefrequency circuit, WiFi (Wireless Fidelity, WiMAX) mould
Block etc..User interface may include display screen (Display), input unit such as keyboard (Keyboard), and optional user connects
Mouth can also include standard wireline interface and wireless interface.Network interface optionally may include the wireline interface, wireless of standard
Interface (such as WI-FI interface).
It will be understood by those skilled in the art that the portrait generating device structure of consumer's risk shown in Fig. 4 is not constituted pair
The restriction of consumer's risk portrait generating device, may include components more more or fewer than diagram, or combine certain components, or
The different component layout of person.
As shown in figure 4, as may include operating system, network communication in a kind of memory 1005 of readable storage medium storing program for executing
Module and consumer's risk portrait generate program.Operating system is to manage and control consumer's risk portrait generating device hardware and soft
The program of part resource supports consumer's risk portrait to generate the operation of program and other softwares and/or program.Network communication module
For realizing the communication between each component in the inside of memory 1005, and with other hardware in consumer's risk portrait generating device and
It is communicated between software.
In consumer's risk portrait generating device shown in Fig. 4, processor 1001 stores in memory 1005 for executing
Consumer's risk portrait generate program, realize the step in above-mentioned consumer's risk portrait each embodiment of generation method.
The present invention provides a kind of readable storage medium storing program for executing, the readable storage medium storing program for executing is preferably that computer can short storage Jie
Matter, the computer-readable recording medium storage have one or more than one program, the one or more programs
It can also be executed by one or more than one processor for realizing above-mentioned consumer's risk portrait each embodiment of generation method
In step.
It should also be noted that, herein, the terms "include", "comprise" or its any other variant are intended to non-
It is exclusive to include, so that the process, method, article or the device that include a series of elements not only include those elements,
It but also including other elements that are not explicitly listed, or further include solid by this process, method, article or device
Some elements.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including
There is also other identical elements in the process, method of the element, article or device.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In readable storage medium storing program for executing (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be hand
Machine, computer, server or network equipment etc.) execute method described in each embodiment of the present invention.
The above description is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all at this
Under the design of invention, using equivalent structure transformation made by description of the invention and accompanying drawing content, or directly/it is used in it indirectly
He is included in scope of patent protection of the invention relevant technical field.
Claims (10)
- The generation method 1. a kind of consumer's risk is drawn a portrait, which is characterized in that point of interest POI type includes risk classifications POI, the use Family risk draw a portrait generation method the following steps are included:The POI probability that user removes each POI in predetermined period is read, and to each POI probability according to the POI type belonged to It is counted, determines that user removes the overall risk POI probability of all risk classifications POI;Judge whether the overall risk POI probability is greater than preset value, if more than the preset value, then to each risk classifications The attribute that POI carries out insurance products is sorted out, and determines sub- risk POI probability of the user relative to all kinds of insurance products;By each sub- risk POI probability and corresponding insurance products formation probability product pair, and by each probability product pair It is set as user characteristics label to be added in default portrait template, the risk for generating user in the predetermined period is drawn a portrait.
- The generation method 2. consumer's risk as described in claim 1 is drawn a portrait, which is characterized in that described that each POI probability is pressed It is counted according to the POI type belonged to, determines that the step of user removes the overall risk POI probability of all risk classifications POI includes:Identifier entrained in each POI probability is read, and is filtered out from each identifier and is attributed to risk classifications Risk identification symbol;It will add up with the POI probability that the risk identification accords with, obtain total wind that user removes all risk classifications POI Dangerous POI probability.
- The generation method 3. consumer's risk as claimed in claim 2 is drawn a portrait, which is characterized in that described to each risk classifications The attribute that POI carries out insurance products is sorted out, and determines step of the user relative to the sub- risk POI probability of all kinds of insurance products Suddenly include:Call the type attribute label of all kinds of insurance products, and by each risk identification symbol one by one with each type category Property label comparison, determine that each risk identification accords with corresponding target type attribute label;Each risk classifications POI with the identical target type attribute label is sorted out, formed with it is all kinds of described The corresponding risk classifications POI set of insurance products;It adds up to the POI probability of each risk classifications POI in each risk classifications POI set, generates and use Sub- risk POI probability of the family relative to all kinds of insurance products.
- The generation method 4. consumer's risk as claimed in claim 3 is drawn a portrait, which is characterized in that the generation user is described default Include: after the step of risk portrait in periodEach sub- risk POI probability and the overall risk POI probability are done into ratio, generate user relative to all kinds of insurances The risk accounting of product;Each risk accounting is compared, determines the maximum target risk accounting of numerical value, and the determining and target risk accounting Corresponding insurance product type;Product information corresponding with the insurance product type is obtained, and the product information is transferred to the end that user is held End.
- The generation method 5. consumer's risk as claimed in claim 4 is drawn a portrait, which is characterized in that the acquisition and the insurance products The step of type corresponding product information includes:User basic information is read, and reads the product attribute of each insurance products corresponding with the insurance product type;According to the matching degree of the user basic information and each product attribute, target insurance products are determined, and will be described The product information of target insurance products is determined as product information corresponding with the insurance product type.
- The generation method 6. consumer's risk as described in any one in claim 1-5 is drawn a portrait, which is characterized in that the reading user exists Include: before the step of removing the POI probability of each POI in predetermined periodEach location information of the user in predetermined period is read, and determines the preset range centered on each location information Interior POI;The POI quantity of the POI is counted, and according to the POI quantity, it is each described to determine that user goes from each location information The POI probability of POI generates the POI probability that user removes each POI in predetermined period.
- The generation method 7. consumer's risk as claimed in claim 6 is drawn a portrait, which is characterized in that it is described according to the POI quantity, really Determine the POI probability that user removes each POI from each location information, generates user and go the POI of each POI general in predetermined period The step of rate includes:According to the distance relation of each location information and the preset range, the preset range is divided into multiple far and near areas Domain;According to the distance relation in each far and near region and the location information, for each far and near region distribution region probability;Product is done with the reciprocal value of the POI quantity and the area probability, determines that user goes to each institute from each location information The POI probability of POI described in far and near region is stated, the POI probability that user removes each POI in predetermined period is generated.
- The generating means 8. a kind of consumer's risk is drawn a portrait, which is characterized in that point of interest POI type includes risk classifications POI, the use Family risk portrait generating means include:Read module removes the POI probability of each POI for reading user in predetermined period, and to each POI probability according to institute The POI type of ownership is counted, and determines that user removes the overall risk POI probability of all risk classifications POI;Determining module, for judging whether the overall risk POI probability is greater than preset value, if more than the preset value, then to each The attribute that the risk classifications POI carries out insurance products is sorted out, and determines sub- wind of the user relative to all kinds of insurance products Dangerous POI probability;Generation module, for by each sub- risk POI probability and corresponding insurance products formation probability product pair, and by each institute It states probability product and is added in default portrait template to user characteristics label is set as, generate user in the risk of the predetermined period Portrait.
- The generating device 9. a kind of consumer's risk is drawn a portrait, which is characterized in that the consumer's risk portrait generating device includes: storage Device, processor, communication bus and the consumer's risk portrait being stored on the memory generate program;The communication bus is for realizing the connection communication between processor and memory;The processor generates program for executing the consumer's risk portrait, to realize such as any one of claim 1-7 institute The step of consumer's risk portrait generation method stated.
- 10. a kind of readable storage medium storing program for executing, which is characterized in that be stored with consumer's risk portrait on the readable storage medium storing program for executing and generate journey Sequence, the consumer's risk portrait, which generates when program is executed by processor, realizes such as user of any of claims 1-7 The step of risk portrait generation method.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811135650.1A CN109447689A (en) | 2018-09-27 | 2018-09-27 | Consumer's risk portrait generation method, device, equipment and readable storage medium storing program for executing |
PCT/CN2018/123218 WO2020062657A1 (en) | 2018-09-27 | 2018-12-24 | User risk profile generation method and apparatus, device and related device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811135650.1A CN109447689A (en) | 2018-09-27 | 2018-09-27 | Consumer's risk portrait generation method, device, equipment and readable storage medium storing program for executing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109447689A true CN109447689A (en) | 2019-03-08 |
Family
ID=65545937
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811135650.1A Pending CN109447689A (en) | 2018-09-27 | 2018-09-27 | Consumer's risk portrait generation method, device, equipment and readable storage medium storing program for executing |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109447689A (en) |
WO (1) | WO2020062657A1 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110322274A (en) * | 2019-05-30 | 2019-10-11 | 深圳壹账通智能科技有限公司 | Crowd portrayal generation method, device and computer equipment based on data analysis |
CN110689446A (en) * | 2019-10-30 | 2020-01-14 | 海腾保险代理有限公司 | Combined insurance recommendation method and device |
CN110766559A (en) * | 2019-10-30 | 2020-02-07 | 海腾保险代理有限公司 | Label configuration method and device |
CN110782361A (en) * | 2019-10-30 | 2020-02-11 | 海腾保险代理有限公司 | Recommendation method and device for customized insurance |
CN111724218A (en) * | 2019-03-18 | 2020-09-29 | 河南省技术产权交易所有限公司 | Intellectual property listing method, device, equipment and computer readable storage medium |
CN115099680A (en) * | 2022-07-14 | 2022-09-23 | 平安科技(深圳)有限公司 | Risk management method, device, equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106656932A (en) * | 2015-11-02 | 2017-05-10 | 阿里巴巴集团控股有限公司 | Business processing method and device |
CN106651603A (en) * | 2016-12-29 | 2017-05-10 | 平安科技(深圳)有限公司 | Risk evaluation method and apparatus based on position service |
CN107566358A (en) * | 2017-08-25 | 2018-01-09 | 腾讯科技(深圳)有限公司 | A kind of Risk-warning reminding method, device, medium and equipment |
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 |
CN107818506A (en) * | 2017-09-30 | 2018-03-20 | 上海壹账通金融科技有限公司 | Electronic installation, credit risk control method and storage medium |
CN108171610A (en) * | 2017-12-28 | 2018-06-15 | 中国平安人寿保险股份有限公司 | Page generation method, page generation equipment, storage medium and device |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106682394A (en) * | 2016-11-30 | 2017-05-17 | 北京拓明科技有限公司 | Big data analyzing method and system of survival risk |
CN107657527A (en) * | 2017-09-29 | 2018-02-02 | 平安科技(深圳)有限公司 | Loan product matching process, device and computer-readable recording medium |
CN108288229B (en) * | 2018-03-02 | 2022-03-15 | 北京邮电大学 | User portrait construction method |
-
2018
- 2018-09-27 CN CN201811135650.1A patent/CN109447689A/en active Pending
- 2018-12-24 WO PCT/CN2018/123218 patent/WO2020062657A1/en active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106656932A (en) * | 2015-11-02 | 2017-05-10 | 阿里巴巴集团控股有限公司 | Business processing method and device |
CN106651603A (en) * | 2016-12-29 | 2017-05-10 | 平安科技(深圳)有限公司 | Risk evaluation method and apparatus based on position service |
CN107566358A (en) * | 2017-08-25 | 2018-01-09 | 腾讯科技(深圳)有限公司 | A kind of Risk-warning reminding method, device, medium and equipment |
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 |
CN107818506A (en) * | 2017-09-30 | 2018-03-20 | 上海壹账通金融科技有限公司 | Electronic installation, credit risk control method and storage medium |
CN108171610A (en) * | 2017-12-28 | 2018-06-15 | 中国平安人寿保险股份有限公司 | Page generation method, page generation equipment, storage medium and device |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111724218A (en) * | 2019-03-18 | 2020-09-29 | 河南省技术产权交易所有限公司 | Intellectual property listing method, device, equipment and computer readable storage medium |
CN110322274A (en) * | 2019-05-30 | 2019-10-11 | 深圳壹账通智能科技有限公司 | Crowd portrayal generation method, device and computer equipment based on data analysis |
CN110689446A (en) * | 2019-10-30 | 2020-01-14 | 海腾保险代理有限公司 | Combined insurance recommendation method and device |
CN110766559A (en) * | 2019-10-30 | 2020-02-07 | 海腾保险代理有限公司 | Label configuration method and device |
CN110782361A (en) * | 2019-10-30 | 2020-02-11 | 海腾保险代理有限公司 | Recommendation method and device for customized insurance |
CN110766559B (en) * | 2019-10-30 | 2023-09-29 | 海腾保险代理有限公司 | Label configuration method and device |
CN115099680A (en) * | 2022-07-14 | 2022-09-23 | 平安科技(深圳)有限公司 | Risk management method, device, equipment and storage medium |
CN115099680B (en) * | 2022-07-14 | 2024-02-02 | 平安科技(深圳)有限公司 | Risk management method, apparatus, device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2020062657A1 (en) | 2020-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109447689A (en) | Consumer's risk portrait generation method, device, equipment and readable storage medium storing program for executing | |
CN107315824B (en) | Method and device for generating thermodynamic diagram | |
CN110020221B (en) | Job distribution confirmation method, apparatus, server and computer readable storage medium | |
WO2019080662A1 (en) | Information recommendation method, device and apparatus | |
CN109859054A (en) | Network community method for digging, device, computer equipment and storage medium | |
CN110765220B (en) | Geographical position determining method based on thermodynamic diagram and electronic equipment | |
US20220067000A1 (en) | Constructing a database of verified individuals | |
CN109272219A (en) | Performance appraisal method, apparatus, computer equipment and storage medium | |
CN110363453A (en) | Distribution information method for visualizing and device | |
CN108090086A (en) | Paging query method and device | |
CN109840851A (en) | A kind of integrated management approach, device and the equipment of data of managing money matters | |
CN109299367A (en) | Information-pushing method, device, computer equipment and storage medium | |
CN109559218A (en) | A kind of determination method, apparatus traded extremely and storage medium | |
CN108596052A (en) | A kind of articles seeking method, system and terminal device | |
CN111339409A (en) | Map display method and system | |
CN113609409A (en) | Method and system for recommending browsing information, electronic device and storage medium | |
CN111414395A (en) | Data processing method, system and computer equipment | |
CN109409936A (en) | Customer consumption portrait generation method, device, equipment and readable storage medium storing program for executing | |
CN113342762B (en) | Intelligent processing method and related device for shared messages of friends of merchants | |
CN107169014B (en) | POI recommendation method, device, equipment and computer readable storage medium | |
CN109670853A (en) | Determination method, apparatus, equipment and the readable storage medium storing program for executing of user characteristic data | |
CN111523043B (en) | Resource information display and management method and device | |
CN108805408B (en) | Access planning method and terminal equipment | |
CN108537654B (en) | Rendering method and device of customer relationship network graph, terminal equipment and medium | |
CN112785163A (en) | Occupation recognition method, device, equipment and medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40002557 Country of ref document: HK |
|
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |