CN109993661B - Insurance claim settlement data analysis method and system - Google Patents
Insurance claim settlement data analysis method and system Download PDFInfo
- Publication number
- CN109993661B CN109993661B CN201910272139.4A CN201910272139A CN109993661B CN 109993661 B CN109993661 B CN 109993661B CN 201910272139 A CN201910272139 A CN 201910272139A CN 109993661 B CN109993661 B CN 109993661B
- Authority
- CN
- China
- Prior art keywords
- data
- information
- item set
- insurance
- degree
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention belongs to the technical field of data analysis, relates to a big data analysis technology, and particularly relates to an insurance claim settlement based data analysis method and system, wherein the method comprises the following steps: s1, acquiring insurance claim settlement data, and processing the claim settlement data according to the input requirements of the association analysis model to obtain an object set; s2, inputting the object set obtained in the step S1 into an association analysis model, analyzing and calculating the input object set by the association analysis model, and screening according to a rule threshold value to obtain a corresponding association object set; and S3, carrying out quantitative analysis on the associated object set to obtain an associated rule item set table. The method analyzes the service indexes of each main body in different time periods and the change condition of the incidence relation of the plurality of main bodies, effectively helps the insurance company to manage and control the insurance claim settlement, adjusts the operation scheme and helps the insurance company to plan the operation strategy.
Description
Technical Field
The invention belongs to the technical field of data analysis, relates to a big data analysis technology, and particularly relates to a data analysis method and system based on insurance claim settlement.
Background
Along with the increasing insurance awareness of people, the frequent insurance claim settlement events of insurance accidents also continuously increase, the data volume accumulated by insurance companies is larger and larger, the large data volume cannot be processed by the original analysis technology, the analysis time is long, the analysis indexes are limited, meanwhile, a very professional data analyst is required to do data processing and data model building work, the requirement on personnel is higher, and the final result user is often unsatisfied.
The insurance market competition is more and more intense, the cost reduction and efficiency improvement also begin to have strict requirements on indexes of a management layer, and in order to improve the overall operation level, analyze and summarize insurance reasons, rationality of a claim settlement process and obtain an insurance rule, effectively help insurance companies to intervene in advance, prevent in advance, set individual operation in different areas, reduce life and property losses of people and reduce the expense of insurance enterprises, a big data technology-based analysis system is urgently needed, business analysis can be performed only by people familiar with business according to a built-in data mining algorithm, business understanding and communication waste is reduced, the system can support mass data, the speed is analyzed efficiently, and the insurance claim data analysis method and system displayed by self-defined analysis indexes are displayed. The method analyzes the service indexes of each main body in different time periods and the change condition of the incidence relation of the plurality of main bodies, effectively helps the insurance company to manage and control the insurance claim settlement, adjusts the operation scheme and helps the insurance company to plan the operation strategy.
Disclosure of Invention
It is a primary object of the present invention to provide an insurance claim data analysis method and system to solve any of the above and other potential problems of the prior art.
In order to achieve the above object, the present invention provides an insurance claim settlement data analysis method, which includes the following steps:
s1, accessing the platform, obtaining insurance claim settlement data, processing the claim settlement data according to the input requirements of the association analysis model, and obtaining an object set;
s2, inputting the object set obtained in the step S1 into an association analysis model, analyzing and calculating the input object set by the association analysis model, and screening according to a rule threshold value to obtain a corresponding association object set;
and S3, carrying out quantitative analysis on the associated object set to obtain an associated rule item set table.
According to the embodiment of the disclosure, the claim data in the S1 is vehicle damage claim data and human injury claim data in the vehicle traffic accident insurance claim settlement process; the vehicle damage claim settlement data comprises vehicle information, report information, site survey information, damage assessment work hour information, damage assessment accessory information, damage assessment personnel information, repair shop information and insurance policy information; the personal injury claim data includes wounded information, household registration information, work information, hospital information, treatment and surgery information, court information, disability identification information, attorney information, and decision information.
According to the embodiment of the present disclosure, the step of performing analysis calculation on the input object set by the association analysis model in S2 is:
s2.1, dividing all claim data in the input object set into p file blocks by using an SON algorithm, wherein each file block is 1/p, and the value of p is a positive integer greater than 0;
s2.2, taking each file block divided in the S2.1 as a sample, executing an Apriori algorithm, and collecting selected frequent item sets in one or more file blocks as candidate frequent item sets;
the frequent item set is a set with a support degree greater than or equal to a minimum support degree (min _ sup). Where support refers to the frequency with which a certain set appears in all transactions. The classic application of a frequent itemset is the shopping basket model.
S2.3, merging the candidate frequent item sets obtained in the S2.2 to obtain a final frequent item set, and calculating the support degree, the confidence degree and the promotion degree of each frequent item set;
and S2.4, comparing the obtained support degree, confidence degree and lifting degree value with a preset threshold value, and screening to obtain a set conforming to the associated object.
FirstMap: and (4) dividing the subsets, finding out the frequency of each item set according to an Apriori algorithm, and outputting the frequent item set of the sample.
First reduce: and summarizing the local frequent item sets output by all map tasks, and outputting a global candidate frequent item set.
Second map: and calculating the occurrence frequency of each candidate frequent item set, and outputting the candidate item sets and the support degrees of the candidate item sets in the map task.
Second reduce: and adding each candidate frequent item set, wherein the result is global support, if the support is greater than a support threshold, reserving, and otherwise, rejecting.
According to the embodiment of the present disclosure, the calculation method of the support degree, the confidence degree, and the lift degree in S2.3 includes:
calculating the support degree of the item set X according to the probability that the item set X in the object set appears in the whole set N at the same time, wherein the formula is as follows:
s (X) = σ (X)/N, N is a positive integer greater than 0;
calculating the confidence coefficient of the item set X according to the probability of the item set Y appearing in the item set X in the object set, wherein the formula is as follows:
c(X → Y) = σ(X∪Y)/σ(X)，
the item set X confidence divided by the item set Y support is called item set X lift, and the formula is as follows:
l(X → Y) = c(X → Y)/s(Y)。
according to the embodiment of the present disclosure, the condition for comparing the support degree, the confidence degree, the lift degree value and the rule threshold in S2.4 is as follows:
if the item set support degree is greater than 0.17, the confidence degree is greater than 0.68, and the promotion degree is greater than 3, the item set is an effective item set, otherwise, the item set is an ineffective item set, and the ineffective item set is cut out.
Another object of the present invention is to provide the system of the insurance claim data analysis method, wherein the insurance claim data analysis system: the system comprises an access management module, a source data import module, an association analysis report module and a self-defined report module;
the access management module is used for applying a user access platform, issuing and managing an access key and managing an access validity period;
the source data import module imports insurance data into a processing inlet, provides a data import integrated interface for the outside, and accesses security control and authentication processing;
the source data management module is used for leading the source data into the self-defined report module by establishing a pipeline,
the user-defined report module is used for marking the data field meaning according to the format after the source data format provided by the data provider is explained, establishing a big data platform data table structure, and setting the mapping relation between a source data field and a big data platform table field, the field type setting, the data format and the segmentation method;
and the association analysis report module is used for generating an association rule item set table, finally calculating to obtain a final analysis data report according to a calculation analysis method, and then sending the final analysis data report to the custom report module.
According to an embodiment of the present disclosure, the system further comprises: the system comprises a report management module, a scheduling management module and a report pushing module;
the report management module is used for distributing the authority of the user for browsing the report sent by the user-defined report module, generating the report and filing and setting the report;
the scheduling management module is used for calling and executing tasks of each module according to a set scheduling period, monitoring the task execution process, processing task exception, managing scheduling period strategies, and mainly carrying out periodic synchronization on source data, periodic generation of reports and message notification after the reports are generated;
the report pushing module is used for notifying a user needing to browse the short link address generated by the chart needing to be shared in a short message mode, clicking the short link grounding address to browse report data after the user receives the short message, and having the functions of password verification and reading timeliness setting processing during browsing.
The invention has the beneficial effects that: by adopting the technical scheme, the insurance claim settlement data analysis method and the insurance claim settlement data analysis system can be used for carrying out business analysis only by people familiar with business according to the built-in data mining algorithm, so that the business understanding and communication waste is reduced, the system can support mass data, the analysis speed is high-efficient, and the user-defined analysis index is displayed. The method analyzes the service indexes of each main body in different time periods and the change condition of the incidence relation of the plurality of main bodies, effectively helps the insurance company to manage and control the insurance claim settlement, adjusts the operation scheme and helps the insurance company to plan the operation strategy.
Drawings
FIG. 1 is a block flow diagram of an insurance claim data analysis method of the present invention.
FIG. 2 is a logic block diagram of an insurance claim data analysis system according to the present invention.
Detailed Description
The technical scheme is further explained in detail by combining the attached drawings in the embodiment of the invention.
As shown in fig. 1, the invention relates to an insurance claim data analysis method, which comprises the following steps:
s1, acquiring insurance claim settlement data, and processing the claim settlement data according to the input requirements of the association analysis model to obtain an object set;
s2, inputting the object set obtained in the step S1 into an association analysis model, analyzing and calculating the input object set by the association analysis model, and screening according to a rule threshold value to obtain a corresponding association object set;
and S3, carrying out quantitative analysis on the associated object set to obtain an associated rule item set table.
According to the embodiment of the disclosure, the claim data in the S1 is vehicle damage claim data and human injury claim data in the vehicle traffic accident insurance claim settlement process; the vehicle damage claim settlement data comprises vehicle information, report information, site survey information, damage assessment work hour information, damage assessment accessory information, damage assessment personnel information, repair shop information and insurance policy information; the personal injury claim data includes wounded information, household registration information, work information, hospital information, treatment and surgery information, court information, disability identification information, attorney information, and decision information.
According to the embodiment of the present disclosure, the step of performing analysis calculation on the input object set by the association analysis model in S2 is:
s2.1, dividing all claim data in the input object set into p file blocks by using an SON algorithm, wherein the value range of p is a positive integer larger than 0;
s2.2, taking each file block divided in the S2.1 as a sample, executing an Apriori algorithm, and collecting selected frequent item sets in one or more file blocks as candidate frequent item sets;
s2.3, merging the candidate frequent item sets obtained in the S2.2 to obtain a final frequent item set, and calculating the support degree, the confidence degree and the promotion degree of each frequent item set;
and S2.4, comparing the obtained support degree, confidence degree and lifting degree value with a preset threshold value, and screening to obtain a set conforming to the associated object.
According to the embodiment of the present disclosure, the calculation method of the support degree, the confidence degree, and the lift degree in S2.3 includes:
calculating the support degree of the item set X according to the probability that the item set X in the object set simultaneously appears in the whole set N, wherein the formula is as follows: s (X) = σ (X)/N, the range of N is a positive integer greater than 0.
Calculating the confidence of the item set X according to the probability of the item set Y appearing in the item set X in the object set, wherein the formula is as follows:
c(X → Y) = σ(X∪Y)/σ(X)，
the item set X confidence divided by the item set Y support is called item set X lift, and the formula is as follows:
l(X → Y) = c(X → Y)/s(Y)。
according to the embodiment of the present disclosure, the condition for comparing the support degree, the confidence degree, and the lift degree value with the preset threshold value in S2.4 is as follows:
if the item set support degree is greater than 0.17, the confidence degree is greater than 0.68, the promotion degree is greater than 3, the item set is an effective item set, otherwise, the item set is an ineffective item set, and the ineffective item set is cut out.
Fig. 2 shows an insurance claim data analysis system according to the present invention, which includes an access management module, a source data import module, an association analysis report module, and a custom report module;
the access management module is used for applying a user access platform, issuing and managing an access key and managing an access validity period;
the source data import module imports insurance data into a processing inlet, provides a data import integrated interface for the outside, and accesses security control and authentication processing;
the source data management module is used for leading the source data into the self-defined report module by establishing a pipeline,
the user-defined report module is used for marking the data field meaning according to the format after the source data format provided by the data provider is explained, establishing a big data platform data table structure, and setting the mapping relation between a source data field and a big data platform table field, the field type setting, the data format and the segmentation method;
and the association analysis report module is used for generating an association rule item set table, finally calculating to obtain a final analysis data report according to a calculation analysis method, and then sending the final analysis data report to the custom report module.
According to an embodiment of the present disclosure, the system further comprises: the system comprises a report management module, a scheduling management module and a report pushing module;
the report management module is used for distributing the authority of the user for browsing the report sent by the user-defined report module, generating the report and filing and setting the report;
the scheduling management module is used for calling and executing tasks of each module according to a set scheduling period, monitoring the task execution process, processing task exception, managing scheduling period strategies, and mainly carrying out periodic synchronization on source data, periodic generation of reports and message notification after the reports are generated;
the report pushing module is used for notifying a user needing to browse the short link address generated by the chart needing to be shared in a short message mode, clicking the short link grounding address to browse report data after the user receives the short message, and having the functions of password verification and reading timeliness setting processing during browsing.
Example (b): when insurance claim data needs to be accessed to a big data platform, a third party access party needs to register a user account on the platform and apply for an access key, after the platform issues the access key, an integration interface provided by the system adopts Restful API, the access party needs to integrate according to an API integration method, and an access management platform controls access authorization, access frequency control, access key issuing and the like;
the source data management module is used for formatting and storing original insurance claim data of a third party in a platform when receiving the data of the third party, the multi-style of the data of the insurance claim of the third party is determined to require the platform to support the multi-format data, the data is analyzed, the analyzed data is mapped to a corresponding field of a Hive table structure, the source data management is used for mapping and managing a source field and a Hive table target field, necessary parameters such as the type, the length, the vacancy and the like of the field are set during mapping, a system data receiving interface adopts an adaptive device mode to self-determine and receive the data format, supports XML and JSON, provides a Restful API interface, converts the format of the received data into a streaming text Json format, formats the Json data into Hive table structure data and stores the data to form a basic database.
The source data import module is used for receiving original insurance claim data of a user, carrying out fault-tolerant processing on the insurance claim data, recording data receiving and processing logs, carrying out current-limiting processing on the insurance claim data of the user, and importing the insurance claim data into a kafka message queue for caching in order to prevent influence on a system caused by large data volume and high concurrency and influence on other user experiences.
The user-defined report module is used for processing the basic insurance claim settlement data on the basis of the basic data according to the requirement of the analysis index;
the correlation analysis report module calculates final analysis data finally according to a calculation and analysis method, in the vehicle insurance claims, mainly relating to objects including vehicle owners, repair factories and loss managers, wherein under the condition of casualties, injured persons, hospitals, law places and court objects exist, in order to better analyze the correlation relationship among the objects, deep excavation is carried out, the vehicle damage objects, the repair factories, the loss managers, vehicles and drivers are taken as object groups, and the hospital, the injured persons, the appraisal places, the law places, lawyers and the court object groups of the human damage cases are subjected to correlation analysis.
The specific correlation analysis method comprises the following steps: calculating the occurrence support of the item set through a set of claims data objects, wherein the formula is s (X) = sigma (X)/N, and the formula is expressed as the probability that the item set X occurs in the whole set N at the same time and is called the item set X support;
the formula is c (X → Y) = σ (X ∪ Y)/σ (X), referred to as confidence of the item set X, according to the probability of the item set Y appearing in the item set X in the object set;
the confidence of the item set X is divided by the support of the item set Y to calculate the lifting degree of the item set X, and the formula is l (X → Y) = c (X → Y)/s (Y).
The judgment conditions are as follows: and (4) the item set support degree is greater than 0.17, the confidence degree is greater than 0.68, the promotion degree is greater than 3, the item set is an effective item set, otherwise, the item set is an ineffective item set, the ineffective item set is cut out, and the effective item set is subjected to quantitative analysis to obtain an association rule item set table.
The report management module manages the generated report, manually updates the abnormal report and the like, checks the update log of the report, calculates the history of logic change and is convenient for tracking the change process of the report.
The report pushing module is used for conducting external network browsing management on the report, generating short links convenient to access, sending browsing short messages, setting browsing permission and browsing timeliness management functions and recording access logs.
The claim data object in the method is the accessory information and the working hour information recorded in the repair and replacement process of the claim car damage case or the wounded, hospital, court, lawyer, medication and operation information recorded in the human injury case.
Wherein the insurance claim data analysis system, said include: the system comprises an access management module, a source data import module, a self-defined report module, a report management module, a scheduling management module and a report pushing module. The method comprises the steps that the synchronization of insurance multi-format data on a big data platform is completed, real-time online synchronization and an offline batch synchronization mode are supported, the system performs rasterization on the data, a data cube of a data warehouse according to subjects and dimensions is established, data analysts use source data to process and conduct layered processing according to source data information and report index requirements, and data mart is established; the report module is used for completing the whole report making, generating and presenting process, and can share the report through the short message to related personnel for browsing and auditing functions.
The system supports analysis and calculation functions of bearing large data volume, arranges data objects for calibration and mining to obtain corresponding results, and flexibly uses various display diagrams to enable data analysts to understand data meaning and data trend at a glance.
The access management module in the system is used for applying by a user access platform, issuing and managing an access key, managing an access validity period, accessing a method, calling URL login, registering and managing an access data format, and applying API (application program interface) during access according to the principles of safety, high efficiency and reliability of user access, data receiving speed control, data caching processing, data exception notification processing when data is abnormal, and the access management module is used for accessing an external user into an entry management center, responding and feeding back by a user request and is all defined and processed by the access management.
The source data management module in the system is a source data establishing pipeline import data field management definition module, after a source data format provided by a data provider is described, a big data platform data table structure is established according to the format marking data field meaning, the mapping relation between a source data field and a big data platform table field is set, the field type is set, the data format is set, and the segmentation method is adopted.
The system supports multiple service scenes in the insurance industry, multi-channel data and different data format fields exist, XML, TXT, JSON and CSV are possible to exist, a large number of platforms are compatible with multiple formats, the introduction of multiple data sources is adapted, external data are stored in a trial mode according to a two-dimensional table, and the subsequent data query, filtering and later-stage hierarchical processing are facilitated.
The source data import module in the system is an insurance data import processing inlet, the module provides a data import integrated interface for the outside, the access safety control and the access authentication processing are carried out, the third party interface configuration processing is called, the platform supports the periodic scheduling processing of the source data import, the increment field is set according to the time period, when the scheduled specified time is reached, the system can actively initiate the data import processing, the external system data is imported into the platform, the subsequent data calculation and report data updating series operation are updated, the report data is updated timely, the manual intervention is reduced, the system intelligence is improved, and the user experience is enhanced.
The user-defined report module in the system is a report making module, the data and the report generate a preview function, a user can analyze the associated data according to the source data and the associated analysis method, and simultaneously, online table data combination, association and duplication removal function calculation modes are carried out to generate a snowflake-shaped data cube according to the dimensionality, and a data presentation mode is set on the data cube, so that various data chart styles can be supported, and the data chart styles can be presented according to broken lines, columns, radars, cakes and maps, and the report source is recanalized.
The report management module in the system is used for distributing the authority of the user for browsing the report, generating the report period and setting the filing process.
The scheduling management module in the system is used for the module period generation processing, the scheduling process, the scheduling exception processing, the scheduling strategy management, the source data periodic scheduling synchronization, the report periodic generation and the report generated message notification.
The report pushing module in the system informs a user needing to browse the short link address generated by the chart needing to be shared in a short message mode, the user clicks the short link grounding address mode to browse report data after receiving the short message, password verification exists during browsing, and the reading timeliness setting processing function is realized.
The foregoing is illustrative and explanatory of the concept of the insurance claim data analysis method and system, and it is intended that those skilled in the art, having the benefit of this disclosure, make numerous modifications, additions and substitutions to the specific embodiments described herein, and that the invention will be readily covered by the appended claims without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (2)
1. An insurance claim data analysis method, characterized by comprising the steps of:
s1, accessing the platform, obtaining insurance claim settlement data, processing the claim settlement data according to the input requirements of the association analysis model, and obtaining an object set;
s2, inputting the object set obtained in the step S1 into an association analysis model, analyzing and calculating the input object set by the association analysis model, and screening according to a rule threshold value to obtain a corresponding association object set; the method for analyzing and calculating the input object set by the association analysis model comprises the following steps:
s2.1, dividing all claim data in the input object set into p file blocks by using an SON algorithm, wherein each file block is 1/p, and the value of p is a positive integer greater than 0;
s2.2, taking each file block 1/p divided by the S2.1 as a sample, executing an Apriori algorithm, and collecting selected frequent item sets in one or more file blocks as candidate frequent item sets;
s2.3, merging the candidate frequent item sets obtained in the S2.2 to obtain a final frequent item set, and calculating the support degree, the confidence degree and the promotion degree of each frequent item set, wherein the specific calculation method comprises the following steps:
calculating the support degree of the item set X according to the probability that the item set X in the object set appears in the whole set N at the same time, wherein the formula is as follows:
s (X) = σ (X)/N, N is a positive integer greater than 0;
calculating the confidence coefficient of the item set X according to the probability of the item set Y appearing in the item set X in the object set, wherein the formula is as follows:
c(X → Y) = σ(X∪Y)/σ(X)，
the item set X confidence divided by the item set Y support is called item set X lift, and the formula is as follows:
l(X → Y) = c(X → Y)/s(Y)；
s2.4, comparing the obtained support degree, confidence degree and lifting degree value with a preset threshold value, screening to obtain a set conforming to the associated object, and comparing the support degree, confidence degree and lifting degree value with a rule threshold value according to the following conditions:
if the item set support degree is greater than 0.17, the confidence degree is greater than 0.68, and the promotion degree is greater than 3, the item set is an effective item set, otherwise, the item set is an ineffective item set, and the ineffective item set is cut;
and S3, carrying out quantitative analysis on the associated object set to obtain an associated rule item set table.
2. The insurance claim data analyzing method according to claim 1, wherein the claim data in S1 are car damage claim data and human injury claim data in the process of vehicle traffic accident insurance claim settlement; the vehicle damage claim settlement data comprises vehicle information, report information, site survey information, damage assessment work hour information, damage assessment accessory information, damage assessment personnel information, repair shop information and insurance policy information; the personal injury claim data includes wounded information, household registration information, work information, hospital information, treatment and surgery information, court information, disability identification information, attorney information, and decision information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910272139.4A CN109993661B (en) | 2019-04-04 | 2019-04-04 | Insurance claim settlement data analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910272139.4A CN109993661B (en) | 2019-04-04 | 2019-04-04 | Insurance claim settlement data analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109993661A CN109993661A (en) | 2019-07-09 |
| CN109993661B true CN109993661B (en) | 2020-04-17 |
Family
ID=67132436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910272139.4A Active CN109993661B (en) | 2019-04-04 | 2019-04-04 | Insurance claim settlement data analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109993661B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942319A (en) * | 2019-11-20 | 2020-03-31 | 万力轮胎股份有限公司 | Method and device for modeling analysis and prediction of product claim data |
| CN111461902B (en) * | 2020-03-31 | 2023-12-15 | 泰康保险集团股份有限公司 | Premium processing method, device, equipment and computer readable storage medium |
| CN112395277B (en) * | 2020-12-09 | 2024-01-09 | 招商华软信息有限公司 | Vehicle information screening method, device, equipment and storage medium |
| CN116342300B (en) * | 2023-05-26 | 2023-08-01 | 凯泰铭科技（北京）有限公司 | Method, device and equipment for analyzing characteristics of insurance claim settlement personnel |
| CN116503182B (en) * | 2023-06-25 | 2023-09-01 | 凯泰铭科技（北京）有限公司 | Method and device for dynamically collecting vehicle insurance person injury data based on rule engine |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106383920B (en) * | 2016-11-28 | 2019-11-12 | 东南大学 | A kind of particularly serious traffic accident causation recognition methods based on correlation rule |
| CN108460685A (en) * | 2017-02-22 | 2018-08-28 | 深圳市赛格车圣智联科技有限公司 | Method and apparatus for excavating the correlation rule between vehicle insurance risks and assumptions |
| CN107146161A (en) * | 2017-04-05 | 2017-09-08 | 昆明理工大学 | A kind of insurance search method selected based on classification |
| CN108427757A (en) * | 2018-03-16 | 2018-08-21 | 江苏智通交通科技有限公司 | Emphasis vehicle pass-through method for early warning based on correlation rule and supervisory systems |
| CN109408448A (en) * | 2018-12-05 | 2019-03-01 | 江苏恒创软件有限公司 | One kind can carry out centralized processing integration data to data and show platform |
| CN109412867B (en) * | 2018-12-06 | 2022-02-08 | 国家电网有限公司信息通信分公司 | Alarm association combination method, device, system, equipment and storage medium |
-
2019
- 2019-04-04 CN CN201910272139.4A patent/CN109993661B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109993661A (en) | 2019-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993661B (en) | Insurance claim settlement data analysis method and system | |
| US10339484B2 (en) | System and method for performing signal processing and dynamic analysis and forecasting of risk of third parties | |
| US11823109B2 (en) | System and method for evaluating images to support multiple risk applications | |
| US10592838B2 (en) | Risk simulation and assessment tool | |
| Hardy et al. | Opening up government data for Big Data analysis and public benefit | |
| CN112241924B (en) | Wisdom gas system | |
| US9542620B1 (en) | Locating persons of interest based on license plate recognition information | |
| US10706475B2 (en) | System and method for rules driven data record reduction | |
| US9324119B2 (en) | Identity and asset risk score intelligence and threat mitigation | |
| CA3155689A1 (en) | Early-warning method for commodity inventory risk based on a statistical interquartile range, and system and computer-readable storage medium thereof | |
| US20140081652A1 (en) | Automated Healthcare Risk Management System Utilizing Real-time Predictive Models, Risk Adjusted Provider Cost Index, Edit Analytics, Strategy Management, Managed Learning Environment, Contact Management, Forensic GUI, Case Management And Reporting System For Preventing And Detecting Healthcare Fraud, Abuse, Waste And Errors | |
| US11455587B2 (en) | Continuous and anonymous risk evaluation | |
| US20040078228A1 (en) | System for monitoring healthcare patient encounter related information | |
| CN111738549A (en) | Food safety risk assessment method, device, equipment and storage medium | |
| US10129119B2 (en) | Systems and methods for analyzing report access data | |
| Burmeister et al. | Enhancing client welfare through better communication of private mental health data between rural service providers | |
| US20230289386A1 (en) | Predicted Data Use Obligation Match Using Data Differentiators | |
| WO2022155740A1 (en) | Systems and methods for outlier detection of transactions | |
| CN102870110B (en) | Document registration system | |
| CN111539852A (en) | Patent transaction system based on SaaS mode | |
| CN110992111B (en) | User portrait mining method of applicant based on big data | |
| CN111754131A (en) | Enterprise information dynamic monitoring method, equipment and medium | |
| CN115630195A (en) | Industrial and commercial universal service construction platform based on industrial and commercial data management | |
| US20190228361A1 (en) | System for triggering enterprise-wide actions in response to detecting monitored events from distributed front line units | |
| RU133632U1 (en) | AUTOMATED SYSTEM "MANAGER'S MONITOR" OF INFORMATION AND ANALYTICAL SUPPORT OF DECISION MAKING IN THE FIELD OF AIR TRANSPORT |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |