CN111180065A - Insurance user evaluation method and device, electronic equipment and computer readable medium - Google Patents
Insurance user evaluation method and device, electronic equipment and computer readable medium Download PDFInfo
- Publication number
- CN111180065A CN111180065A CN201811330057.2A CN201811330057A CN111180065A CN 111180065 A CN111180065 A CN 111180065A CN 201811330057 A CN201811330057 A CN 201811330057A CN 111180065 A CN111180065 A CN 111180065A
- Authority
- CN
- China
- Prior art keywords
- data
- insurance
- disease risk
- disease
- user
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 31
- 201000010099 disease Diseases 0.000 claims abstract description 149
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 149
- 238000000034 method Methods 0.000 claims abstract description 71
- 238000012545 processing Methods 0.000 claims abstract description 42
- 238000004422 calculation algorithm Methods 0.000 claims description 31
- 238000003860 storage Methods 0.000 claims description 20
- 238000010801 machine learning Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 238000013398 bayesian method Methods 0.000 claims description 2
- 238000003066 decision tree Methods 0.000 claims description 2
- 238000012795 verification Methods 0.000 abstract description 5
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000012502 risk assessment Methods 0.000 description 20
- 230000008569 process Effects 0.000 description 18
- 238000003745 diagnosis Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 12
- 230000036541 health Effects 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 7
- 239000003795 chemical substances by application Substances 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 206010012601 diabetes mellitus Diseases 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005429 filling process Methods 0.000 description 1
- 238000005111 flow chemistry technique Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 208000001072 type 2 diabetes mellitus Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Technology Law (AREA)
- Economics (AREA)
- Pathology (AREA)
- Development Economics (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The disclosure relates to an insurance user assessment method, device, electronic equipment and computer readable medium based on a disease risk model. Relating to the field of medical insurance information processing, the method comprises the following steps: acquiring medical data of a user through at least one data source; performing data processing on the medical data to generate characteristic data; inputting the characteristic data into at least one disease risk model to obtain disease risk data; and determining a risk label for the user from the disease risk data. The insurance user evaluation method, the insurance user evaluation device, the electronic equipment and the computer readable medium based on the disease risk model can quickly and accurately identify the user insurance policy with risks at the insurance verification end and assist in accurate insurance pricing.
Description
Technical Field
The present disclosure relates to the field of medical information processing, and in particular, to a method and an apparatus for evaluating insurance users based on a disease risk model, an electronic device, and a computer-readable medium.
Background
The personal insurance is the insurance taking the life and body of a person as the insurance target. Health notification is the process of informing the insured person of their physical health to the insurer for them to make risk assessment and ultimately determine if they can underwrite. In order to assess the health of the insured life and to determine the underwriting rate, each insurer requests that they fill out a health advice, i.e., an explanation of the health condition, when they accept the application for a client's application for insurance. According to the sixteenth rule of insurance Law, the insurance applicant can tell the obligation that the insurance company has enough influence to decide whether to take insurance or increase insurance rate, and the insurance company has the right to release the insurance contract, and the insurance company does not pay the insurance money for the insurance accident before the release of the insurance contract, and does not return the insurance fee.
However, in insurance practice, a considerable number of insurance applicants and insureds are often aware of the importance of insurance participation after the disease is present, and the insurance application does not show the medical history as well. According to incomplete statistics, the policy occupation ratio is not really informed to be as high as 15% -20% every year, and billions of additional losses are brought to the whole insurance industry.
To avoid loss due to improper notification, insurance companies typically review application for insurance (which may be during the customer's application, post-underwriting period, or claims settlement period). Because of the high cost and low time efficiency of physical examination and manual investigation, insurance companies can only verify some suspected insurance policies. And under the condition of insufficient information, the underwriter can only judge the suspected risk manually by experience. This process is labor intensive and has limited accuracy. Whether the insurance policy can be quickly and accurately identified at the underwriting end or not is an urgent need of the insurance company at present.
Therefore, the present application proposes a new insurance user assessment method, apparatus, electronic device and computer readable medium based on disease risk model.
The above information disclosed in this background section is only for enhancement of understanding of the background of the disclosure and therefore it may contain information that does not constitute prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
In view of this, the present disclosure provides an insurance user assessment method, apparatus, electronic device and computer readable medium based on a disease risk model, which can quickly and accurately identify a user policy with risk at an insurance verification end, and assist in accurate insurance pricing.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.
According to an aspect of the present disclosure, an insurance user assessment method based on a disease risk model is provided, the method including: acquiring medical data of a user through a plurality of data sources; performing data processing on the medical data to generate characteristic data; inputting the characteristic data into at least one disease risk model to obtain disease risk data; and determining a risk label for the user from the disease risk data.
In an exemplary embodiment of the present disclosure, further comprising: and establishing a disease risk model through historical medical data.
In an exemplary embodiment of the present disclosure, the establishing a disease determination model by historical medical data includes: classifying the historical medical data according to disease characteristics; and respectively establishing the disease risk model for each type of the historical medical data.
In an exemplary embodiment of the present disclosure, further comprising: determining an insurance cost for the user based on the disease risk data.
In an exemplary embodiment of the present disclosure, acquiring medical data of a user through a plurality of data sources includes: acquiring data of a user through the plurality of data sources; and generating the medical data through the data screening according to a preset mapping rule.
In an exemplary embodiment of the present disclosure, the data processing the medical data to generate feature data includes: performing natural language structuralization processing on the medical data to generate structured data; carrying out normalization processing on the structured data to generate normalized data; and performing feature processing on the normalized data to generate feature data.
In an exemplary embodiment of the present disclosure, the disease risk data includes: disease name, risk score, accuracy, and timeliness.
According to an aspect of the present disclosure, there is provided an insurance user evaluation apparatus, the apparatus including: the data module is used for acquiring medical data of a user through a plurality of data sources; the processing module is used for carrying out data processing on the medical data to generate characteristic data; a scoring module for inputting the feature data into at least one disease risk model to obtain disease risk data; and a result module for determining a risk label of the user according to the disease risk data.
According to an aspect of the present disclosure, an electronic device is provided, the electronic device including: one or more processors; storage means for storing one or more programs; when executed by one or more processors, cause the one or more processors to implement a method as above.
According to an aspect of the disclosure, a computer-readable medium is proposed, on which a computer program is stored, which program, when being executed by a processor, carries out the method as above.
According to the insurance user evaluation method and device based on the disease risk model, the electronic equipment and the computer readable medium, the user insurance policy with risks can be quickly and accurately identified at the insurance verification end, and accurate insurance pricing is assisted.
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.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings. The drawings described below are merely some embodiments of the present disclosure, and other drawings may be derived from those drawings by those of ordinary skill in the art without inventive effort.
FIG. 1 is a flow diagram illustrating a method for insurance user assessment based on a disease risk model according to an exemplary embodiment.
FIG. 2 is a flow diagram illustrating a method for insurance user assessment based on a disease risk model according to another exemplary embodiment.
Fig. 3 is a schematic diagram illustrating a disease risk model-based insurance user assessment method according to another exemplary embodiment.
FIG. 4 is a block diagram illustrating an insurance user assessment apparatus based on a disease risk model according to an exemplary embodiment.
FIG. 5 is a block diagram illustrating an electronic device in accordance with an example embodiment.
FIG. 6 is a schematic diagram illustrating a computer-readable storage medium according to an example embodiment.
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 embodiments 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 same reference numerals denote the same or similar parts in the drawings, and thus, a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. 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 means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one element from another. Thus, a first component discussed below may be termed a second component without departing from the teachings of the disclosed concept. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It is to be understood by those skilled in the art that the drawings are merely schematic representations of exemplary embodiments, and that the blocks or processes shown in the drawings are not necessarily required to practice the present disclosure and are, therefore, not intended to limit the scope of the present disclosure.
The inventor of the present application finds that, in the prior art, an insurance company initiates an established underwriting risk model, wherein the underwriting risk scoring model considers both unrealistic notification risks and risks within two years in a natural state (unrealistic notification). The data source is based on the internal data of Taikang and comprises basic information of insurance policy (premium, channel and the like), information of insured persons (health condition, financial condition, past claims and the like) and information of agents (grade, working life and the like). The model is used in automatic underwriting rules, namely, the risk of the insured person is automatically judged through the model, and if the risk is higher, the insured person is required to provide more detailed health data and manually check the health data. Common regression algorithms such as logistic regression and the like are adopted for training in the algorithm to ensure the transparency and the interpretability of the model.
In the prior art, an insurance company initiates an established physical examination model, and the purpose of the model is to judge a high-risk insured person so as to assist in determining whether the insured person needs further physical examination. The data source is similar to Taikang and also takes the basic information of the insurance policy, the information of the insured person and the information of the agent as the basis of the internal data. The algorithm also adopts logistic regression to train the model. Different from the risk scoring model, the physical examination model establishes two models for evaluation according to risk definition of risk taking and insurance refusal/delay taking within two years, and finally preferentially selects a model with better effect according to actual running conditions.
The risk model improves unrealistic notification recognition probability and realizes certain degree of on-line automatic recognition by using data and a machine learning algorithm, but has a plurality of defects in practice:
the accuracy is low: only information such as insurance policy, insured person and agent in the insurance company is used for establishing a model, the information can only depict risk figures of the insured person, the characteristics of disease granularity are lacked, and the actual accuracy is often less than 30%;
poor interpretability: in actual insurance practice, once identified as a high risk insured life, the insurance company may respond to issuing physical examination or investigation, or even direct rejection, which may affect the sale and raise the doubt of the sales department or customer. However, the insurant is considered to be insufficient in explaining persuasiveness for being similar to the case in the picture without actually informing the case in history based on the model;
the recognition precision is low: the risk model can only judge whether the insured person has high risk, and cannot judge in disease or health granularity, so that the insurance underwriter is difficult to determine which method to further verify the specific disease risk;
depending on insurance data quality: since the risk model is built from insurance policy, insurer-investor information within the insurance company that may be filled in by the insurer or agent at their own discretion, because the filling process does not provide good quality control, or may be deliberately unworkable to mask unrealistic advice. Such models built based on low confidence data may have significant errors;
susceptible to warranty capacity interference: the risk model (especially taking underwriting as a judgment standard) takes a risk insured person with definite history as a model training observation object, but in practice, a large number of risk customers are still not effectively identified due to the lack of effective means. The different companies or the underwriters have different underwriting capabilities and different recognition risk ratios. When a large number of unidentified risky clients misunderstand no risk, their portrait features are also included in the risk-free category. The lower the underwriting capability is, the larger the error is, the more insured persons are mistaken as no risk, the recognition rate is further reduced, and the condition of entering a vicious circle is caused;
is greatly influenced by the distribution of customer groups: due to the difference of insurance company products and different stages of sales strategies, the distribution characteristics of the client group will change continuously, for example, the insurance company originally facing the first-line city starts to attack the village and town market. The risk model constructed based on the first-line city client is probably not suitable for the village and town client group. Once the customer base changes, the effectiveness of the risk model is greatly affected, resulting in a rapid decline in the model effect.
Based on the defects in the prior art, the application provides an insurance user evaluation method based on a disease risk model, and particularly provides a risk identification method for realizing unrealistic notification of disease granularity; the insurance user evaluation method based on the disease risk model is not influenced by the client distribution, the underwriting capability and the data quality of the historical policy of the insurance company, can improve the interpretability, can provide the operation suggestion of insurance practices, can feed back quickly in real time, and does not influence the client experience.
FIG. 1 is a flow diagram illustrating a method for insurance user assessment based on a disease risk model according to an exemplary embodiment. The insurance user assessment method 10 based on the disease risk model includes at least steps S102 to S108.
As shown in fig. 1, in S102, medical data of a user is acquired through at least one data source. The method comprises the following steps: acquiring data of a user through the plurality of data sources; and generating the medical data through the data screening according to a preset mapping rule.
The data for risk assessment mainly refers to data authorized by all insureds and used for assessing the risk of disease of the insured, and the sources thereof usually include but are not limited to policy information filled out or submitted by clients when making insurance or claims, historical claim records, physical examination reports, case data and the like.
The data fields need to be determined according to the risk characteristics on which the disease risk assessment depends, and the credibility and objectivity of the data need to be fully considered. For example, the credibility of the information manually input by the client or the agent is generally considered to be low, the credibility of the disease, underwriting or claim conclusion filled by a professional doctor, underwriting or claim adjuster is high but the accuracy may be influenced by the professional ability of the individual, and the result of the precision medical examination or inspection is relatively objective and accurate, so that the data source and the original data acquisition mode are also very important information besides the definition of the data field.
Authorization requires that the data be used before it is authorized for the risk assessment agency to collect and use its personal information for purposes of unpractical notification of risk assessment. Since the data is only used for disease risk assessment, the data does not contain personal privacy information, such as names, identification numbers and contact ways, and the personal information is fully desensitized and safely protected in the whole using process.
Wherein, the field mapping refers to mapping the medical contents belonging to the same category into a standard field. For example, diagnosis results (such as in-patient diagnosis, out-patient diagnosis, surgery diagnosis, claim diagnosis, etc.) from different data sources belong to disease diagnosis, and can be mapped into fields of diagnosis uniformly. Medical data is acquired after field mapping.
In S104, the medical data is subjected to data processing to generate feature data. The method comprises the following steps: performing natural language structuralization processing on the medical data to generate structured data; carrying out normalization processing on the structured data to generate normalized data; and performing feature processing on the normalized data to generate feature data.
The data processing is mainly based on data use standard requirements required by disease risk assessment and combined with medical related professional knowledge to perform data processing such as structuralization, normalization and feature calculation on input data.
The structured processing refers to a processing procedure of extracting information required for disease risk assessment from a medical text or a medical image by using a natural language structured technology, for example, extracting previous disease information from a previous history of a medical record of a hospital, and generating structured data by using the extracted information.
Wherein, the normalization process refers to converting the information in the structured data into standard format and units, such as diagnosis name type two diabetes, different source writing method (may be type 2 diabetes, diabetes II, etc.), and uniformly classifying into the same name or code, and obtaining the normalized data after the normalization process.
The feature processing refers to a process of feature calculation, the feature calculation refers to calculating source data into feature variables which can be used for input of an evaluation algorithm according to disease evaluation requirements, for example, an original field is a diagnosis name, but the evaluation algorithm requires input of whether diabetes exists or not, calculation for logically judging diagnosis content is required, and feature data are generated after feature processing.
In the present application, the data processing method is not limited to the above-described steps, and any data processing method may be used as long as it can convert the content of the source data into variables that can be directly used for the calculation of the risk of disease through data processing.
In S106, the feature data is input into at least one disease risk model to obtain disease risk data. A disease risk model refers to a mathematical model that assesses the risk of disease for an insured person at the time of insurable. The disease granularity at which the risk of disease is assessed may be a large category of disease systems or may be a particular disease subtype, determined by the need for different risk categories. The disease risk model can be a disease risk assessment model established based on medical big data or diagnosis following data, or an expert rule according to the precise standard of an authoritative diagnosis and treatment guideline. The evaluation results are given in a risk scoring mode, and accuracy is given according to the accuracy of different evaluation methods. Wherein the disease risk data comprises: disease name, risk score, accuracy, and timeliness.
In one embodiment, the characteristic data is respectively input into different disease risk models, and disease risk data of the user with respect to different diseases is obtained. The characteristic data can be input into all disease risk models existing in the system, for example, or the characteristic data can be determined to be input into part of the disease risk models through preliminary judgment on special data, for example, judgment on certain parameters before the characteristic data is input, so that the purpose of improving the calculation efficiency of the models is achieved.
In S108, a risk label for the user is determined from the disease risk data. And according to the disease risk degree, combining the existing insurance business data, and providing an underwriting risk label and an operation suggestion conclusion by utilizing an underwriting risk label evaluation rule or algorithm agreed in advance and a corresponding practical operation rule.
In one embodiment, further comprising: determining an insurance cost for the user based on the disease risk data. It may be determined, for example, from the disease risk data of the insured life risk label whether the insured life needs to be up-regulated or down-regulated.
According to the insurance user evaluation method based on the disease risk model, the data from different sources are processed, the data are input into the disease risk model, and the risk label of the user is determined through the disease risk scoring, so that the insurance policy of the user with risk can be quickly and accurately identified at the insurance verification end, and accurate insurance pricing is assisted.
It should be clearly understood that this disclosure describes how to make and use particular examples, but the principles of this disclosure are not limited to any details of these examples. Rather, these principles can be applied to many other embodiments based on the teachings of the present disclosure.
FIG. 2 is a flow diagram illustrating a method for insurance user assessment based on a disease risk model according to another exemplary embodiment. The process shown in fig. 2 is a detailed description of the disease risk model establishment process in S106 "inputting the feature data into at least one disease risk model to obtain disease risk data" in the process shown in fig. 1.
As shown in fig. 2, in S202, historical medical data is acquired. The historical medical data can be data authorized by all insureds in history and used for evaluating disease risks of the insured, and the sources of the historical medical data generally comprise but are not limited to policy information, historical claim records, physical examination reports, case data and the like which are filled or submitted when clients make insurance or claim in the historical data.
In S204, the historical medical data is classified according to disease characteristics. The historical data may be classified into different categories according to different disease characteristics, for example, the characteristics of the disease may be established according to relevant references of insurance companies, and may be classified by medical data or clinical data, for example, which is not limited in this application.
In one embodiment, when designing and developing a disease assessment model, it is necessary to perform disease-based assessment, and the reference characteristics of different disease risk assessment methods are different, so the input of each disease risk assessment method is different.
In one embodiment, the disease granularity in the disease assessment model for assessing disease risk may be a disease system wide category or may be a specific disease subtype, as determined by the need for different risk categories.
In one embodiment, the risk of the insured life is evaluated, the occurrence time of the data source can come from historical cases and can also be the case of emergency or visit after the insured life, and the timeliness of the difference is considered due to the difference between the occurrence time of the original data and the insured time;
in one embodiment, the different disease risk assessment methods reference different characteristics, so the input for each disease risk assessment method is different; the output of the disease risk assessment includes: disease name, disease risk score, disease assessment accuracy, and disease assessment timeliness.
In S206, the disease risk model is established separately for each type of the historical medical data. For each class of data, a disease risk model may be established, e.g., by machine learning algorithms, respectively.
Machine Learning (ML) is a multi-domain cross subject, and relates to multiple subjects such as probability theory, statistics, approximation theory, convex analysis and algorithm complexity theory. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer.
Depending on the similarity of the function and form of the algorithms, the machine learning algorithms may be, for example, regression algorithms, regularization methods, instance-based algorithms, decision tree algorithms, bayesian methods, kernel-based algorithms, clustering algorithms, artificial neural network algorithms, and the like. The machine learning algorithm in the present application may, for example, include one or a combination of the above algorithms, and the present application is not limited thereto.
In one embodiment, the disease assessment model for assessing disease risk may be a disease risk assessment model established based on medical big data or follow-up data, or expert rules according to the precise standards of an authoritative medical guideline. The evaluation results are given in a risk scoring mode, and accuracy is given according to the accuracy of different evaluation methods.
According to the insurance auditing method disclosed by the invention, a risk assessment mode is carried out on the insured person by establishing a disease risk model, the risk of the insured person when the insured person is applied or before the insured person suffers from a disease can be assessed according to the data in the aspect of medical health of the insured person, and then corresponding underwriting measures are taken according to the disease risk degree and the risk time.
Fig. 3 is a schematic diagram illustrating a disease risk model-based insurance user assessment method according to another exemplary embodiment. FIG. 3 is an exemplary illustration of the overall process of the insurance user assessment method based on the disease risk model.
As shown in FIG. 3, the data sources and authorized data for risk assessment refer to data authorized by all insureds and available for assessing risk of disease of insured life, and the sources usually include but are not limited to policy information, historical claims records, physical examination reports, case data, etc. which are filled or submitted by clients during insurance or claim settlement.
The health data preprocessing is used for carrying out data processing such as field mapping, structuring, normalization and feature calculation on input data according to data use standard requirements required by disease risk assessment and by combining medical related professional knowledge.
The disease risk assessment is used to input the medical health characteristic variables into a disease risk model to assess the disease risk of the insured person at the time of insuring.
The underwriting risk rating and operation suggestion are used for providing an underwriting risk label and an operation suggestion conclusion according to the disease risk degree, by combining the existing insurance business data and utilizing a pre-agreed underwriting risk label evaluation rule or algorithm and a corresponding practical operation rule.
According to the insurance user evaluation method based on the disease risk model, unreal identification can be effectively carried out, and the client can be informed, so that extra compensation loss and labor cost can be avoided; the risk can be informed of the unreal disease granularity, so that the risk of the client can be verified and evaluated more accurately by an underwriting department, and corresponding underwriting business operation is given;
according to the insurance user evaluation method based on the disease risk model, the whole process is automatically completed, the clients can be fed back quickly, the online insurance application process cannot be blocked, and loss of honest and high-quality clients due to overlong manual auditing process is avoided; moreover, the rules of the method are relatively objective, standard and uniform, and cannot be influenced by the human judgment capability of the underwriter and the malicious notification of the client.
It is worth mentioning that the insurance user evaluation method based on the disease risk model not only carries out risk identification in the stage of underwriting pre-underwriting, but also can adopt the method to carry out unrealistic notification risk identification in the stage of underwriting and claim settlement;
the insurance user evaluation method based on the disease risk model can be implemented in a rule tree or a model at one time except that the disease risk evaluation, the underwriting risk rating and the operation rule are implemented respectively;
the insurance user evaluation method based on the disease risk model can be used for false notification identification, inverse selection identification and accurate underwriting pricing of secondary target customers
Those skilled in the art will appreciate that all or part of the steps implementing the above embodiments are implemented as computer programs executed by a CPU. When executed by the CPU, performs the functions defined by the above-described methods provided by the present disclosure. The program may be stored in a computer readable storage medium, which may be a read-only memory, a magnetic or optical disk, or the like.
Furthermore, it should be noted that the above-mentioned figures are only schematic illustrations of the processes involved in the methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods. For details not disclosed in the embodiments of the apparatus of the present disclosure, refer to the embodiments of the method of the present disclosure.
FIG. 4 is a block diagram illustrating an insurance user evaluation device according to an exemplary embodiment. The insurance user evaluation device 40 includes: a data module 402, a processing module 404, a scoring module 406, and a results module 408.
The data module 402 is used to obtain medical data of a user through a plurality of data sources. The method comprises the following steps: acquiring data of a user through the plurality of data sources; and generating the medical data through the data screening according to a preset mapping rule.
The processing module 404 is configured to perform data processing on the medical data to generate feature data. The method comprises the following steps: performing natural language structuralization processing on the medical data to generate structured data; carrying out normalization processing on the structured data to generate normalized data; and performing feature processing on the normalized data to generate feature data.
The scoring module 406 is configured to input the feature data into at least one disease risk model to obtain disease risk data. A disease risk model refers to a mathematical model that assesses the risk of disease for an insured person at the time of insurable. The disease granularity at which the risk of disease is assessed may be a large category of disease systems or may be a particular disease subtype, determined by the need for different risk categories. The disease risk model can be a disease risk assessment model established based on medical big data or diagnosis following data, or an expert rule according to the precise standard of an authoritative diagnosis and treatment guideline. The evaluation results are given in a risk scoring mode, and accuracy is given according to the accuracy of different evaluation methods.
The results module 408 is configured to determine a risk label for the user based on the disease risk data. May also be used to determine an insurance cost for the user based on the disease risk data. Wherein the disease risk data comprises: disease name, risk score, accuracy, and timeliness.
According to the insurance user evaluation device disclosed by the invention, the data from different sources are subjected to data processing, the data are input into the disease risk model, and the risk label of the user is determined through disease risk scoring, so that the insurance policy of the user with risk can be quickly and accurately identified at the insurance verification end, and accurate underwriting pricing is assisted.
FIG. 5 is a block diagram illustrating an electronic device in accordance with an example embodiment.
An electronic device 200 according to this embodiment of the present disclosure is described below with reference to fig. 5. The electronic device 200 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 disclosure.
As shown in fig. 5, the electronic device 200 is embodied in the form of a general purpose computing device. The components of the electronic device 200 may include, but are not limited to: at least one processing unit 210, at least one memory unit 220, a bus 230 connecting different system components (including the memory unit 220 and the processing unit 210), a display unit 240, and the like.
Wherein the storage unit stores program code executable by the processing unit 210 to cause the processing unit 210 to perform the steps according to various exemplary embodiments of the present disclosure described in the above-mentioned electronic prescription flow processing method section of the present specification. For example, the processing unit 210 may perform the steps shown in fig. 1 and fig. 2.
The memory unit 220 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)2201 and/or a cache memory unit 2202, and may further include a read only memory unit (ROM) 2203.
The storage unit 220 may also include a program/utility 2204 having a set (at least one) of program modules 2205, such program modules 2205 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 200 may also communicate with one or more external devices 300 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 200, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 200 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 250. Also, the electronic device 200 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 260. The network adapter 260 may communicate with other modules of the electronic device 200 via the bus 230. 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 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiments of the present disclosure.
Fig. 6 schematically illustrates a computer-readable storage medium in an exemplary embodiment of the disclosure.
Referring to fig. 6, a program product 400 for implementing the above method according to an embodiment of the present disclosure 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 disclosure is not limited thereto, and in this 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 the present disclosure 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).
The computer readable medium carries one or more programs which, when executed by a device, cause the computer readable medium to perform the functions of: acquiring medical data of a user through a plurality of data sources; performing data processing on the medical data to generate characteristic data; inputting the characteristic data into at least one disease risk model to obtain disease risk data; and determining a risk label for the user from the disease risk data.
Those skilled in the art will appreciate that the modules described above may be distributed in the apparatus according to the description of the embodiments, or may be modified accordingly in one or more apparatuses unique from the embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
Exemplary embodiments of the present disclosure are specifically illustrated and described above. It is to be understood that the present disclosure is not limited to the precise arrangements, instrumentalities, or instrumentalities described herein; on the contrary, the disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
In addition, the structures, the proportions, the sizes, and the like shown in the drawings of the present specification are only used for matching with the contents disclosed in the specification, so as to be understood and read by those skilled in the art, and are not used for limiting the limit conditions which the present disclosure can implement, so that the present disclosure has no technical essence, and any modification of the structures, the change of the proportion relation, or the adjustment of the sizes, should still fall within the scope which the technical contents disclosed in the present disclosure can cover without affecting the technical effects which the present disclosure can produce and the purposes which can be achieved. In addition, the terms "above", "first", "second" and "a" as used in the present specification are for the sake of clarity only, and are not intended to limit the scope of the present disclosure, and changes or modifications of the relative relationship may be made without substantial changes in the technical content.
Claims (10)
1. An insurance user assessment method based on a disease risk model is characterized by comprising the following steps:
acquiring medical data of a user through at least one data source;
processing the medical data to generate characteristic data;
inputting the characteristic data into at least one disease risk model to obtain disease risk data; and
determining a risk label for the user from the disease risk data.
2. The method of claim 1, further comprising:
and establishing a disease risk model through historical medical data and a machine learning algorithm.
3. The method of claim 1, wherein the building a disease risk model through historical medical data and machine learning algorithms comprises:
classifying the historical medical data according to disease characteristics; and
and establishing the disease risk model by the machine learning algorithm according to each type of the historical medical data.
4. The method of claim 1, wherein the machine learning algorithm comprises one or more of the following algorithms:
regression algorithms, regularization methods, example-based algorithms, decision tree algorithms, bayesian methods, kernel-based algorithms, clustering algorithms, artificial neural network algorithms.
5. The method of claim 1, wherein obtaining medical data of a user through a plurality of data sources comprises:
acquiring data of a user through the plurality of data sources; and
and generating the medical data through the data screening according to a preset mapping rule.
6. The method of claim 1, wherein data processing the medical data to generate feature data comprises:
performing natural language structuralization processing on the medical data to generate structured data;
carrying out normalization processing on the structured data to generate normalized data; and
and performing feature processing on the normalized data to generate feature data.
7. The method of claim 1, wherein disease risk data comprises:
disease name, risk score, accuracy, and timeliness.
8. An insurance user evaluation apparatus, comprising:
the data module is used for acquiring medical data of a user through at least one data source;
the processing module is used for carrying out data processing on the medical data to generate characteristic data;
a scoring module for inputting the feature data into at least one disease risk model to obtain disease risk data; and
a result module to determine a risk label for the user based on the disease risk data.
9. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811330057.2A CN111180065A (en) | 2018-11-09 | 2018-11-09 | Insurance user evaluation method and device, electronic equipment and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811330057.2A CN111180065A (en) | 2018-11-09 | 2018-11-09 | Insurance user evaluation method and device, electronic equipment and computer readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111180065A true CN111180065A (en) | 2020-05-19 |
Family
ID=70651639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811330057.2A Pending CN111180065A (en) | 2018-11-09 | 2018-11-09 | Insurance user evaluation method and device, electronic equipment and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111180065A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN112183113A (en) * | 2020-10-14 | 2021-01-05 | 山东健康医疗大数据有限公司 | Insurance client list screening method and device based on health medical big data |
| CN112270222A (en) * | 2020-10-14 | 2021-01-26 | 招商银行股份有限公司 | Information standardization processing method, equipment and computer readable storage medium |
| CN112419025A (en) * | 2020-11-20 | 2021-02-26 | 泰康保险集团股份有限公司 | User data processing method and device, storage medium and electronic equipment |
| CN113706223A (en) * | 2021-09-24 | 2021-11-26 | 泰康保险集团股份有限公司 | Data processing method and device |
| CN113779635A (en) * | 2021-09-17 | 2021-12-10 | 平安医疗健康管理股份有限公司 | Medical data verification method, device, equipment and storage medium |
| CN114792568A (en) * | 2022-06-27 | 2022-07-26 | 天津幸福生命科技有限公司 | Hospitalization risk prediction method and device, storage medium and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610779A (en) * | 2017-10-25 | 2018-01-19 | 医渡云（北京）技术有限公司 | Disease Assessment Scale and risk appraisal procedure and device |
| 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 |
-
2018
- 2018-11-09 CN CN201811330057.2A patent/CN111180065A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610779A (en) * | 2017-10-25 | 2018-01-19 | 医渡云（北京）技术有限公司 | Disease Assessment Scale and risk appraisal procedure and device |
| 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 |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN112183113A (en) * | 2020-10-14 | 2021-01-05 | 山东健康医疗大数据有限公司 | Insurance client list screening method and device based on health medical big data |
| CN112270222A (en) * | 2020-10-14 | 2021-01-26 | 招商银行股份有限公司 | Information standardization processing method, equipment and computer readable storage medium |
| CN112419025A (en) * | 2020-11-20 | 2021-02-26 | 泰康保险集团股份有限公司 | User data processing method and device, storage medium and electronic equipment |
| CN113779635A (en) * | 2021-09-17 | 2021-12-10 | 平安医疗健康管理股份有限公司 | Medical data verification method, device, equipment and storage medium |
| CN113779635B (en) * | 2021-09-17 | 2024-04-05 | 深圳平安医疗健康科技服务有限公司 | Medical data verification method, device, equipment and storage medium |
| CN113706223A (en) * | 2021-09-24 | 2021-11-26 | 泰康保险集团股份有限公司 | Data processing method and device |
| CN113706223B (en) * | 2021-09-24 | 2024-01-26 | 泰康保险集团股份有限公司 | Data processing method and device |
| CN114792568A (en) * | 2022-06-27 | 2022-07-26 | 天津幸福生命科技有限公司 | Hospitalization risk prediction method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111180065A (en) | Insurance user evaluation method and device, electronic equipment and computer readable medium | |
| US20240095845A1 (en) | Insurance risk scoring based on credit utilization ratio | |
| JP5586373B2 (en) | Computer-readable storage medium storing a program for causing a computer system to realize the function of a component that processes a payment request, and a method of operating a computer system that causes a computer system to process a payment request | |
| Nyce et al. | Predictive analytics white paper | |
| CN108921708B (en) | Insurance service optimization method, insurance service optimization device and storage medium | |
| US20130036038A1 (en) | Financial activity monitoring system | |
| US20140058763A1 (en) | Fraud detection methods and systems | |
| WO2006099492A2 (en) | Credit scoring method and system | |
| US11804302B2 (en) | Supervised machine learning-based modeling of sensitivities to potential disruptions | |
| Corcos et al. | Leaving the market or reducing the coverage? A model-based experimental analysis of the demand for insurance | |
| CN111192133A (en) | Method and device for generating risk model after user loan and electronic equipment | |
| Chircop et al. | Common auditors and cross-country M&A transactions | |
| Tavares et al. | Public satisfaction with health system coverage, empirical evidence from SHARE data | |
| US20200051172A1 (en) | Method and system for creating a legal casefile | |
| JP2021185526A (en) | Insurance information management device, information processing device, and program | |
| US20230075217A1 (en) | Method for evaluation and payout of parametric risk-coverage for hard-to-insure risks using distributed ledger and associated system | |
| Srivastava et al. | Benchmarking Indian general insurance firms | |
| CN111179096A (en) | Medical data auditing method and device, electronic equipment and computer readable medium | |
| CN116416072A (en) | Risk assessment method, risk assessment device, computer equipment and storage medium | |
| CN111950829A (en) | Risk object positioning method and device, computer storage medium and electronic equipment | |
| Kaal | Private Fund Disclosures Under the Dodd-Frank Act | |
| US11625788B1 (en) | Systems and methods to evaluate application data | |
| KR20210126408A (en) | Device and method for ai calculating damage using disease big data | |
| Dzupire et al. | Constructing Malawian Ordinary Actuarial Tables: Reflection of the COVID-19 Era | |
| Savadatti | Sectoral Analysis of Bombay Stock Exchange Application of GARCH Model |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |