CN109636638A - Insurance Pricing method, apparatus, equipment and readable storage medium storing program for executing based on big data - Google Patents
Insurance Pricing method, apparatus, equipment and readable storage medium storing program for executing based on big data Download PDFInfo
- Publication number
- CN109636638A CN109636638A CN201811529190.0A CN201811529190A CN109636638A CN 109636638 A CN109636638 A CN 109636638A CN 201811529190 A CN201811529190 A CN 201811529190A CN 109636638 A CN109636638 A CN 109636638A
- Authority
- CN
- China
- Prior art keywords
- insurance
- information
- cluster
- special medicine
- default
- 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 51
- 239000003814 drug Substances 0.000 claims abstract description 206
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 95
- 201000010099 disease Diseases 0.000 claims abstract description 67
- 238000012552 review Methods 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000013139 quantization Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 abstract description 6
- 238000007405 data analysis Methods 0.000 abstract description 4
- 229940079593 drug Drugs 0.000 description 11
- 238000007726 management method Methods 0.000 description 10
- 239000002775 capsule Substances 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000003745 diagnosis Methods 0.000 description 7
- 239000004744 fabric Substances 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000012550 audit Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000005484 gravity Effects 0.000 description 3
- 101001012157 Homo sapiens Receptor tyrosine-protein kinase erbB-2 Proteins 0.000 description 2
- 235000014676 Phragmites communis Nutrition 0.000 description 2
- 102100030086 Receptor tyrosine-protein kinase erbB-2 Human genes 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002018 overexpression Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 206010006187 Breast cancer Diseases 0.000 description 1
- 208000026310 Breast neoplasm Diseases 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 206010025323 Lymphomas Diseases 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229940022353 herceptin Drugs 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 230000029305 taxis Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001960 triggered effect 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
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
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)
- Entrepreneurship & Innovation (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention provides a kind of Insurance Pricing method based on big data, device, equipment and readable storage medium storing program for executing, by reference to having the special medicine of the target group of similar features to be applicable in disease disease incidence with warrantee, and combine special medicine cost of use, multiple influence factors such as operation cost calculate the gross premium of special medicine insurance plan, it is fixed a price in a manner of big data analysis processing to special medicine insurance plan, to more fully consider special medicine insurance plan Influence Factors of Price, price result is enabled more to meet the actual conditions of warrantee and the true operation situation of insurance institution, improve the reasonability and accuracy of price, advantageously reduce the operation cost of insurance plan.
Description
Technical field
The present invention relates to data analysis field more particularly to a kind of Insurance Pricing method, apparatus, equipment based on big data
And readable storage medium storing program for executing.
Background technique
With the development of medical technology, special medicine (carries out special treatment for a certain disease, there is high science to contain in the market
Amount, the high drug of technical difficulty) gradually increase, such as her cloth can be for Buddhist nun's piece for Buddhist nun's capsule (hundred million jade-like stones), reed (victory is scrupulously and respectfully defended);But market
On special medicine price costly.In order to mitigate burden of patients, some insurance institutions propose for the medical expenses of special medicine to be incorporated into
Insurance reimbursement range, provides special medicine insurance service for client;And at present when fixing a price to the insurance of special medicine, mainly by expert
It carries out manual analysis and fixes a price, this pricing method low efficiency, human factor is big, and it reduce the standards of special medicine insurance plan price
True property.
Summary of the invention
The Insurance Pricing method, apparatus that the main purpose of the present invention is to provide a kind of based on big data, equipment and readable
Storage medium, it is intended to improve the accuracy of special medicine Insurance Pricing.
To achieve the above object, the present invention provides a kind of Insurance Pricing method based on big data, the Insurance Pricing side
Method includes:
When receiving the pricing requests of special medicine insurance, warrantee's information that the pricing requests correspond to warrantee is obtained,
And obtain the annual cost per capita of the corresponding special medicine of special medicine insurance and the payout schedule of the special medicine insurance;
Warrantee's information and the various kinds information in default sample population are gathered based on default clustering rule
Alanysis obtains target information cluster, wherein the target information cluster includes warrantee's information and target sample information;
Target group is determined in the default sample population according to the target sample information, and obtains the special medicine
Disease is applicable in the applicable disease disease incidence of the target group;
According to the annual cost per capita, described it is applicable in disease disease incidence and the payout schedule calculates year of the special medicine insurance
Risk premium, and the year gross premium per capita that the special medicine insures is calculated according to the year risk premium and default Management plan.
In addition, to achieve the above object, the present invention also provides a kind of the Insurance Pricing device based on big data, the insurance
Pricing device includes:
Data obtaining module, for obtaining the pricing requests and corresponding to quilt when receiving the pricing requests of special medicine insurance
Warrantee's information of guarantor, and obtain the annual cost per capita of the corresponding special medicine of special medicine insurance and the compensation of the special medicine insurance
The scheme of paying;
Information cluster module, for based on default clustering rule to warrantee's information with it is each in default sample population
Sample people's information carry out clustering, obtain target information cluster, wherein the target information cluster include warrantee's information and
Target sample information;
Crowd's determining module, for determining target person in the default sample population according to the target sample information
Group, and obtain the special medicine is applicable in disease in the applicable disease disease incidence of the target group;
Gross premium calculates module, for according to annual cost, the applicable disease disease incidence and the payout schedule per capita
Calculate the year risk premium of the special medicine insurance, and is protected according to the year risk premium and the measuring and calculating of default the Management plan special medicine
The year gross premium per capita of danger.
In addition, to achieve the above object, the present invention also provides a kind of the Insurance Pricing equipment based on big data, the insurance
Pricing equipment includes processor, memory and is stored on the memory and can be determined by the insurance that the processor executes
Valence program, wherein realizing when the Insurance Pricing program is executed by the processor as the above-mentioned insurance based on big data is fixed
The step of valence method.
In addition, to achieve the above object, the present invention also provides a kind of readable storage medium storing program for executing, being deposited on the readable storage medium storing program for executing
Insurance Pricing program is contained, wherein when the Insurance Pricing program is executed by processor, is realized as above-mentioned based on big data
The step of Insurance Pricing method.
The present invention is combined by reference to having the special medicine of the target group of similar features to be applicable in disease disease incidence with warrantee
Multiple influence factors such as special medicine cost of use, operation cost calculate the gross premium of special medicine insurance plan, are handled with big data analysis
Mode fixed a price to special medicine insurance plan, to more fully consider special medicine insurance plan Influence Factors of Price, make
The result that must fix a price can more meet the actual conditions of warrantee and the true operation situation of insurance institution, improve the conjunction of price
Rationality and accuracy advantageously reduce the operation cost of insurance plan.
Detailed description of the invention
Fig. 1 is the hardware configuration signal of the Insurance Pricing equipment based on big data involved in the embodiment of the present invention
Figure;
Fig. 2 is that the present invention is based on the flow diagrams of the Insurance Pricing method first embodiment of big data;
Fig. 3 is that the present invention is based on the functional block diagrams of the Insurance Pricing device first embodiment of big data.
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 embodiments relate to the Insurance Pricing method based on big data be mainly used in the insurance based on big data
Pricing equipment, being somebody's turn to do the Insurance Pricing equipment based on big data can be personal computer (personal computer, PC), pen
Remember the equipment having data processing function such as this computer, server.
Referring to Fig.1, Fig. 1 is the hardware knot of the Insurance Pricing equipment based on big data involved in the embodiment of the present invention
Structure schematic diagram.In the embodiment of the present invention, the Insurance Pricing equipment based on big data may include (such as the centre of processor 1001
Manage device Central Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, storage
Device 1005.Wherein, communication bus 1002 is for realizing the connection communication between these components;User interface 1003 may include showing
Display screen (Display), input unit such as keyboard (Keyboard);Network interface 1004 optionally may include the wired of standard
Interface, wireless interface (such as Wireless Fidelity WIreless-FIdelity, WI-FI interface);It is random that memory 1005 can be high speed
It accesses memory (random access memory, RAM), is also possible to stable memory (non-volatile
Memory), such as magnetic disk storage, memory 1005 optionally can also be the storage dress independently of aforementioned processor 1001
It sets.It will be understood by those skilled in the art that hardware configuration shown in Fig. 1 and not constituting a limitation of the invention, may include
Than illustrating more or fewer components, certain components or different component layouts are perhaps combined.
With continued reference to Fig. 1, the memory 1005 in Fig. 1 as a kind of computer readable storage medium may include operation system
System, network communication module and Insurance Pricing program.In Fig. 1, network communication module can be used for connecting database, with database
Carry out data communication;And processor 1001 can call the Insurance Pricing program stored in memory 1005, and execute the present invention
The Insurance Pricing method based on big data that embodiment provides.
The Insurance Pricing method based on big data that the embodiment of the invention provides a kind of.
It is that the present invention is based on the flow diagrams of the Insurance Pricing method first embodiment of big data referring to Fig. 2, Fig. 2.
In the present embodiment, the Insurance Pricing method includes:
Step S10 obtains the pricing requests and corresponds to being protected for warrantee when receiving the pricing requests of special medicine insurance
People's information, and obtain the annual cost per capita of the corresponding special medicine of special medicine insurance and the payout schedule of the special medicine insurance.
With the development of medical technology, special medicine (carries out special treatment for a certain disease, there is high science to contain in the market
Amount, the high drug of technical difficulty) gradually increase, such as her cloth can be for Buddhist nun's piece for Buddhist nun's capsule (hundred million jade-like stones), reed (victory is scrupulously and respectfully defended);But market
On special medicine price costly.In order to mitigate burden of patients, some insurance institutions propose for the medical expenses of special medicine to be incorporated into
Insurance reimbursement range, provides special medicine insurance service for client;And at present when fixing a price to the insurance of special medicine, mainly by expert
It carries out manual analysis and fixes a price, this pricing method low efficiency, human factor is big, and it reduce the standards of special medicine insurance plan price
True property.In this regard, proposing a kind of Insurance Pricing method based on big data in the present embodiment, there are similar features with reference to warrantee
The special medicine of target group be applicable in disease disease incidence, and it is special to combine multiple influence factors such as special medicine cost of use, operation cost to calculate
The gross premium of medicine insurance plan fixes a price to special medicine insurance plan in a manner of big data analysis processing, thus more comprehensively
Ground considers special medicine insurance plan Influence Factors of Price, and price result is enabled more to meet actual conditions and the guarantor of warrantee
The true operation situation of dangerous mechanism improves the reasonability and accuracy of price, advantageously reduces the operation cost of insurance plan.
The Insurance Pricing method based on big data in the present embodiment is realized by the Insurance Pricing equipment based on big data
, which is illustrated by taking Insurance Pricing terminal as an example, which can also be PC, service
Device etc..In the present embodiment, the personnel that insure, can be in terminal of insuring it should be understood that when the price of special medicine insurance is to judge whether purchase
Corresponding operating is carried out on (terminal of insuring can be PC PC, laptop, mobile phone etc.), terminal of insuring is then according to throwing
The operation of guarantor person sends corresponding special medicine Insurance Pricing request to Insurance Pricing terminal.It can also be with certainly for the pricing requests
It is to be triggered by business personnel and be sent to Insurance Pricing terminal on service terminal according to business demand.Insurance Pricing terminal is connecing
When receiving the pricing requests, it will acquire special medicine first and insure targeted warrantee (warrantee can not be same with insurer
People) warrantee's information, which may include the target city where warrantee's name, gender, age, warrantee
The contents such as city, height, weight, medical history, present health condition.For these warrantee's information, Insurance Pricing end can be
End provides prompt when receiving the pricing requests, to terminal of insuring (or service terminal) return information, so that the personnel that insure (or
Business personnel) it is supplemented according to the prompt and replys warrantee's information;It can certainly be insurer (or business personnel) at end of insuring
Relevant warrantee is directly entered when the triggering pricing requests of end (or service terminal), by terminal of insuring (or service terminal) by the quilt
Guarantor's information is added in pricing requests is sent to Insurance Pricing terminal together.
Insurance Pricing terminal will also determine special medicine corresponding to the pricing requests while obtaining warrantee's information,
Determine the insurance service for needing to buy any class spy's medicine (which class spy's medicine is included in insurance reimbursement range).Really for spy's medicine
It is fixed, it is similar with the acquisition of above-mentioned warrantee's information, it can be Insurance Pricing terminal when receiving pricing requests, to terminal of insuring
Special medicine inquiry message is returned, includes optional special pharmacopoeia class in spy's medicine inquiry message, so that the personnel that insure believe according to the inquiry
Breath is manually entered the special pharmacopoeia class (or by way of selecting menu option) of selection in terminal of insuring and is sent to guarantor
Danger price terminal;Or insurer directly enters the special pharmacopoeia category information of relevant insurance when terminal of insuring carries out and insures and operate,
Insurance spy's pharmacopoeia class of selection is added in special medicine taking out insurances request by terminal of insuring and is sent to Insurance Pricing terminal together.
Insurance Pricing terminal will obtain the expense situation of spy's medicine in the special medicine for determining selection;Wherein special medicine takes
It is to buy the disbursement of spy's medicine with situation, for the expense situation, it is contemplated that the factors such as special medication journey, application method, this
Characterized in embodiment with annual cost per capita (i.e. applicable disease patient normal use spy's medicine of spy's medicine the case where next year needed for
The special medicine buying expenses wanted).For the annual cost per capita of special medicine, it can be and be calculated by special medicine specification information, this is said
Bright letter breath includes application method (instructions of taking);For convenience of description, the annual fee per capita being calculated by specification information
With can be described as " specification per capita annual cost ".Specifically, Insurance Pricing terminal will obtain first insure special medicine illustrate letter
It ceases, including specification unit price, course for the treatment of dosage (box, branch, bottle etc.), course for the treatment of duration (moon, week etc.) etc. in the specification information, such as
Buddhist nun's capsule (hundred million jade-like stones, a kind of special medicine suitable for previously at least receiving a kind of lymphoma mantle cell for the treatment of) is replaced for her cloth,
Specification unit price is 40824 yuan/bottle, 4 bottles of each course for the treatment of dosage, and when each course for the treatment of is 3 months a length of;It was calculated by 12 months within 1 year, then
For the specification of Buddhist nun's capsule, annual cost is specification monovalent (12/ course for the treatment of of course for the treatment of dosage * of annual cost=specification per capita to Yi Bu per capita
Duration)=653184 yuan.
For the annual cost per capita of special medicine, can also be determined with reference to the historical data in other known city;For description
Convenient, this annual cost per capita according to historical data determination can be described as " history per capita annual cost ";Again due to different cities
Attributes all different froms such as weather, landform, the level of consumption, and these attributes may be to the applicable disease disease incidence of special medicine
And/or the data such as annual cost have an impact per capita, therefore the accuracy in order to guarantee its data, be in the present embodiment with reference to
There is the related data in the reference city of similar City attribution to be determined for target cities where warrantee.Specifically, insurance
Price terminal can determine the target cities where warrantee according to obtained warrantee's information.Insurance Pricing terminal is determining target
When city, it will the City attribution information (or for urban characteristic information) for obtaining target cities can be with for the City attribution
Be be defined by multiple latitudes, such as may include longitude and latitude, weather, landform, the level of consumption (the regular period city occupy
It is civilian in the summation for meeting itself daily subsistence item expenditure), crowd characteristic (size of population) etc..Insurance Pricing terminal exists
When obtaining the City attribution information of target cities, the target city will be determined in Urban Data library based on similar city model is preset
The reference city in city;It wherein, include at least two sample cities and each respective sample in sample city in Urban Data library
This attribute (i.e. the City attribution in sample city, for convenience of description, referred to as " sample attribute "), certainly, Urban Data also wraps in library
Special medicine is included in the history annual cost data per capita in the sample city.When determining with reference to city, can obtaining special medicine, this refers to city
The history in city annual cost per capita.
Further, the attribute value (i.e. element) in city can be unified to be indicated with numerical character (certainly for
Different types of attribute value, numberical range can be with different froms), for different types of attribute value, different numberical ranges is then
Different features can be represented, the performance precision of City attribution so can be improved, such as weather, 11-20 is sub- heat
Band weather, 21-30 is temperate climate, and 31-40 is climate of frigid zone;If wherein the attribute value in some city more approaches some numerical value model
The lower limit or the upper limit enclosed, then it is believed that the attribute in the city the similar to the attribute of another numerical value section, for example, weather attribute value is
21 city A, although belonging to temperate climate, it is also contemplated that relatively trend and subtropical climate;In addition, if two city generics
Property value difference it is bigger, then it is believed that two cities differed on the attribute it is bigger and combine relevant diversity factor algorithm calculate city
Between diversity factor, further increase the accuracy of city similarity analysis.Specifically, Urban Data library includes at least two samples
The respective sample attribute group in this city and each sample city, each sample attribute group include at least two elements, and each element
Form is numerical value;When Insurance Pricing terminal obtains determining target cities, it is also necessary to obtain above-mentioned 5 attributes in target cities
Attribute information (longitude and latitude, weather landform, the level of consumption, crowd characteristic), then according to character types of each attribute and each
The attribute is translated to corresponding Numeric Attributes element by the character meaning of attribute type, so that objective attribute target attribute group is obtained, the mesh
With the element with each sample set of properties same number and type, (i.e. objective attribute target attribute group includes same type sum number in mark set of properties
The attribute data of amount);Then Insurance Pricing terminal is respectively by the sample of the objective attribute target attribute group of target cities and other each sample cities
This set of properties is substituting to the attribute difference degree that objective attribute target attribute group and sample attribute group are calculated in default diversity factor formula, and with the category
Sex differernce degree characterizes target cities and sample city difference, and attribute difference degree is smaller, target cities are got over sample city difference
Small namely the two is more similar, and Insurance Pricing terminal can be using the smallest sample city of attribute difference degree as with reference to city.And it presets
Diversity factor formula can be with are as follows:
Wherein, V1 is objective attribute target attribute group, and V2 is the sample attribute group, and d (V1, V2) is objective attribute target attribute group and sample attribute
The diversity factor of group;V1i is i-th of element of the objective attribute target attribute group, and v2i is i-th of element of the sample attribute group, i >
0.It certainly, is all properties elements to be imparted to same calculated specific gravity (specific gravity is for above-mentioned diversity factor formula
1);And in practice, for different property elements, different calculated specific gravities can also be set according to the actual situation, with characterization
Its influence degree to city similarity analysis, so that the analysis can more be bonded actual needs.
In the present embodiment, Insurance Pricing terminal is at the reference city for determining target cities, it will obtains with reference to city
History consumption cost (historical data);The history consumption cost can be in Insurance Pricing terminal and with reference to the hospital in city
System (or medical system), which connects, simultaneously to be acquired, the history consumption cost include with reference to special medicine each in city a certain year (or
Nearest 1 year) history annual total costs, medication number;Ginseng can be calculated according to the history annual total costs, medication number
The history annual cost per capita of each spy's medicine in the city of Kaocheng City, namely:
History annual cost=history annual total costs/number of users per capita.
Certainly, the history that obtains above by historical data annual cost and is obtained by specification information per capita
Specification annual cost per capita belongs to experience and/or predicts the obtained data of scope, therefore can be collectively referred to as prediction per capita
Annual cost;In order to enable subsequent calculated result can tally with the actual situation, it may be incorporated into preset expense loading risks and assumptions
(expense loading risks and assumptions are greater than or equal to zero), the time trend factor (the time trend factor is greater than or equal to zero), with characterization
Next insurance period possible risk situation (such as characterization currency inflation, drug price variation), thus per capita to prediction
Annual cost is adjusted (or amendment), to obtain annual cost per capita;Specifically, can annual cost (be gone through per capita according to above-mentioned prediction
History annual cost or specification annual cost per capita per capita) and expense loading risks and assumptions, the time trend factor, calculate the people of special medicine
Equal annual cost, it may be assumed that
Annual cost=prediction annual cost * (1+ expense loading risks and assumptions) * (the 1+ time trend factor) per capita per capita.
For example, expense loading risks and assumptions take 0.15, and the time trend factor takes when annual cost is 653184 yuan per capita for prediction
When 0, the annual cost per capita for insuring special medicine is
Annual cost=653184* (1+15%) * (1+0)=751161.6 (member) per capita.
In the present embodiment, Insurance Pricing terminal also needs to get the payout schedule of special medicine insurance, which is hair
The compensation standard of insurance institution and explanation (or plan, amount of money etc.) when raw compensation event.For example, the payout schedule includes payout ratio
Example table, shown in table 1 specific as follows
Table 1 compensates ratio table
Amount paid (ten thousand) | Compensation ratio |
No more than 10,000 | 95% |
More than 10,000 to 30,000 part | 95% |
More than 30,000 to 50,000 part | 95% |
Part more than 50,000 | 95% |
It, can be according to the branch when determining event expenditure (expenditure of buying special medicine) of the warrantee when compensation event occurs
Out and above-mentioned compensation ratio meter is calculated and compensates the amount of money.Certainly, in specific implementation, payout schedule can be carries out in other ways
It indicates.
Step S20 believes the various kinds in warrantee's information and default sample population based on default clustering rule
Breath carries out clustering, target information cluster is obtained, wherein the target information cluster includes warrantee's information and target sample
Information.
In the present embodiment, price insures terminal to fix a price, it is also necessary to obtain the probability of compensation event generation, i.e. quilt
Guarantor replaces the probability of Buddhist nun's capsule using her cloth, which, which can be, is characterized with her cloth for the applicable disease disease incidence of Buddhist nun's capsule.And it is right
It is to choose and protected in order to more be bonded the actual conditions of warrantee, in the present embodiment in the determination for being applicable in disease disease incidence
People has the target group of similar features as analysis object, is applicable in applicable disease of the disease in the target group using spy's medicine and sends out
Sick rate carries out Insurance Pricing.Specifically, being previously stored with sample population information, the sample in Insurance Pricing terminal or in database
Include in this crowd information each sample people sample people information (in the sample population include at least two sample people, and point
Respective sample people information is not corresponded to), these samples people information is similar with warrantee's information, including someone's name, gender, year
Target cities, height where age, warrantee, weight, medical history, furthermore sample people information further includes having special medicine to be applicable in disease
Disease condition (whether with the applicable disease of spy's medicine).For these samples people's information can be by history insurance data or its
The Medical Data of its medical system is configured.Insurance Pricing terminal by based on certain clustering rule to warrantee's information and
Sample people's information carries out clustering, to search warrantee's information sample people information cluster similar with feature in same letter
It ceases in cluster, which can be described as target information cluster, which includes warrantee's information and target sample information, for
The target sample information is to be considered that warrantee has sample people's information of the target sample people of similar features.
Further, for the process of the clustering, it can be and realized by way of K mean cluster (K-Means)
's.Specifically, firstly the need of according to a certain amount rule by warrantee's information quantization be corresponding warrantee's set of coordinates (or
For Vector Groups, information character group etc.), wherein each coordinate in warrantee's set of coordinates can be unified to use for the convenience of subsequent cluster
Numerical character is indicated, and certainly for different types of attribute value, numberical range can be with different from.Such as warrantee
In information, including age and weight, this two directly directly can quantify pair in set of coordinates according to age (year) and weight (kg)
Answer coordinate;The weather in city where further including in warrantee's information, such as weather, the number of set of coordinates mesoclimate coordinate
Value 11-20 is subtropical climate, and 21-30 is temperate climate, and 31-40 is climate of frigid zone, if the attribute value in some city more approaches
The lower limit or the upper limit of some numberical range are carrying out then it is believed that the attribute in the city the similar to the attribute of another numerical value section
It can be corresponding numeric type weather coordinate by this warrantee's information quantization according to climatic condition when quantization.It is worth noting that
For warrantee's set of coordinates, dimension can be to be configured according to the actual situation, such as can be two-dimensional coordinate group, may be used also
Be three-dimensional or more (herein " and more than " include this number, similarly hereinafter) higher-dimension set of coordinates.Similar, for each sample of sample population
People's information can also be quantified as corresponding sample people set of coordinates, and the dimension of sample people's set of coordinates and warrantee according to aforesaid way
The dimension of set of coordinates is consistent.
When set of coordinates quantifies to complete, Insurance Pricing terminal can be selected at random in warrantee's set of coordinates and sample people's set of coordinates
More than two set of coordinates are selected as initial cluster center;The wherein letter of the quantity of the initial cluster center namely cluster process
Cease number of clusters amount.When determining initial cluster center, will calculate the set of coordinates at each initial clustering and each non-initial center it is initial away from
From (can be with a distance from this indicates in several ways, such as Euclidean distance, manhatton distance, Chebyshev's distance etc.).For example,
By taking two-dimensional coordinate group (including XY coordinate) as an example, warrantee's set of coordinates is P1, sample for warrantee's set of coordinates and sample people set of coordinates
People's group table group includes P2, P3, P4, P5, P6, the coordinate of each set of coordinates such as the following table 2
The coordinates table of 2 set of coordinates of table
X | Y | |
P1 | 0 | 0 |
P2 | 1 | 2 |
P3 | 3 | 1 |
P4 | 8 | 8 |
P5 | 9 | 10 |
P6 | 10 | 7 |
In 6 above-mentioned set of coordinates, two set of coordinates of P1 and P2 are chosen as initial cluster center;Then it can calculate
The initial distance with P3, P4, P5, P6, the initial distance are identified respectively with Euclidean distance by P1, P2, namely
Wherein, XInFor the X-coordinate of initial cluster center, YInFor the Y-coordinate of initial cluster center;XnFor n-th of set of coordinates
X-coordinate, YnFor the X-coordinate of n-th of set of coordinates, n is greater than 0;DnFor the Euclidean distance of initial cluster center and n-th of set of coordinates.
According to coordinates table shown in above-mentioned formula and table 2, the initial of P1 and P2 and each non-initial centre coordinate group can be obtained
Distance, as shown in table 3 below
The initial distance table of 3 initial cluster center of table and each non-initial centre coordinate group
P1 | P2 | |
P3 | 3.16 | 2.24 |
P4 | 11.3 | 9.22 |
P5 | 13.5 | 11.3 |
P6 | 12.2 | 10.3 |
When obtaining the initial distance of each initial cluster center and each non-initial centre coordinate group, that is, can determine each initial poly-
The corresponding initial clustering set of coordinates in class center, and to each non-initial centre coordinate group, it also will be in closer initial clustering
The heart is as oneself cluster target, to obtain initial clustering cluster.P3, P4, P5, P6 as escribed above, distance P2 is closer, therefore
Initial clustering cluster where P1 only includes mono- set of coordinates of P1, and the initial clustering cluster where P2 includes P2, P3, P4, P5, P6 five
Set of coordinates.
When obtaining initial clustering cluster, can be determined in secondary cluster in each initial clustering cluster by certain election algorithm
The heart, which can be is determined by way of coordinate mean value computation.And in secondary cluster centre, with initial clustering
The heart is slightly different, i.e., the secondary cluster centre can be virtual set of coordinates.For example, for the initial clustering where above-mentioned P1
Cluster, secondary cluster centre are PIn 21(0,0), also as P1;For the initial clustering cluster where P2, secondary cluster centre is
PIn 22For ((1+3+8+9+10)/5, (2+1+8+10+7)/5) namely PIn 22(6.2,5.6), the PIn 22For virtual set of coordinates.?
When determining secondary cluster centre, the secondary range of each secondary cluster centre and the secondary centre coordinate group of Ge Fei will be calculated separately, is counted
Calculation process is similar with initial distance calculating, and obtained secondary range is as shown in table 3 below:
The secondary range table of 3 two cluster centres of table and each non-secondary centre coordinate group
PIn 21(P1) | PIn 22 | |
P2 | 2.24 | 6.3 |
P3 | 3.16 | 5.6 |
P4 | 11.3 | 3 |
P5 | 13.5 | 5.2 |
P6 | 12.2 | 4.0 |
When obtaining the secondary range of secondary beginning cluster centre and each non-secondary centre coordinate group, that is, can determine each secondary poly-
The corresponding secondary cluster set of coordinates in class center, to obtain secondary clustering cluster.P2, P3 as escribed above, distance PIn 21(i.e. P1) more
Closely;And P4, P5, P6, distance PIn 22It is closer;Therefore PIn 21The secondary clustering cluster at place only includes tri- set of coordinates of P1, P2, P3,
PIn 22The secondary clustering cluster at place includes tri- set of coordinates of P4, P5, P6.
When obtaining secondary clustering cluster, Insurance Pricing terminal can gather the cluster situation of the secondary clustering cluster with previous
The cluster situation of class cluster (i.e. initial clustering cluster) is compared, and judges whether the two is consistent.If consistent, it is believed that cluster is received
It holds back, i.e., cluster is completed, and the clustering cluster where warrantee's set of coordinates P1 can be determined as target information cluster at this time, the target information cluster
Including sample people's information be target sample information, sample people corresponding to these target sample information be with warrantee have
There is the people of similar characteristics, crowd composed by sample people can be described as target group.And if the two is inconsistent, it is believed that cluster not
Convergence needs again to be iterated in cluster, namely the cluster three times of determining each secondary clustering cluster secondary clustering cluster at this time, and
The distance three times of cluster centre and each non-group of centre coordinate three times three times is calculated, and distance acquisition is corresponding three times three times according to this
Clustering cluster, then judge clustering cluster three times set of coordinates classification situation and preceding primary (i.e. secondary clustering cluster) classification situation whether
Unanimously;If consistent, clustering convergence can determine target information cluster at this time;If inconsistent, continue iteration cluster;So
Circulation directly restrains, and determines target information cluster.
Step S30 determines target group according to the target sample information in the default sample population, and obtains institute
That states special medicine is applicable in disease in the applicable disease disease incidence of the target group.
In the present embodiment, Insurance Pricing terminal, can be according to target sample information therein when obtaining target information cluster
Determine that target group, the target group are regarded as the crowd for having similar features with warrantee in default sample population.This
When Insurance Pricing terminal will determine crowd's quantity of the target group, and determine applicable disease with special medicine in the target group
Number of patients;Then it is sent out according to the disease that is applicable in that crowd's quantity and number of patients can calculate special medicine in the applicable disease of target group
Sick rate, namely
It is applicable in disease disease incidence=target group number of patients/target group crowd's quantity.
Step S40, according to the annual cost per capita, the applicable disease disease incidence and the payout schedule measuring and calculating special medicine
The year risk premium of insurance, and the hair of year per capita that the special medicine insures is calculated according to the year risk premium and default Management plan
Premium.
It, can be according to above-mentioned annual cost per capita, applicable disease morbidity when obtaining the applicable disease disease incidence in the present embodiment
Rate and payout schedule carry out Insurance Pricing, calculate the year risk premium of special medicine insurance.Specifically, can be first according to the annual cost per capita
Compensating in estimated year per capita for special medicine, which is obtained, with payout schedule (pays the number to need to compensate when annual cost per capita warrantee's year
Volume);For example, may include compensation ratio table as shown in Table 1 above for payout schedule, and special medicine her cloth is for Buddhist nun's capsule
Annual cost is 653184 yuan per capita, then her cloth is for compensating in estimated year per capita for Buddhist nun's capsule
It is expected that year compensation=(10000-0) * 0.95+ (30000-10000) * 0.95+ (50000-30000) * 0.95+ per capita
(653184-50000) * 0.95=620524.8 (member).
It is obtaining insuring when compensating in estimated year per capita of special medicine, can compensate in year per capita on the estimation and applicable disease disease incidence meter
It calculates and obtains the year risk premium of special medicine insurance, it may be assumed that
Special medicine risk premium=estimated * that compensates per capita is applicable in disease disease incidence.
In the present embodiment, special medicine has been arrived when obtaining year risk premium and has insured expenditure in terms of warrantee's compensation
Data, and for the price of special medicine insurance, it is also necessary to consider the factors such as operation expenditure and the profit of insurance institution.Specifically, protecting
Danger price terminal also needs to obtain default Management plan, and the people of special medicine insurance is calculated according to default Management plan and year risk premium
Equal year gross premium;The default Management plan can be the data being set in advance in financial system or operation system, Insurance Pricing
Terminal is obtained from the financial system or operation system fixing a price;Can certainly be stored in advance in Insurance Pricing terminal
In.Wherein, default Management plan may include default operation cost per capita, default expenses of taxation ratio and default profit margin;Per capita
Operation cost provides the operation cost (including system cost, human cost etc.) when insurance service for each warrantee;Default tax
Expense ratio is the ratio of paying taxes of premium;Default profit margin then characterizes the estimated profit situation of insurance institution.It is protected obtaining year risk
When taking, presetting operation cost, default expenses of taxation ratio and default profit margin per capita, Insurance Pricing terminal can be carried it into default hair
In premium formula, the year gross premium per capita of special medicine insurance is calculated, presets gross premium formula are as follows:
Wherein, F is the year gross premium per capita;
R is the year risk premium, R > 0;
C is the default operation cost per capita, C > 0;
T is the default expenses of taxation ratio, 0 < T < 1;
Pr is the default profit margin, 0 < pr < 1.
In the present embodiment, Insurance Pricing terminal completes spy when the gross premium of year per capita of special medicine insurance is calculated
The price-setting process of medicine insurance.
Further, Insurance Pricing terminal can also generate correspondence after the year gross premium per capita for obtaining special medicine insurance
Price report, so that related personnel checks.Specifically, being previously stored with report template in Insurance Pricing terminal;Insurance
Terminal of fixing a price can record relevant pricing data during price;Wherein pricing data include input data (such as
Special pharmacopoeia class, warrantee's information), data source (such as historical data, specification information), intermediate data (such as annual cost per capita, pre-
Meter per capita compensate by year) and output data (such as per capita year gross premium) recorded;When fixing a price completion, Insurance Pricing terminal will be mentioned
This report template is taken, and these data are filled into report template, obtains price report, and price report is deposited
Storage, or price report is sent to insure terminal or when that price report is sent to relevant service security is whole
End, so that relevant service security personnel are monitored service security.
In the present embodiment, when receiving the pricing requests of special medicine insurance, obtains the pricing requests and correspond to warrantee's
Warrantee's information, and obtain the annual cost per capita of the corresponding special medicine of special medicine insurance and the payout schedule of the special medicine insurance;
Clustering is carried out to the various kinds information in warrantee's information and default sample population based on default clustering rule, is obtained
Target information cluster is taken, wherein the target information cluster includes warrantee's information and target sample information;According to the target
Sample information determines target group in the default sample population, and obtains the applicable disease of the special medicine in the target group
Applicable disease disease incidence;According to the annual cost per capita, the applicable disease disease incidence and the payout schedule measuring and calculating special medicine
The year risk premium of insurance, and the hair of year per capita that the special medicine insures is calculated according to the year risk premium and default Management plan
Premium.By the above-mentioned means, the special medicine that the present embodiment refers to the target group for having similar features with warrantee is applicable in disease morbidity
Rate, and multiple influence factors such as the special medicine cost of use of combination, operation cost calculate the gross premium of special medicine insurance plans, with big data
The mode of analysis processing fixes a price to special medicine insurance plan, to more fully consider special medicine insurance plan price
Factor enables price result more to meet the actual conditions of warrantee and the true operation situation of insurance institution, improves
The reasonability and accuracy of price, advantageously reduce the operation cost of insurance plan.
Based on above-mentioned embodiment illustrated in fig. 2, propose that the present invention is based on the second embodiments of the Insurance Pricing method of big data.
In the present embodiment, after step S40 further include:
Corresponding special medicine insurance policy and payment link are generated according to the gross premium of year per capita, and by the payment link
It is sent to corresponding terminal of insuring, for completing the payment of the special medicine insurance policy.
In the present embodiment, Insurance Pricing terminal, can be according to this per capita when obtaining the gross premium of year per capita of special medicine insurance
The corresponding special medicine insurance policy of year gross premium generation.Certainly, which further includes the essential information of warrantee, such as surname
Name, address, contact method etc., Insurance Pricing terminal will additionally generate corresponding payment chain while generating special medicine insurance policy
It connects, and the payment link is back to terminal of insuring.Terminal of insuring can show special medicine insurance when receiving the payment link
The generated prompt of declaration form, and show the payment link for personnel's pay-per-click of insuring.The personnel that insure are clicked in terminal insuring
After opening the payment link, payment interface can be entered, believe the product for showing this special medicine insurance policy in the payment interface
It ceases and (insures special medicine), the gross premium information of year per capita of required payment, and show the different types of selective (example of means of payment option
Such as bank card, Third-party payment platform), the personnel of insuring can be chosen according to their own situation suitable mode, pay into correlation
Interface inputs account information to pay.Wherein, if the personnel that insure are paid by way of bank card, the personnel that insure are being propped up
When paying successfully, bank Fang Huixiang Insurance Pricing terminal sends relevant notice of transferring accounts;Insurance Pricing terminal is transferred accounts receiving this
When notice, that is, think that declaration form completes payment, then can send corresponding payment successful information to terminal of insuring;And Third-party payment is flat
The payment detection of platform is similar with the detection of bank card, and details are not described herein again.
When detecting that the special medicine insurance policy completes payment, if receiving special pharmacology pays for request, obtain corresponding
Claims Review information, and the Claims Review information is audited based on default Claims Resolution rule, to judge that the special pharmacology is paid for
Whether request reasonable.
In the present embodiment, Insurance Pricing terminal is when detecting that special medicine insurance policy completes payment, i.e., it is believed that being completed
It insures operation, and provides corresponding special medicine insurance service for warrantee.Hereafter, if there is Claims Resolution event, (warrantee's illness is simultaneously
Have purchased the insurance spy medicine arranged in special medicine insurance), then warrantee (or insurer or beneficiary) can be by a Claims Resolution eventually
End (the Claims Resolution terminal can be PC PC, laptop, mobile phone etc.) carries out Claims Resolution operation, and then basis should for Claims Resolution terminal
Claims Resolution operation sends corresponding special pharmacology to Insurance Pricing terminal and pays for request.Insurance Pricing terminal receive spy's pharmacology compensation ask
When asking, it will obtain corresponding Claims Review information, and judge whether spy's pharmacology pays for request reasonable based on default Claims Resolution rule.
It is worth noting that generally require to determine the illness record of warrantee, medical treatment situation, prescription record etc. when being settled a claim, and
For different insurance spy's medicines, since it is applicable in disease difference, illness Claims Review data may there is also differences, therefore, protect
Danger price terminal can be the Claims Review that corresponding types are obtained according to the type for insuring special medicine when obtaining Claims Review information
Information.
Optionally, it when being audited to Claims Review information, judging whether Claims Resolution request is reasonable, can be from multiple dimensions
Degree is audited, such as can audit whether medication suits the medicine to the illness.Specifically, Insurance Pricing terminal can be obtained from Claims Review acquisition of information
It is recorded to medical diagnosis on disease, includes warrantee in medical diagnosis on disease record in disease of diagnosing a disease really given by Shi doctor of going to a doctor;Then
Insurance Pricing terminal will acquire the applicable disease information for insuring special medicine, and whether the disease that judges to diagnose a disease really in medical diagnosis on disease record belongs to
Insure the applicable disease of special medicine;For example, being mainly used for treating the transfer of HER2 overexpression for special medicine injection Herceptin
Property breast cancer (HER2 overexpression is defined as IHC3+ the or IHC2+/FISH+ result that obtains using the detection method having verified that),
Insurance Pricing terminal audit when need according to medical diagnosis on disease record judge whether warrantee make a definite diagnosis illness whether belong to it is above-mentioned
It is applicable in disease;If this, which makes a definite diagnosis illness, belongs to the applicable disease for insuring special medicine, it is believed that it is reasonable that spy's pharmacology, which pays for request,;And if should
It makes a definite diagnosis illness to be not belonging to insure the applicable disease of special medicine, then may be the behavior that warrantee has false reimbursement, fraud insurance fraud, at this time
It is believed that it is unreasonable that spy's pharmacology, which pays for request,.
Optionally, when being audited to Claims Review information, judging whether Claims Resolution request is reasonable, it can also be audit quilt
Whether the medicinal dose of spy of guarantor is normal.Specifically, Insurance Pricing terminal can obtain special medicine purchase from Claims Review acquisition of information
Record can determine that the actual purchase amount of warrantee's medicine special for insurance according to spy's medicine purchaser record;Meanwhile Insurance Pricing is whole
End can also obtain the specification information for insuring special medicine, and theoretical the using of the special medicine of insurance is calculated according to the specification information
Amount,;Then, Insurance Pricing terminal can compare theoretical usage amount and actual purchase amount, be judged according to theoretical usage amount real
Whether border purchase volume is abnormal, if actual purchase amount is not more than theoretical usage amount, (or actual purchase amount is not more than theoretical usage amount
Presupposition multiple), then it is believed that the actual purchase amount is normal, it is thus regarded that spy's pharmacology pays for request rationally;And if actual purchase amount
Greater than theoretical usage amount (or actual purchase amount is greater than presupposition multiple of theoretical usage amount), then it is believed that the actual purchase amount is different
Often, which may be that warrantee causes in the presence of the behavior of false purchase medicine, and Insurance Pricing terminal is believed that spy's pharmacology is paid at this time
It requests unreasonable.
Worth explanation yes, is illustrated for above two audit, be may be used in combination in specific implementation, such as first judgement is used
Whether medicine suits the medicine to the illness, and judges whether purchase dose is normal again when medication is suited the medicine to the illness;When medication is suited the medicine to the illness and purchase dose is normal, just think special
It is reasonable that pharmacology pays for request.Certainly, (whether can also be deposited from the reasonability that other aspects pay for request to special pharmacology in specific implementation
In insurance fraud) it is audited.
If spy's pharmacology pays for request rationally, is sent to corresponding financial system and suggest compensating information.
In the present embodiment, Insurance Pricing terminal is after auditing Claims Review information, if no abnormal information is (such as
Fraud, insurance fraud etc.), it is believed that spy's pharmacology pays for request rationally, then Insurance Pricing terminal will send to associated financial system and suggest
Information is compensated, is carried out at corresponding compensation so that financial system (or relevant financial personnel) compensates information according to the suggestion
Reason.Certainly, it is operated for convenience of subsequent compensation, Insurance Pricing terminal also when judging that special pharmacology compensation request is reasonable, is examined from Claims Resolution
Special medicine disbursement is obtained in nuclear information, then the payout schedule according to special medicine support cost and step S10 is calculated
Compensation expense;When obtaining compensation expense, corresponding suggestions compensation information can be generated according to the compensation expense, and by the suggestion
It compensates information and is sent to financial system, compensated so as to obtain financial system according to the compensation expense.In addition, the suggestion is compensated
It can also include other contents in information, the msu message of request, associated policy information etc. are paid for for example including special pharmacology.And
In specific implementation, if Insurance Pricing terminal, after auditing to Claims Review information, if noting abnormalities, (such as medicine is not suited the medicine to the illness, is purchased
Dose exception etc.), it is believed that spy's pharmacology compensation request is unreasonable, then can return to the processing information for refusing to settle a claim to Claims Resolution terminal, again
It is either sent to relevant review terminal and suggests review information, carried out so that related reviewing officer pays for request to spy's pharmacology
Review.
In the present embodiment, after client carries out special medicine taking out insurances, the Claims Resolution can also be examined by preset Claims Resolution rule
Nuclear information is audited automatically, to realize intelligent and automation settlement of insurance claim, improves the service of special medicine settlement of insurance claim
Efficiency also helps reduction human cost.
In addition, the embodiment of the present invention also provides a kind of Insurance Pricing device based on big data.
It is that the present invention is based on the signals of the functional module of the Insurance Pricing device first embodiment of big data referring to Fig. 3, Fig. 3
Figure.
In the present embodiment, the Insurance Pricing device includes:
Data obtaining module 10, for it is corresponding to obtain the pricing requests when receiving the pricing requests of special medicine insurance
Warrantee's information of warrantee, and obtain the annual cost per capita and the special medicine insurance of the corresponding special medicine of special medicine insurance
Payout schedule;
Information cluster module 20, for based on default clustering rule in warrantee's information and default sample population
Various kinds information carries out clustering, target information cluster is obtained, wherein the target information cluster includes warrantee's information
With target sample information;
Crowd's determining module 30, for determining target person in the default sample population according to the target sample information
Group, and obtain the special medicine is applicable in disease in the applicable disease disease incidence of the target group;
Gross premium calculates module 40, for according to annual cost, the applicable disease disease incidence and the compensation side per capita
Case calculates the year risk premium of the special medicine insurance, and according to the year risk premium and the measuring and calculating of default the Management plan special medicine
The year gross premium per capita of insurance.
Wherein, each virtual functions module of the above-mentioned Insurance Pricing device based on big data is stored in shown in Fig. 1 based on big
It is functional for realizing the institute of Insurance Pricing program in the memory 1005 of the Insurance Pricing equipment of data;Each module is processed
, it can be achieved that the intelligent pricing function of special medicine insurance plan when device 1001 executes.
Further, crowd's determining module 30 includes:
Expense acquiring unit, for obtaining the specification information of the special medicine, according to specification information measuring and calculating
The annual cost per capita of special medicine;
Or, for determining the target cities where the warrantee according to warrantee's information, and it is similar based on presetting
City model determines the reference city of the target cities in Urban Data library, to obtain the special medicine described with reference to city
Annual cost per capita.
Further, crowd's determining module 30 includes:
Number determination unit for determining crowd's quantity of the target group, and is determined and is suffered from the target group
The number of patients for being applicable in disease of spy's medicine;
Disease incidence calculates unit, for calculating the applicable disease of the special medicine according to crowd's quantity and number of patients in institute
State the applicable disease disease incidence of target group.
Further, the default Management plan includes default operation cost per capita, default expenses of taxation ratio and default profit
Rate,
The gross premium calculates module 40, be specifically used for according to the year risk premium, the default operation cost per capita,
The special medicine insurance plan is calculated per capita in the default expenses of taxation ratio, the default profit margin and default gross premium formula
Year gross premium, wherein the default gross premium formula are as follows:
Wherein, F is the year gross premium per capita;
R is the year risk premium, R > 0;
C is the default operation cost per capita, C > 0;
T is the default expenses of taxation ratio, 0 < T < 1;
Pr is the default profit margin, 0 < pr < 1.
Further, the Insurance Pricing device further include:
Declaration form generation module, for generating corresponding special medicine insurance policy and payment chain according to the year gross premium per capita
It connects, and the payment link is sent to corresponding terminal of insuring, for completing the payment of the special medicine insurance policy;
Judgment module is requested, for being paid for if receiving special pharmacology when detecting that the special medicine insurance policy completes payment
Request is then obtained corresponding Claims Review information, and is audited based on default Claims Resolution rule to the Claims Review information, with
Judge whether the special pharmacology pays for request reasonable;
Information sending module sends to corresponding financial system if paying for request rationally for the special pharmacology and suggests paying for
Pay information.
Further, the information sending module includes:
Measuring and calculating unit is compensated, it is special according to the Claims Review acquisition of information if paying for request rationally for the special pharmacology
Medicine disbursement, and compensation expense is calculated according to the special medicine disbursement and the payout schedule;
Information transmitting unit, for generating corresponding suggestions compensation information according to the compensation expense, and by the suggestion
It compensates information and is sent to corresponding financial system.
Further, the information cluster module 20 includes:
Information quantization unit, for being corresponding warrantee seat according to quantizing rule is preset by warrantee's information quantization
Mark group, by the various kinds information quantization be corresponding sample people set of coordinates;
First computing unit, it is more than two for being randomly selected in warrantee's set of coordinates and sample people's set of coordinates
Set of coordinates as initial cluster center, and calculate separately each initial cluster center and each non-initial centre coordinate group it is initial away from
From;
First obtains unit, for being determined according to the initial distance of each initial cluster center and each non-initial centre coordinate group
The corresponding initial clustering set of coordinates of each initial cluster center, and it is corresponding according to each initial cluster center and each initial cluster center
Initial clustering set of coordinates obtains initial clustering cluster;
Second computing unit, for determining secondary cluster centre in each initial clustering cluster based on default election algorithm, and
Calculate separately the secondary range of each initial cluster center Yu each non-secondary centre coordinate group;
Second obtaining unit, for being determined according to the secondary range of each secondary cluster centre and each non-secondary centre coordinate group
The corresponding secondary cluster set of coordinates of each secondary cluster centre, and it is corresponding according to each secondary cluster centre and each secondary cluster centre
Secondary cluster set of coordinates obtains secondary clustering cluster;
Cluster judging unit, for judge each secondary clustering cluster and each initial clustering cluster coordinate group cluster situation whether one
It causes;
Informational cluster determination unit, if being determined as the secondary clustering cluster where warrantee's set of coordinates for consistent
Target information cluster;
Iteration cluster cell, if being iterated cluster to the secondary clustering cluster for inconsistent, until what is obtained changes
It is consistent with the set of coordinates of preceding clustering cluster classification situation for clustering cluster, and the iteration where warrantee's set of coordinates is clustered
Cluster is determined as target information cluster.
Wherein, the function of modules is realized with above-mentioned based on big data in the above-mentioned Insurance Pricing device based on big data
Insurance Pricing embodiment of the method in each step it is corresponding, function and realization process no longer repeat one by one here.
In addition, the embodiment of the present invention also provides a kind of readable storage medium storing program for executing.
Insurance Pricing program is stored on readable storage medium storing program for executing of the present invention, wherein the Insurance Pricing program is held by processor
When row, realize such as the step of the above-mentioned Insurance Pricing method based on big data.
Wherein, Insurance Pricing program, which is performed realized method, can refer to Insurance Pricing the present invention is based on big data
Each embodiment of method, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
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 storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of Insurance Pricing method based on big data, which is characterized in that the Insurance Pricing method includes:
When receiving the pricing requests of special medicine insurance, obtains the pricing requests and correspond to warrantee's information of warrantee, and obtain
The special medicine is taken to insure the annual cost per capita of corresponding special medicine and the payout schedule of the special medicine insurance;
Cluster point is carried out to the various kinds information in warrantee's information and default sample population based on default clustering rule
Analysis obtains target information cluster, wherein the target information cluster includes warrantee's information and target sample information;
Target group is determined in the default sample population according to the target sample information, and obtains being applicable in for the special medicine
Applicable disease disease incidence of the disease in the target group;
According to the annual cost per capita, described it is applicable in disease disease incidence and the payout schedule calculates the year risk of the special medicine insurance
Premium, and the year gross premium per capita that the special medicine insures is calculated according to the year risk premium and default Management plan.
2. Insurance Pricing method as described in claim 1, which is characterized in that the acquisition special corresponding special medicine of medicine insurance
The step of annual cost includes: per capita
The specification information for obtaining the special medicine calculates the annual cost per capita of the special medicine according to the specification information;
Or, determining the target cities where the warrantee according to warrantee's information, and it is based on presetting similar city model
Determine the reference city of the target cities, in Urban Data library to obtain the special medicine in the year per capita with reference to city
Expense.
3. Insurance Pricing method as described in claim 1, which is characterized in that the applicable disease for obtaining the special medicine is described
The step of applicable disease disease incidence of target group includes:
It determines crowd's quantity of the target group, and determines the illness for being applicable in disease with the special medicine in the target group
Number;
It is fallen ill according to the disease that is applicable in that crowd's quantity and number of patients calculate the special medicine in the applicable disease of the target group
Rate.
4. Insurance Pricing method as described in claim 1, which is characterized in that the default Management plan includes presetting to transport per capita
Cost, default expenses of taxation ratio and default profit margin are sought,
The step of gross premium of year per capita that the special medicine insurance is calculated according to the year risk premium and default Management plan
Include:
According to the year risk premium, the default operation cost per capita, the default expenses of taxation ratio, the default profit margin and
The year gross premium per capita of the special medicine insurance plan is calculated in default gross premium formula, wherein the default gross premium formula
Are as follows:
Wherein, F is the year gross premium per capita;
R is the year risk premium, R > 0;
C is the default operation cost per capita, C > 0;
T is the default expenses of taxation ratio, 0 < T < 1;
Pr is the default profit margin, 0 < pr < 1.
5. Insurance Pricing method as described in claim 1, which is characterized in that the annual cost, described suitable per capita according to
The year risk premium of the special medicine insurance is calculated with disease disease incidence and the payout schedule, and according to the year risk premium and in advance
If Management plan was calculated after the step of gross premium of year per capita of the special medicine insurance, further includes:
Corresponding special medicine insurance policy and payment link are generated according to the gross premium of year per capita, and the payment link is sent
To corresponding terminal of insuring, for completing the payment of the special medicine insurance policy;
When detecting that the special medicine insurance policy completes payment, if receiving special pharmacology pays for request, corresponding Claims Resolution is obtained
Msu message, and the Claims Review information is audited based on default Claims Resolution rule, to judge that the special pharmacology pays for request
Whether rationally;
If spy's pharmacology pays for request rationally, is sent to corresponding financial system and suggest compensating information.
6. Insurance Pricing method as claimed in claim 5, which is characterized in that if spy's pharmacology pays for request rationally,
It is sent to corresponding financial system and suggests that the step of compensating information includes:
If spy's pharmacology pays for request rationally, according to the Claims Review acquisition of information spy medicine disbursement, and according to described
Special medicine disbursement and the payout schedule calculate compensation expense;
Corresponding suggestion is generated according to the compensation expense and compensates information, and suggestion compensation information is sent to corresponding wealth
Business system.
7. such as Insurance Pricing method described in any one of claims 1 to 6, which is characterized in that described based on default cluster rule
Clustering then is carried out to the sample population information of warrantee's information and default sample population, obtains the step of target information cluster
Suddenly include:
According to default quantizing rule by warrantee's information quantization be corresponding warrantee's set of coordinates, by the various kinds letter
Breath is quantified as corresponding sample people set of coordinates;
More than two set of coordinates are randomly selected as in initial clustering in warrantee's set of coordinates and sample people's set of coordinates
The heart, and calculate separately the initial distance of each initial cluster center Yu each non-initial centre coordinate group;
Determine that each initial cluster center is corresponding with the initial distance of each non-initial centre coordinate group according to each initial cluster center
Initial clustering set of coordinates, and obtained just according to each initial cluster center and the corresponding initial clustering set of coordinates of each initial cluster center
Beginning clustering cluster;
Secondary cluster centre is determined in each initial clustering cluster based on default election algorithm, and calculates separately each initial cluster center
With the secondary range of each non-secondary centre coordinate group;
Determine that each secondary cluster centre is corresponding with the secondary range of each non-secondary centre coordinate group according to each secondary cluster centre
Secondary cluster set of coordinates, and two are obtained according to the corresponding secondary cluster set of coordinates of each secondary cluster centre and each secondary cluster centre
Secondary clustering cluster;
Judge whether each secondary clustering cluster is consistent with the coordinate group cluster situation of each initial clustering cluster;
If consistent, the secondary clustering cluster where warrantee's set of coordinates is determined as target information cluster;
If inconsistent, cluster is iterated to the secondary clustering cluster, until obtained iteration clustering cluster and preceding primary cluster
The set of coordinates classification situation of cluster is consistent, and the iteration clustering cluster where warrantee's set of coordinates is determined as target information cluster.
8. a kind of Insurance Pricing device based on big data, which is characterized in that the Insurance Pricing device includes:
Data obtaining module, for obtaining the pricing requests and corresponding to warrantee when receiving the pricing requests of special medicine insurance
Warrantee's information, and obtain the annual cost per capita of the corresponding special medicine of special medicine insurance and the compensation side of the special medicine insurance
Case;
Information cluster module, for based on default clustering rule to each sample in warrantee's information and default sample population
People's information carries out clustering, target information cluster is obtained, wherein the target information cluster includes warrantee's information and target
Sample information;
Crowd's determining module, for determining target group in the default sample population according to the target sample information, and
Obtain the special medicine is applicable in disease in the applicable disease disease incidence of the target group;
Gross premium calculates module, for according to the annual cost per capita, the applicable disease disease incidence and payout schedule measuring and calculating
The year risk premium of spy's medicine insurance, and the special medicine insurance is calculated according to the year risk premium and default Management plan
Year gross premium per capita.
9. a kind of Insurance Pricing equipment based on big data, which is characterized in that the Insurance Pricing equipment includes processor, storage
Device and it is stored in the Insurance Pricing program that can be executed on the memory and by the processor, wherein the Insurance Pricing
When program is executed by the processor, the Insurance Pricing side based on big data as described in any one of claims 1 to 7 is realized
The step of method.
10. a kind of readable storage medium storing program for executing, which is characterized in that Insurance Pricing program is stored on the readable storage medium storing program for executing, wherein
When the Insurance Pricing program is executed by processor, the guarantor based on big data as described in any one of claims 1 to 7 is realized
The step of dangerous pricing method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811529190.0A CN109636638A (en) | 2018-12-13 | 2018-12-13 | Insurance Pricing method, apparatus, equipment and readable storage medium storing program for executing based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811529190.0A CN109636638A (en) | 2018-12-13 | 2018-12-13 | Insurance Pricing method, apparatus, equipment and readable storage medium storing program for executing based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109636638A true CN109636638A (en) | 2019-04-16 |
Family
ID=66073849
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811529190.0A Pending CN109636638A (en) | 2018-12-13 | 2018-12-13 | Insurance Pricing method, apparatus, equipment and readable storage medium storing program for executing based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109636638A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110084641A (en) * | 2019-04-17 | 2019-08-02 | 新地能源工程技术有限公司 | Gas works design pricing method and device and management equipment and storage medium |
CN111128353A (en) * | 2019-11-20 | 2020-05-08 | 泰康保险集团股份有限公司 | Method and device for monitoring medicine selling behaviors of fixed-point pharmacy and storage medium |
-
2018
- 2018-12-13 CN CN201811529190.0A patent/CN109636638A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110084641A (en) * | 2019-04-17 | 2019-08-02 | 新地能源工程技术有限公司 | Gas works design pricing method and device and management equipment and storage medium |
CN111128353A (en) * | 2019-11-20 | 2020-05-08 | 泰康保险集团股份有限公司 | Method and device for monitoring medicine selling behaviors of fixed-point pharmacy and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109615536A (en) | Settlement of insurance claim method, apparatus, equipment and readable storage medium storing program for executing based on OCR technique | |
CN109636632A (en) | Settlement of insurance claim method, apparatus, equipment and storage medium based on machine learning | |
US20090204446A1 (en) | Systems and methods for valuation of life insurance policies | |
US11030581B2 (en) | Medical claims lead summary report generation | |
US20140297306A1 (en) | System and method for detecting drug fraud and abuse | |
US20080288298A1 (en) | Method and system for providing low-cost life insurance | |
Brot-Goldberg et al. | Rationing medicine through bureaucracy: authorization restrictions in medicare | |
Nandi et al. | Using an equity-based framework for evaluating publicly funded health insurance programmes as an instrument of UHC in Chhattisgarh State, India | |
US20140288958A1 (en) | Healthcare point of service adjudication and payment system | |
Woldemichael et al. | Community-based health insurance and out-of-pocket healthcare spending in africa: evidence from Rwanda | |
CN109636638A (en) | Insurance Pricing method, apparatus, equipment and readable storage medium storing program for executing based on big data | |
CN109685557A (en) | Insurance Pricing method, apparatus, equipment and readable storage medium storing program for executing based on big data | |
Coffey | Casemix information in the United States: fifteen years of management and clinical experience | |
US8429113B2 (en) | Framework and system for identifying partners in nefarious activities | |
Cantor et al. | The response of substance use disorder treatment providers to changes in macroeconomic conditions | |
Colón | Creating a patient-centered, global, decentralized health system: combining new payment and care delivery models with telemedicine, AI, and blockchain technology | |
CN109472709A (en) | Insurance price calculation method, device, computer equipment and storage medium | |
Tomini et al. | Can people afford to pay for health care?: new evidence on financial protection in Albania | |
Lucarelli et al. | Measuring welfare and the effects of regulation in a government-created market: The case of Medicare Part D plans | |
CN109658263A (en) | Insurance Pricing method, apparatus, equipment and readable storage medium storing program for executing based on big data | |
Sajadi et al. | Informal payments for outpatient health care: Country-wide evidence from Iran | |
CN110782360A (en) | Settlement data processing method and device, storage medium and electronic equipment | |
US11915287B2 (en) | Backend bundled healthcare services payment systems and methods | |
CN109658144A (en) | Pricing method, device, equipment and the readable storage medium storing program for executing of special medicine insurance plan | |
Bernz et al. | HPR7 Alignment with Services Providers was the Single Most Challenging Change in the Brazilian National Agency for Private Healthcare System (ANS) Value-Based Healthcare (VBHC) Project. |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20220525 Address after: 518000 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Block H, 666 Beijing East Road, Huangpu District, Shanghai 200000 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |