CN108346036A - Insurance policy concentrates vouching method, electronic device and readable storage medium storing program for executing - Google Patents
Insurance policy concentrates vouching method, electronic device and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN108346036A CN108346036A CN201810182943.9A CN201810182943A CN108346036A CN 108346036 A CN108346036 A CN 108346036A CN 201810182943 A CN201810182943 A CN 201810182943A CN 108346036 A CN108346036 A CN 108346036A
- Authority
- CN
- China
- Prior art keywords
- insurance policy
- mean
- risk part
- preset
- insurance
- 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 54
- 239000012141 concentrate Substances 0.000 title claims description 38
- 201000010099 disease Diseases 0.000 claims description 18
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000004321 preservation Methods 0.000 claims description 6
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 238000013136 deep learning model Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 239000000284 extract Substances 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000004069 differentiation Effects 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000012550 audit Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000000007 visual 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention relates to a kind of insurance policy concentration vouching method, electronic device and readable storage medium storing program for executing, this method to include:Receive pending insurance policy;The preset attribute information in the insurance policy is extracted, judges whether the insurance policy is risk part based on the preset attribute information and using preset risk part decision rule;If judging, the insurance policy is risk part, and distributing the insurance policy by the default method of salary distribution enters risk part core guarantor's flow;If it is risk part to judge the insurance policy not, it is directly entered preset normal Claims Resolution flow.Present invention saves artificial and time costs, and are judged as that the insurance policy of non-risk part can improve Claims Resolution efficiency, promote customer experience directly automatically into normal Claims Resolution flow.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of insurance policy concentrate vouching method, electronic device and
Readable storage medium storing program for executing.
Background technology
Intensification with people to the understanding of insurance industry, insurer's quantity is also more and more, and insurance policy is settled a claim therewith
The quantity of process risk part also increases significantly.The processing procedure of doubtful risk part is generally as follows in the prior art:
After the personnel that are in danger collect related data, insurance policy is manually screened, by the correlation of wherein doubtful risk part
Data uploads to general headquarters by modes such as faxes, and then general headquarters have the He Bao team progress artificial judgment of profession, later by people
Work judging result is handed down to domestic corporation and is handled again.Whole process is time-consuming and laborious entirely by manually come push process, with wind
Dangerous number of packages amount sharply increases, and can consume a large amount of artificial and time costs, greatly reduce Claims Resolution efficiency, cause customer experience not
It is good.
Invention content
The purpose of the present invention is to provide a kind of insurance policies to concentrate vouching method, electronic device and readable storage medium storing program for executing,
It is intended to improve the vouching efficiency of insurance policy and Claims Resolution efficiency.
To achieve the above object, the present invention provides a kind of electronic device, and the electronic device includes memory, processor,
The insurance policy that be stored on the memory to run on the processor concentrates vouching system, the insurance policy to concentrate
Vouching system realizes following steps when being executed by the processor:
Receive pending insurance policy;
The preset attribute information in the insurance policy is extracted, based on the preset attribute information and is utilized preset
Risk part decision rule judges whether the insurance policy is risk part;
If judging, the insurance policy is risk part, and distributing the insurance policy by the default method of salary distribution enters risk part
Core protects flow;If it is risk part to judge the insurance policy not, it is directly entered preset normal Claims Resolution flow.
It is preferably based on the preset attribute information and judges the insurance using preset risk part decision rule
The step of whether declaration form is risk part include:
Each preset attribute information in the insurance policy is extracted, and by the preset attribute information of extraction by default segmentation
Conversion regime is converted into corresponding attribute value point;And each attribute value point being converted to is substituted into following formula:
P=Gauss (a1, mean (A1), mean ((a1-mean (A1)) ^2)) * Gauss (a2, mean (A2), mean
((a2-mean (A2)) ^2)) * Gauss (an, mean (An), mean ((an-mean (An)) ^2))
Wherein, a1 to an is the transformed declaration form attribute value of the 1st to n preset attribute information in the insurance policy
Point, A1 to An are the transformed ginseng of corresponding 1st to the n preset attribute information of all normal Claims Resolution parts in default filing database
Examine the set of attribute value point;
Gauss (an, mean (An), mean ((an-mean (An)) ^2)) is n-th of declaration form attribute in the insurance policy
For numerical point at corresponding n-th with reference to the probability of occurrence value in the Gaussian Profile probability space of the set of attribute value point, P is institute
State the superposition value of the probability of occurrence value of the 1st to n declaration form attribute value point in insurance policy;
If P is more than predetermined probabilities threshold value, it is risk part to judge the insurance policy not;
If P is less than or equal to predetermined probabilities threshold value, judge that the insurance policy is risk part.
Preferably, the default method of salary distribution includes:
Manual acquisition core guarantor's task that task trigger button reception user sends out is protected by the pre-set manual core that obtains
Instruction, and the insurance policy is sent to the user, it is protected so that the user carries out risk part core to the insurance policy;Or
Person,
In preset task processing ratio, by the insurance policy, distribution to corresponding user progress risk part core is protected automatically;Or
Person,
According to the insurance reporting types of the insurance policy or insurance report region distribute automatically to corresponding user into
Sector-style danger part core is protected.
Preferably, the insurance policy is medical insurance declaration form, and the preset attribute information includes:
Warrantee's goes out strategical vantage point, and gender, at the age, schooling, work industry, and income level treats Hospital Grade, disease
Grade, at least one of duration, reimbursed sum.
In addition, to achieve the above object, the present invention also provides a kind of insurance policies to concentrate vouching method, the insurance policy
Concentrate vouching method include:
Receive pending insurance policy;
The preset attribute information in the insurance policy is extracted, based on the preset attribute information and is utilized preset
Risk part decision rule judges whether the insurance policy is risk part;
If judging, the insurance policy is risk part, and distributing the insurance policy by the default method of salary distribution enters risk part
Core protects flow;If it is risk part to judge the insurance policy not, it is directly entered preset normal Claims Resolution flow.
It is preferably based on the preset attribute information and judges the insurance using preset risk part decision rule
The step of whether declaration form is risk part include:
Each preset attribute information in the insurance policy is extracted, and by the preset attribute information of extraction by default segmentation
Conversion regime is converted into corresponding attribute value point;And each attribute value point being converted to is substituted into following formula:
P=Gauss (a1, mean (A1), mean ((a1-mean (A1)) ^2)) * Gauss (a2, mean (A2), mean
((a2-mean (A2)) ^2)) * Gauss (an, mean (An), mean ((an-mean (An)) ^2))
Wherein, a1 to an is the transformed declaration form attribute value of the 1st to n preset attribute information in the insurance policy
Point, A1 to An are the transformed ginseng of corresponding 1st to the n preset attribute information of all normal Claims Resolution parts in default filing database
Examine the set of attribute value point;
Gauss (an, mean (An), mean ((an-mean (An)) ^2)) is n-th of declaration form attribute in the insurance policy
For numerical point at corresponding n-th with reference to the probability of occurrence value in the Gaussian Profile probability space of the set of attribute value point, P is institute
State the superposition value of the probability of occurrence value of the 1st to n declaration form attribute value point in insurance policy;
If P is more than predetermined probabilities threshold value, it is risk part to judge the insurance policy not;
If P is less than or equal to predetermined probabilities threshold value, judge that the insurance policy is risk part.
Preferably, the default method of salary distribution includes:
Manual acquisition core guarantor's task that task trigger button reception user sends out is protected by the pre-set manual core that obtains
Instruction, and the insurance policy is sent to the user, it is protected so that the user carries out risk part core to the insurance policy;Or
Person,
In preset task processing ratio, by the insurance policy, distribution to corresponding user progress risk part core is protected automatically;Or
Person,
According to the insurance reporting types of the insurance policy or insurance report region distribute automatically to corresponding user into
Sector-style danger part core is protected.
Preferably, the insurance policy is medical insurance declaration form, and the preset attribute information includes:
Warrantee's goes out strategical vantage point, and gender, at the age, schooling, work industry, and income level treats Hospital Grade, disease
Grade, at least one of duration, reimbursed sum.
Preferably, this method further includes:
The insurance policy and the core of feedback are protected into result and are associated preservation, and by the core of the insurance policy and feedback
Result is protected to store into default filing database.
The present invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage has insurance to protect
Single to concentrate vouching system, the insurance policy concentrates vouching system that can be executed by least one processor, so that described at least one
A processor executes the step of concentrating vouching method such as above-mentioned insurance policy.
Insurance policy proposed by the present invention concentrates vouching method, system and readable storage medium storing program for executing, by extracting business personnel
Preset attribute information in the insurance policy of upload judges that the insurance policy is using pre-set risk part decision rule
It is no be risk part, if judging, the insurance policy is risk part, by the default method of salary distribution to the insurance policy be allocated with into
One step core is protected, that is, enters pre-set risk part workflow:If it is normal part that judge the insurance policy not, which be risk part,
Declaration form insurance is then directly set to enter normal Claims Resolution flow.Due to can be by the stream of all insurance policy risk parts and non-risk part
Journey is unitized, and the auditing flow of risk part is automated, can by a large amount of insurance policies risk part and non-risk part carry out just
The differentiation of step judges, without manually judging that doubtful risk part is manually sent to core by the doubtful risk part in a large amount of insurance policies again
Guarantor center judges, has saved artificial and time cost, and be judged as that the insurance policy of non-risk part can be directly automatically into just
Convention pays for flow, improves Claims Resolution efficiency, promotes customer experience.
Description of the drawings
Fig. 1 is the running environment schematic diagram that insurance policy of the present invention concentrates 10 preferred embodiment of vouching system;
Fig. 2 is the flow diagram that insurance policy of the present invention concentrates one embodiment of vouching method.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
The every other embodiment obtained is put, shall fall within the protection scope of the present invention.
It should be noted that the description for being related to " first ", " second " etc. in the present invention is used for description purposes only, and cannot
It is interpreted as indicating or implying its relative importance or implicitly indicates the quantity of indicated technical characteristic.Define as a result, " the
One ", the feature of " second " can explicitly or implicitly include at least one of the features.In addition, the skill between each embodiment
Art scheme can be combined with each other, but must can be implemented as basis with those of ordinary skill in the art, when technical solution
Will be understood that the combination of this technical solution is not present in conjunction with there is conflicting or cannot achieve when, also not the present invention claims
Protection domain within.
The present invention provides a kind of insurance policy concentration vouching system.Referring to Fig. 1, being that insurance policy of the present invention concentrates vouching
The running environment schematic diagram of 10 preferred embodiment of system.
In the present embodiment, the insurance policy is concentrated vouching system 10 to install and is run in electronic device 1.The electricity
Sub-device 1 may include, but be not limited only to, memory 11, processor 12 and display 13.Fig. 1 is illustrated only with component 11-13
Electronic device 1, it should be understood that be not required for implementing all components shown, the implementation that can be substituted it is more or
Less component.
The memory 11 is the readable computer storage medium of at least one type, and the memory 11 is implemented at some
Can be the internal storage unit of the electronic device 1, such as the hard disk or memory of the electronic device 1 in example.The memory
11 can also be to be equipped on the External memory equipment of the electronic device 1, such as the electronic device 1 in further embodiments
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card,
Flash card (Flash Card) etc..Further, the memory 11 can also both include the storage inside of the electronic device 1
Unit also includes External memory equipment.The memory 11 for store the application software for being installed on the electronic device 1 and respectively
Class data, such as the insurance policy concentrate the program code etc. of vouching system 10.The memory 11 can be also used for temporarily
Ground stores the data that has exported or will export.
The processor 12 can be in some embodiments a central processing unit (Central Processing Unit,
CPU), microprocessor or other data processing chips, for running the program code stored in the memory 11 or processing number
According to, such as execute the insurance policy and concentrate vouching system 10 etc..
The display 13 can be light-emitting diode display, liquid crystal display, touch-control liquid crystal display in some embodiments
And OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) touches device etc..The display 13 is used
In being shown in the information handled in the electronic device 1 and for showing visual user interface, such as in insurance policy
Each attribute information, insurance policy whether be that the judging result of risk part, risk part core are protected and waits for interface, interface of normally settling a claim
Deng.The component 11-13 of the electronic device 1 is in communication with each other by system bus.
It includes at least one computer-readable finger being stored in the memory 11 that insurance policy, which concentrates vouching system 10,
It enables, which can be executed by the processor 12, to realize each embodiment of the application.
Wherein, following steps are realized when above-mentioned insurance policy concentrates vouching system 10 to be executed by the processor 12:
Step S1 receives pending insurance policy.
In the present embodiment, electronic device can be docked by network with the Claims Resolution terminal system of business personnel, protected
When dangerous declaration form vouching, declaration form relevant information is committed to insurance policy by terminal system of settling a claim and concentrates vouching system by business personnel.
For example, can receive user preassembled visitor in the terminals such as mobile phone, tablet computer, hand-held Claims Resolution terminal, self-help terminal equipment
The insurance policy and relevant information sent on the end of family, or user is received in mobile phone, tablet computer, hand-held Claims Resolution terminal, self-service
The insurance policy and relevant information sent on browser in the terminals such as terminal device.
Step S2 extracts the preset attribute information in the insurance policy, based on the preset attribute information and using in advance
The risk part decision rule first set judges whether the insurance policy is risk part.
After receiving pending insurance policy, the preset attribute information in the insurance policy is can extract, for example, working as
When the insurance policy is medical insurance declaration form, the preset attribute information of extraction includes but not limited to:Warrantee's goes out strategical vantage point, property
Not, the age, schooling, work industry, income level, treatment Hospital Grade, disease grade, the duration, reimbursed sum, etc.
Deng.And judge whether the insurance policy is risk part using preset risk part decision rule, for example, a kind of optional
Embodiment in, can be by multiple preset attributes of extraction (for example, selection several more important attribute such as ages, cultural journey
Degree, income level, treatment Hospital Grade, disease grade, reimbursed sum) information be input to as several insurance vouching factors it is pre-
First trained deep learning model obtains the output of the deep learning model as a result, and according to output result to judge
State whether insurance policy is risk part.Wherein, which includes but not limited to following several models:Convolutional Neural net
Network (CNN), recurrent neural network RNN and LSTM, recurrence tensor neural network RNTN, autocoder Autoencoder etc..
By following steps, training obtains the deep learning model in advance:
Extract the normal part of preset quantity (500,000) respectively from fixed insurance policy in passing historical data
With risk part as sample, and multiple preset attributes in each sample are extracted (for example, the several more important categories of selection
Property for example the age, schooling, income level, treatment Hospital Grade, disease grade, reimbursed sum) information as several samples
The factor;
It is trained to preset deep learning model using the sample factor as input input, obtains trained deep learning
The output of model;
(such as the value of each weight in optimization CNN networks adjusts the hidden of model to the parameter of the deep learning model of adjusting training
Layer parameter), the core to minimize the obtained output and sample protects the error between result (normal part or risk part);
If error meets preset condition (such as less than default error threshold), terminates to train, obtain trained depth
Practise model.
Step S3, if judging, the insurance policy is risk part, by the default method of salary distribution distribute the insurance policy into
Enter risk part core and protects flow.For example, protecting the hand that task trigger button reception user sends out by the pre-set manual core that obtains
The dynamic core that obtains protects assignment instructions, and the insurance policy is sent to the user, so that the user carries out the insurance policy
Risk part core is protected;It provides team and obtains task function manually.Alternatively, handling ratio by the insurance policy in preset task
Automatic distribution carries out risk part core to corresponding user and protects.Alternatively, according to the insurance reporting types of the insurance policy or guarantor
Danger reports region various dimensions, and distribution to corresponding user progress risk part core is protected automatically.A variety of flexible are provided in the present embodiment
Business allocation model carries out risk part core guarantor to distribute.Largely avoid treatment people since ability to work is different or
Slow situation is handled caused by the reasons such as slack in work, improves the feedback timeliness for protecting assessment to the core of risk part.
If it is risk part to judge the insurance policy not, it is directly entered preset normal Claims Resolution flow.For example, can
It is automatic to redirect or wait for preset time (5 seconds) without preset normal Claims Resolution operation interface is directly entered after operation, to complete
Normal Claims Resolution flow.
Preset attribute information in insurance policy of the present embodiment by extracting business personnel's upload, utilization are pre-set
Risk part decision rule judge whether the insurance policy is risk part, if judging, the insurance policy is risk part, by default
The method of salary distribution is allocated the insurance policy and is protected with further core, that is, enters pre-set risk part workflow:If sentencing
It is normal part that the disconnected insurance policy, which is not risk part, then declaration form insurance is directly made to enter normal Claims Resolution flow.Due to that can incite somebody to action
The flow of all insurance policy risk parts and non-risk part is unitized, and the auditing flow of risk part is automated, can will be a large amount of
Risk part and non-risk part in insurance policy carry out preliminary differentiation judgement, without manually judging doubting in a large amount of insurance policies
Doubtful risk part is manually sent to core again like risk part and protects center judgement, has saved artificial and time cost, and be judged as
The insurance policy of non-risk part can improve Claims Resolution efficiency, promote customer experience directly automatically into normal Claims Resolution flow.
In an optional embodiment, on the basis of the embodiment of above-mentioned Fig. 1, the insurance policy concentrates vouching system
10 by the processor 12 execute realize the step S2 when, specifically include:
The preset attribute information in the insurance policy is extracted, and each preset attribute information of extraction is pressed respectively and is preset
Segmentation conversion regime is converted into corresponding attribute value point;And each attribute value point being converted to is substituted into following formula:
P=Gauss (a1, mean (A1), mean ((a1-mean (A1)) ^2)) * Gauss (a2, mean (A2), mean
((a2-mean (A2)) ^2)) * ... Gauss (an, mean (An), mean ((an-mean (An)) ^2))
Wherein, a1, a2 ... an be the insurance policy in the 1st, 2 ... the transformed declaration form attribute of n preset attribute information
Numerical point, A1, A2 to An are corresponding 1st, 2 to the n preset attribute information of all normal Claims Resolution parts in default filing database
The transformed set with reference to attribute value point;
Gauss (an, mean (An), mean ((an-mean (An)) ^2)) is n-th of declaration form attribute in the insurance policy
For numerical point at corresponding n-th with reference to the probability of occurrence value in the Gaussian Profile probability space of the set of attribute value point, P is institute
State the superposition value of the probability of occurrence value of the 1st, 2 to n declaration form attribute value point in insurance policy;
If P is more than predetermined probabilities threshold value, it is risk part to judge the insurance policy not;
If P is less than or equal to predetermined probabilities threshold value, judge that the insurance policy is risk part.
In the present embodiment, since Claims Resolution risk part and normal Claims Resolution part are compared and are bound to larger difference, and it is normal
All there is similitude in the case where Claims Resolution part.Therefore, if each attribute that refers in part that each insurance policy is settled a claim (is such as protected
People's goes out strategical vantage point, and gender, at the age, schooling, work industry, income level, treats Hospital Grade, disease grade, when continuing
Between, reimbursed sum etc.) be converted into each numerical point, then in certain area, in several normal Claims Resolutions of historgraphic data recording
There is the probability spaces of a Gaussian Profile for the space of points inner periphery each occurred in part.Based on this principle, in the present embodiment,
Insurance policy concentrates vouching system after the declaration form relevant information for receiving business personnel's upload, first, extracts the declaration form of upload
Preset attribute information in relevant information, such as can be by the strategical vantage point that goes out of warrantee, and gender, at the age, schooling, work industry, receives
Enter level, treats Hospital Grade, disease grade, the duration, the information such as reimbursed sum report data and guarantor from the personnel that are in danger
It is extracted in single system, then is converted into corresponding to by default segmentation conversion regime respectively by each preset attribute information of extraction
Attribute value point illustrate by taking age attribute as an example herein, as the age is for example, being converted into numerical point in segmented fashion
0-16 Sui is identified as 1;17-22 Sui is identified as 2;23-35 Sui is identified as 3;36-50 Sui is identified as 4;51-65 Sui
It is identified as 5;66 years old or more it is identified as 7;Other attributes and so on, details are not described herein.
The history case for once carrying out the judgement of risk part is preserved in the default filing database of passing historical data
Information finds out all normal Claims Resolution parts in history case.Judging current insurance according to the insurance policy relevant information of upload
When whether declaration form is risk part, there is following formula:
P=Gauss (a1, mean (A1), mean ((a1-mean (A1)) ^2)) * Gauss (a2, mean (A2), mean
((a2-mean (A2)) ^2)) * ... Gauss (an, mean (An), mean ((an-mean (An)) ^2))
1st, 2 to n preset attribute information in wherein, a1, a2 to the current insurance policy that an is this vouching (for example,
Select several more important attributes such as age, schooling, income level, treatment Hospital Grade, disease grade, reimbursement gold
Volume) transformed declaration form attribute value point, A1, A2 to An are all normal Claims Resolution parts the corresponding 1st in default filing database,
2 to n preset attribute information (with identical attribute in the current insurance policy of extraction, as the age, schooling, income level,
Treat Hospital Grade, disease grade, reimbursed sum) the transformed set with reference to attribute value point.In formula, mean (A1) is
The mean value for seeking A1 determines that the position of Gaussian Profile (i.e. normal distribution) probability graph, mean ((a1-mean (A1)) ^2) are to seek a1
With the amplitude of the distribution of the standard deviation and Gaussian Profile (i.e. normal distribution) of mean (A1).Gauss (an, mean (An),
Mean ((an-mean (An)) ^2)) it is that at corresponding n-th, reference belongs to n-th of declaration form attribute value point in the insurance policy
Property numerical point set Gaussian Profile probability space in probability of occurrence value, P be the insurance policy in the 1st, 2 ... n protect
The superposition value of the probability of occurrence value of single attribute value point;The P values being finally calculated are the current insurance policy of this vouching
For the probability for part of normally settling a claim.
Due to being mentioned above, in certain area, each occur in several normal Claims Resolution parts of historgraphic data recording
Space of points inner periphery there is the probability spaces of a Gaussian Profile, i.e., normally between Claims Resolution part there are similitude, using working as
Before the insurance policy to be judged it is whether similar to the normal Claims Resolution part of historgraphic data recording come judge current insurance policy whether be
Risk part.Namely each numerical point appears in several normal Claims Resolution parts of historgraphic data recording in the insurance policy currently to be judged
In each put nearby spatial position probability it is higher, then the insurance policy currently to be judged with normally settle a claim part similarity get over
It is high.Specifically in formula, the parameter P that the probability value of each point is superimposed is higher, then the insurance policy currently to be judged is just
The possibility that convention pays for part is bigger.
Therefore, a rational predetermined probabilities threshold value can be preset in the present embodiment, if the current declaration form being calculated
It is less than the predetermined probabilities threshold value for the probability i.e. P values for part of normally settling a claim, then judges current insurance policy and normal part not phase of settling a claim
Seemingly, that is, current insurance policy is judged for doubtful Claims Resolution risk part, then core is transferred to protect center artificial treatment;If P values are default more than this
Probability threshold value then judges that current insurance policy is similar to normal Claims Resolution part, that is, judges current insurance policy for normal Claims Resolution part, then
The label that can settle a claim is returned to, to allow it to walk normal Claims Resolution flow.
It, can be by several Claims Resolution parts of historgraphic data recording (including Claims Resolution risk part and just when presetting probability threshold value
Convention pays for part) utilize formula:
P=Gauss (a1, mean (A1), mean ((a1-mean (A1)) ^2)) * Gauss (a2, mean (A2), mean
((a2-mean (A2)) ^2)) * ... Gauss (an, mean (An), mean ((an-mean (An)) ^2)) constantly train and verify
The reasonability of probability threshold value, after reaching certain accuracy, you can set a rational predetermined probabilities threshold value.Certainly, rear
In continuous actual application, which can also be adjusted by user according to the needs of different application scene, such as
In requiring risk part to judge stringenter scene, the threshold value can suitably be turned up;Less strict scene is being judged risk part
In, it can suitably turn down the threshold value.It is more flexible, practical.
In an optional embodiment, when the insurance policy concentrates vouching system 10 to be executed by the processor 12, also
Following steps can be achieved:
The insurance policy and the core of feedback are protected into result and are associated preservation, and by the core of the insurance policy and feedback
Result is protected to store into default filing database.
In the present embodiment, filing system can be also introduced, by the judgement result that the insurance policy of each upload is final with it
Be associated preservation and file, such as by the core of the current insurance policy and feedback protect result (being risk part or normal part) into
Row association preserves, and the insurance policy and the core of feedback are protected result and stored into default filing database.It will insure
The Claims Resolution data such as single and final suggestions made after examination (be risk part or normal part, and result finally is protected to the artificial nucleus of risk part)
Filing can stay audit opinion card, and can give reference to same subscriber and similar Claims Resolution situation in the follow-up process.
As shown in Fig. 2, Fig. 2 is the flow diagram that insurance policy of the present invention concentrates one embodiment of vouching method, the insurance
Declaration form concentrates vouching method to include the following steps:
Step S10 receives pending insurance policy.
In the present embodiment, electronic device can be docked by network with the Claims Resolution terminal system of business personnel, protected
When dangerous declaration form vouching, declaration form relevant information is committed to insurance policy by terminal system of settling a claim and concentrates vouching system by business personnel.
For example, can receive user preassembled visitor in the terminals such as mobile phone, tablet computer, hand-held Claims Resolution terminal, self-help terminal equipment
The insurance policy and relevant information sent on the end of family, or user is received in mobile phone, tablet computer, hand-held Claims Resolution terminal, self-service
The insurance policy and relevant information sent on browser in the terminals such as terminal device.
Step S20 extracts the preset attribute information in the insurance policy, based on the preset attribute information and using in advance
The risk part decision rule first set judges whether the insurance policy is risk part.
After receiving pending insurance policy, the preset attribute information in the insurance policy is can extract, for example, working as
When the insurance policy is medical insurance declaration form, the preset attribute information of extraction includes but not limited to:Warrantee's goes out strategical vantage point, property
Not, the age, schooling, work industry, income level, treatment Hospital Grade, disease grade, the duration, reimbursed sum, etc.
Deng.And judge whether the insurance policy is risk part using preset risk part decision rule, for example, a kind of optional
Embodiment in, can be by multiple preset attributes of extraction (for example, selection several more important attribute such as ages, cultural journey
Degree, income level, treatment Hospital Grade, disease grade, reimbursed sum) information be input to as several insurance vouching factors it is pre-
First trained deep learning model obtains the output of the deep learning model as a result, and according to output result to judge
State whether insurance policy is risk part.Wherein, which includes but not limited to following several models:Convolutional Neural net
Network (CNN), recurrent neural network RNN and LSTM, recurrence tensor neural network RNTN, autocoder Autoencoder etc..
By following steps, training obtains the deep learning model in advance:
Extract the normal part of preset quantity (500,000) respectively from fixed insurance policy in passing historical data
With risk part as sample, and multiple preset attributes in each sample are extracted (for example, the several more important categories of selection
Property for example the age, schooling, income level, treatment Hospital Grade, disease grade, reimbursed sum) information as several samples
The factor;
It is trained to preset deep learning model using the sample factor as input input, obtains trained deep learning
The output of model;
(such as the value of each weight in optimization CNN networks adjusts the hidden of model to the parameter of the deep learning model of adjusting training
Layer parameter), the core to minimize the obtained output and sample protects the error between result (normal part or risk part);
If error meets preset condition (such as less than default error threshold), terminates to train, obtain trained depth
Practise model.
Step S30, if judging, the insurance policy is risk part, by the default method of salary distribution distribute the insurance policy into
Enter risk part core and protects flow.For example, protecting the hand that task trigger button reception user sends out by the pre-set manual core that obtains
The dynamic core that obtains protects assignment instructions, and the insurance policy is sent to the user, so that the user carries out the insurance policy
Risk part core is protected;It provides team and obtains task function manually.Alternatively, handling ratio by the insurance policy in preset task
Automatic distribution carries out risk part core to corresponding user and protects.Alternatively, according to the insurance reporting types of the insurance policy or guarantor
Danger reports region various dimensions, and distribution to corresponding user progress risk part core is protected automatically.A variety of flexible are provided in the present embodiment
Business allocation model carries out risk part core guarantor to distribute.Largely avoid treatment people since ability to work is different or
Slow situation is handled caused by the reasons such as slack in work, improves the feedback timeliness for protecting assessment to the core of risk part.
If it is risk part to judge the insurance policy not, it is directly entered preset normal Claims Resolution flow.For example, can
It is automatic to redirect or wait for preset time (5 seconds) without preset normal Claims Resolution operation interface is directly entered after operation, to complete
Normal Claims Resolution flow.
Preset attribute information in insurance policy of the present embodiment by extracting business personnel's upload, utilization are pre-set
Risk part decision rule judge whether the insurance policy is risk part, if judging, the insurance policy is risk part, by default
The method of salary distribution is allocated the insurance policy and is protected with further core, that is, enters pre-set risk part workflow:If sentencing
It is normal part that the disconnected insurance policy, which is not risk part, then declaration form insurance is directly made to enter normal Claims Resolution flow.Due to that can incite somebody to action
The flow of all insurance policy risk parts and non-risk part is unitized, and the auditing flow of risk part is automated, can will be a large amount of
Risk part and non-risk part in insurance policy carry out preliminary differentiation judgement, without manually judging doubting in a large amount of insurance policies
Doubtful risk part is manually sent to core again like risk part and protects center judgement, has saved artificial and time cost, and be judged as
The insurance policy of non-risk part can improve Claims Resolution efficiency, promote customer experience directly automatically into normal Claims Resolution flow.
In an optional embodiment, on the basis of the above embodiments, the step S20 is specifically included:
The preset attribute information in the insurance policy is extracted, and each preset attribute information of extraction is pressed respectively and is preset
Segmentation conversion regime is converted into corresponding attribute value point;And each attribute value point being converted to is substituted into following formula:
P=Gauss (a1, mean (A1), mean ((a1-mean (A1)) ^2)) * Gauss (a2, mean (A2), mean
((a2-mean (A2)) ^2)) * ... Gauss (an, mean (An), mean ((an-mean (An)) ^2))
Wherein, a1, a2 to an be the insurance policy in the transformed declaration form attribute of the 1st, 2 to n preset attribute information
Numerical point, A1, A2 to An are corresponding 1st, 2 to the n preset attribute information of all normal Claims Resolution parts in default filing database
The transformed set with reference to attribute value point;
Gauss (an, mean (An), mean ((an-mean (An)) ^2)) is n-th of declaration form attribute in the insurance policy
For numerical point at corresponding n-th with reference to the probability of occurrence value in the Gaussian Profile probability space of the set of attribute value point, P is institute
State the superposition value of the probability of occurrence value of the 1st, 2 to n declaration form attribute value point in insurance policy;
If P is more than predetermined probabilities threshold value, it is risk part to judge the insurance policy not;
If P is less than or equal to predetermined probabilities threshold value, judge that the insurance policy is risk part.
In the present embodiment, since Claims Resolution risk part and normal Claims Resolution part are compared and are bound to larger difference, and it is normal
All there is similitude in the case where Claims Resolution part.Therefore, if each attribute that refers in part that each insurance policy is settled a claim (is such as protected
People's goes out strategical vantage point, and gender, at the age, schooling, work industry, income level, treats Hospital Grade, disease grade, when continuing
Between, reimbursed sum etc.) be converted into each numerical point, then in certain area, in several normal Claims Resolutions of historgraphic data recording
There is the probability spaces of a Gaussian Profile for the space of points inner periphery each occurred in part.Based on this principle, in the present embodiment,
Insurance policy concentrates vouching system after the declaration form relevant information for receiving business personnel's upload, first, extracts the declaration form of upload
Preset attribute information in relevant information, such as can be by the strategical vantage point that goes out of warrantee, and gender, at the age, schooling, work industry, receives
Enter level, treats Hospital Grade, disease grade, the duration, the information such as reimbursed sum report data and guarantor from the personnel that are in danger
It is extracted in single system, then is converted into corresponding to by default segmentation conversion regime respectively by each preset attribute information of extraction
Attribute value point illustrate by taking age attribute as an example herein, as the age is for example, being converted into numerical point in segmented fashion
0-16 Sui is identified as 1;17-22 Sui is identified as 2;23-35 Sui is identified as 3;36-50 Sui is identified as 4;51-65 Sui
It is identified as 5;66 years old or more it is identified as 7;Other attributes and so on, details are not described herein.
The history case for once carrying out the judgement of risk part is preserved in the default filing database of passing historical data
Information finds out all normal Claims Resolution parts in history case.Judging current insurance according to the insurance policy relevant information of upload
When whether declaration form is risk part, there is following formula:
P=Gauss (a1, mean (A1), mean ((a1-mean (A1)) ^2)) * Gauss (a2, mean (A2), mean
((a2-mean (A2)) ^2)) * ... Gauss (an, mean (An), mean ((an-mean (An)) ^2))
1st, 2 to n preset attribute information in wherein, a1, a2 to the current insurance policy that an is this vouching (for example,
Select several more important attributes such as age, schooling, income level, treatment Hospital Grade, disease grade, reimbursement gold
Volume) transformed declaration form attribute value point, A1, A2 to An are all normal Claims Resolution parts the corresponding 1st in default filing database,
2 to n preset attribute information (with identical attribute in the current insurance policy of extraction, as the age, schooling, income level,
Treat Hospital Grade, disease grade, reimbursed sum) the transformed set with reference to attribute value point.In formula, mean (A1) is
The mean value for seeking A1 determines that the position of Gaussian Profile (i.e. normal distribution) probability graph, mean ((a1-mean (A1)) ^2) are to seek a1
With the amplitude of the distribution of the standard deviation and Gaussian Profile (i.e. normal distribution) of mean (A1).Gauss (an, mean (An),
Mean ((an-mean (An)) ^2)) it is that at corresponding n-th, reference belongs to n-th of declaration form attribute value point in the insurance policy
Property numerical point set Gaussian Profile probability space in probability of occurrence value, P be the insurance policy in the 1st, 2 to n protect
The superposition value of the probability of occurrence value of single attribute value point;The P values being finally calculated are the current insurance policy of this vouching
For the probability for part of normally settling a claim.
Due to being mentioned above, in certain area, each occur in several normal Claims Resolution parts of historgraphic data recording
Space of points inner periphery there is the probability spaces of a Gaussian Profile, i.e., normally between Claims Resolution part there are similitude, using working as
Before the insurance policy to be judged it is whether similar to the normal Claims Resolution part of historgraphic data recording come judge current insurance policy whether be
Risk part.Namely each numerical point appears in several normal Claims Resolution parts of historgraphic data recording in the insurance policy currently to be judged
In each put nearby spatial position probability it is higher, then the insurance policy currently to be judged with normally settle a claim part similarity get over
It is high.Specifically in formula, the parameter P that the probability value of each point is superimposed is higher, then the insurance policy currently to be judged is just
The possibility that convention pays for part is bigger.
Therefore, a rational predetermined probabilities threshold value can be preset in the present embodiment, if the current declaration form being calculated
It is less than the predetermined probabilities threshold value for the probability i.e. P values for part of normally settling a claim, then judges current insurance policy and normal part not phase of settling a claim
Seemingly, that is, current insurance policy is judged for doubtful Claims Resolution risk part, then core is transferred to protect center artificial treatment;If P values are default more than this
Probability threshold value then judges that current insurance policy is similar to normal Claims Resolution part, that is, judges current insurance policy for normal Claims Resolution part, then
The label that can settle a claim is returned to, to allow it to walk normal Claims Resolution flow.
It, can be by several Claims Resolution parts of historgraphic data recording (including Claims Resolution risk part and just when presetting probability threshold value
Convention pays for part) utilize formula:
P=Gauss (a1, mean (A1), mean ((a1-mean (A1)) ^2)) * Gauss (a2, mean (A2), mean
((a2-mean (A2)) ^2)) * ... Gauss (an, mean (An), mean ((an-mean (An)) ^2)) constantly train and verify
The reasonability of probability threshold value, after reaching certain accuracy, you can set a rational predetermined probabilities threshold value.Certainly, rear
In continuous actual application, which can also be adjusted by user according to the needs of different application scene, such as
In requiring risk part to judge stringenter scene, the threshold value can suitably be turned up;Less strict scene is being judged risk part
In, it can suitably turn down the threshold value.It is more flexible, practical.
In an optional embodiment, this method further includes:
The insurance policy and the core of feedback are protected into result and are associated preservation, and by the core of the insurance policy and feedback
Result is protected to store into default filing database.
In the present embodiment, filing system can be also introduced, by the judgement result that the insurance policy of each upload is final with it
Be associated preservation and file, such as by the core of the current insurance policy and feedback protect result (being risk part or normal part) into
Row association preserves, and the insurance policy and the core of feedback are protected result and stored into default filing database.It will insure
The Claims Resolution data such as single and final suggestions made after examination (be risk part or normal part, and result finally is protected to the artificial nucleus of risk part)
Filing can stay audit opinion card, and can give reference to same subscriber and similar Claims Resolution situation in the follow-up process.
In addition, the present invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage has
Insurance policy concentrates vouching system, and the insurance policy concentrates vouching system that can be executed by least one processor, so that described
At least one processor executes the step of concentrating vouching method such as the insurance policy in above-described embodiment, the insurance policy collection center
The specific implementation process such as step S10, S20, S30 of folk prescription method are as described above, and details are not described herein.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that process, method, article or device including a series of elements include not only those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this
There is also other identical elements in the process of element, method, article or device.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to be realized by hardware, but very much
In the case of the former be more preferably embodiment.Based on this understanding, technical scheme of the present invention is substantially in other words to existing
The part that technology contributes can be expressed in the form of software products, which is stored in a storage
In medium (such as ROM/RAM, magnetic disc, CD), including some instructions are used so that a station terminal equipment (can be mobile phone, calculate
Machine, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
Above by reference to the preferred embodiment of the present invention has been illustrated, not thereby limit to the interest field of the present invention.On
It is for illustration only to state serial number of the embodiment of the present invention, can not represent the quality of embodiment.It is patrolled in addition, though showing in flow charts
Sequence is collected, but in some cases, it can be with the steps shown or described are performed in an order that is different from the one herein.
Those skilled in the art do not depart from the scope of the present invention and essence, can there are many variant scheme realize the present invention,
It can be used for another embodiment for example as the feature of one embodiment and obtain another embodiment.All technologies with the present invention
All any modification, equivalent and improvement made by within design, should all be within the interest field of the present invention.
Claims (10)
1. a kind of electronic device, which is characterized in that the electronic device includes memory, processor, is stored on the memory
There is the insurance policy that can be run on the processor that vouching system, the insurance policy is concentrated to concentrate vouching system by the place
Reason device realizes following steps when executing:
Receive pending insurance policy;
The preset attribute information in the insurance policy is extracted, based on the preset attribute information and utilizes preset risk
Part decision rule judges whether the insurance policy is risk part;
If judging, the insurance policy is risk part, and distributing the insurance policy by the default method of salary distribution enters risk part core guarantor
Flow;If it is risk part to judge the insurance policy not, it is directly entered preset normal Claims Resolution flow.
2. electronic device as described in claim 1, which is characterized in that based on the preset attribute information and using presetting
Risk part decision rule judge that the step of whether insurance policy is risk part includes:
Each preset attribute information in the insurance policy is extracted, and the preset attribute information of extraction is converted by default segmentation
Mode is converted into corresponding attribute value point;And each attribute value point being converted to is substituted into following formula:
P=Gauss (a1, mean (A1), mean ((a1-mean (A1)) ^2)) * Gauss (a2, mean (A2), mean ((a2-
Mean (A2)) ^2)) * Gauss (an, mean (An), mean ((an-mean (An)) ^2))
Wherein, a1 to an is the transformed declaration form attribute value point of the 1st to n preset attribute information in the insurance policy, A1
It is all normal Claims Resolution parts the corresponding 1st in default filing database to An, until n preset attribute information is transformed with reference to category
The set of property numerical point;
Gauss (an, mean (An), mean ((an-mean (An)) ^2)) is n-th of declaration form attribute value in the insurance policy
For point at corresponding n-th with reference to the probability of occurrence value in the Gaussian Profile probability space of the set of attribute value point, P is the guarantor
The superposition value of the probability of occurrence value of 1st to n declaration form attribute value point in dangerous declaration form;
If P is more than predetermined probabilities threshold value, it is risk part to judge the insurance policy not;
If P is less than or equal to predetermined probabilities threshold value, judge that the insurance policy is risk part.
3. electronic device as claimed in claim 1 or 2, which is characterized in that the default method of salary distribution includes:
Manual acquisition core guarantor's assignment instructions that task trigger button reception user sends out are protected by the pre-set manual core that obtains,
And the insurance policy is sent to the user, it is protected so that the user carries out risk part core to the insurance policy;Alternatively,
In preset task processing ratio, by the insurance policy, distribution to corresponding user progress risk part core is protected automatically;Alternatively,
Region is reported to be distributed automatically to corresponding user into sector-style according to the insurance reporting types of the insurance policy or insurance
Dangerous part core is protected.
4. electronic device as claimed in claim 1 or 2, which is characterized in that the insurance policy is medical insurance declaration form, described
Preset attribute information includes:
Warrantee's goes out strategical vantage point, and gender, at the age, schooling, work industry, and income level treats Hospital Grade, disease etc.
Grade, at least one of duration, reimbursed sum.
5. a kind of insurance policy concentrates vouching method, which is characterized in that the insurance policy concentrates the vouching method to include:
Receive pending insurance policy;
The preset attribute information in the insurance policy is extracted, based on the preset attribute information and utilizes preset risk
Part decision rule judges whether the insurance policy is risk part;
If judging, the insurance policy is risk part, and distributing the insurance policy by the default method of salary distribution enters risk part core guarantor
Flow;If it is risk part to judge the insurance policy not, it is directly entered preset normal Claims Resolution flow.
6. insurance policy as claimed in claim 5 concentrates vouching method, which is characterized in that simultaneously based on the preset attribute information
Judge that the step of whether insurance policy is risk part includes using preset risk part decision rule:
Each preset attribute information in the insurance policy is extracted, and the preset attribute information of extraction is converted by default segmentation
Mode is converted into corresponding attribute value point;And each attribute value point being converted to is substituted into following formula:
P=Gauss (a1, mean (A1), mean ((a1-mean (A1)) ^2)) * Gauss (a2, mean (A2), mean ((a2-
Mean (A2)) ^2)) * Gauss (an, mean (An), mean ((an-mean (An)) ^2))
Wherein, a1 to an is the transformed declaration form attribute value point of the 1st to n preset attribute information in the insurance policy, A1
It is the corresponding transformed reference category of 1st to n preset attribute information of all normal Claims Resolution parts in default filing database to An
The set of property numerical point;
Gauss (an, mean (An), mean ((an-mean (An)) ^2)) is n-th of declaration form attribute value in the insurance policy
For point at corresponding n-th with reference to the probability of occurrence value in the Gaussian Profile probability space of the set of attribute value point, P is the guarantor
The superposition value of the probability of occurrence value of 1st to n declaration form attribute value point in dangerous declaration form;
If P is more than predetermined probabilities threshold value, it is risk part to judge the insurance policy not;
If P is less than or equal to predetermined probabilities threshold value, judge that the insurance policy is risk part.
7. as insurance policy described in claim 5 or 6 concentrates vouching method, which is characterized in that the default method of salary distribution packet
It includes:
Manual acquisition core guarantor's assignment instructions that task trigger button reception user sends out are protected by the pre-set manual core that obtains,
And the insurance policy is sent to the user, it is protected so that the user carries out risk part core to the insurance policy;Alternatively,
In preset task processing ratio, by the insurance policy, distribution to corresponding user progress risk part core is protected automatically;Alternatively,
Region is reported to be distributed automatically to corresponding user into sector-style according to the insurance reporting types of the insurance policy or insurance
Dangerous part core is protected.
8. as insurance policy described in claim 5 or 6 concentrates vouching method, which is characterized in that the insurance policy is medical treatment
Insurance policy, the preset attribute information include:
Warrantee's goes out strategical vantage point, and gender, at the age, schooling, work industry, and income level treats Hospital Grade, disease etc.
Grade, at least one of duration, reimbursed sum.
9. as insurance policy described in claim 5 or 6 concentrates vouching method, which is characterized in that this method further includes:
The insurance policy and the core of feedback are protected into result and are associated preservation, and the insurance policy and the core of feedback are protected and tied
Fruit stores into default filing database.
10. a kind of computer readable storage medium, which is characterized in that be stored with insurance on the computer readable storage medium and protect
It is single to concentrate vouching system, it is realized when the insurance policy concentrates vouching system to be executed by processor as any in claim 5 to 9
The step of insurance policy described in concentrates vouching method.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810182943.9A CN108346036A (en) | 2018-03-06 | 2018-03-06 | Insurance policy concentrates vouching method, electronic device and readable storage medium storing program for executing |
PCT/CN2018/089719 WO2019169768A1 (en) | 2018-03-06 | 2018-06-03 | Centralized insurance policy auditing method, electronic device, and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810182943.9A CN108346036A (en) | 2018-03-06 | 2018-03-06 | Insurance policy concentrates vouching method, electronic device and readable storage medium storing program for executing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108346036A true CN108346036A (en) | 2018-07-31 |
Family
ID=62957848
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810182943.9A Pending CN108346036A (en) | 2018-03-06 | 2018-03-06 | Insurance policy concentrates vouching method, electronic device and readable storage medium storing program for executing |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN108346036A (en) |
WO (1) | WO2019169768A1 (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109165849A (en) * | 2018-08-27 | 2019-01-08 | 众安信息技术服务有限公司 | Methods of risk assessment and device |
CN109360112A (en) * | 2018-10-27 | 2019-02-19 | 平安医疗健康管理股份有限公司 | A kind of psychotic disorder authentication method and relevant device based on data processing |
CN109492095A (en) * | 2018-10-16 | 2019-03-19 | 平安健康保险股份有限公司 | Claims Resolution data processing method, device, computer equipment and storage medium |
CN109636510A (en) * | 2018-11-28 | 2019-04-16 | 阿里巴巴集团控股有限公司 | A kind of determining consumer's risk preference, the recommended method of finance product and device |
CN109636625A (en) * | 2018-10-31 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Processing method and processing device, storage medium, the computer equipment of insurance electronic contract |
CN109885736A (en) * | 2019-01-24 | 2019-06-14 | 平安科技(深圳)有限公司 | Recognition methods, device, computer equipment and the storage medium of abnormal declaration form |
CN110009515A (en) * | 2019-03-12 | 2019-07-12 | 中国平安财产保险股份有限公司 | Document method of calibration, device, server and medium based on recognition of face |
CN111008902A (en) * | 2019-11-25 | 2020-04-14 | 泰康保险集团股份有限公司 | Method, device, equipment and medium for processing data of underwriting |
CN111105318A (en) * | 2019-12-29 | 2020-05-05 | 北京车与车科技有限公司 | Intelligent insurance and image processing method on vehicle insurance line |
CN111652746A (en) * | 2020-05-29 | 2020-09-11 | 泰康保险集团股份有限公司 | Information generation method and device, electronic equipment and storage medium |
CN112419072A (en) * | 2020-10-30 | 2021-02-26 | 中汽研(天津)汽车工程研究院有限公司 | Automobile insurance anti-leakage calculation method based on automobile physical attributes |
CN113469826A (en) * | 2021-07-22 | 2021-10-01 | 阳光人寿保险股份有限公司 | Information processing method, device, equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105159948A (en) * | 2015-08-12 | 2015-12-16 | 成都数联易康科技有限公司 | Medical insurance fraud detection method based on multiple features |
CN106682987A (en) * | 2016-11-21 | 2017-05-17 | 中国平安财产保险股份有限公司 | Property insurance claim settlement realization method and realization system thereof |
CN107103658A (en) * | 2017-04-25 | 2017-08-29 | 哈尔滨工业大学 | Aerial engine air passage method for detecting abnormality based on deep learning and Gaussian Profile |
CN107240024A (en) * | 2017-05-22 | 2017-10-10 | 中国平安人寿保险股份有限公司 | The anti-fraud recognition methods of settlement of insurance claim and device |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9892441B2 (en) * | 2016-04-01 | 2018-02-13 | OneTrust, LLC | Data processing systems and methods for operationalizing privacy compliance and assessing the risk of various respective privacy campaigns |
CN106651588A (en) * | 2016-11-09 | 2017-05-10 | 前海企保科技(深圳)有限公司 | Underwriting method and apparatus for logistics insurance policy |
-
2018
- 2018-03-06 CN CN201810182943.9A patent/CN108346036A/en active Pending
- 2018-06-03 WO PCT/CN2018/089719 patent/WO2019169768A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105159948A (en) * | 2015-08-12 | 2015-12-16 | 成都数联易康科技有限公司 | Medical insurance fraud detection method based on multiple features |
CN106682987A (en) * | 2016-11-21 | 2017-05-17 | 中国平安财产保险股份有限公司 | Property insurance claim settlement realization method and realization system thereof |
CN107103658A (en) * | 2017-04-25 | 2017-08-29 | 哈尔滨工业大学 | Aerial engine air passage method for detecting abnormality based on deep learning and Gaussian Profile |
CN107240024A (en) * | 2017-05-22 | 2017-10-10 | 中国平安人寿保险股份有限公司 | The anti-fraud recognition methods of settlement of insurance claim and device |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109165849A (en) * | 2018-08-27 | 2019-01-08 | 众安信息技术服务有限公司 | Methods of risk assessment and device |
CN109492095A (en) * | 2018-10-16 | 2019-03-19 | 平安健康保险股份有限公司 | Claims Resolution data processing method, device, computer equipment and storage medium |
CN109360112A (en) * | 2018-10-27 | 2019-02-19 | 平安医疗健康管理股份有限公司 | A kind of psychotic disorder authentication method and relevant device based on data processing |
CN109636625A (en) * | 2018-10-31 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Processing method and processing device, storage medium, the computer equipment of insurance electronic contract |
CN109636510A (en) * | 2018-11-28 | 2019-04-16 | 阿里巴巴集团控股有限公司 | A kind of determining consumer's risk preference, the recommended method of finance product and device |
CN109885736A (en) * | 2019-01-24 | 2019-06-14 | 平安科技(深圳)有限公司 | Recognition methods, device, computer equipment and the storage medium of abnormal declaration form |
CN110009515A (en) * | 2019-03-12 | 2019-07-12 | 中国平安财产保险股份有限公司 | Document method of calibration, device, server and medium based on recognition of face |
CN111008902A (en) * | 2019-11-25 | 2020-04-14 | 泰康保险集团股份有限公司 | Method, device, equipment and medium for processing data of underwriting |
CN111105318A (en) * | 2019-12-29 | 2020-05-05 | 北京车与车科技有限公司 | Intelligent insurance and image processing method on vehicle insurance line |
CN111652746A (en) * | 2020-05-29 | 2020-09-11 | 泰康保险集团股份有限公司 | Information generation method and device, electronic equipment and storage medium |
CN111652746B (en) * | 2020-05-29 | 2023-08-29 | 泰康保险集团股份有限公司 | Information generation method, device, electronic equipment and storage medium |
CN112419072A (en) * | 2020-10-30 | 2021-02-26 | 中汽研(天津)汽车工程研究院有限公司 | Automobile insurance anti-leakage calculation method based on automobile physical attributes |
CN112419072B (en) * | 2020-10-30 | 2022-10-14 | 中汽研(天津)汽车工程研究院有限公司 | Automobile insurance anti-leakage method based on automobile physical attributes |
CN113469826A (en) * | 2021-07-22 | 2021-10-01 | 阳光人寿保险股份有限公司 | Information processing method, device, equipment and storage medium |
CN113469826B (en) * | 2021-07-22 | 2022-12-09 | 阳光人寿保险股份有限公司 | Information processing method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2019169768A1 (en) | 2019-09-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108346036A (en) | Insurance policy concentrates vouching method, electronic device and readable storage medium storing program for executing | |
CN107632995B (en) | The method and model training control system of Random Forest model training | |
CN110400215B (en) | Method and system for constructing enterprise family-oriented small micro enterprise credit assessment model | |
CN107910068A (en) | Insure health risk Forecasting Methodology, device, equipment and the storage medium of user | |
CN108492196A (en) | The air control method of medical insurance unlawful practice is inferred by data analysis | |
CN107767021A (en) | A kind of risk control method and equipment | |
CN110516910A (en) | Declaration form core based on big data protects model training method and core protects methods of risk assessment | |
CN110020002A (en) | Querying method, device, equipment and the computer storage medium of event handling scheme | |
CN109285082A (en) | Insurance products recommended method, device and computer readable storage medium | |
CN107203866A (en) | The processing method and device of order | |
CN109740689A (en) | A kind of error label data screening method and system of image, semantic segmentation | |
CN105719045A (en) | Retention risk determiner | |
CN109978619B (en) | Method, system, equipment and medium for screening air ticket pricing strategy | |
KR102491947B1 (en) | Apparatus and method for providing information on regulatory laws based on artificial intelligence learning | |
CN110610431A (en) | Intelligent claim settlement method and intelligent claim settlement system based on big data | |
CN110909195A (en) | Picture labeling method and device based on block chain, storage medium and server | |
CN110751317A (en) | Power load prediction system and prediction method | |
CN108492137A (en) | Telephone outbound call control and analysis, electronic device and readable storage medium storing program for executing | |
CN106294524A (en) | A kind for the treatment of method and apparatus of relation data | |
CN111179095A (en) | Health risk assessment-based underwriting method, system, equipment and storage medium | |
CN114444863A (en) | Enterprise production safety assessment method, system, device and storage medium | |
CN113837189A (en) | Intelligent management method and system for unit vehicle | |
CN107679635A (en) | Client's follow-up method, system and readable storage medium storing program for executing based on priority | |
CN109558887A (en) | A kind of method and apparatus of predictive behavior | |
CN116843481A (en) | Knowledge graph analysis method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180731 |