CN111179095A - Health risk assessment-based underwriting method, system, equipment and storage medium - Google Patents
Health risk assessment-based underwriting method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN111179095A CN111179095A CN201811329665.1A CN201811329665A CN111179095A CN 111179095 A CN111179095 A CN 111179095A CN 201811329665 A CN201811329665 A CN 201811329665A CN 111179095 A CN111179095 A CN 111179095A
- Authority
- CN
- China
- Prior art keywords
- risk
- attribute
- evaluation
- type
- 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
Images
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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides an underwriting method, a system, equipment and a storage medium based on health risk assessment, wherein the method comprises the following steps: collecting attribute values of each first type of evaluation attribute of the insurance user; classifying the attribute values of the first-class evaluation attributes of the insurance users into corresponding risk classes according to the mapping relation between the pre-stored risk classes and the first-class evaluation attributes to obtain first-class evaluation attribute data sets of the risk classes; and inputting the first-class evaluation attribute data sets of the risk types into the first probability calculation models corresponding to the risk types to obtain the claim probability values of the risk types. By adopting the scheme of the invention, based on the big data training model, the risk probability is automatically calculated by adopting the model, the development cost is reduced, the multi-risk species underwriting evaluation is supported, the underwriting efficiency is improved, and the accuracy of the risk evaluation is improved by taking big data statistics as the basis.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an underwriting method, system, equipment and storage medium based on health risk assessment.
Background
The commercial health insurance is an important component of a medical security system in China, the development of the commercial health insurance is accelerated, the multi-level medical security system is favorably tamped, and the diversified health security requirements of people are met. In the traditional health insurance underwriting process, once the insured has the notification content in the health notification, the insured needs to be manually checked and judged. Because the insurance awareness of the customers is gradually increased in recent years, in order to avoid the refusal of the insurance company due to the inferior notice, the quantity of the health notice of the customers is increased when the insurance is applied, and the workload of manual insurance checking is increased. Therefore, a method for automatically judging the underwriting conclusion in real time according to the notice of the health condition of the client is urgently needed.
At present, a question-answering decision method for fixed questions of a single risk category is realized by designing a series of fixed questions, options and underwriting conclusions in advance, asking an applicant or an insured to select the questions during application and automatically generating different underwriting conclusions according to different options selected by a client.
Fig. 1 is a schematic flow chart of a question-answer decision method for fixed questions of a single risk category. The decision method has the following disadvantages:
(1) the questions and answers are based entirely on the experience of insurance company professionals and lack the ability to automatically analyze the generated rules for big data statistics.
(2) And passively waiting for the notification of the client, such as intentionally not notifying the insurance client, so that the action risk assessment function cannot be performed.
(3) The questions and the answers are fixed, and the willingness persons can be informed of the questions and the answers in a mode of avoiding the heavy things and the light things repeatedly and trying to avoid the risk assessment.
(4) The development cost is high. Each insurance product needs to make questions, options and underwriting conclusions separately, thus requiring a large number of underwriting professionals to manually handle it.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide an underwriting method, a system, equipment and a storage medium based on health risk assessment, a mature model is trained based on big data, and the risk probability is automatically calculated by adopting the model, so that the development cost is reduced, the multi-risk underwriting assessment is supported, and the underwriting efficiency is improved.
The embodiment of the invention provides a health risk assessment-based underwriting method, which comprises the following steps:
collecting attribute values of each first type of evaluation attribute of the insurance user;
classifying the attribute values of the first-class evaluation attributes of the insurance users into corresponding risk classes according to the mapping relation between the pre-stored risk classes and the first-class evaluation attributes to obtain first-class evaluation attribute data sets of the risk classes;
and inputting the first-class evaluation attribute data sets of the various dangerous types into the first probability calculation models corresponding to the various dangerous types to obtain the claim probability values of the various dangerous types, inputting the first-class evaluation attribute data sets of the various dangerous types into the first probability calculation models corresponding to the various dangerous types, and outputting the first-class evaluation attribute data sets including the claim probability values.
Optionally, the collecting attribute values of the first type evaluation attributes of the insurance users comprises collecting attribute values of the first type evaluation attributes of the insurance users from an insurance company management system.
Optionally, the method further comprises the steps of:
collecting a plurality of policy data from an insurance company management system, wherein each policy data comprises attribute values of each first type of evaluation attribute and information on whether the claim occurs or not, generating a first type of attribute value array, marking whether the claim occurs or not on the first type of attribute value array, and adding the marked first type of attribute value array into a training set of a first probability calculation model of a risk type to which the policy belongs;
a training set of first probability calculation models for each risk category, the first probability calculation models for each risk category being trained.
Optionally, the method further includes obtaining a preset weight of each first-type evaluation attribute, and performing weight marking on each attribute value in the first-type attribute value array according to the preset weight.
Optionally, the first-class evaluation attribute data set of each risk category includes a first-class attribute value array of the insurance user.
Optionally, the collecting attribute values of the first-class assessment attributes of the insurance user includes the following steps:
pre-storing evaluation problems and options corresponding to the first type of evaluation attributes, and pre-storing scores of the options of the evaluation problems;
and collecting the response results of the insurance users to each evaluation question, and taking the scores of the options selected by the insurance users as the attribute values corresponding to the first type of evaluation attributes.
Optionally, the method further comprises the steps of:
collecting attribute values of each second type evaluation attribute of the insurable user;
classifying the collected attribute values of the second type evaluation attributes into corresponding risk types according to the mapping relation between the risk types and the second type evaluation attributes to obtain second type evaluation attribute data sets of the risk types;
and inputting the second type evaluation attribute data sets of the various dangerous types into the second probability calculation models corresponding to the various dangerous types to obtain the risk probability values of the various dangerous types, inputting the second type evaluation attribute data sets of the various dangerous types into the second probability calculation models corresponding to the various dangerous types, and outputting the second type evaluation attribute data sets including the risk probability values.
Optionally, the second type of assessment attribute comprises a medical type assessment attribute, a financial type assessment attribute, and a credit type assessment attribute;
the collecting of the attribute values of the second evaluation attributes of the insurance users comprises collecting the attribute values of the medical evaluation attributes of the insurance users from a medical data management system, collecting the attribute values of the financial evaluation attributes of the insurance users from a financial information management system and collecting the attribute values of the credit investigation type evaluation attributes of the insurance users from a credit investigation information management system;
the second probability calculation model includes a disease probability calculation model, a financial probability calculation model, and a credit probability calculation model.
Optionally, the method further comprises the steps of:
collecting attribute values of medical evaluation attributes of a plurality of users from a medical data management system and whether the plurality of users have a specified disease, adding a training set of a disease probability calculation model, collecting attribute values of financial evaluation attributes of the plurality of users from a financial probability calculation model and whether the plurality of users have a financial risk, adding the training set of the financial probability calculation model, collecting attribute values of credit investigation attribute of the plurality of users from a credit investigation information management system and whether the plurality of users have a credit investigation risk, and adding the training set of the credit investigation probability calculation model;
and training a disease probability calculation model by adopting the training set of the disease probability calculation model, training a financial probability calculation model by adopting the training set of the financial probability calculation model, and training a credit investigation probability calculation model by adopting the training set of the credit investigation probability calculation model.
Optionally, the method further comprises the steps of:
and generating an insurance conclusion of the insurance user aiming at each risk according to the claim probability value and the risk probability value of each risk.
The embodiment of the invention also provides an underwriting system based on health risk assessment, which is applied to the underwriting method based on health risk assessment, and the system comprises:
the first attribute library is used for storing the mapping relation between the plurality of risk types and the plurality of first-type evaluation attributes;
the first model storage module is used for storing trained first probability calculation models corresponding to the risk varieties, the input of the first probability calculation models corresponding to the risk varieties comprises first type evaluation attribute data sets of the risk varieties, and the output of the first probability calculation models corresponding to the risk varieties comprises claim probability values;
the first data acquisition module is used for acquiring the attribute values of the first type evaluation attributes of the insurance users;
the first attribute classification module is used for classifying the attribute values of the first-class evaluation attributes of the insurance users into corresponding risk classes according to the mapping relation between the risk classes and the first-class evaluation attributes to obtain first-class evaluation attribute data sets of the risk classes;
and the first evaluation module is used for inputting the first type of evaluation attribute data sets of each risk category into the corresponding first probability calculation model to obtain the claim probability value of each risk category.
An embodiment of the present invention further provides an underwriting device based on health risk assessment, including:
a processor;
a memory having stored therein executable instructions of the processor;
wherein the processor is configured to perform the steps of the health risk assessment based underwriting method via execution of the executable instructions.
The embodiment of the present invention further provides a computer-readable storage medium for storing a program, where the program implements the steps of the health risk assessment-based underwriting method when executed.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
The health risk assessment-based underwriting method, system, equipment and storage medium provided by the invention have the following advantages:
(1) the method has the advantages that the mature claim probability model is trained by adopting the insurance big data and the insurance policy output insurance conditions of a plurality of users, the attribute values of the insurance users are collected, the claim probability value of the users is automatically calculated according to the claim probability model, compared with manual processing, the calculation efficiency is improved, the big data statistics is used as the support, and the accuracy of risk assessment is improved;
(2) and (3) supporting multi-risk species insurance evaluation: by utilizing a health risk integration method, a plurality of risk subsets of the dangerous species are integrated into a total risk set, and a user only needs to perform question-answer decision once to complete the insurance risk assessment of the multiple dangerous species, so that the repeated question-answer decision making of the user is avoided, the insurance efficiency is improved, and the user experience is improved;
(3) the method can further collect external data such as medical big data, financial data and credit investigation data, train a mature risk probability model according to the external data and corresponding risk values, automatically calculate the probability value of risk occurrence of the user according to the attribute value of the insurance user corresponding to the external attribute, and synthesize the internal data and the external data of the insurance policy, so that the accuracy of risk assessment can be greatly improved, and one-time accurate underwriting of multiple insurance categories can be realized.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, with reference to the accompanying drawings.
FIG. 1 is a flow diagram of a prior art underwriting decision question-answering for a single risk species;
FIG. 2 is a flow chart of a health risk assessment based underwriting method according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a health risk assessment-based underwriting system according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of an underwriting system with a second type of risk assessment added according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a health risk assessment based underwriting apparatus according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
As shown in fig. 2, in order to solve the above technical problem, an embodiment of the present invention provides a health risk assessment-based underwriting method, which includes the following steps:
s100: collecting attribute values of each first type of evaluation attribute of the insurance user;
s200: classifying the attribute values of the first-class evaluation attributes of the insurance users into corresponding risk classes according to the mapping relation between the risk classes and the first-class evaluation attributes to obtain first-class evaluation attribute data sets of the risk classes;
the relationship between the risk type and the first type evaluation attribute is a many-to-many relationship, for example, the risk type A may correspond to the attribute A, B, C, D, E, F, the risk type B may correspond to the attribute A, C, D, M, L, and the risk type C may correspond to the attribute B, C, M, N, etc.;
s300: and inputting the first-class evaluation attribute data sets of all the risk types into the corresponding first probability calculation models to obtain the claim probability values of all the risk types.
Because the mode of judging the paying probability of each risk is different, the first probability calculation model in the invention is classified into the risk, namely, each risk trains one first probability calculation model.
Therefore, in this embodiment, the mature claims probability model is trained by adopting the insurance big data and the policy issuing insurance condition of a plurality of users in advance, the attribute values of the insurable users are collected in step S100, and the claims probability value of the user is automatically calculated according to the claims probability model in step S300.
As shown in fig. 3, correspondingly, an embodiment of the present invention further provides an underwriting system based on health risk assessment, where the system includes:
a first attribute library M110 for storing a mapping relationship between a plurality of risk types and a plurality of first-type evaluation attributes;
a first model storage module M120, configured to store trained first probability calculation models corresponding to the respective risk categories, where an input of the first probability calculation model corresponding to the respective risk category includes a first category evaluation attribute data set of the respective risk category, and an output of the first probability calculation model corresponding to the respective risk category includes a claim probability value;
the first data acquisition module M130 is used for acquiring attribute values of each first-type evaluation attribute of the insurance user;
the first attribute classification module M140 is configured to classify, according to a mapping relationship between the risk types and the first-class evaluation attributes, the attribute values of the first-class evaluation attributes of the insurance users into corresponding risk types, so as to obtain first-class evaluation attribute data sets of the risk types;
the first evaluation module M150 is configured to input the first-class evaluation attribute data sets of each risk category into the corresponding first probability calculation model, so as to obtain a claim probability value of each risk category.
In this embodiment, the first data collection module M130 collects attribute values of the first type of assessment attribute of the insurance user from the insurance company management system. Correspondingly, the first type of evaluation attribute may include some personal information of the user, such as age, occupation, income, residence, etc., and may also include health notification information of the user, such as whether the family has a genetic disease, whether there is an excessive disease in the near future, etc.
In this embodiment, the health risk assessment-based underwriting method may further include the following steps:
collecting a plurality of policy data from an insurance company management system, wherein each policy data comprises attribute values of each first type of evaluation attribute and information on whether the claim occurs or not, generating a first type of attribute value array, marking whether the claim occurs or not on the first type of attribute value array, and adding the marked first type of attribute value array into a training set of a first probability calculation model of a risk type to which the policy belongs;
and training the first probability calculation model of each risk type by adopting the training set of the first probability calculation model of each risk type. The first model training module may train the first probability calculation model based on an existing machine learning method, for example, an existing classifier such as a linear classifier (LR) or a Support Vector Machine (SVM) is used for training, but the invention is not limited thereto.
Correspondingly, in this embodiment, the health risk assessment-based underwriting system further includes a first training set acquisition module and a first model training module, which are respectively used for acquiring the training sets of the first probability calculation models and training each first probability calculation model by using the training sets of the first probability training models.
Further, the first training set acquisition module is further configured to acquire a preset weight of each first-class evaluation attribute, and perform weight labeling on each attribute value in the first-class attribute value array according to the preset weight. The preset weight of each first-type evaluation attribute can be a preset weight of an insurance company, namely, the importance of each attribute is judged by a worker according to experience. Therefore, the embodiment introduces the existing experience into the model training of machine learning through a method of presetting the weight, better combines the existing technology and the automatic model identification technology, and improves the accuracy of the claim probability value.
In this embodiment, the first type of evaluation attribute data set for each risk category includes a first type of attribute value array for the insurable user.
Further, in the health risk assessment-based underwriting method, S100: the method for collecting the attribute value of the first type of evaluation attribute of the insurance user comprises the following steps:
pre-storing evaluation problems and options corresponding to the first type of evaluation attributes, and pre-storing scores of the options of the evaluation problems;
and collecting the response results of the insurance users to each evaluation question, and taking the scores of the options selected by the insurance users as the attribute values corresponding to the first type of evaluation attributes.
When the insurance company management system collects the answer results of the users to the assessment questions, the assessment questions and options corresponding to the insurance risk can be selected from the underwriting question management module according to the types of the risks required to be applied by the insurance users, then the assessment questions and options of various insurance risks are integrated together to obtain a questionnaire, and the insurance users are asked to answer. Therefore, by adopting the underwriting system of the embodiment, the insurance user only needs to answer once, and the system can quickly acquire the first evaluation attribute data of a plurality of required risks. The first data acquisition module can generate the attribute value of the required first-class evaluation attribute after acquiring the answer result of the user to each evaluation question from the insurance company management system.
Further, in the health risk assessment-based underwriting method, in addition to the assessment of the internal risk factors (first-type assessment attributes), the assessment of the external risk factors (second-type assessment attributes) may be added. The second type of evaluation attribute is further described below.
Based on this, the health risk assessment-based underwriting method further comprises the following steps:
collecting attribute values of each second type evaluation attribute of the insurable user;
classifying the collected attribute values of the second type evaluation attributes into corresponding risk types according to the mapping relation between the risk types and the second type evaluation attributes to obtain second type evaluation attribute data sets of the risk types, inputting the second type evaluation attribute data sets of the risk types to the second probability calculation models corresponding to the risk types, and outputting the second type evaluation attribute data sets including risk probability values
And inputting the second type evaluation attribute data sets of each risk type into the corresponding second probability calculation model to obtain the risk probability value of each risk type.
As shown in fig. 3, after adding the evaluation of the second type of evaluation attribute, the health risk evaluation-based underwriting system further includes:
the second evaluation attribute library M210 is used for storing mapping relations between a plurality of risk types and a plurality of second type evaluation attributes;
the second model storage module M220 is used for storing the trained second probability calculation models corresponding to the dangerous species;
the second data acquisition module M230 is used for acquiring the attribute values of the second type evaluation attributes of the insurance users;
the second attribute classification module M240 is configured to classify the acquired attribute values of the second-class evaluation attributes into corresponding risk classes according to the mapping relationship between the risk classes and the second-class evaluation attributes, so as to obtain second-class evaluation attribute data sets of the risk classes;
and the second evaluation module M250 is configured to input the second type evaluation attribute data sets of each risk category to the corresponding second probability calculation models to obtain risk probability values of each risk category.
In this embodiment, the second type of assessment attributes includes a medical type assessment attribute, a financial type assessment attribute, and a credit type assessment attribute;
the second data acquisition module M230 acquires the attribute value of the medical evaluation attribute of the insurance user from the medical data management system, acquires the financial evaluation attribute and the attribute value of the insurance user from the financial information management system, and acquires the attribute value of the credit investigation type evaluation attribute of the insurance user from the credit investigation information management system; the medical evaluation attribute may be information such as the age, residence, medical position, health evaluation level, etc. of the user, the financial evaluation attribute may be information such as the age, income, deposit, consumption amount, etc. of the user, and the credit evaluation attribute may be the age, payment record, overdue record, etc. of the user.
Correspondingly, the second probability calculation model comprises a disease probability calculation model, a financial probability calculation model and a credit investigation probability calculation model.
In this embodiment, the health risk assessment-based underwriting method further includes the following steps:
collecting attribute values of medical evaluation attributes of a plurality of users from a medical data management system and whether the plurality of users have a specified disease, adding a training set of a disease probability calculation model, collecting attribute values of financial evaluation attributes of the plurality of users from a financial probability calculation model and whether the plurality of users have a financial risk, adding the training set of the financial probability calculation model, collecting attribute values of credit investigation attribute of the plurality of users from a credit investigation information management system and whether the plurality of users have a credit investigation risk, and adding the training set of the credit investigation probability calculation model;
and training a disease probability calculation model by adopting the training set of the disease probability calculation model, training a financial probability calculation model by adopting the training set of the financial probability calculation model, and training a credit investigation probability calculation model by adopting the training set of the credit investigation probability calculation model. The second model training module may train the second probability calculation model based on an existing machine learning method, for example, an existing classifier such as a linear classifier (LR) or a Support Vector Machine (SVM) is used for training, but the invention is not limited thereto.
Correspondingly, the health risk assessment-based underwriting system may further include a second training set acquisition module and a second model training module, which are respectively configured to acquire a training set of the second probability calculation model from each cooperative system and train each second probability calculation model according to the training set of the second probability calculation model.
The second evaluation module M250 may input the attribute value of the medical-type evaluation attribute of the insurance user into the disease probability calculation model to obtain the probability that the insurance user may have a specified disease, input the attribute value of the financial-type evaluation attribute of the insurance user into the financial probability calculation model to obtain the probability that the financial condition of the insurance user may have a risk, where the risk may be generated, which means that the income and the guarantee amount of the user may be obviously mismatched, there is a fraud suspicion, and the like, and input the attribute value of the credit investigation attribute of the insurance user into the credit investigation probability calculation model to obtain the probability that the credit investigation of the insurance user has a risk, where the risk may be generated, which means that the personal fraud record of the user is poor, there may be a fraud suspicion, and the like.
Therefore, the embodiment can obtain the internal risk probability value through the machine learning and model calculation of the internal risk factor (the first type of evaluation attribute), and can obtain the external risk probability value through the machine learning and model calculation of the external risk factor (the second type of evaluation attribute). And the accurate and effective insurance risk evaluation result can be obtained by integrating the internal risk evaluation and the external risk evaluation.
Further, as shown in fig. 3, the health risk assessment-based underwriting system further includes:
and the underwriting conclusion generating module M300 is used for generating underwriting conclusions of the insurance users for the various dangerous types according to the claims probability value and the risk probability value of the various dangerous types.
Therefore, the invention can automatically generate the insurance conclusion of a plurality of dangerous species only by filling the questionnaire once by the insurance user, thereby improving the user experience and the efficiency and the accuracy of the insurance.
Correspondingly, the health risk assessment-based underwriting method can further comprise the following steps:
and generating an insurance conclusion of the insurance user aiming at each risk according to the claim probability value and the risk probability value of each risk.
Specifically, the judgment conditions of various insurance conclusions of various risk types may be set, the judgment conditions include a range of a claim probability value and a range of a risk probability value, and if the claim probability value and the risk probability value belong to the range of the judgment conditions of one insurance conclusion, the insurance conclusion is determined to be the insurance conclusion of the corresponding risk type. Therefore, the invention can automatically generate the insurance conclusion of a plurality of dangerous species only by filling the questionnaire once by the insurance user, thereby improving the user experience and the efficiency and the accuracy of the insurance.
Therefore, by adopting the health risk assessment-based underwriting method of the embodiment, the use of the insurance company end can be facilitated, the manual operation workload of the insurance company end is reduced, more than 40% of manual underwriting auditing work can be replaced, the underwriting efficiency is improved, the development cost of a question-answering decision method is reduced, multi-risk underwriting is supported, the application scene in insurance sales is expanded, and the premium income is increased. In addition, the insurance company can be supported to adjust and update the insurance application health notification items of different dangerous species in real time, and the insurance conclusion judgment conditions of the dangerous species can be freely modified and updated, so that the application flexibility of the insurance scheme is improved. In addition, the health risk factor checking and protecting method can conveniently adjust the checking and protecting problem and/or options of the health risk factors, provide more accurate checking and protecting problem, and judge whether the corresponding health risk factors have risks or not according to feedback data of the client on the checking and protecting problem in a more targeted manner.
In this embodiment, the underwriting conclusion may include at least one of a body, a rejection, an exclusionary, a fee, and a limit premium. In practical applications, other types of underwriting conclusions can be added, or selected from the underwriting conclusions listed here, all of which fall within the scope of the present invention.
The embodiment of the invention also provides health risk assessment-based underwriting equipment, which comprises a processor; a memory having stored therein executable instructions of the processor; wherein the processor is configured to perform the steps of the health risk assessment based underwriting method via execution of the executable instructions.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a method, system, or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" platform.
An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 5. The electronic device 600 shown in fig. 5 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 5, the electronic device 600 is embodied in the form of a general purpose computing device. The combination of the electronic device 600 may include, but is not limited to: at least one processing unit 610, at least one memory unit 620, a bus 630 connecting different platform combinations (including memory unit 620 and processing unit 610), a display unit 640, etc.
Wherein the storage unit stores program code executable by the processing unit 610 to cause the processing unit 610 to perform steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of the present specification. For example, the processing unit 610 may perform the steps as shown in fig. 2.
The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.
The memory unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 600 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, to name a few.
The embodiment of the present invention further provides a computer-readable storage medium for storing a program, where the program implements the steps of the health risk assessment-based underwriting method when executed. In some possible embodiments, aspects of the present invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of this specification, when the program product is run on the terminal device.
Referring to fig. 6, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
In summary, compared with the prior art, the health risk assessment-based underwriting method, system, device and storage medium provided by the invention have the following advantages:
(1) the method has the advantages that the mature claim probability model is trained by adopting the insurance big data and the insurance policy output insurance conditions of a plurality of users, the attribute values of the insurance users are collected, the claim probability value of the users is automatically calculated according to the claim probability model, compared with manual processing, the calculation efficiency is improved, the big data statistics is used as the support, and the accuracy of risk assessment is improved;
(2) and (3) supporting multi-risk species insurance evaluation: by utilizing a health risk integration method, a plurality of risk subsets of the dangerous species are integrated into a total risk set, and a user only needs to perform question-answer decision once to complete the insurance risk assessment of the multiple dangerous species, so that the repeated question-answer decision making of the user is avoided, the insurance efficiency is improved, and the user experience is improved;
(3) the method can further collect external data such as medical big data, financial data and credit investigation data, train a mature risk probability model according to the external data and corresponding risk values, automatically calculate the probability value of risk occurrence of the user according to the attribute value of the insurance user corresponding to the external attribute, and synthesize the internal data and the external data of the insurance policy, so that the accuracy of risk assessment can be greatly improved, and one-time accurate underwriting of multiple insurance categories can be realized.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (13)
1. An underwriting method based on health risk assessment, characterized by comprising the following steps:
collecting attribute values of each first type of evaluation attribute of the insurance user;
classifying the attribute values of the first-class evaluation attributes of the insurance users into corresponding risk classes according to the mapping relation between the pre-stored risk classes and the first-class evaluation attributes to obtain first-class evaluation attribute data sets of the risk classes;
and inputting the first-class evaluation attribute data sets of the various dangerous types into the first probability calculation models corresponding to the various dangerous types to obtain the claim probability values of the various dangerous types, inputting the first-class evaluation attribute data sets of the various dangerous types into the first probability calculation models corresponding to the various dangerous types, and outputting the first-class evaluation attribute data sets including the claim probability values.
2. The health risk assessment based underwriting method according to claim 1, wherein the collecting attribute values of the first type assessment attributes of the insurance users comprises collecting attribute values of the first type assessment attributes of the insurance users from an insurance company management system.
3. The health risk assessment based underwriting method according to claim 2, further comprising the steps of:
collecting a plurality of policy data from an insurance company management system, wherein each policy data comprises attribute values of each first type of evaluation attribute and information on whether the claim occurs or not, generating a first type of attribute value array, marking whether the claim occurs or not on the first type of attribute value array, and adding the marked first type of attribute value array into a training set of a first probability calculation model of a risk type to which the policy belongs;
a training set of first probability calculation models for each risk category, the first probability calculation models for each risk category being trained.
4. The health risk assessment based underwriting method according to claim 3, further comprising obtaining a preset weight of each first type assessment attribute, and performing weight marking on each attribute value in the first type attribute value array according to the preset weight.
5. The health risk assessment-based underwriting method according to claim 4, wherein the first-class assessment attribute data set of each risk category comprises a first-class attribute value array of an insurance user.
6. The health risk assessment based underwriting method according to claim 5, wherein the collecting attribute values of the first type assessment attributes of the insurance users comprises the following steps:
pre-storing evaluation problems and options corresponding to the first type of evaluation attributes, and pre-storing scores of the options of the evaluation problems;
and collecting the response results of the insurance users to each evaluation question, and taking the scores of the options selected by the insurance users as the attribute values corresponding to the first type of evaluation attributes.
7. The health risk assessment based underwriting method according to claim 1, further comprising the steps of:
collecting attribute values of each second type evaluation attribute of the insurable user;
classifying the collected attribute values of the second type evaluation attributes into corresponding risk types according to the mapping relation between the risk types and the second type evaluation attributes to obtain second type evaluation attribute data sets of the risk types;
and inputting the second type evaluation attribute data sets of the various dangerous types into the second probability calculation models corresponding to the various dangerous types to obtain the risk probability values of the various dangerous types, inputting the second type evaluation attribute data sets of the various dangerous types into the second probability calculation models corresponding to the various dangerous types, and outputting the second type evaluation attribute data sets including the risk probability values.
8. The health risk assessment based underwriting method according to claim 7, wherein the second type of assessment attributes comprises a medical type assessment attribute, a financial type assessment attribute and a credit type assessment attribute;
the collecting of the attribute values of the second evaluation attributes of the insurance users comprises collecting the attribute values of the medical evaluation attributes of the insurance users from a medical data management system, collecting the attribute values of the financial evaluation attributes of the insurance users from a financial information management system and collecting the attribute values of the credit investigation type evaluation attributes of the insurance users from a credit investigation information management system;
the second probability calculation model includes a disease probability calculation model, a financial probability calculation model, and a credit probability calculation model.
9. The health risk assessment based underwriting method according to claim 8, further comprising the steps of:
collecting attribute values of medical evaluation attributes of a plurality of users from a medical data management system and whether the plurality of users have a specified disease, adding a training set of a disease probability calculation model, collecting attribute values of financial evaluation attributes of the plurality of users from a financial probability calculation model and whether the plurality of users have a financial risk, adding the training set of the financial probability calculation model, collecting attribute values of credit investigation attribute of the plurality of users from a credit investigation information management system and whether the plurality of users have a credit investigation risk, and adding the training set of the credit investigation probability calculation model;
and training a disease probability calculation model by adopting the training set of the disease probability calculation model, training a financial probability calculation model by adopting the training set of the financial probability calculation model, and training a credit investigation probability calculation model by adopting the training set of the credit investigation probability calculation model.
10. The health risk assessment based underwriting method according to claim 7, further comprising the steps of:
and generating an insurance conclusion of the insurance user aiming at each risk according to the claim probability value and the risk probability value of each risk.
11. An underwriting system based on health risk assessment, which is applied to the underwriting method based on health risk assessment according to any one of claims 1 to 10, and comprises:
the first attribute library is used for storing the mapping relation between the plurality of risk types and the plurality of first-type evaluation attributes;
the first model storage module is used for storing trained first probability calculation models corresponding to the risk varieties, the input of the first probability calculation models corresponding to the risk varieties comprises first type evaluation attribute data sets of the risk varieties, and the output of the first probability calculation models corresponding to the risk varieties comprises claim probability values;
the first data acquisition module is used for acquiring the attribute values of the first type evaluation attributes of the insurance users;
the first attribute classification module is used for classifying the attribute values of the first-class evaluation attributes of the insurance users into corresponding risk classes according to the mapping relation between the risk classes and the first-class evaluation attributes to obtain first-class evaluation attribute data sets of the risk classes;
and the first evaluation module is used for inputting the first type of evaluation attribute data sets of each risk category into the corresponding first probability calculation model to obtain the claim probability value of each risk category.
12. An underwriting device based on health risk assessment, comprising:
a processor;
a memory having stored therein executable instructions of the processor;
wherein the processor is configured to perform the steps of the health risk assessment based underwriting method of any one of claims 1 to 10 via execution of the executable instructions.
13. A computer readable storage medium storing a program, wherein the program when executed implements the steps of the health risk assessment-based underwriting method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811329665.1A CN111179095A (en) | 2018-11-09 | 2018-11-09 | Health risk assessment-based underwriting method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811329665.1A CN111179095A (en) | 2018-11-09 | 2018-11-09 | Health risk assessment-based underwriting method, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111179095A true CN111179095A (en) | 2020-05-19 |
Family
ID=70653514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811329665.1A Pending CN111179095A (en) | 2018-11-09 | 2018-11-09 | Health risk assessment-based underwriting method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111179095A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112150298A (en) * | 2020-09-28 | 2020-12-29 | 建信金融科技有限责任公司 | Data processing method, system, device and readable medium |
| CN113240531A (en) * | 2021-05-11 | 2021-08-10 | 建信金融科技有限责任公司 | Data processing method and device |
| CN113393331A (en) * | 2021-06-10 | 2021-09-14 | 罗忠明 | Database and algorithm based big data insurance accurate wind control, management, intelligent customer service and marketing system |
| CN116029839A (en) * | 2023-02-10 | 2023-04-28 | 中国人民健康保险股份有限公司深圳分公司 | Automatic execution operating system for operation of service system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107818513A (en) * | 2017-11-24 | 2018-03-20 | 泰康保险集团股份有限公司 | Methods of risk assessment and device, storage medium, electronic equipment |
| CN107910068A (en) * | 2017-11-29 | 2018-04-13 | 平安健康保险股份有限公司 | Insure health risk Forecasting Methodology, device, equipment and the storage medium of user |
| CN108198591A (en) * | 2017-12-28 | 2018-06-22 | 泰康保险集团股份有限公司 | For the method and apparatus of remote upload document |
| CN108416669A (en) * | 2018-03-13 | 2018-08-17 | 腾讯科技（深圳）有限公司 | User behavior data processing method, device, electronic equipment and computer-readable medium |
| CN108596440A (en) * | 2018-03-30 | 2018-09-28 | 北京有保无险科技有限公司 | A kind of insurance risk assessment method and system based on user |
| CN108734588A (en) * | 2017-04-14 | 2018-11-02 | 太平金融科技服务（上海）有限公司 | Intelligent core insurance system and intelligent core protect method |
-
2018
- 2018-11-09 CN CN201811329665.1A patent/CN111179095A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108734588A (en) * | 2017-04-14 | 2018-11-02 | 太平金融科技服务（上海）有限公司 | Intelligent core insurance system and intelligent core protect method |
| CN107818513A (en) * | 2017-11-24 | 2018-03-20 | 泰康保险集团股份有限公司 | Methods of risk assessment and device, storage medium, electronic equipment |
| CN107910068A (en) * | 2017-11-29 | 2018-04-13 | 平安健康保险股份有限公司 | Insure health risk Forecasting Methodology, device, equipment and the storage medium of user |
| CN108198591A (en) * | 2017-12-28 | 2018-06-22 | 泰康保险集团股份有限公司 | For the method and apparatus of remote upload document |
| CN108416669A (en) * | 2018-03-13 | 2018-08-17 | 腾讯科技（深圳）有限公司 | User behavior data processing method, device, electronic equipment and computer-readable medium |
| CN108596440A (en) * | 2018-03-30 | 2018-09-28 | 北京有保无险科技有限公司 | A kind of insurance risk assessment method and system based on user |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112150298A (en) * | 2020-09-28 | 2020-12-29 | 建信金融科技有限责任公司 | Data processing method, system, device and readable medium |
| CN112150298B (en) * | 2020-09-28 | 2022-12-09 | 建信金融科技有限责任公司 | Data processing method, system, device and readable medium |
| CN113240531A (en) * | 2021-05-11 | 2021-08-10 | 建信金融科技有限责任公司 | Data processing method and device |
| CN113393331A (en) * | 2021-06-10 | 2021-09-14 | 罗忠明 | Database and algorithm based big data insurance accurate wind control, management, intelligent customer service and marketing system |
| CN116029839A (en) * | 2023-02-10 | 2023-04-28 | 中国人民健康保险股份有限公司深圳分公司 | Automatic execution operating system for operation of service system |
| CN116029839B (en) * | 2023-02-10 | 2023-09-26 | 中国人民健康保险股份有限公司深圳分公司 | Automatic execution operating system for operation of service system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11861560B2 (en) | System and method for data record selection by application of predictive models and velocity analysis | |
| CN111179095A (en) | Health risk assessment-based underwriting method, system, equipment and storage medium | |
| US10445844B2 (en) | System and method for detecting, profiling and benchmarking intellectual property professional practices and the liability risks associated therewith | |
| CN111383101B (en) | Post-credit risk monitoring method, post-credit risk monitoring device, post-credit risk monitoring equipment and computer readable storage medium | |
| CN110349009B (en) | Multi-head lending default prediction method and device and electronic equipment | |
| US20150242856A1 (en) | System and Method for Identifying Procurement Fraud/Risk | |
| CN110910257A (en) | Information prediction method, information prediction device, electronic equipment and computer readable medium | |
| US10666576B2 (en) | Processing system responsive to analysis filter criteria | |
| CN111145009A (en) | Method and device for evaluating risk after user loan and electronic equipment | |
| US11783259B2 (en) | Interactive graphical user interface for insurance claim handlers including identifying insurance claim risks and health scores via a body diagram dashboard | |
| CN111180065A (en) | Insurance user evaluation method and device, electronic equipment and computer readable medium | |
| CN111199469A (en) | User payment model generation method and device and electronic equipment | |
| Karami et al. | Computational analysis of insurance complaints: Geico case study | |
| CN111597343B (en) | APP-based intelligent user occupation judgment method and device and electronic equipment | |
| CN109492859A (en) | Employees classification method and device based on neural network model, equipment, medium | |
| CN111210332A (en) | Method and device for generating post-loan management strategy and electronic equipment | |
| US20190279306A1 (en) | System and method for auditing insurance claims | |
| CN111192120B (en) | Pension community cost management method, system, equipment and storage medium | |
| CN116843481A (en) | Knowledge graph analysis method, device, equipment and storage medium | |
| CN115809930A (en) | Anti-fraud analysis method, device, equipment and medium based on data fusion matching | |
| CN116485019A (en) | Data processing method and device | |
| CN112070564B (en) | Advertisement pulling method, device and system and electronic equipment | |
| CN112712270B (en) | Information processing method, device, equipment and storage medium | |
| CN115238588A (en) | Graph data processing method, risk prediction model training method and device | |
| CN114942993A (en) | Hotel evaluation index acquisition method, system, 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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230317 Address after: 100195 room 304, unit 1, floor 4, building 9, West District, yard 9, Linglong Road, Haidian District, Beijing Applicant after: BEIJING YIYIYUN TECHNOLOGY Co.,Ltd. Address before: 301800 220-41, customs building, Baodi energy saving and environmental protection industrial zone, Baodi District, Tianjin Applicant before: TIANJIN HAPPINESS LIFE TECHNOLOGY Co.,Ltd. |