CN117634873A - System and method for evaluating risk of sales personnel in insurance industry - Google Patents
System and method for evaluating risk of sales personnel in insurance industry Download PDFInfo
- Publication number
- CN117634873A CN117634873A CN202311516656.4A CN202311516656A CN117634873A CN 117634873 A CN117634873 A CN 117634873A CN 202311516656 A CN202311516656 A CN 202311516656A CN 117634873 A CN117634873 A CN 117634873A
- Authority
- CN
- China
- Prior art keywords
- risk
- data
- sales
- module
- level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000012795 verification Methods 0.000 claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 21
- 238000012360 testing method Methods 0.000 claims abstract description 18
- 238000005457 optimization Methods 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 33
- 230000006870 function Effects 0.000 claims description 11
- 238000010801 machine learning Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 abstract description 3
- 238000010606 normalization Methods 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a system and a method for evaluating risk of sales personnel in insurance industry. According to the system, the data acquisition module acquires multidimensional data comprising enterprise internal data and external data, so that comprehensiveness and accuracy of constructing a risk identification model data source are ensured; the data preprocessing module performs feature selection and data preprocessing on the collected data, the processed data is transmitted to the risk recognition module to construct a risk recognition model, and the risk of sales personnel is detected through the risk recognition model. In the system, the verification module is added to carry out manual verification on the detection result of the risk identification module, so that the accuracy and the reliability of the system are further ensured. And the optimization module feeds the test result of the correction module back to the risk identification model, so that the model is continuously optimized and adjusted, and the accuracy is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a system and a method for evaluating risk of sales personnel in the insurance industry.
Background
Currently, sales agents in the domestic insurance industry are huge in number, hundreds of job-seeking resumes are processed by staff responsible for recruitment every day, and risk level assessment of sales staff is completely dependent on manual operation, and more seriously, due to lack of a continuous management and control system of sales staff, some personnel data related to risks are easy to lose and information is not shared, so that the personnel possibly reenter a company, and cannot be effectively checked and managed.
Some methods provided by the prior art have the following disadvantages:
1. low efficiency and poor accuracy: relying on manual assessment of risk level can not guarantee the accuracy and consistency of assessment, and meanwhile, the processing speed is greatly reduced.
2. Risk personnel management loss: the secondary entering of risk personnel cannot be effectively prevented, and the operation risk of enterprises is increased.
3. Lack of data utilization: deep analysis and learning are not fully performed by using the data, and comprehensive assessment of risks is limited.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a system and a method for evaluating the risk of sales personnel in the insurance industry.
In order to achieve the above purpose, the invention adopts the following technical scheme: a system for assessing risk of sales personnel in an insurance industry, comprising: the system comprises a data acquisition module, a data preprocessing module, a risk identification module, a checking module and an optimizing module.
The data acquisition module is used for acquiring data related to sales personnel to form a data set table;
the data acquisition module comprises an enterprise internal data acquisition unit and an external data acquisition unit;
the enterprise internal data acquisition unit acquires basic information of sales personnel, including personal information, sales data, sales history, performance indexes and training records;
the external data acquisition unit acquires information disclosed by national law, including information of a person who is not trusted, a person who is restricted to consume and a person who is executed;
the data preprocessing module is used for preprocessing the data acquired by the data acquisition module and comprises a data cleaning unit, a missing value processing unit and a data conversion unit;
the risk identification module takes the data in the data set table as training data, and builds a risk identification model to detect whether sales personnel are high risk personnel or not;
the checking module is used for checking the risk identification module detected as a high-risk sales person;
and the optimization module is used for checking the information of the qualified sales personnel and the information which is detected by the risk identification module and is not the information of the high-risk sales personnel, feeding back the information into the risk identification module, and retraining and adjusting the risk identification model to continuously optimize the risk identification model and improve the accuracy of the system.
Further, the personal information includes: gender, age segment, academic, working years, market level codes, job channels, risk level;
the risk level is artificially defined in advance, and comprises a normal level and a higher level.
Further, the missing value processing unit determines missing data in the data set table, fills in with "0" for the columns of the numeric type, and fills in with "normal" for the columns of the risk level.
Further, the data conversion unit performs label coding on gender, age segmentation, academic, working years, market level codes, job channels, undertrusted executives, limited consumers, executives information and risk levels, converts the information into numerical representation, and performs standardization or normalization on the numerical characteristics.
Further, the risk recognition module divides the dataset of the dataset table into a training set and a testing set, and automatically selects and trains a machine learning model most suitable for the dataset table by using an AutoML function in the FLAML library;
further, the checking module performs manual checking, and organizes teams with related knowledge and experience to perform manual checking work to establish a standardized analysis flow; the method comprises the steps of analyzing the basic condition and the history of an individual, comparing the predicted result of a model with the actual condition of the individual, recording the verification result of each sample, and collecting feedback.
According to the system, the data acquisition module acquires multidimensional data comprising enterprise internal data and external data, so that comprehensiveness and accuracy of constructing a risk identification model data source are ensured; the data preprocessing module performs feature selection and data preprocessing on the collected data, the processed data is transmitted to the risk recognition module to construct a risk recognition model, and the risk of sales personnel is detected through the risk recognition model. In the system, the verification module is added to carry out manual verification on the detection result of the risk identification module, so that the accuracy and the reliability of the system are further ensured. And the optimization module feeds the test result of the correction module back to the risk identification model, so that the model is continuously optimized and adjusted, and the accuracy is improved.
A method of assessing risk of sales personnel in an insurance industry, comprising the steps of:
s1, collecting data related to sales personnel to form a data set table;
the sales force related data includes enterprise internal data and external data;
the enterprise internal data are basic information of sales personnel, including personal information, sales data, sales history, performance indexes and training records;
the external data is information disclosed by national law, and comprises information of a trusted executor, a limited consumer and an executed person;
the personal information includes: gender, age segment, academic, working years, market level codes, job channels, risk level;
the risk level is artificially defined in advance and comprises a normal level and a higher level;
the last column of the data set table is a risk level;
s2, performing feature selection and data preprocessing on data in a data set table, determining a feature set, and dividing a training set and a testing set of a training risk identification model;
s3, training a risk identification model by adopting a machine learning algorithm according to the divided training set and the test set;
specifically, using an autopl function in a FLAML library, automatically selecting and training the most suitable machine learning model as a risk recognition model;
s4, evaluating the risk of the sales personnel by using the trained risk identification model;
s5, performing manual verification on the evaluation result of the risk identification model.
Further, the step S2 specifically includes the following sub-steps:
s21, data preprocessing: the missing values in the numerical feature column are filled with '0', and the missing values in the risk level column are filled with 'normal';
s22, designating a column name of a column needing tag coding, comprising: gender, age segmentation, academic, working years, market level codes, job channels, trusted executives, limited consumers, executable information and risk levels; calling a function train_label to perform tag coding on the appointed column, and replacing original data; wherein, in the risk level column, the normal value is 1, and the higher value is 0;
s23, selecting a characteristic column: selecting columns except for the last column of risk level from the data set table after tag coding as characteristic columns, and converting the characteristic columns into a list format;
s24, dividing a training set and a testing set: dividing the feature column after feature selection and the last column of risk level as parameters; and randomly selecting half of data with higher risk level and data with normal risk level as a training set and a testing set respectively.
Further, in step S4, the risk recognition model outputs the risk level of the sales person according to the input feature set data of the sales person, so as to determine whether the sales person is a high risk person; the method specifically comprises the following substeps:
s41, if the output risk level is 0, judging that the risk identification model is a high risk person, and entering a step S5;
s42, if the output risk level is 1, the risk identification model judges that the risk identification model is not a high risk person, and the step S43 is performed;
s43, feeding the detection result back to the risk identification model for optimization.
Further, step S5, a team with related knowledge and experience is organized to execute manual verification work, and a standardized analysis flow is established; analyzing the basic condition and the history of an individual, comparing the predicted result of a model with the actual condition of the individual, and recording the verification result of each sample;
if the manual verification result is high risk personnel, the step S43 is entered;
and if the manual verification result is not high risk personnel, correcting the original data, and feeding the corrected data back to the risk identification model again for model optimization.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the system, the data acquisition module acquires multidimensional data comprising enterprise internal data and external data, so that comprehensiveness and accuracy of constructing a risk identification model data source are ensured; the data preprocessing module performs feature selection and data preprocessing on the collected data, the processed data is transmitted to the risk recognition module to construct a risk recognition model, and the risk of sales personnel is detected through the risk recognition model.
2. In the system, the verification module is added to carry out manual verification on the detection result of the risk identification module, so that the accuracy and the reliability of the system are further ensured.
3. And the optimization module feeds the test result of the correction module back to the risk identification model, so that the model is continuously optimized and adjusted, and the accuracy is improved.
4. The invention improves the accuracy and consistency of risk assessment by means of a machine learning model, and reduces the false judgment rate; by an automatic and intelligent system, the risk assessment and decision making process is accelerated, and the processing speed is improved.
Description of the embodiments
For a further understanding of the objects, construction, features, and functions of the invention, reference should be made to the following detailed description of the preferred embodiments.
Examples
A system for assessing risk of sales personnel in an insurance industry, comprising: the system comprises a data acquisition module, a data preprocessing module, a risk identification module, a checking module and an optimizing module.
The data acquisition module is used for acquiring data related to sales personnel to form a data set table;
the data acquisition module comprises an enterprise internal data acquisition unit and an external data acquisition unit;
the enterprise internal data acquisition unit acquires basic information of sales personnel, including personal information, sales data, sales history, performance indexes and training records;
the external data acquisition unit acquires information disclosed by national law, including information of a person who is not trusted, a person who is restricted to consume and a person who is executed;
the data preprocessing module is used for preprocessing the data acquired by the data acquisition module and comprises a data cleaning unit, a missing value processing unit and a data conversion unit;
the risk identification module takes the data in the data set table as training data, and builds a risk identification model to detect whether sales personnel are high risk personnel or not;
the checking module is used for checking the risk identification module detected as a high-risk sales person;
and the optimization module is used for feeding back the information of the salesperson checked as qualified by the checking module and the information which is detected by the risk recognition module and is not the high-risk salesperson to the risk recognition module, and carrying out retraining adjustment on the risk recognition model.
Further, the personal information includes: gender, age segment, academic, working years, market level codes, job channels, risk level;
the risk level is artificially defined in advance, and comprises a normal level and a higher level.
Further, the missing value processing unit determines missing data in the data set table, fills in with "0" for the columns of the numeric type, and fills in with "normal" for the columns of the risk level.
Further, the data conversion unit performs label coding on gender, age segmentation, academic, working years, market level codes, job channels, undertrusted executives, limited consumers, executives information and risk levels, converts the information into numerical representation, and performs standardization or normalization on the numerical characteristics.
Further, the risk recognition module divides the dataset of the dataset table into a training set and a testing set, and automatically selects and trains a machine learning model most suitable for the dataset table by using an AutoML function in the FLAML library;
further, the checking module performs manual checking, and organizes teams with related knowledge and experience to perform manual checking work to establish a standardized analysis flow; the method comprises the steps of analyzing the basic condition and the history of an individual, comparing the predicted result of a model with the actual condition of the individual, recording the verification result of each sample, and collecting feedback.
Examples
A method of assessing risk of sales personnel in an insurance industry, comprising the steps of:
s1, collecting data related to sales personnel to form a data set table;
the sales force related data includes enterprise internal data and external data;
the enterprise internal data are basic information of sales personnel, including personal information, sales data, sales history, performance indexes and training records;
the external data is information disclosed by national law, and comprises information of a trusted executor, a limited consumer and an executed person;
the personal information includes: gender, age segment, academic, working years, market level codes, job channels, risk level;
the risk level is artificially defined in advance and comprises a normal level and a higher level;
the last column of the data set table is a risk level;
s2, performing feature selection and data preprocessing on data in a data set table, determining a feature set, and dividing a training set and a testing set of a training risk identification model; the method specifically comprises the following substeps:
s21, data preprocessing: the missing values in the numerical feature column are filled with '0', and the missing values in the risk level column are filled with 'normal';
s22, designating a column name of a column needing tag coding, comprising: gender, age segmentation, academic, working years, market level codes, job channels, trusted executives, limited consumers, executable information and risk levels; calling a function train_label to perform tag coding on the appointed column, and replacing original data; wherein, in the risk level column, the normal value is 1, and the higher value is 0;
s23, selecting a characteristic column: selecting columns except for the last column of risk level from the data set table after tag coding as characteristic columns, and converting the characteristic columns into a list format;
s24, dividing a training set and a testing set: : calling a function train_test_split to divide the feature column and the last column risk level after feature selection as parameters; and randomly selecting half of data with higher risk level and data with normal risk level as a training set and a testing set respectively.
In a specific embodiment of the present invention, the feature set data includes: 8 basic information (sex, age, working years, etc.), 3 external information (information of a trusted executor, a limited consumer, a executed person), 20 internal data (policy of the last three years, borrowing amount, return of policy, etc.), 150 headquarter behavior patterns (multiple repeated failure and return of policy, multiple self-protection element return of policy, lower reference rate, etc.), 13 headquarter risk categories (misleading sales, no in-place policy maintenance, no actual manpower to collect rewarding body, etc.).
S3, training a risk identification model by adopting a machine learning algorithm according to the divided training set and the test set;
specifically, using an autopl function in a FLAML library, automatically selecting and training the most suitable machine learning model as a risk recognition model;
s4, evaluating the risk of the sales personnel by using the trained risk identification model; the risk identification model outputs the risk level of the sales person according to the input feature set data of the sales person, so as to judge whether the sales person is a high risk person; the method specifically comprises the following substeps:
s41, if the output risk level is 0, judging that the risk identification model is a high risk person, and entering a step S5;
s42, if the output risk level is 1, the risk identification model judges that the risk identification model is not a high risk person, and the step S43 is performed;
s43, feeding the detection result back to the risk identification model for optimization.
S5, performing manual verification on the evaluation result of the risk identification model;
specifically, a team with related knowledge and experience is organized to execute manual verification work, and a standardized analysis flow is established; analyzing the basic condition and the history of an individual, comparing the predicted result of a model with the actual condition of the individual, and recording the verification result of each sample;
if the manual verification result is high risk personnel, the step S43 is entered;
and if the manual verification result is not high risk personnel, correcting the original data, and feeding the corrected data back to the risk identification model again for model optimization.
The invention has been described with respect to the above-described embodiments, however, the above-described embodiments are merely examples of practicing the invention. It should be noted that the disclosed embodiments do not limit the scope of the invention. On the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
Claims (10)
1. A system for assessing risk of sales personnel in an insurance industry, characterized by: the system comprises a data acquisition module, a data preprocessing module, a risk identification module, a checking module and an optimization module;
the data acquisition module is used for acquiring data related to sales personnel to form a data set table;
the data acquisition module comprises an enterprise internal data acquisition unit and an external data acquisition unit;
the enterprise internal data acquisition unit acquires basic information of sales personnel, including personal information, sales data, sales history, performance indexes and training records;
the external data acquisition unit acquires information disclosed by national law, including information of a person who is not trusted, a person who is restricted to consume and a person who is executed;
the data preprocessing module is used for preprocessing the data acquired by the data acquisition module and comprises a data cleaning unit, a missing value processing unit and a data conversion unit;
the risk identification module takes the data in the data set table as training data, and builds a risk identification model to detect whether sales personnel are high risk personnel or not;
the checking module is used for checking the risk identification module detected as a high-risk sales person;
and the optimization module is used for feeding back the information of the salesperson checked as qualified by the checking module and the information which is detected by the risk recognition module and is not the high-risk salesperson to the risk recognition module, and carrying out retraining adjustment on the risk recognition model.
2. The system for assessing the risk of a sales person in an insurance industry according to claim 1, wherein: the personal information includes: gender, age segment, academic, working years, market level codes, job channels, risk level;
the risk level is artificially defined in advance, and comprises a normal level and a higher level.
3. The system for assessing the risk of a sales person in an insurance industry according to claim 2, wherein: the missing value processing unit determines missing data in the data set table, fills in with "0" for the columns of the numeric type and fills in with "normal" for the columns of the risk level.
4. A system for assessing the risk of a sales person in an insurance industry according to claim 3, wherein: the data conversion unit carries out tag coding on gender, age segmentation, academic, working years, market level codes, job channels, trusted executives, limited consumers, executable information and risk levels, converts the information into numerical representation and standardizes or normalizes the numerical characteristics.
5. The system for assessing the risk of a sales person in an insurance industry according to claim 4, wherein: the risk recognition module divides the dataset of the dataset table into a training set and a testing set, and automatically selects and trains a machine learning model most suitable for the dataset table by using an AutoML function in the FLAML library.
6. The system for assessing the risk of a sales person in an insurance industry according to claim 5, wherein: the verification module performs manual verification, and organizes teams with related knowledge and experience to perform manual verification work and establish a standardized analysis flow; the method comprises the steps of analyzing the basic condition and the history of an individual, comparing the predicted result of a model with the actual condition of the individual, recording the verification result of each sample, and collecting feedback.
7. A method of assessing risk of sales personnel in an insurance industry, applicable to the system for assessing risk of sales personnel in an insurance industry as claimed in claims 1-6, comprising the steps of:
s1, collecting data related to sales personnel to form a data set table;
the sales force related data includes enterprise internal data and external data;
the enterprise internal data are basic information of sales personnel, including personal information, sales data, sales history, performance indexes and training records;
the external data is information disclosed by national law, and comprises information of a trusted executor, a limited consumer and an executed person;
the personal information includes: gender, age segment, academic, working years, market level codes, job channels, risk level;
the risk level is artificially defined in advance and comprises a normal level and a higher level;
the last column of the data set table is a risk level;
s2, performing feature selection and data preprocessing on data in a data set table, determining a feature set, and dividing a training set and a testing set of a training risk identification model;
s3, training a risk identification model by adopting a machine learning algorithm according to the divided training set and the test set;
specifically, using an autopl function in a FLAML library, automatically selecting and training the most suitable machine learning model as a risk recognition model;
s4, evaluating the risk of the sales personnel by using the trained risk identification model;
s5, performing manual verification on the evaluation result of the risk identification model.
8. The method of assessing the risk of a sales person in an insurance industry according to claim 7, wherein: the step S2 specifically includes the following substeps:
s21, data preprocessing: the missing values in the numerical feature column are filled with '0', and the missing values in the risk level column are filled with 'normal';
s22, designating a column name of a column needing tag coding, comprising: gender, age segmentation, academic, working years, market level codes, job channels, trusted executives, limited consumers, executable information and risk levels; calling a function train_label to perform tag coding on the appointed column, and replacing original data; wherein, in the risk level column, the normal value is 1, and the higher value is 0;
s23, selecting a characteristic column: selecting columns except for the last column of risk level from the data set table after tag coding as characteristic columns, and converting the characteristic columns into a list format;
s24, dividing a training set and a testing set: dividing the feature column after feature selection and the last column of risk level as parameters; and randomly selecting half of data with higher risk level and data with normal risk level as a training set and a testing set respectively.
9. The method of assessing the risk of a sales person in an insurance industry according to claim 8, wherein: in step S4, the risk identification model outputs the risk level of the sales personnel according to the input feature set data of the sales personnel, so as to judge whether the sales personnel is a high risk personnel; the method specifically comprises the following substeps:
s41, if the output risk level is 0, judging that the risk identification model is a high risk person, and entering a step S5;
s42, if the output risk level is 1, the risk identification model judges that the risk identification model is not a high risk person, and the step S43 is performed;
s43, feeding the detection result back to the risk identification model for optimization.
10. The method of assessing the risk of a sales person in an insurance industry according to claim 9, wherein: s5, performing manual verification work by organizing teams with related knowledge and experience, and establishing a standardized analysis flow; analyzing the basic condition and the history of an individual, comparing the predicted result of a model with the actual condition of the individual, and recording the verification result of each sample;
if the manual verification result is high risk personnel, the step S43 is entered;
and if the manual verification result is not high risk personnel, correcting the original data, and feeding the corrected data back to the risk identification model again for model optimization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311516656.4A CN117634873A (en) | 2023-11-15 | 2023-11-15 | System and method for evaluating risk of sales personnel in insurance industry |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311516656.4A CN117634873A (en) | 2023-11-15 | 2023-11-15 | System and method for evaluating risk of sales personnel in insurance industry |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117634873A true CN117634873A (en) | 2024-03-01 |
Family
ID=90034843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311516656.4A Pending CN117634873A (en) | 2023-11-15 | 2023-11-15 | System and method for evaluating risk of sales personnel in insurance industry |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117634873A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108694521A (en) * | 2018-07-02 | 2018-10-23 | 平安健康保险股份有限公司 | Individual risk's pricing method and system |
| WO2020015089A1 (en) * | 2018-07-18 | 2020-01-23 | 平安科技（深圳）有限公司 | Identity information risk assessment method and apparatus, and computer device and storage medium |
| CN110910002A (en) * | 2019-11-15 | 2020-03-24 | 安徽海汇金融投资集团有限公司 | Account receivable default risk identification method and system |
| CN112182207A (en) * | 2020-09-16 | 2021-01-05 | 神州数码信息系统有限公司 | Invoice false-proof risk assessment method based on keyword extraction and rapid text classification |
| CN113537693A (en) * | 2021-05-14 | 2021-10-22 | 广州市高科通信技术股份有限公司 | Personnel risk level obtaining method, terminal and storage device |
| CN115470962A (en) * | 2022-08-03 | 2022-12-13 | 浙江鸿程计算机系统有限公司 | LightGBM-based enterprise confidence loss risk prediction model construction method |
| CN115759758A (en) * | 2022-12-15 | 2023-03-07 | 中国平安人寿保险股份有限公司 | Risk assessment method, device, equipment and storage medium |
| CN116823496A (en) * | 2023-06-06 | 2023-09-29 | 深圳市邦德布拉泽科技有限公司 | Intelligent insurance risk assessment and pricing system based on artificial intelligence |
-
2023
- 2023-11-15 CN CN202311516656.4A patent/CN117634873A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108694521A (en) * | 2018-07-02 | 2018-10-23 | 平安健康保险股份有限公司 | Individual risk's pricing method and system |
| WO2020015089A1 (en) * | 2018-07-18 | 2020-01-23 | 平安科技（深圳）有限公司 | Identity information risk assessment method and apparatus, and computer device and storage medium |
| CN110910002A (en) * | 2019-11-15 | 2020-03-24 | 安徽海汇金融投资集团有限公司 | Account receivable default risk identification method and system |
| CN112182207A (en) * | 2020-09-16 | 2021-01-05 | 神州数码信息系统有限公司 | Invoice false-proof risk assessment method based on keyword extraction and rapid text classification |
| CN113537693A (en) * | 2021-05-14 | 2021-10-22 | 广州市高科通信技术股份有限公司 | Personnel risk level obtaining method, terminal and storage device |
| CN115470962A (en) * | 2022-08-03 | 2022-12-13 | 浙江鸿程计算机系统有限公司 | LightGBM-based enterprise confidence loss risk prediction model construction method |
| CN115759758A (en) * | 2022-12-15 | 2023-03-07 | 中国平安人寿保险股份有限公司 | Risk assessment method, device, equipment and storage medium |
| CN116823496A (en) * | 2023-06-06 | 2023-09-29 | 深圳市邦德布拉泽科技有限公司 | Intelligent insurance risk assessment and pricing system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112859822B (en) | Equipment health analysis and fault diagnosis method and system based on artificial intelligence | |
| CN111259947A (en) | Power system fault early warning method and system based on multi-mode learning | |
| CN112488507B (en) | Expert classification portrait method and device based on clustering and storage medium | |
| CN117196066A (en) | Intelligent operation and maintenance information analysis model | |
| CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
| CN112084220A (en) | Method and device for diagnosing abnormity of electric energy metering device and readable storage medium | |
| CN115719283A (en) | Intelligent accounting management system | |
| CN110443528A (en) | A kind of business risk quantitative evaluation and tracking system based on machine learning | |
| CN114298604A (en) | Intelligent comprehensive evaluation management system for incubator living enterprise based on big data dynamic monitoring analysis | |
| CN113628024A (en) | Financial data intelligent auditing system and method based on big data platform system | |
| CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
| CN117634873A (en) | System and method for evaluating risk of sales personnel in insurance industry | |
| CN110852621A (en) | Power customer load characteristic analysis and classification method, device and readable storage medium | |
| CN113642669B (en) | Feature analysis-based fraud prevention detection method, device, equipment and storage medium | |
| CN113393169B (en) | Financial industry transaction system performance index analysis method based on big data technology | |
| CN115130872A (en) | Recruitment risk assessment system based on deep learning judgment | |
| CN115392663A (en) | Data acquisition and processing method based on big data | |
| CN114528314A (en) | Engineering construction project supervision system and method | |
| CN114168409A (en) | Service system running state monitoring and early warning method and system | |
| CN116957306B (en) | User side response potential evaluation method and system based on resource collaborative interaction | |
| CN113159131B (en) | Hierarchical prediction method and hierarchical prediction system for running conditions of bioreactor | |
| Li | Statistical Method of Social Audit Risk Based on Machine Learning in the Context of Big Data | |
| CN115330131A (en) | Method for extracting key influence factors of evaluation indexes | |
| CN115049370A (en) | Intelligent control software for wind power plant | |
| Li et al. | Design of Enterprise Financial and Economic Risk Early Warning System Based on Machine Learning Algorithms |
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 |