CN117237126B - Insurance platform and insurance data processing method - Google Patents
Insurance platform and insurance data processing method Download PDFInfo
- Publication number
- CN117237126B CN117237126B CN202311207984.6A CN202311207984A CN117237126B CN 117237126 B CN117237126 B CN 117237126B CN 202311207984 A CN202311207984 A CN 202311207984A CN 117237126 B CN117237126 B CN 117237126B
- Authority
- CN
- China
- Prior art keywords
- insurance
- data
- standard
- abnormal
- sequence
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims abstract description 164
- 238000001514 detection method Methods 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 10
- 230000035605 chemotaxis Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 description 14
- 238000004891 communication Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000004075 alteration Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 238000012550 audit Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application provides an insurance platform and an insurance data processing method, which are used for collecting and obtaining insurance claim data sequences, differentiating each insurance claim data segment obtained by dividing the insurance claim data sequences to obtain corresponding insurance claim differential data segments, further determining the data jitter factor of each insurance claim data segment, and determining a stable insurance claim data sequence according to the data jitter factor of each insurance claim data segment; determining a standard insurance claim data sequence according to the stable insurance claim data sequence, determining the claim anomaly degree of each standard insurance claim data segment obtained by dividing the standard insurance claim data sequence, and determining the claim anomaly degree of the standard insurance claim data sequence according to the claim anomaly degree of all standard insurance claim data segments; and when the abnormal data balance is higher than a preset abnormal balance threshold, detecting the standard insurance claim data sequence as abnormal insurance claim data so as to improve the abnormal detection accuracy of the insurance claim data.
Description
Technical Field
The application relates to the technical field of insurance data processing, in particular to an insurance platform and an insurance data processing method.
Background
The insurance platform is a comprehensive digital platform and is used for providing insurance service, managing insurance service and meeting customer requirements, the insurance platform can cover various aspects including purchase of insurance products, insurance claim processing, customer service, data analysis and the like, the insurance platform provides online claim settlement service, and customers can submit insurance claim settlement application, upload related files and track insurance claim settlement progress, so that transparency and efficiency of insurance claim settlement are improved.
The insurance claim data refers to various data related to insurance claim, including claim application, information in the claim processing process and final claim payment condition, etc. which are presented by clients, and has important value for insurance companies, and can be used for risk assessment, business decision, fraud detection, client service and product optimization, etc. various data related to insurance are obtained from various insurance companies, third party data providers and regulatory authorities, including policy data, claim settlement data, market trend data, etc., and abnormal modes and trends are identified by monitoring and analyzing the insurance claim settlement data by using a data analysis method, which is helpful for improving the auditing efficiency of insurance claim settlement and reducing the fraud of insurance claim settlement.
However, in the prior art, recognition of the fraudulent practice of the insurance claim is challenging, because a large amount of insurance claim data may cause a long data processing time, and in the case of recognizing the abnormality of the insurance claim data, there is a technical problem that the abnormality detection accuracy of the insurance claim data is low.
Disclosure of Invention
The application provides an insurance platform and an insurance data processing method, which are used for solving the technical problem of low abnormality detection accuracy of insurance claim data.
In order to solve the technical problems, the application adopts the following technical scheme:
in a first aspect, the present application provides an insurance data processing method, including the steps of:
Collecting insurance claim data in an insurance platform to obtain an insurance claim data sequence, dividing the insurance claim data sequence into a plurality of insurance claim data segments, and differentiating each insurance claim data segment to obtain a corresponding insurance claim differential data segment;
Determining the data jitter factor of each insurance claim data segment according to the corresponding insurance claim differential data segment, and determining a stable insurance claim data sequence according to the data jitter factor of each insurance claim data segment;
mapping the stable insurance claim data sequence into a standard space to obtain a standard insurance claim data sequence, and dividing the standard insurance claim data sequence into a plurality of standard insurance claim data segments;
Determining the abnormal degree of the claim of each standard insurance claim data segment, and determining the abnormal balance degree of the claim of the standard insurance claim data sequence according to the abnormal degree of the claim of all standard insurance claim data segments;
And when the data abnormal balance degree of the standard insurance claim data sequence is higher than a preset abnormal balance threshold value, detecting the standard insurance claim data sequence as abnormal insurance claim data.
In some embodiments, differentiating each insurance claim data segment to obtain a corresponding insurance claim differential data segment specifically includes:
And for each insurance claim data segment, carrying out forward phase subtraction on all insurance claim data in the insurance claim data segment to obtain insurance claim differential data segments, and further determining the insurance claim differential data segments corresponding to each insurance claim data segment.
In some embodiments, determining the data dithering factor for each insurance claim data segment based on the corresponding insurance claim differential data segment specifically includes:
Determining a preset insurance claim differential threshold;
for each insurance claim differential data segment, acquiring all insurance claim differential data and the total amount of the insurance claim differential data in the insurance claim differential data segment;
Determining the total amount of insurance claim differential data in the insurance claim differential data segment;
Determining the data jitter factor of the insurance claim data segment corresponding to the insurance claim differential data segment according to the preset insurance claim differential threshold, the insurance claim differential data segment, the insurance claim differential data in the insurance claim differential data segment and the total amount of the insurance claim differential data, and further determining the data jitter factor of each insurance claim data segment, wherein the data jitter factor of the insurance claim data segment is determined according to the following formula:
Wherein κ s represents the data jitter factor of the S-th insurance claim data segment, D s (·) represents the insurance claim differential data segment corresponding to the S-th insurance claim data segment, N s represents the sum of the insurance claim differential data segment D s (·), num represents the statistical function, x i represents the i-th insurance claim differential data in the insurance claim differential data segment D s (·), and H p represents the preset insurance claim differential threshold.
In some embodiments, determining the sequence of stationary insurance claim data based on the data jitter factor of each of the insurance claim data segments specifically includes:
deleting the insurance claim data segment with the data jitter factor value larger than the preset data jitter threshold value;
taking an insurance claim data segment with the data jitter factor value not larger than a preset data jitter threshold value as a stable insurance claim data segment;
And forming all the stable insurance claim data segments into a stable insurance claim data sequence according to the time sequence.
In some embodiments, mapping the stationary insurance claim data sequence into a standard space, the obtaining the standard insurance claim data sequence specifically includes:
Acquiring all the stable insurance claim data of the stable insurance claim data sequence;
determining a mean value of the stationary insurance claim data in the stationary insurance claim data sequence;
determining a stationary insurance claim dataset chemotaxis of the stationary insurance claim data sequence;
Determining a standard insurance claim data sequence according to the all the stable insurance claim data, the stable insurance claim data set chemotaxis and the total stable insurance claim data, wherein the standard insurance claim data in the standard insurance claim data sequence is determined according to the following formula:
Wherein y' i represents the i-th standard insurance claim data in the standard insurance claim data sequence, y i represents the i-th stationary insurance claim data in the stationary insurance claim data sequence, And (3) representing the chemotaxis of the stationary insurance claim data set of the stationary insurance claim data sequence, and m represents the total stationary insurance claim data in the stationary insurance claim data sequence.
In some embodiments, determining the claim anomalies for each standard insurance claim data segment specifically includes:
and for each standard insurance claim data segment, determining the claim anomaly degree of the standard insurance claim data segment according to the total data amount and the data average value in the standard insurance claim data segment, and further determining the claim anomaly degree of each standard insurance claim data segment.
In some embodiments, detecting the sequence of standard insurance claim data as abnormal insurance claim data specifically includes:
obtaining an abnormal insurance claim detection result by taking the abnormal insurance claim data as input data of an abnormal detection method;
and optimizing and adjusting the insurance claim settlement scheme according to the abnormal insurance claim settlement detection result.
In a second aspect, the present application provides an insurance platform including a claim data anomaly detection unit, the claim data anomaly detection unit including:
The system comprises an insurance claim differential data segment determining module, a data processing module and a data processing module, wherein the insurance claim differential data segment determining module is used for collecting insurance claim data in an insurance platform to obtain an insurance claim data sequence, dividing the insurance claim data sequence into a plurality of insurance claim data segments, and differentiating each insurance claim data segment to obtain a corresponding insurance claim differential data segment;
The system comprises a stationary insurance claim data sequence determining module, a stationary insurance claim data sequence determining module and a data processing module, wherein the stationary insurance claim data sequence determining module is used for determining the data jitter factor of each insurance claim data segment according to the corresponding insurance claim differential data segment and determining the stationary insurance claim data sequence according to the data jitter factor of each insurance claim data segment;
the standard insurance claim data segment determining module is used for mapping the stable insurance claim data sequence into a standard space to obtain a standard insurance claim data sequence, and dividing the standard insurance claim data sequence into a plurality of standard insurance claim data segments;
the system comprises a claim abnormal balance determining module, a standard insurance claim data sequence determining module and a standard insurance claim data sequence determining module, wherein the claim abnormal balance determining module is used for determining the claim abnormal degree of each standard insurance claim data segment and determining the claim abnormal balance of the standard insurance claim data sequence according to the claim abnormal degree of all standard insurance claim data segments;
And the abnormal insurance claim data detection module is used for detecting the standard insurance claim data sequence as abnormal insurance claim data when the data abnormal balance degree of the standard insurance claim data sequence is higher than a preset abnormal balance threshold value.
In a third aspect, the present application provides a computer device comprising a memory for storing a computer program and a processor for calling and running the computer program from the memory, so that the computer device performs the insurance data processing method described above.
In a fourth aspect, the present application provides a computer readable storage medium having instructions or code stored therein which, when executed on a computer, cause the computer to perform the insurance data processing method described above.
The technical scheme provided by the embodiment of the application has the following beneficial effects:
In the insurance platform and the insurance data processing method provided by the application, insurance claim data in the insurance platform are collected to obtain an insurance claim data sequence, the insurance claim data sequence is divided into a plurality of insurance claim data segments, and each insurance claim data segment is differentiated to obtain a corresponding insurance claim differential data segment; determining the data jitter factor of each insurance claim data segment according to the corresponding insurance claim differential data segment, and determining a stable insurance claim data sequence according to the data jitter factor of each insurance claim data segment; mapping the stable insurance claim data sequence into a standard space to obtain a standard insurance claim data sequence, and dividing the standard insurance claim data sequence into a plurality of standard insurance claim data segments; determining the abnormal degree of the claim of each standard insurance claim data segment, and determining the abnormal balance degree of the claim of the standard insurance claim data sequence according to the abnormal degree of the claim of all standard insurance claim data segments; and when the data abnormal balance degree of the standard insurance claim data sequence is higher than a preset abnormal balance threshold value, detecting the standard insurance claim data sequence as abnormal insurance claim data.
According to the application, firstly, the difference is carried out on the insurance claim data segments, so that the accuracy of abnormal detection of the insurance claim data can be improved, secondly, the fluctuation and noise in the insurance claim data can be identified and quantified by determining the data jitter factor, so that the fluctuation is reduced to a small extent, the misjudgment caused by the noise and the abnormality of the insurance claim data can be reduced, then, the data trend of the insurance claim data and the abnormality of the insurance claim data can be identified more accurately by standardizing the steady insurance claim data sequence, so that the real data characteristic of the steady insurance claim data can be better presented, further, the overall abnormal condition of the standard insurance claim data sequence can be known more comprehensively by determining the abnormal balance of the standard insurance claim data sequence, so that the value and the reliability of the analysis of the standard insurance claim data sequence are improved, and finally, the potential abnormal condition of the insurance claim data can be identified more accurately by determining the abnormal insurance claim data and detecting, and the abnormal condition of the insurance claim data can be warned more accurately when the abnormal condition occurs, and the abnormal condition of the insurance claim data can be detected early, so that the abnormal condition is detected.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is an exemplary flow chart of an insurance data processing method according to some embodiments of the application;
FIG. 2 is a schematic diagram of exemplary hardware and/or software of a claim data anomaly detection unit, according to some embodiments of the present application;
Fig. 3 is a schematic diagram of a computer device implementing insurance data processing methods according to some embodiments of the application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The embodiment of the application provides an insurance platform and an insurance data processing method, which are characterized in that insurance claim data in the insurance platform are collected to obtain an insurance claim data sequence, the insurance claim data sequence is divided into a plurality of insurance claim data segments, and each insurance claim data segment is differentiated to obtain a corresponding insurance claim difference data segment; determining the data jitter factor of each insurance claim data segment according to the corresponding insurance claim differential data segment, and determining a stable insurance claim data sequence according to the data jitter factor of each insurance claim data segment; mapping the stable insurance claim data sequence into a standard space to obtain a standard insurance claim data sequence, and dividing the standard insurance claim data sequence into a plurality of standard insurance claim data segments; determining the abnormal degree of the claim of each standard insurance claim data segment, and determining the abnormal balance degree of the claim of the standard insurance claim data sequence according to the abnormal degree of the claim of all standard insurance claim data segments; and when the data abnormal balance degree of the standard insurance claim data sequence is higher than a preset abnormal balance threshold value, detecting the standard insurance claim data sequence as abnormal insurance claim data so as to improve the abnormal detection accuracy of the insurance claim data.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments. Referring to FIG. 1, which is an exemplary flowchart of an insurance data processing method according to some embodiments of the present application, the insurance data processing method 100 mainly includes the steps of:
In step 101, insurance claim data in an insurance platform is collected to obtain an insurance claim data sequence, the insurance claim data sequence is divided into a plurality of insurance claim data segments, and each insurance claim data segment is differentiated to obtain a corresponding insurance claim differential data segment.
In some embodiments, the relevant data of the insurance claim case, namely, the insurance claim data sequence is collected from the insurance platform, the insurance claim data sequence comprises insurance claim information such as insurance claim amount, claim number and the like at different time points, the whole insurance claim data sequence is divided into a plurality of segments according to a certain time interval, each insurance claim data segment represents the insurance claim data in a continuous time interval,
In some embodiments, each insurance claim data segment is differentiated, and the following manner may be specifically adopted to obtain the corresponding insurance claim differential data segment, namely:
And for each insurance claim data segment, carrying out forward phase subtraction on all insurance claim data in the insurance claim data segment to obtain insurance claim differential data segments, and further determining the insurance claim differential data segments corresponding to each insurance claim data segment.
In specific implementation, for each insurance claim data segment, continuous insurance claim data in the insurance claim data segment is subtracted sequentially to obtain difference values between adjacent insurance claim time points, and all the difference values are combined together according to time sequence to obtain the insurance claim differential data segment corresponding to the insurance claim data segment, for example, the i-th insurance claim data x i and the i-1-th insurance claim data x i-1 in one insurance claim data segment, and then the first insurance claim differential data in the insurance claim differential data segment corresponding to the insurance claim data segment is x i-xi-1.
It should be noted that, by differentiating the insurance claim data segment, the abnormal situation in the insurance claim data segment is more easily observed, the abnormal insurance claim data may be represented as a larger value after the differentiation, and is easier to be detected, thereby helping to improve the accuracy of the abnormal detection of the insurance claim data.
In step 102, a data jitter factor of each insurance claim data segment is determined according to the corresponding insurance claim differential data segment, and a stationary insurance claim data sequence is determined according to the data jitter factor of each insurance claim data segment.
In some embodiments, the determining the data jitter factor of each insurance claim data segment according to the corresponding insurance claim differential data segment may specifically be performed by:
Determining a preset insurance claim differential threshold;
for each insurance claim differential data segment, acquiring all insurance claim differential data and the total amount of the insurance claim differential data in the insurance claim differential data segment;
Determining the total amount of insurance claim differential data in the insurance claim differential data segment;
Determining the data jitter factor of the insurance claim data segment corresponding to the insurance claim differential data segment according to the preset insurance claim differential threshold value, the insurance claim differential data segment, the insurance claim differential data in the insurance claim differential data segment and the total amount of the insurance claim differential data, and further determining the data jitter factor of each insurance claim data segment, wherein the data jitter factor of the insurance claim data segment can be determined according to the following formula when the method is concretely implemented:
Wherein κ s represents the data jitter factor of the S-th insurance claim data segment, D s (·) represents the insurance claim differential data segment corresponding to the S-th insurance claim data segment, N s represents the sum of the insurance claim differential data segment D s (·), num represents the statistical function, x i represents the i-th insurance claim differential data in the insurance claim differential data segment D s (·), and H p represents the preset insurance claim differential threshold.
In the present application, the preset insurance claim differential threshold is used to determine whether the insurance claim differential data is considered as a critical value of data jitter, the data jitter factor indicates a degree of variation of the insurance claim data segment, the larger the data jitter factor indicates a more severe variation of the insurance claim data segment, and the larger the data jitter factor indicates a smaller fluctuation of the insurance claim data segment.
In some embodiments, the determining the stationary insurance claim data sequence according to the data jitter factor of each insurance claim data segment may specifically be performed by:
deleting the insurance claim data segment with the data jitter factor value larger than the preset data jitter threshold value;
taking an insurance claim data segment with the data jitter factor value not larger than a preset data jitter threshold value as a stable insurance claim data segment;
And forming all the stable insurance claim data segments into a stable insurance claim data sequence according to the time sequence.
In particular, when the insurance claim data segment with the data jitter factor value greater than the preset data jitter threshold is regarded as a high jitter data segment, the fluctuation in the insurance claim data segment may be indicated to be too large and is not suitable to be used as a part of the stable insurance claim data sequence, so that the high jitter data segments are deleted, the insurance claim data segment with the data jitter factor value not greater than the preset data jitter threshold is regarded as having smaller volatility and is relatively stable, the insurance claim data segment may be more suitable to be used for constructing the stable insurance claim data sequence, and the reserved low jitter data segments are combined together according to the time sequence to form the stable insurance claim data sequence.
It should be noted that, determining the data jitter factor may help to identify and quantify the volatility and noise in the insurance claim data, so as to reduce the volatility to a smaller extent, the data segment with a higher data jitter factor may indicate that a larger fluctuation or abnormal change occurs, and by screening and retaining the more stable insurance claim data segment, the erroneous judgment caused by the insurance claim data noise and abnormality may be reduced, so that the analysis and decision may be more accurate.
In step 103, the stationary insurance claim data sequence is mapped into a standard space to obtain a standard insurance claim data sequence, and the standard insurance claim data sequence is divided into a plurality of standard insurance claim data segments.
In some embodiments, the mapping the stationary insurance claim data sequence to the standard space may specifically be the following manner to obtain the standard insurance claim data sequence:
Acquiring all the stable insurance claim data of the stable insurance claim data sequence;
determining a stationary insurance claim dataset chemotaxis of the stationary insurance claim data sequence;
Determining a total amount of the stationary insurance claim data in the stationary insurance claim data sequence;
Determining a standard insurance claim data sequence according to the all the stable insurance claim data, the tendency of the stable insurance claim data set and the total stable insurance claim data, wherein the standard insurance claim data in the standard insurance claim data sequence can be determined according to the following formula when the standard insurance claim data is concretely implemented:
Wherein y' i represents the i-th standard insurance claim data in the standard insurance claim data sequence, y i represents the i-th stationary insurance claim data in the stationary insurance claim data sequence, And (3) representing the chemotaxis of the stationary insurance claim data set of the stationary insurance claim data sequence, and m represents the total stationary insurance claim data in the stationary insurance claim data sequence.
In specific implementation, the sum of all the stationary insurance claim data in the stationary insurance claim data sequence is divided by the total stationary insurance claim data to obtain stationary insurance claim data set chemotaxis, wherein the stationary insurance claim data set chemotaxis is an index for measuring the central trend of the stationary insurance claim data in the stationary insurance claim data sequence, and it is noted that through the steps, all the stationary insurance claim data in the stationary insurance claim data sequence can be constrained to be between 0 and 1, namely, all the stationary insurance claim data are mapped to a standard space between 0 and 1.
In some embodiments, the sequence of standard insurance claim data is divided into a plurality of standard insurance claim data segments at equal intervals, i.e., each standard insurance claim data segment contains standard insurance claim data over a period of time.
It should be noted that, by normalizing the sequence of the stationary insurance claim data, the data trend of the stationary insurance claim data and the abnormality of the stationary insurance claim data can be more accurately identified, and the normalization can help reduce the noise influence in the stationary insurance claim data, thereby better presenting the real data characteristics of the stationary insurance claim data.
In step 104, the odds of the claims of each standard insurance claim data segment are determined, and the odds of the claims of the standard insurance claim data sequence are determined according to the odds of the claims of all standard insurance claim data segments.
In some embodiments, the determination of the degree of claim anomalies for each standard insurance claim data segment may be performed in the following manner:
and determining the data anomaly degree and the data total amount corresponding to the standard insurance claim data segments for each standard insurance claim data segment, and determining the claim anomaly degree of the standard insurance claim data segments according to the data anomaly degree and the data total amount corresponding to the standard insurance claim data segments, thereby determining the claim anomaly degree of each standard insurance claim data segment.
In the above embodiment, the abnormal degree of the claim of the standard insurance claim data segment is determined according to the abnormal degree of the data and the total data amount corresponding to the standard insurance claim data segment, and in a specific implementation, the abnormal degree of the claim is determined according to the following formula:
Wherein, Representing the degree of anomalies in claims of the v-th standard insurance claim data segment, g i representing the i-th standard insurance claim data in the v-th standard insurance claim data segment,Indicating the degree of data anomaly corresponding to the v standard insurance claim data segment, and N v indicates the total amount of data in the v standard insurance claim data segment.
In particular, the abnormal degree of the standard insurance claim data segment can be obtained through the method, the data average value corresponding to the standard insurance claim data segment is determined, the difference between each standard insurance claim data and the data average value in the standard insurance claim data segment is further determined, the sum of all the differences is divided by the total data amount in the standard insurance claim data segment, the abnormal degree of the data corresponding to the standard insurance claim data segment can be obtained, the abnormal degree of the data corresponding to the standard insurance claim data segment represents the difference degree of the data of the whole standard insurance claim data segment relative to the average value, and the description is that, in the application, the abnormal degree of the claim represents the variation degree of the standard insurance claim data in the standard insurance claim data segment, namely the variation degree of the standard insurance claim data in the standard insurance claim data segment is in direct proportion to the variation degree of the standard insurance claim data.
In some embodiments, determining the abnormal balance of claims of the standard insurance claim data sequence based on the abnormal degree of claims of all standard insurance claim data segments may specifically be performed by:
acquiring the abnormal degree of the claim of all standard insurance claim data segments in the standard insurance claim data sequence;
determining the total amount of the abnormal degree of the claim of all the standard insurance claim data segments in the standard insurance claim data sequence;
determining the degree of abnormality of the claim of the standard insurance claim data sequence;
Determining the abnormal balance of the standard insurance claim data sequence through presetting the abnormal adjustment of the claim, the abnormal degree of the claim of all the standard insurance claim data segments, the total amount of the abnormal degree of the claim of all the standard insurance claim data segments and the abnormal degree of the claim of the standard insurance claim data sequence, wherein the abnormal balance of the claim can be determined according to the following formula in specific implementation:
wherein eta represents the abnormal balance of the claim of the standard insurance claim data sequence, eta 0 represents the abnormal adjustment quantity of the preset claim, V represents the total abnormal degree of the claim of all the standard insurance claim data segments in the standard insurance claim data sequence, Representing the degree of anomalies in the claims of the v-th standard insurance claim data segment, v representing the index of the degree of anomalies in the claims,In the present application, the abnormal balance of the claim represents the abnormal degree of the claim of the standard insurance claim data sequence, that is, the abnormal balance of the claim is proportional to the abnormal degree of the claim of the standard insurance claim data sequence.
In particular, when the abnormal degree of the claim of all the standard insurance claim data segments is added up to obtain the abnormal degree of the claim of the standard insurance claim data sequence, the total amount of the abnormal degree of the claim of all the standard insurance claim data segments in the standard insurance claim data sequence is the number of the standard insurance claim data segments, and it is to be noted that in the application, the preset abnormal adjustment amount of the claim is a preset adjustment value for adjusting the abnormal balance degree of the claim of the standard insurance claim data sequence and ensuring the accuracy and the precision of the abnormal balance degree of the claim.
It should be noted that, by determining the abnormal balance of claim settlement of the standard insurance claim data sequence, the abnormal situation can be quantified, so that the abnormality becomes more interpretable, and the abnormal characteristics of the standard insurance claim data sequence can be better understood, so that the abnormal situation of the whole standard insurance claim data sequence can be more comprehensively understood, the quality and reliability of the data can be more comprehensively understood by evaluating the abnormal balance, and the value and credibility of the analysis of the standard insurance claim data sequence can be improved.
And in step 105, when the data abnormal balance degree of the standard insurance claim data sequence is higher than a preset abnormal balance threshold value, detecting the standard insurance claim data sequence as abnormal insurance claim data.
The method comprises the steps of judging a standard insurance claim data sequence through a preset abnormal balance threshold value to determine whether the standard insurance claim data sequence is abnormal insurance claim data, and taking data abnormality of the standard insurance claim data sequence as abnormal insurance claim data when the data abnormality balance of the standard insurance claim data sequence is higher than the preset abnormal balance threshold value.
In some embodiments, the detecting the standard insurance claim data sequence as the abnormal insurance claim data may specifically be the following manner:
obtaining an abnormal insurance claim detection result by taking the abnormal insurance claim data as input data of an abnormal detection method;
and optimizing and adjusting the insurance claim settlement scheme according to the abnormal insurance claim settlement detection result.
In particular, when the abnormal insurance claim data is detected by using the abnormal detection method, the abnormal detection is carried out on the abnormal insurance claim data by using the support vector machine, and other abnormal detection methods can be used for carrying out the abnormal detection on the abnormal insurance claim data in practical implementation, for example, the abnormal insurance claim data is identified and positioned by a statistical method, a machine learning algorithm and the like, the abnormal insurance claim detection result can be obtained by applying the abnormal detection method on the abnormal insurance claim data, and can be a series of marked abnormal insurance claim data points, abnormal time periods or other abnormal modes, and according to the obtained abnormal insurance claim detection result, the problem or abnormality of the insurance claim data can be known, so that the insurance claim scheme can be optimized and adjusted to better cope with the abnormal situation, for example, a specific type of insurance claim case can be subjected to more detailed examination, the claim procedure can be adjusted, or a risk assessment model can be improved.
It should be noted that, by determining the abnormal insurance claim data and detecting, the method is helpful for more accurately identifying the potential abnormal condition of insurance claim, and may detect and warn in early stage of occurrence of abnormal insurance claim, so that there is an opportunity to take measures to avoid or reduce loss in time, and by the abnormal insurance claim detection result, more accurate business strategy and decision can be made, so that policy can be adjusted in time or potential risk can be reduced by taking measures in time.
According to the application, firstly, the difference is carried out on the insurance claim data segments, so that the accuracy of abnormal detection of the insurance claim data can be improved, secondly, the fluctuation and noise in the insurance claim data can be identified and quantified by determining the data jitter factor, so that the fluctuation is reduced to a small extent, the misjudgment caused by the noise and the abnormality of the insurance claim data can be reduced, then, the data trend of the insurance claim data and the abnormality of the insurance claim data can be identified more accurately by standardizing the steady insurance claim data sequence, so that the real data characteristic of the steady insurance claim data can be better presented, further, the overall abnormal condition of the standard insurance claim data sequence can be known more comprehensively by determining the abnormal balance of the standard insurance claim data sequence, so that the value and the reliability of the analysis of the standard insurance claim data sequence are improved, and finally, the potential abnormal condition of the insurance claim data can be identified more accurately by determining the abnormal insurance claim data and detecting, and the abnormal condition of the insurance claim data can be warned more accurately when the abnormal condition occurs, and the abnormal condition of the insurance claim data can be detected early, so that the abnormal condition is detected.
In addition, in another aspect of the present application, in some embodiments, the present application provides an insurance platform including a claim data anomaly detection unit, referring to fig. 2, which is a schematic diagram of exemplary hardware and/or software of the claim data anomaly detection unit according to some embodiments of the present application, the claim data anomaly detection unit 200 includes: the insurance claim differential data segment determining module 201, the stationary insurance claim data sequence determining module 202, the standard insurance claim data segment determining module 203, the claim abnormal balance determining module 204 and the abnormal insurance claim data detecting module 205 are respectively described as follows:
The insurance claim differential data segment determining module 201 is mainly used for collecting insurance claim data in an insurance platform to obtain an insurance claim data sequence, dividing the insurance claim data sequence into a plurality of insurance claim data segments, and differentiating each insurance claim data segment to obtain a corresponding insurance claim differential data segment;
The stationary insurance claim data sequence determining module 202 in the present application, the stationary insurance claim data sequence determining module 202 is mainly configured to determine a data jitter factor of each insurance claim data segment according to the corresponding insurance claim differential data segment, and determine a stationary insurance claim data sequence according to the data jitter factor of each insurance claim data segment;
The standard insurance claim data segment determining module 203 is mainly used for mapping the standard insurance claim data sequence into a standard space to obtain the standard insurance claim data sequence, and dividing the standard insurance claim data sequence into a plurality of standard insurance claim data segments;
The abnormal balance degree determination module 204 of claim, the abnormal balance degree determination module 204 of claim in the application is mainly used for determining abnormal degree of claim of each standard insurance claim data segment, and determining abnormal balance degree of claim of standard insurance claim data sequence according to abnormal degree of claim of all standard insurance claim data segments;
The abnormal insurance claim data detection module 205 is mainly configured to detect the standard insurance claim data sequence as abnormal insurance claim data when the data abnormal balance of the standard insurance claim data sequence is higher than a preset abnormal balance threshold.
While the foregoing details of the examples of the insurance platform and the insurance data processing method provided by the embodiments of the present application have been described, it may be understood that, in order to implement the foregoing functions, the corresponding devices include corresponding hardware structures and/or software modules that perform the respective functions. Those of skill in the art will readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In some embodiments, the present application also provides a computer device including a memory for storing a computer program and a processor for calling and running the computer program from the memory, so that the computer device performs the insurance data processing method described above.
In some embodiments, reference is made to fig. 3, in which a dashed line indicates that the unit or the module is optional, which is a schematic structural diagram of a computer device for an insurance data processing method according to an embodiment of the present application. The above insurance data processing method in the above embodiment may be implemented by a computer device shown in fig. 3, where the computer device 300 includes at least one processor 301, a memory 302, and at least one communication unit 305, and the computer device 300 may be a terminal device or a server or a chip.
Processor 301 may be a general purpose processor or a special purpose processor. For example, the processor 301 may be a central processing unit (central processing unit, CPU) which may be used to control the computer device 300, execute software programs, process data of the software programs, and the computer device 300 may further comprise a communication unit 305 for enabling input (receiving) and output (sending) of signals.
For example, the computer device 300 may be a chip, the communication unit 305 may be an input and/or output circuit of the chip, or the communication unit 305 may be a communication interface of the chip, which may be an integral part of a terminal device or a network device or other devices.
For another example, the computer device 300 may be a terminal device or a server, the communication unit 305 may be a transceiver of the terminal device or the server, or the communication unit 305 may be a transceiver circuit of the terminal device or the server.
The computer device 300 may include one or more memories 302 having a program 304 stored thereon, the program 304 being executable by the processor 301 to generate instructions 303 such that the processor 301 performs the methods described in the method embodiments above in accordance with the instructions 303. Optionally, data (e.g., a goal audit model) may also be stored in memory 302. Alternatively, the processor 301 may also read data stored in the memory 302, which may be stored at the same memory address as the program 304, or which may be stored at a different memory address than the program 304.
The processor 301 and the memory 302 may be provided separately or may be integrated together, for example, on a System On Chip (SOC) of the terminal device.
It should be understood that the steps of the above-described method embodiments may be accomplished by logic circuitry in hardware or instructions in software in the processor 301, and the processor 301 may be a central processing unit, a digital signal processor (digital signalprocessor, DSP), an Application SPECIFIC INTEGRATED Circuit (ASIC), a field programmable gate array (field programmable GATE ARRAY, FPGA), or other programmable logic device, such as discrete gates, transistor logic, or discrete hardware components.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
For example, in some embodiments, the present application also provides a computer-readable storage medium having instructions or code stored therein that, when executed on a computer, cause the computer to perform the insurance data processing method described above.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. A method of insurance data processing comprising the steps of:
Collecting insurance claim data in an insurance platform to obtain an insurance claim data sequence, dividing the insurance claim data sequence into a plurality of insurance claim data segments, and differentiating each insurance claim data segment to obtain a corresponding insurance claim differential data segment;
Determining the data jitter factor of each insurance claim data segment according to the corresponding insurance claim differential data segment, and determining a stable insurance claim data sequence according to the data jitter factor of each insurance claim data segment;
mapping the stable insurance claim data sequence into a standard space to obtain a standard insurance claim data sequence, and dividing the standard insurance claim data sequence into a plurality of standard insurance claim data segments;
Determining the abnormal degree of the claim of each standard insurance claim data segment, and determining the abnormal balance degree of the claim of the standard insurance claim data sequence according to the abnormal degree of the claim of all standard insurance claim data segments;
when the abnormal balance degree of the standard insurance claim data sequence is higher than a preset abnormal balance threshold value, detecting the standard insurance claim data sequence as abnormal insurance claim data;
Wherein, the abnormal balance degree of the claim is expressed as the abnormal degree of the claim of the standard insurance claim data sequence;
The determining the data jitter factor of each insurance claim data segment according to the corresponding insurance claim differential data segment specifically includes:
Determining a preset insurance claim differential threshold;
for each insurance claim differential data segment, acquiring all insurance claim differential data and the total amount of the insurance claim differential data in the insurance claim differential data segment;
Determining the total amount of insurance claim differential data in the insurance claim differential data segment;
Determining the data jitter factor of the insurance claim data segment corresponding to the insurance claim differential data segment according to the preset insurance claim differential threshold, the insurance claim differential data segment, the insurance claim differential data in the insurance claim differential data segment and the total amount of the insurance claim differential data, and further determining the data jitter factor of each insurance claim data segment, wherein the data jitter factor of the insurance claim data segment is determined according to the following formula:
Wherein, Represent the firstThe data jitter factor of the individual insurance claim data segments,Represent the firstAn insurance claim differential data segment corresponding to the insurance claim data segment,Differential data segment representing insurance claimThe sum of the insurance claim differential data,Representing a statistical function of the data,Differential data segment representing insurance claimThe first of (3)Differential data of individual insurance claims is provided,Representing a preset insurance claim differential threshold;
Wherein, determining the claim anomaly degree of each standard insurance claim data segment specifically comprises:
For each standard insurance claim data segment, determining the claim anomaly degree of the standard insurance claim data segment according to the total data amount and the data average value in the standard insurance claim data segment, and further determining the claim anomaly degree of each standard insurance claim data segment;
The method for determining the abnormal degree of the claim of the standard insurance claim data segment according to the total data amount and the data average value in the standard insurance claim data segment specifically comprises the following steps:
determining the abnormal degree of the claim of the standard insurance claim data segment according to the data abnormal degree and the total data amount corresponding to the standard insurance claim data segment, wherein the abnormal degree of the claim is determined according to the following formula:
Wherein, Represent the firstThe degree of anomalies in the claims of the individual standard insurance claim data segment,Represent the firstThe first of the standard insurance claim data segmentsThe data of a standard insurance claim is stored,Represent the firstData outliers corresponding to the standard insurance claim data segments, the data outliers representing the degree of variance of the data of the standard insurance claim data segments in their entirety relative to the mean,Represent the firstThe total amount of data in the data segment of a standard insurance claim.
2. The method of claim 1, wherein differentiating each insurance claim data segment to obtain a corresponding insurance claim differential data segment comprises:
And for each insurance claim data segment, carrying out forward phase subtraction on all insurance claim data in the insurance claim data segment to obtain insurance claim differential data segments, and further determining the insurance claim differential data segments corresponding to each insurance claim data segment.
3. The method of claim 1, wherein determining a sequence of stationary insurance claim data based on the data jitter factor of each of the insurance claim data segments comprises:
deleting the insurance claim data segment with the data jitter factor value larger than the preset data jitter threshold value;
taking an insurance claim data segment with the data jitter factor value not larger than a preset data jitter threshold value as a stable insurance claim data segment;
And forming all the stable insurance claim data segments into a stable insurance claim data sequence according to the time sequence.
4. The method of claim 1, wherein mapping the sequence of flat insurance claim data into a standard space to obtain a sequence of standard insurance claim data comprises:
Acquiring all the stable insurance claim data of the stable insurance claim data sequence;
determining a stationary insurance claim dataset chemotaxis of the stationary insurance claim data sequence;
Determining a total amount of the stationary insurance claim data in the stationary insurance claim data sequence;
Determining a standard insurance claim data sequence according to the all the stable insurance claim data, the stable insurance claim data set chemotaxis and the total stable insurance claim data, wherein the standard insurance claim data in the standard insurance claim data sequence is determined according to the following formula:
Wherein, Representing the first in a standard insurance claim data sequenceThe data of a standard insurance claim is stored,Representing the first in a sequence of data for a stationary insurance claimThe data of the claim of the stable insurance,A stationary insurance claim data set trend indicative of a stationary insurance claim data sequence,Representing the total amount of the flat insurance claim data in the flat insurance claim data sequence.
5. The method of claim 1, wherein detecting the sequence of standard insurance claim data as abnormal insurance claim data comprises:
obtaining an abnormal insurance claim detection result by taking the abnormal insurance claim data as input data of an abnormal detection method;
and optimizing and adjusting the insurance claim settlement scheme according to the abnormal insurance claim settlement detection result.
6. An insurance platform controlled by the method of any one of claims 1 to 5, characterized in that the insurance platform comprises a claim data anomaly detection unit comprising:
The system comprises an insurance claim differential data segment determining module, a data processing module and a data processing module, wherein the insurance claim differential data segment determining module is used for collecting insurance claim data in an insurance platform to obtain an insurance claim data sequence, dividing the insurance claim data sequence into a plurality of insurance claim data segments, and differentiating each insurance claim data segment to obtain a corresponding insurance claim differential data segment;
The system comprises a stationary insurance claim data sequence determining module, a stationary insurance claim data sequence determining module and a data processing module, wherein the stationary insurance claim data sequence determining module is used for determining the data jitter factor of each insurance claim data segment according to the corresponding insurance claim differential data segment and determining the stationary insurance claim data sequence according to the data jitter factor of each insurance claim data segment;
the standard insurance claim data segment determining module is used for mapping the stable insurance claim data sequence into a standard space to obtain a standard insurance claim data sequence, and dividing the standard insurance claim data sequence into a plurality of standard insurance claim data segments;
the system comprises a claim abnormal balance determining module, a standard insurance claim data sequence determining module and a standard insurance claim data sequence determining module, wherein the claim abnormal balance determining module is used for determining the claim abnormal degree of each standard insurance claim data segment and determining the claim abnormal balance of the standard insurance claim data sequence according to the claim abnormal degree of all standard insurance claim data segments;
And the abnormal insurance claim data detection module is used for detecting the standard insurance claim data sequence as abnormal insurance claim data when the claim abnormal balance degree of the standard insurance claim data sequence is higher than a preset abnormal balance threshold value.
7. A computer device, characterized in that the computer device comprises a memory for storing a computer program and a processor for calling and running the computer program from the memory, so that the computer device performs the insurance data processing method according to any one of claims 1 to 5.
8. A computer readable storage medium having instructions or code stored therein which, when run on a computer, cause the computer to perform the insurance data processing method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311207984.6A CN117237126B (en) | 2023-09-18 | 2023-09-18 | Insurance platform and insurance data processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311207984.6A CN117237126B (en) | 2023-09-18 | 2023-09-18 | Insurance platform and insurance data processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117237126A CN117237126A (en) | 2023-12-15 |
| CN117237126B true CN117237126B (en) | 2024-07-05 |
Family
ID=89092531
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311207984.6A Active CN117237126B (en) | 2023-09-18 | 2023-09-18 | Insurance platform and insurance data processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117237126B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117851951B (en) * | 2024-01-16 | 2024-08-02 | 广州美保科技有限公司 | Safety data safety wind control platform and control method thereof |
| CN117745454A (en) * | 2024-02-04 | 2024-03-22 | 中保金服(深圳)科技有限公司 | Pet identification claim settlement method based on application and related device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742124A (en) * | 2022-02-28 | 2022-07-12 | 山东鲁软数字科技有限公司 | Abnormal data processing method, system and device |
| CN116149926A (en) * | 2022-07-22 | 2023-05-23 | 马上消费金融股份有限公司 | Abnormality monitoring method, device, equipment and storage medium for business index |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20200010621A (en) * | 2018-06-19 | 2020-01-31 | (주)위세아이텍 | Device and method for insurance unfair claim and unfair pattern detection based on artificial intelligence |
| CN109191312A (en) * | 2018-08-07 | 2019-01-11 | 阳光财产保险股份有限公司 | A kind of anti-fraud air control method and device of Claims Resolution |
| US11567914B2 (en) * | 2018-09-14 | 2023-01-31 | Verint Americas Inc. | Framework and method for the automated determination of classes and anomaly detection methods for time series |
| US11494850B1 (en) * | 2019-03-13 | 2022-11-08 | Alight Solutions Llc | Applied artificial intelligence technology for detecting anomalies in payroll data |
| US11321304B2 (en) * | 2019-09-27 | 2022-05-03 | International Business Machines Corporation | Domain aware explainable anomaly and drift detection for multi-variate raw data using a constraint repository |
| CN112799923B (en) * | 2020-12-24 | 2024-07-30 | 深圳前海微众银行股份有限公司 | System abnormality cause determination method, device, equipment and storage medium |
| CN114693016A (en) * | 2020-12-26 | 2022-07-01 | 顺丰科技有限公司 | Abnormal influence detection method and device, computer equipment and storage medium |
| CN114169901A (en) * | 2021-11-25 | 2022-03-11 | 达而观数据(成都)有限公司 | Medical insurance abnormity detection method and system based on behavior sequence classification |
| CN114170029A (en) * | 2021-11-26 | 2022-03-11 | 深圳麦亚信科技股份有限公司 | Data processing method and device, computer equipment and storage medium |
-
2023
- 2023-09-18 CN CN202311207984.6A patent/CN117237126B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742124A (en) * | 2022-02-28 | 2022-07-12 | 山东鲁软数字科技有限公司 | Abnormal data processing method, system and device |
| CN116149926A (en) * | 2022-07-22 | 2023-05-23 | 马上消费金融股份有限公司 | Abnormality monitoring method, device, equipment and storage medium for business index |
Non-Patent Citations (1)
| Title |
|---|
| 基于灰色关联模型的遥测数据趋势异常分析;鄢青青等;航天控制;20210430;第39卷(第2期);1-7 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117237126A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117237126B (en) | Insurance platform and insurance data processing method | |
| WO2020114110A1 (en) | Risk prevention and control method and apparatus for merchant | |
| WO2017143919A1 (en) | Method and apparatus for establishing data identification model | |
| CN113570396A (en) | Time series data abnormity detection method, device, equipment and storage medium | |
| CN110443698A (en) | Credit evaluation device and credit evaluation system | |
| CA3053894A1 (en) | Defect prediction using historical inspection data | |
| CN114298547A (en) | User loyalty scoring method, device, equipment and readable storage medium | |
| WO2020257784A1 (en) | Inspection risk estimation using historical inspection data | |
| CN116843452A (en) | Risk supervision method, apparatus, device, medium, and program product | |
| CN112581291B (en) | Risk assessment change detection method, apparatus, device and storage medium | |
| CN116992265B (en) | Carbon emission estimation method, apparatus, device, and storage medium | |
| US9544445B1 (en) | Telecommunication price-based routing apparatus, system and method | |
| WO2019076040A1 (en) | Bank risk data processing method and apparatus, computer device and storage medium | |
| CN117437019A (en) | Credit card overdue risk prediction method, apparatus, device, medium and program product | |
| CN117827593A (en) | Method and system for determining abnormality cause based on abnormality recognition result | |
| CN116630020A (en) | Risk assessment method and device, storage medium and electronic equipment | |
| CN115168159A (en) | Abnormality detection method, abnormality detection device, electronic apparatus, and storage medium | |
| US11935075B2 (en) | Card inactivity modeling | |
| KR102336462B1 (en) | Apparatus and method of credit rating | |
| CN113298575A (en) | Method, system, equipment and storage medium for trademark value batch evaluation | |
| CN112308295B (en) | Method and device for predicting default probability | |
| US12045261B2 (en) | Method and apparatus for measuring material risk in a data set | |
| CN112882822B (en) | Method, apparatus, device and storage medium for generating load prediction model | |
| CN117035433B (en) | Illegal funds transfer customer identification method and device | |
| US20240281672A1 (en) | Method and system for testing a classification machine learning (ml) model of a tenant of a service provider, in a cloud-based environment |
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 |