CN114723570B

CN114723570B - Agricultural risk monitoring method and device, storage medium and computer equipment

Info

Publication number: CN114723570B
Application number: CN202110008024.1A
Authority: CN
Inventors: 姚嘉; 许馨; 王嘉启; 张梦婕
Original assignee: Bank Of China Insurance Information Technology Management Co ltd
Current assignee: Bank Of China Insurance Information Technology Management Co ltd
Priority date: 2021-01-05
Filing date: 2021-01-05
Publication date: 2024-02-09
Anticipated expiration: 2041-01-05
Also published as: CN114723570A

Abstract

The invention discloses a risk monitoring method, a risk monitoring device, a storage medium and computer equipment for agricultural risks, and relates to the technical field of big data analysis. The method comprises the following steps: collecting agricultural insurance policy and claim case data of each insurance company on a national agricultural insurance platform, wherein the agricultural insurance policy and claim case data comprises agricultural insurance policy data and agricultural insurance claim case data; generating risk index data based on the agricultural insurance policy claim case data and the insurance category to which the agricultural insurance policy claim case data belongs, wherein the risk index data comprises one or more of underwriting risk index data, claim settlement risk index data, aging risk index data and fraud risk index data; and generating a risk monitoring result according to the risk index data, and pushing the risk monitoring result to a target user. The method can reflect the overall risk level of the agricultural insurance industry and the agricultural insurance business operated by each insurance company from the data angle, and is beneficial to quantification and identification of various agricultural insurance risks by each insurance company and supervision organization.

Description

Agricultural risk monitoring method and device, storage medium and computer equipment

Technical Field

The invention relates to the technical field of big data analysis, in particular to a risk monitoring method, a risk monitoring device, a storage medium and computer equipment.

Background

Agricultural insurance (agricultural insurance for short) refers to an insurance for guaranteeing economic losses caused by natural disasters, accidents, epidemic diseases, diseases and other insurance accidents in the production process of planting industry, breeding industry and forestry of agricultural producers. Due to special policy attributes of agricultural insurance and asymmetric information caused by factors such as decentralized agricultural production and operation, land circulation in rural areas and the like, a series of illegal and illegal actions such as virtual increase or financial subsidy fund collection of virtual targets, false claim case creation and the like occur in recent years.

For the above-mentioned illegal and illegal actions, each insurance company is also actively working against countermeasures, for example, at present, the compliance departments of some insurance companies have established their own agricultural insurance compliance management system, which avoids the compliance management risk by regular compliance supervision and internal audit, and thus carries out compliance special audit for weak links in policy agricultural insurance management, and prevents and controls the management risk. However, such a risk monitoring method has a certain limitation, and also lacks timeliness and accuracy of risk monitoring, for example, the existing risk monitoring method cannot effectively monitor risks related to cross regions, cross years and cross companies, and the existing risk monitoring method has a defect of risk monitoring of the virtual augmented financial subsidy.

Based on the above, a set of risk monitoring method is needed in the agricultural insurance industry at present to improve the timeliness and accuracy of agricultural insurance risk monitoring, thereby being beneficial to the supervision department to further standardize the agricultural insurance operation, improve the agricultural insurance compliance operation level and promote the continuous and healthy development of agricultural insurance.

Disclosure of Invention

In view of the above, the present application provides a risk monitoring method, device, storage medium and computer equipment for agricultural risk, which mainly aims to solve the technical problems of the existing risk monitoring method, such as large limitation, and insufficient monitoring timeliness and accuracy.

According to a first aspect of the present invention there is provided a method of risk monitoring of agricultural hazards, the method comprising:

collecting agricultural insurance policy and claim case data of each insurance company on a national agricultural insurance platform, wherein the agricultural insurance policy and claim case data comprises agricultural insurance policy data and agricultural insurance claim case data;

generating risk index data based on the agricultural insurance policy claim case data and the insurance category to which the agricultural insurance policy claim case data belongs, wherein the risk index data comprises one or more of underwriting risk index data, claim settlement risk index data, aging risk index data and fraud risk index data;

And generating a risk monitoring result according to the risk index data, and pushing the risk monitoring result to a target user.

According to a second aspect of the present invention there is provided an agricultural risk monitoring apparatus comprising:

the data acquisition module is used for acquiring the agricultural insurance policy and claim case data of each insurance company on the national agricultural insurance platform, wherein the agricultural insurance policy and claim case data comprises agricultural insurance policy data and agricultural insurance claim case data;

the data processing module is used for generating risk index data based on the agricultural insurance policy claim case data and insurance categories to which the agricultural insurance policy claim case data belongs, wherein the risk index data comprises one or more of underwriting risk index data, claim settlement risk index data, aging risk index data and fraud risk index data;

and the result output module is used for generating a risk monitoring result according to the risk index data and pushing the risk monitoring result to the target user.

According to a third aspect of the present invention there is provided a storage medium having stored thereon a computer program which when executed by a processor implements the above-described risk monitoring method.

According to a fourth aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the agricultural risk monitoring method described above when executing the program.

The invention provides a method, a device, a storage medium and computer equipment for monitoring agricultural risk, which are characterized in that agricultural risk insurance policy and claim case data of each insurance company are firstly collected on national agricultural risk platforms, a series of risk index data is generated based on the agricultural insurance policy and claim case data and the insurance category to which the agricultural insurance policy and claim case data belong, the risk index data comprises one or more of underwriting risk index data, claim settlement risk index data, aging risk index data and fraud risk index data, and finally a risk monitoring result is generated according to the risk index data and is pushed to a target user. According to the method, objective agricultural insurance policy and claim data are collected on the national agricultural insurance platform, and index measurement and risk prediction are carried out by utilizing the collected data, so that the overall risk level of agricultural insurance business operated by the agricultural insurance industry and each insurance company can be reflected from the data angle, various agricultural insurance risks can be quantized and identified by each insurance company and supervision organization, and accordingly the risk management and control capability and the compliance management capability of the agricultural insurance industry and each insurance company are improved.

The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:

fig. 1 shows a schematic flow chart of an agricultural risk monitoring method according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of another risk monitoring method for agricultural risk according to an embodiment of the present invention;

fig. 3 shows a schematic structural diagram of an agricultural risk monitoring device according to an embodiment of the present invention;

fig. 4 shows a schematic structural diagram of another risk monitoring device for agricultural risk according to an embodiment of the present invention.

Detailed Description

The invention will be described in detail hereinafter with reference to the drawings in conjunction with embodiments. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.

In one embodiment, as shown in fig. 1, there is provided an agricultural risk monitoring method, which is described by taking application of the method to a computer device such as a client or a server, and includes the following steps:

101. and collecting the agricultural insurance policy and claim case data of each insurance company on the national agricultural insurance platform, wherein the agricultural insurance policy and claim case data comprises the agricultural insurance policy data and the agricultural insurance claim case data.

The platform is a national agricultural insurance information management platform, is simply referred to as an agricultural insurance platform, realizes centralized management of agricultural insurance business data of the whole industry by establishing system butt joint with insurance companies operating agricultural insurance business, combines external data such as remote sensing, disasters, weather and the like, and further realizes centralized management of the whole data of the agricultural insurance industry. The national agricultural insurance platform can perform efficient and timely centralized management on real agricultural insurance policy and claim data, and is more efficient compared with other supervision systems for later reporting of data.

Specifically, the computer device may collect the full amount of agricultural insurance policy and claim data of each insurance company from the national agricultural insurance platform at regular time or in real time, where the agricultural insurance policy and claim data mainly includes agricultural insurance policy data and agricultural insurance claim data in the relevant fields of planting industry, breeding industry, forestry and the like, where the agricultural insurance policy data and the agricultural insurance claim data have a corresponding relationship, and it is to be noted that not every agricultural insurance policy data corresponds to one agricultural insurance claim data, but only the agricultural insurance policy data having an claim. Specifically, the agricultural insurance policy claim case data may include information of policy numbers of respective policies of respective insurance companies, affiliated insurance companies, branches, service types, insurance modes, product types, date of underwriting, policy expiration date, administrative division codes, administrative division names (province, city, county, village), insurance organizers/applicant, certificate types, certificate numbers, insurance targets, number of underwriting, insurance amounts, and the like. In this embodiment, the computer device may collect the total amount of agricultural insurance service data of the agricultural insurance industry from the national agricultural insurance platform, then wash and group the collected agricultural insurance service data to obtain various types of agricultural insurance policy claim data required for calculation, and finally store the various types of agricultural insurance policy claim data in a classified manner according to the date, region, insurance company, risk and other dimensions, so as to facilitate the computer device to further process the collected data.

102. And generating risk index data based on the agricultural insurance policy claim case data and the insurance category to which the agricultural insurance policy claim case data belongs.

Specifically, the computer device can perform risk identification on the agricultural insurance policy and claim data of each insurance company collected from the national agricultural insurance platform one by one, so as to generate a plurality of pieces of risk index data aiming at each insurance policy. In this embodiment, the risk indicator data may include one or more of underwriting risk indicator data, claim risk indicator data, aging risk indicator data, and fraud risk indicator data. The risk index data can be obtained through judgment of preset risk screening rules, and can also be obtained through calculation by means of a plurality of prediction models.

In this embodiment, the underwriting risk indicator data may include one or more of inverted label risk data, underwriting high risk data, account hanging risk data of accounts for charges, virtual increased underwriting quantity risk data and virtual reporting underwriting quantity risk data, where the underwriting risk indicator data may be used to remind each insurance company whether risks related to underwriting occur in the agricultural insurance policy data, so that each insurance company and the regulatory agency can timely learn about risk factors existing in the insurance policy in the underwriting stage, so as to respond in advance.

Further, the claim risk index data may include one or more of agreement pay risk data, claim high risk data, benefit rate abnormality risk data, case report period abnormality risk data and insurance responsibility abnormality risk data, where the claim risk index data may be used to remind each insurance company whether risk related to claim matters occurs in the claim case data, so that each insurance company and the regulatory agency can predict possible risk behaviors in time in the claim period to make a pre-judgement in advance.

Further, the aging risk index data may include one or more of case setting period abnormal risk data, case setting payment period abnormal risk data and list case setting payment period abnormal risk data, where the aging risk index data may be used to remind each insurance company whether a risk related to service aging occurs in the agricultural insurance policy data and the agricultural insurance claim data, so that each insurance company timely knows whether a vulnerability occurs in each service aging of each insurance company, so as to repair the corresponding service in time, and also can timely know the service level of each insurance company by a supervision mechanism, so as to conduct targeted supervision.

Further, the fraud risk indicator data may include one or more of repeat application risk data, false colluder risk data, suspected fraud risk data applied after the risk is raised, and abnormal claim risk data. The fraud risk index data can be used for reminding whether the risk related to fraud occurs in the agricultural insurance policy data and the agricultural insurance claim case data of each insurance company, so that each insurance company and the supervision organization can timely discover the fraud in the insurance policy in the process of underwriting and claiming so as to reduce or recover the economic loss caused by the fraud to the insurance company.

Further, the insurance categories to which the insurance policy claim case data belong may include planting industry, aquaculture industry, forestry, and the like, based on which the computer device may generate risk index data under each insurance category according to the insurance policy claim case data of different insurance categories, for example, the set risk screening rules may be different for different insurance categories, or different prediction models may be trained, and in this way, the risk index data corresponding to the insurance categories may be generated pertinently for the business characteristics of different insurance categories. For example, in the case report closing period abnormal risk data in the claim risk index data, in the insurance policy of the planting industry, the shorter the case report closing period is, the larger the risk is, and in the insurance policy of the breeding industry, the longer the case report closing period is, the larger the risk is, so that different risk screening rules or risk prediction models are formulated for two different insurance categories of the planting industry and the breeding industry, and whether the case report closing period abnormal risk data is generated in the agricultural insurance policy of each insurance category is judged.

In this embodiment, each item of the agricultural insurance policy data may correspond to one or more items of risk index data, and to one or more items of risk data in the risk index data. For example, there is a piece of agricultural insurance policy claim case data with a policy number of 001 in the agricultural insurance policy claim case data, and according to the agricultural insurance policy claim case data and the insurance category to which the agricultural insurance policy claim case data belongs, the following risk index data may be generated: the risk corresponding to the agricultural insurance policy claim data with policy number 001 is as follows: 1. the insurance policy has the insurance risk and relates to the inverted signing risk in the insurance risk; 2. the policy is at risk of fraud and relates to the risk of suspected fraud that is applied after the risk of fraud. Through the risk index data, the target user can quickly know the risk matters related to each piece of the agricultural insurance policy and claim case data in the agricultural insurance policy and claim case data, so that countermeasures can be timely made.

103. And generating a risk monitoring result according to the risk index data, and pushing the risk monitoring result to a target user.

Specifically, the computer device may generate corresponding risk monitoring results according to each risk index data, and push the risk monitoring results to each insurance company and the supervision institution respectively. The risk monitoring result may be a risk monitoring list or a risk suspected list of the whole industry or each insurance company, risk statistics data of each region or each insurance company, a risk monitoring chart and risk screening information generated according to the risk index data, and the like. The form of the risk monitoring result is not particularly limited in this embodiment, and may be determined according to actual situations. Through the risk monitoring result, the monitoring mechanism can accurately monitor the overall risk level of the agricultural insurance industry and quickly track the risk management and control performance of each insurance company, so that the objects needing to be mainly monitored are found, and each insurance company can timely find the risks of various underwriting, claiming, aging and fraud in the insurance business operation process, so that the insurance policies related to the risks can be pre-judged and processed in time.

According to the agricultural risk monitoring method provided by the embodiment, agricultural risk insurance policy and claim case data of each insurance company are collected on an agricultural risk platform of the whole country, a series of risk index data comprising one or more of underwriting risk index data, claim settlement risk index data, aging risk index data and fraud risk index data are generated based on the agricultural risk policy and claim case data and insurance categories to which the agricultural risk policy and claim case data belong, and finally risk monitoring results are generated according to the risk index data and are pushed to target users. According to the method, objective agricultural insurance policy and claim data are collected on the national agricultural insurance platform, and index measurement and risk prediction are carried out by utilizing the collected data, so that the overall risk level of agricultural insurance business operated by the agricultural insurance industry and each insurance company can be reflected from the data angle, various agricultural insurance risks can be quantized and identified by each insurance company and supervision organization, and accordingly the risk management and control capability and the compliance management capability of the agricultural insurance industry and each insurance company are improved.

Further, as a refinement and extension of the specific implementation manner of the foregoing embodiment, in order to fully describe the implementation process of the embodiment, a risk monitoring method for agricultural risk is provided, as shown in fig. 2, and the method includes the following steps:

201. And collecting the agricultural insurance policy and claim case data of each insurance company on the national agricultural insurance platform, wherein the agricultural insurance policy and claim case data comprises the agricultural insurance policy data and the agricultural insurance claim case data.

Specifically, the computer device may collect the full amount of agricultural insurance policy and claim data of each insurance company from the national agricultural insurance platform at regular time or in real time, where the agricultural insurance policy and claim data mainly includes agricultural insurance policy data and agricultural insurance claim data in the relevant fields of planting industry, breeding industry, forestry and the like, where the agricultural insurance policy data and the agricultural insurance claim data have a corresponding relationship, and it is to be noted that not every agricultural insurance policy data corresponds to one agricultural insurance claim data, but only the agricultural insurance policy data having an claim. Specifically, the agricultural insurance policy claim case data may include the policy number of each policy of each insurance company, the insurance company to which the insurance company belongs, the branch office, the service type, the insurance mode, the product type, the date of the warranty effective, the date of the insurance application, the expiration date of the policy, the administrative division code, the administrative division name (province, city, county, village), the insurance organizer/applicant, the certificate type, the certificate number, the insurance standard, the amount of underwriting, the insurance amount, and the like. In this embodiment, the computer device may collect the total amount of agricultural insurance service data of the agricultural insurance industry from the national agricultural insurance platform, then wash and group the collected agricultural insurance service data to obtain various types of agricultural insurance policy claim data required for calculation, and finally store the various types of agricultural insurance policy claim data in a classified manner according to the date, region, insurance company, risk and other dimensions, so as to facilitate the computer device to further process the collected data.

202. And generating risk index data based on the agricultural insurance policy claim case data and the insurance category to which the agricultural insurance policy claim case data belongs.

Further, the insurance categories to which the insurance policy claim case data belong can include planting industry, breeding industry, forestry and the like, and based on the insurance policy claim case data, the computer equipment can generate risk index data under each insurance category in a targeted manner according to the insurance policy claim case data of different insurance categories. In one embodiment, step 202 may be implemented by: and generating risk index data according to the comparison result between each numerical value in the agricultural insurance policy data and the agricultural insurance claim data and the threshold value of each numerical value corresponding to the insurance category to which the agricultural insurance policy data and the agricultural insurance claim data belong. For example, when the computer device generates the abnormal risk data of the case settlement period in the risk index data of claim, the case settlement period of the insurance policy in the case data of the agricultural insurance policy of the planting industry can be compared with the threshold value of the case settlement period of the insurance policy of the planting industry, if the abnormal risk data of the case settlement period corresponding to the insurance policy is smaller than the threshold value, and when the case data of the insurance policy of the planting industry is monitored, the abnormal risk data of the case settlement period in the case data of the insurance policy of the agricultural industry is compared with the threshold value of the case settlement period of the planting industry, if the abnormal risk data of the case settlement period corresponding to the insurance policy is larger than the threshold value, therefore, the set risk screening rule can be distinguished for different insurance categories, and the monitoring result can be more true and accurate. By comparing each numerical value in the agricultural insurance policy and the case data with the threshold value of each numerical value corresponding to the insurance category to which the agricultural insurance policy and case data belong, the risk index data under each insurance category can be obtained quickly, and the mode is simpler and more effective and has higher efficiency.

Further, when the risk indicator data includes underwriting risk indicator data, the step of generating the risk indicator data in step 202 may include the following: if the check-up date in the single agricultural insurance policy data is later than the policy effective date and the check-up date is within a preset number of days before the expiration date in the policy, generating the inverted signing risk data which can be used for indicating the risk that the policy is applied after the accident occurs; if the number value of the cancellation policy and/or the full-batch withdrawal policy in the preset area exceeds the preset number value, generating high-risk-bearing data, wherein the preset area and the preset time can be set according to requirements, for example, the preset area can be the same administrative area, such as a province, a city, a county, a village or a village, the preset time can be a quarter, a month or a week, and the like, and in addition, the cancellation policy and the full-batch withdrawal policy can be independently compared with the preset number value or can be added and then compared, and the risk data can be used for indicating high-risk-bearing in the policy; if the actual self-payment premium value in the single agricultural insurance policy data does not reach the self-payment premium value in the policy before the check date, generating premium account-hanging risk data which can be used for indicating that the policy cannot pay the self-payment premium before the policy is issued, and the premium account-hanging risk exists; if the number value of the average user underwriting in the single agricultural insurance policy data exceeds the preset multiple of the preset number value of the average user underwriting, generating virtual increased underwriting number risk data, wherein the preset multiple is a positive number larger than 1, and the preset multiple is used for indicating that the number value of the average user underwriting in the agricultural insurance policy data is obviously higher than the preset number value of the average user underwriting; if the underwriting quantity value in the single agricultural insurance policy data can be divided by 1000, generating false report underwriting quantity risk data; the last two risk data may be used to indicate that there is a risk of a virtual increase or a virtual report underwriting number in the policy. Finally, the computer device may generate the underwriting risk indicator data according to one or more of the inverted ticket risk data, the underwriting high risk data, the accounts hanging risk data of the chargeable premium, the virtual increased underwriting quantity risk data, and the virtual report underwriting quantity risk data. The underwriting risk index data can be used for reminding whether risks related to underwriting occur in the agricultural insurance policy data of each insurance company, so that each insurance company and the supervision organization can timely know risk factors existing in the insurance policy in the underwriting stage so as to respond in advance.

Further, when the risk indicator data includes claim risk indicator data, the step of generating the risk indicator data in step 202 may include: if the amount of the determined claim or payment in the individual agricultural insurance claim case data can be divided by 1000 and/or the rate of the payment in the individual agricultural insurance claim case data can be divided by 10 or 5, generating agreement claim risk data, wherein the risk data can be used for indicating that the policy has the risk of agreement claim for return of premium; if the odds in the individual agricultural insurance odds are outside the preset odds range, generating high-risk data for the odds, wherein the high-risk data can be used for indicating that the odds of the insurance policy are too high or too low, and the risk of false odds is existed; if the family benefit rate in the single agricultural insurance claim case data is out of the preset family benefit rate range and/or the area benefit rate in the single agricultural insurance claim case data is out of the preset area benefit rate range, generating benefit rate abnormal risk data, wherein the risk data can be used for indicating that the insurance policy has risks of centralizing the claims on a small number of people or average pay of the insurance policy; if the period between the report date and the final date in the single agricultural insurance claim data is out of the range of the preset report final period, generating report final period abnormal risk data, wherein the risk data can be used for indicating that false claim settlement risks exist in a insurance policy or risks that investigation and damage are not performed in time and the target object is undefined exist; if the report date in the single agricultural insurance claim data is later than the insurance policy expiration date, generating insurance liability abnormal risk data, wherein the risk data can be used for indicating that the insurance policy has insurance liability risks. Finally, the computer device may generate the claim risk indicator data according to one or more of the above-mentioned agreement pay risk data, claim high risk data, benefit rate anomaly risk data, case report period anomaly risk data, and insurance liability anomaly risk data. The risk index data of the claim can be used for reminding whether risks related to the claim settlement matters occur in the agricultural insurance claim case data of each insurance company, so that each insurance company and the supervision organization can timely predict possible risk behaviors in the claim settlement process in the claim settlement stage so as to make a pre-judgment in advance.

Further, when the risk indicator data includes ageing risk indicator data, the step of generating the risk indicator data in step 202 may include the following: if the case setting period between the case reporting date and the case setting date in the single agricultural insurance claim case data is out of the range of the preset case setting period, generating case setting period abnormal risk data, wherein the risk data can be used for indicating that the case is not set for a long time after the insurance claim case is reported, and has the risks of not timely investigation and damage assessment and lower service timeliness; if the case setting period between the insurance policy expiration date and the case setting date in the individual agricultural insurance claim case data is out of the preset case setting period range, generating case setting period abnormal risk data which can be used for indicating that the insurance policy is not set for a long time after the insurance policy is set for the insurance policy, the insurance applicant cannot receive the insurance claim in time, and service timeliness is low; if the payment period between the settlement payment date and the settlement payment date in the single agricultural insurance claim case data is out of the preset payment period range, generating case settlement payment period abnormal risk data which can be used for indicating that the long-term unpaid claim after the insurance policy settlement is performed, wherein certain system operation risks and the risk that the refund is not timely processed exist, the insurance applicant cannot timely receive the claim, and the settlement time is low; if the claim period in the claim list is out of the preset claim period range, generating list settlement payment period abnormal risk data, wherein the risk data can be used for indicating that a large number of refunds exist and risks are not processed in time when the applicant receives the overlength of the claim period in the insurance policy claim list, and the claim settlement timeliness is low. Finally, the computer device may generate ageing risk indicator data according to one or more of the above case-setting cycle abnormal risk data, case-setting payment cycle abnormal risk data, and list case-setting payment cycle abnormal risk data. The aging risk index data can be used for reminding whether risks related to service aging occur in the agricultural insurance policy data and the agricultural insurance claim data of each insurance company, so that each insurance company can timely know whether loopholes occur in each service aging of the insurance company so as to repair the loopholes in time, and a supervision mechanism can timely know the service level of each insurance company so as to conduct targeted supervision.

Further, when the risk indicator data includes fraud risk indicator data, the step of generating the risk indicator data in step 202 may include the following: if the target, insured persons and service types in the plurality of agricultural insurance policy data in the preset area are the same, the overlapping degree of the insurance date ranges in the plurality of agricultural insurance policy data exceeds the preset overlapping degree, and the underwriting companies are different, repeated insurance application risk data are generated, the risk data can be used for indicating that the same insurance applicant applies agricultural insurance to different insurance institutions according to the same target, and the risk of taking double financial subsidies or obtaining double claims from different companies by the same insurance responsibility of an accident exists; if the corresponding leaders and the corresponding leadership accounts of different insured persons in the claim case list are the same, false leaders risk data are generated, and the risk data can be used for indicating that a person receiving the claim has false claim cases and suspicions of using the claim, and the applicant even does not receive the claim or only receives a small amount of claim risks; if the insurance period between the insurance date and the insurance date in the single agricultural insurance policy data and the agricultural insurance claim case data is shorter than the preset insurance period, the insurance date is later than the effective date of the insurance policy, the payment amount is larger than the preset payment amount or the payment rate is larger than the preset payment rate, generating suspected fraud risk data of insurance after insurance, wherein the agricultural insurance policy data and the agricultural insurance claim case data in the screening rule have a corresponding relation, and the risk data can be used for indicating that the insurance policy is suspected to have fraud risk of insurance after insurance; if the odds in the individual agricultural insurance odds data are higher than the average of odds in the area to which the insurance policy belongs, and the number of times that the odds of the insured person in the agricultural insurance odds data are higher than the average of odds in the area to which the insurance policy belongs exceeds a preset number of times, abnormal odds risk data are generated, and the risk data can be used for indicating that the insurer has a certain fraud risk. Finally, the computer device may generate fraud risk indicator data based on one or more of the repeated application risk data, the false colluder risk data, the post-risk applied suspected fraud risk data, and the abnormal claim risk data. The fraud risk index data can be used for reminding whether the risk related to fraud occurs in the agricultural insurance policy data and the agricultural insurance claim data of each insurance company, so that each insurance company and the supervision organization can timely discover the fraud in the insurance policy in the process of underwriting and claiming so as to reduce or recover the economic loss caused by the fraud to the insurance company.

It should be noted that, the risk screening rules listed in the embodiments are not unique and fixed, but may be adjusted in real time according to actual situations, and the risk data in the risk index data may set scores according to different risk degrees, so as to obtain risk scoring results of each item of agricultural insurance policy and claim data in the agricultural insurance policy and claim data. In addition, each piece of the agricultural insurance policy data may correspond to one or more items of risk index data, and to one or more items of risk data in the risk index data. For example, there is a piece of agricultural insurance policy claim case data with a policy number of 001 in the agricultural insurance policy claim case data, and according to the agricultural insurance policy claim case data and the insurance category to which the agricultural insurance policy claim case data belongs, the following risk index data may be generated: the risk corresponding to the agricultural insurance policy claim data with policy number 001 is as follows: 1. the insurance policy has the insurance risk and relates to the inverted signing risk in the insurance risk; 2. the policy is at risk of fraud and relates to the risk of suspected fraud that is applied after the risk of fraud. By the method, the target user can review the basic information and risk conditions of the claim data of each agricultural insurance policy at any time, so that pre-judgment and response processing can be carried out on risks possibly existing in the insurance policy.

Finally, the computer device may generate risk indicator data based on one or more of the underwriting risk indicator data, the claim risk indicator data, the aging risk indicator data, and the fraud risk indicator data. The generated risk index data can comprise one or more of underwriting risk index data, claim risk index data, aging risk index data and fraud risk index data, each item of risk index data can further comprise one or more specific risk data, the risk index data generated in the mode can cover the risk condition of aspects of the agricultural insurance industry, and various insurance companies and regulatory authorities can be helped to quantify and identify various agricultural risk risks according to different risk index data and specific risk data, so that countermeasures can be made in a targeted manner.

203. And generating a risk monitoring result according to the risk index data, and pushing the risk monitoring result to a target user.

In one embodiment, the step 203 may be implemented by the following steps: firstly, a risk monitoring list is generated according to the risk index data, then data statistics is carried out according to the region where the risk index data are located and the insurance company to which the risk index data belong, so that the risk monitoring result of each region and the risk monitoring result of each insurance company are obtained, and finally, the risk monitoring list and/or the risk monitoring result of each region and the risk monitoring result of each company are pushed to each insurance company and a supervision organization. It can be understood that when the risk monitoring results are pushed to the insurance companies and the regulatory authorities, more important and targeted contents can be recommended according to different users of the target, for example, a risk monitoring list can be pushed to each insurance company so that the insurance company can pay attention to and correct each risk in combination with own business, and the risk monitoring list can be pushed to the regulatory authorities firstly so that the insurance company can perform on-site or off-site inspection, and then statistics data and scoring data of the regional and the regional companies are pushed so that the regulatory authorities integrally grasp the risk conditions of each region and each company. In addition, the risk monitoring list can also set different pushing periods according to different risk screening rules, for example, the pushed risk monitoring list can be divided into a daily list or a monthly list and the like. The content in the risk monitoring list may include, in addition to the risk index data corresponding to each risk policy, the policy number, insurance company, branch office, service type, insurance mode, product type, date of underwriting, policy expiration date, administrative division code, administrative division name (province, city, county, village, town), insurance organizer/applicant, certificate type, certificate number, insurance standard, quantity of underwriting, amount of insurance, and the like.

Further, in the above embodiment, the generation mode of the risk monitoring results of each region and each insurance company may be realized by the following method: firstly classifying risk index data according to the region where the risk index data is located and the insurance company to which the risk index data belongs, then carrying out weighted evaluation on the risk degree value of each region according to the risk index data of each region and the weighted value corresponding to the risk index data to obtain the risk monitoring result of each region, and finally carrying out weighted evaluation on the risk degree value of each insurance company according to the risk index data of each insurance company and the weighted value corresponding to the risk index data to obtain the risk monitoring result of each insurance company. In the above embodiment, different risk scores may be assigned to different risk data in the risk index data, for example, in the agricultural risk practice, if the risk of the risk data with abnormal insurance responsibility is high, a higher score may be assigned to the risk data, and if the risk of the cancellation and full-batch refund policy risk data is low, a lower score may be assigned to the risk data, and by using parameters such as the risk data assigned score and the number of risk data of each region and each insurance company in the risk monitoring list, the risk monitoring result (i.e., the risk scoring result) of each region and each insurance company may be obtained. Through the result, the user can intuitively observe the risk level of each region and each insurance company, so as to make corresponding prejudgments.

204. And generating a risk monitoring chart and/or risk screening information according to the risk monitoring result.

205. And outputting and displaying the risk monitoring chart and/or risk screening information.

Specifically, the computer device may generate a corresponding risk monitoring chart according to the risk monitoring result and display the risk monitoring chart. The dimension and time range of the risk monitoring chart may be set according to the selection of the user, for example, the computer device may generate a risk monitoring score trend chart of a region or an insurance company in a period of time, or a risk monitoring score comparison chart of each insurance company in a certain time range, and so on. In addition, the computer equipment can also generate corresponding risk screening information according to the risk monitoring result and output the corresponding risk screening information to corresponding insurance companies or regulatory authorities so as to prompt the insurance companies or the regulatory authorities to pay attention to corresponding risk conditions, and thus timely response is made.

206. And responding to the query request of the target user, and acquiring the agricultural insurance policy case data, the risk monitoring index data and the risk monitoring result corresponding to the query request.

207. And outputting and/or displaying the agricultural insurance policy case data, the risk monitoring index data and the risk monitoring result corresponding to the query request to the target user.

Specifically, the computer device may also provide a data query window to the outside, or provide a data query interface to other systems, so as to provide a query call service to the target user. In this way, the computer device can respond to the query request of the target user, acquire corresponding agricultural insurance policy and claim data, risk monitoring index data or risk monitoring results from the database according to the query request, and finally return or display the data to the target user. By the mode, the risk monitoring industry chain of the agricultural insurance industry can be perfected, and the monitoring effect is improved.

Further, as a specific implementation of the methods shown in fig. 1 and fig. 2, the present embodiment provides an agricultural risk monitoring device, as shown in fig. 3, including: a data acquisition module 31, a data processing module 32 and a result output module 33.

The data acquisition module 31 is configured to acquire agricultural insurance policy and claim data of each insurance company on a national agricultural insurance platform, where the agricultural insurance policy and claim data includes agricultural insurance policy data and agricultural insurance claim data;

the data processing module 32 may be configured to generate risk indicator data based on the agricultural insurance policy claim case data and an insurance class to which the agricultural insurance policy claim case data belongs, where the risk indicator data includes one or more of underwriting risk indicator data, claim settlement risk indicator data, aging risk indicator data, and fraud risk indicator data;

The result output module 33 may be configured to obtain an overall risk monitoring result of the agricultural insurance industry and an individual risk monitoring result of each insurance company according to the risk monitoring index data of each insurance company.

In a specific application scenario, insurance categories include plantation, farming and forestry; the data processing module 32 may be specifically configured to generate risk indicator data according to a comparison result between the values in the agricultural insurance policy data and the agricultural insurance claim data and the threshold values of the values corresponding to the insurance categories to which the agricultural insurance policy data and the agricultural insurance claim data belong.

In a specific application scenario, the data processing module 32 may be specifically configured to generate the inverted label risk data if the check date in the single agricultural insurance policy data is later than the policy effective date and the check date is within a preset number of days before the expiration date in the policy; if the number value of the cancellation insurance policy and/or the full batch withdrawal insurance policy of the preset area in the preset time exceeds the preset number value, generating the underwriting high risk data; if the actual self-paying premium value in the single agricultural insurance policy data does not reach the self-paying premium value in the policy before the check date, generating premium account-hanging risk data; if the number value of the average user underwriting in the single agricultural insurance policy data exceeds the preset multiple of the preset number value of the average user underwriting, generating virtual increased underwriting number risk data; if the underwriting quantity value in the single agricultural insurance policy data can be divided by 1000, generating false report underwriting quantity risk data; generating underwriting risk index data according to one or more of inverted label risk data, underwriting high risk data, account-hanging risk data of accounts for the premium, virtual increased underwriting quantity risk data and virtual report underwriting quantity risk data;

If the amount of the determined claim or the payment in the single agricultural insurance claim case data can be divided by 1000 and/or the payment rate in the single agricultural insurance claim case data can be divided by 10 or 5, generating agreement payment risk data; if the odds in the single agricultural insurance odds data are out of the preset odds range, generating high-risk data for odds settlement; if the family benefit rate in the single agricultural risk claim case data is out of the preset family benefit rate range and/or the area benefit rate in the single agricultural risk claim case data is out of the preset area benefit rate range, generating benefit rate abnormal risk data; if the period between the case reporting date and the case settling date in the single agricultural insurance claim case data is out of the range of the preset case settling period, generating case settling period abnormal risk data; if the report date in the single agricultural insurance claim data is later than the policy expiration date, generating insurance responsibility abnormal risk data; generating claim settlement risk index data according to one or more of claim settlement risk data, claim settlement high risk data, benefit rate abnormal risk data, report case closing period abnormal risk data and insurance responsibility abnormal risk data;

if the case setting period between the case reporting date and the case setting date in the single agricultural insurance claim case data is out of the range of the preset case setting period, generating case setting period abnormal risk data; if the case settling period between the policy ending date and the case settling date in the single agricultural insurance claim case data is out of the preset case settling period range, generating case settling period abnormal risk data; if the payment period between the settlement date and the payment date in the single agricultural insurance claim case data is out of the preset payment period range, generating case settlement payment period abnormal risk data; if the claim period in the claim list is out of the preset claim period range, generating list settlement payment period abnormal risk data; generating aging risk index data according to one or more of case setting period abnormal risk data, case setting payment period abnormal risk data and list case setting payment period abnormal risk data;

If the target, insured persons and service types in the plurality of agricultural insurance policy data in the preset area are the same, the overlapping degree of the insurance date ranges in the plurality of agricultural insurance policy data exceeds the preset overlapping degree, and the underwriting companies are different, generating repeated insurance risk data; if the corresponding colluders and the corresponding colluder accounts of different insured persons in the claim list are the same, false colluder risk data are generated; if the insurance period between the insurance applying date and the insurance releasing date in the single agricultural insurance policy data and the agricultural insurance claim case data is shorter than the preset insurance releasing period, the insurance checking date is later than the effective date of the insurance policy, and the payment amount is larger than the preset payment amount or the payment rate is larger than the preset payment rate, generating suspected fraud risk data applied after insurance; if the odds in the single agricultural insurance odds data are higher than the average of odds in the area to which the insurance policy belongs, and the number of times that the odds of the insured person in the agricultural insurance odds data are higher than the average of odds in the area to which the insurance policy belongs exceeds the preset number of times, abnormal odds risk data are generated; generating fraud risk index data according to one or more of repeated application risk data, false colluder risk data, suspected fraud risk data and abnormal claim risk data which are applied after the risk is raised; the risk indicator data is generated based on one or more of underwriting risk indicator data, claim risk indicator data, aging risk indicator data, and fraud risk indicator data.

In a specific application scenario, the result output module 33 may be specifically configured to generate a risk monitoring list according to risk indicator data; carrying out data statistics according to the region where the risk index data are located and the insurance company to which the risk index data belong to obtain risk monitoring results of all regions and risk monitoring results of all insurance companies; and pushing the risk monitoring list and/or the risk monitoring results of each region and each company to each insurance company and the supervision organization.

In a specific application scenario, the result output module 33 may be specifically further configured to classify the risk indicator data according to the region where the risk indicator data is located and the insurance company to which the risk indicator data belongs; according to the risk index data of each region and the weighted value corresponding to the risk index data, weighting and evaluating the risk degree value of each region to obtain a risk monitoring result of each region; and carrying out weighted evaluation on the risk degree value of each insurance company according to the risk index data of each insurance company and the weighted value corresponding to the risk index data to obtain the risk monitoring result of each insurance company.

In a specific application scenario, the data processing module 32 may be specifically further configured to generate a risk monitoring chart and/or risk screening information according to the risk monitoring result; the result output module 33 may be further configured to output and display a risk monitoring chart and/or risk screening information.

In a specific application scenario, as shown in fig. 4, the apparatus further includes a request response module 34, where the request response module 34 is specifically configured to obtain, in response to a query request of a target user, agricultural insurance policy claim data, risk monitoring index data, and risk monitoring result corresponding to the query request; the result output module 33 may be further specifically configured to output and/or display the agricultural insurance policy case data, the risk monitoring index data, and the risk monitoring result corresponding to the query request to the target user.

It should be noted that, other corresponding descriptions of each functional unit related to the agricultural risk monitoring device provided in this embodiment may refer to corresponding descriptions in fig. 1 and fig. 2, and are not described herein again.

Based on the above methods shown in fig. 1 and fig. 2, correspondingly, the present embodiment further provides a storage medium, on which a computer program is stored, where the program is executed by a processor to implement the method for risk monitoring of agricultural risk shown in fig. 1 and fig. 2.

Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, where the software product to be identified may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disc, a mobile hard disk, etc.), and include several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to execute the method described in each implementation scenario of the present application.

Based on the method shown in fig. 1 and fig. 2 and the embodiments of the risk monitoring device for agricultural risk shown in fig. 3 and fig. 4, in order to achieve the above objective, this embodiment further provides an entity device for risk monitoring for agricultural risk, which may specifically be a personal computer, a server, a smart phone, a tablet computer, a smart watch, or other network devices, where the entity device includes a storage medium and a processor; a storage medium storing a computer program; a processor for executing a computer program to implement the method as shown in fig. 1 and 2.

Optionally, the physical device may further include a user interface, a network interface, a camera, radio Frequency (RF) circuitry, sensors, audio circuitry, WI-FI modules, and the like. The user interface may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), etc.

It will be appreciated by those skilled in the art that the structure of the entity device for risk monitoring of agricultural risk provided in this embodiment is not limited to the entity device, and may include more or fewer components, or may combine certain components, or may be different in arrangement of components.

The storage medium may also include an operating system, a network communication module. The operating system is a program for managing the entity equipment hardware and the software resources to be identified, and supports the operation of the information processing program and other software and/or programs to be identified. The network communication module is used for realizing communication among all components in the storage medium and communication with other hardware and software in the information processing entity equipment.

From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general hardware platforms, or may be implemented by hardware. By applying the technical scheme, the agricultural insurance policy and claim case data of each insurance company are collected on a national agricultural insurance platform, a series of risk index data including one or more of underwriting risk index data, claim settlement risk index data, aging risk index data and fraud risk index data are generated based on the agricultural insurance policy and claim case data and the insurance category to which the agricultural insurance policy and claim case data belongs, and finally a risk monitoring result is generated according to the risk index data and pushed to a target user. Compared with the prior art, the method has the advantages that objective agricultural insurance policy and claim data are collected on the national agricultural insurance platform, index measurement and calculation and risk prediction are carried out by utilizing the collected data, the overall risk level of the agricultural insurance business operated by the agricultural insurance industry and each insurance company can be reflected from the data angle, and various agricultural insurance risks can be quantized and identified by each insurance company and each supervision organization, so that the risk management and control capability and the compliance management capability of the agricultural insurance industry and each insurance company are improved.

Those skilled in the art will appreciate that the drawings are merely schematic illustrations of one preferred implementation scenario, and that the modules or flows in the drawings are not necessarily required to practice the present application. Those skilled in the art will appreciate that modules in an apparatus in an implementation scenario may be distributed in an apparatus in an implementation scenario according to an implementation scenario description, or that corresponding changes may be located in one or more apparatuses different from the implementation scenario. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.

The foregoing application serial numbers are merely for description, and do not represent advantages or disadvantages of the implementation scenario. The foregoing disclosure is merely a few specific implementations of the present application, but the present application is not limited thereto and any variations that can be considered by a person skilled in the art shall fall within the protection scope of the present application.

Claims

1. A method for risk monitoring of agricultural hazards, the method comprising:

generating risk index data based on the agricultural insurance policy claim case data and an insurance category to which the agricultural insurance policy claim case data belongs, wherein the risk index data comprises one or more of underwriting risk index data, claim settlement risk index data, aging risk index data and fraud risk index data;

The underwriting risk indicator data includes one or more of: if the check-up date in the single agricultural insurance policy data is later than the policy effective date and the check-up date is within a preset number of days before the policy ending date, generating the inverted policy risk data; if the number value of the cancellation insurance policy and/or the full batch withdrawal insurance policy of the preset area in the preset time exceeds the preset number value, generating the underwriting high risk data; if the actual self-paying premium value in the single agricultural insurance policy data does not reach the self-paying premium value in the policy before the check date, generating premium account-hanging risk data; if the number value of the average user underwriting in the single agricultural insurance policy data exceeds the preset multiple of the preset number value of the average user underwriting, generating virtual increased underwriting number risk data; if the underwriting quantity value in the single agricultural insurance policy data can be divided by 1000, generating false report underwriting quantity risk data;

the claim risk indicator data includes one or more of: if the amount of the determined claim or the payment in the single agricultural insurance claim case data can be divided by 1000 and/or the payment rate in the single agricultural insurance claim case data can be divided by 10 or 5, generating agreement payment risk data; if the odds in the single agricultural insurance odds data are out of the preset odds range, generating high-risk data for odds settlement; if the family benefit rate in the single agricultural risk claim case data is out of the preset family benefit rate range and/or the area benefit rate in the single agricultural risk claim case data is out of the preset area benefit rate range, generating benefit rate abnormal risk data; if the period between the case reporting date and the case settling date in the single agricultural insurance claim case data is out of the range of the preset case settling period, generating case settling period abnormal risk data; if the report date in the single agricultural insurance claim data is later than the policy expiration date, generating insurance responsibility abnormal risk data;

The ageing risk indicator data comprises one or more of the following: if the case setting period between the case reporting date and the case setting date in the single agricultural insurance claim case data is out of the range of the preset case setting period, generating case setting period abnormal risk data; if the case settling period between the policy ending date and the case settling date in the single agricultural insurance claim case data is out of the preset case settling period range, generating case settling period abnormal risk data; if the payment period between the settlement date and the payment date in the single agricultural insurance claim case data is out of the preset payment period range, generating case settlement payment period abnormal risk data; if the claim period in the claim list is out of the preset claim period range, generating list settlement payment period abnormal risk data;

the fraud risk indicator data includes one or more of: if the target, insured persons and service types in the plurality of agricultural insurance policy data in the preset area are the same, and the overlapping degree of the insurance date ranges in the plurality of agricultural insurance policy data exceeds the preset overlapping degree, and the underwriting companies are different, generating repeated insurance risk data; if the colluders and the collude accounts corresponding to different insured persons in the claim list are the same, false colluder risk data are generated; if the insurance period between the insurance applying date and the insurance releasing date in the single agricultural insurance policy data and the agricultural insurance claim case data is shorter than the preset insurance releasing period, the insurance checking date is later than the effective date of the insurance policy, and the payment amount is larger than the preset payment amount or the payment rate is larger than the preset payment rate, generating suspected fraud risk data applied after insurance; if the odds in the single agricultural insurance odds data are higher than the average of odds in the area to which the insurance policy belongs, and the number of times that the odds of the insured person in the agricultural insurance odds data are higher than the average of odds in the area to which the insurance policy belongs exceeds the preset number of times, abnormal odds risk data are generated;

2. The method of claim 1, wherein the insurance categories include plantation, farming, and forestry; generating risk index data based on the agricultural insurance policy claim case data and the insurance category to which the agricultural insurance policy claim case data belongs, including:

and generating risk index data according to a comparison result between each numerical value in the agricultural insurance policy data and the agricultural insurance claim data and a threshold value of each numerical value corresponding to an insurance class to which the agricultural insurance policy data and the agricultural insurance claim data belong.

3. The method of claim 1, wherein generating risk monitoring results from the risk indicator data and pushing the risk monitoring results to a target user comprises:

generating a risk monitoring list according to the risk index data;

carrying out data statistics according to the region where the risk index data are located and the insurance company to which the risk index data belong to obtain risk monitoring results of all regions and risk monitoring results of all insurance companies;

and pushing the risk monitoring list and/or the risk monitoring results of all areas and the risk monitoring results of all companies to all insurance companies and regulatory authorities.

4. The method according to claim 3, wherein the step of performing data statistics according to the region where the risk index data is located and the insurance company to which the risk index data belongs to obtain risk monitoring results of each region and risk monitoring results of each insurance company includes:

classifying the risk index data according to the region and the insurance company to which the risk index data belongs;

according to the risk index data of each region and the weighting value corresponding to the risk index data, weighting evaluation is carried out on the risk degree value of each region, and a risk monitoring result of each region is obtained;

and carrying out weighted evaluation on the risk degree value of each insurance company according to the risk index data of each insurance company and the weighted value corresponding to the risk index data to obtain the risk monitoring result of each insurance company.

5. The method according to claim 1, wherein the method further comprises:

generating a risk monitoring chart and/or risk screening information according to the risk monitoring result;

outputting and displaying the risk monitoring chart and/or the risk screening information.

6. The method according to claim 1, wherein the method further comprises:

responding to a query request of a target user, and acquiring agricultural insurance policy claim data, risk monitoring index data and risk monitoring results corresponding to the query request;

And outputting and/or displaying the agricultural insurance policy case data, the risk monitoring index data and the risk monitoring result corresponding to the query request to the target user.

7. An agricultural risk monitoring device, the device comprising:

the data processing module is used for generating risk index data based on the agricultural insurance policy and insurance category to which the agricultural insurance policy and insurance policy data belong, wherein the risk index data comprises one or more of underwriting risk index data, claim settlement risk index data, aging risk index data and fraud risk index data;

and the result output module is used for generating a risk monitoring result according to the risk index data and pushing the risk monitoring result to a target user.

8. A storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method of any of claims 1 to 6.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when executed by the processor implements the steps of the method according to any one of claims 1 to 6.