CN113537693A - Personnel risk level obtaining method, terminal and storage device - Google Patents

Personnel risk level obtaining method, terminal and storage device Download PDF

Info

Publication number
CN113537693A
CN113537693A CN202110528759.7A CN202110528759A CN113537693A CN 113537693 A CN113537693 A CN 113537693A CN 202110528759 A CN202110528759 A CN 202110528759A CN 113537693 A CN113537693 A CN 113537693A
Authority
CN
China
Prior art keywords
risk
person
risk level
data set
indexes
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
Application number
CN202110528759.7A
Other languages
Chinese (zh)
Inventor
彭世财
赵丽莎
陈彦文
刘剑鸿
邬东坡
甄祯
周龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Gaoke Communications Technology Co ltd
Original Assignee
Guangzhou Gaoke Communications Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Gaoke Communications Technology Co ltd filed Critical Guangzhou Gaoke Communications Technology Co ltd
Priority to CN202110528759.7A priority Critical patent/CN113537693A/en
Publication of CN113537693A publication Critical patent/CN113537693A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Artificial Intelligence (AREA)
  • Tourism & Hospitality (AREA)
  • Evolutionary Computation (AREA)
  • General Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a personnel risk level acquisition method, a terminal and a storage device, wherein the personnel risk level acquisition method comprises the following steps: s101: acquiring risk information of a first person, and preprocessing the risk information to acquire a risk index; s102: performing feature selection on the risk indexes, and acquiring effective risk indexes in the risk indexes according to feature selection results; s103: forming a known data set and an unknown data set based on the effective risk indexes, and performing supervised learning training through the known data set to form a risk level evaluation model; s104: and optimizing the risk level evaluation model through the unknown data set, and acquiring the risk level of the second person by using the optimized risk level evaluation model. The method for evaluating the personnel by using the risk grade evaluation model has the advantages of short time consumption, high efficiency, small workload, reduced labor cost and high accuracy of the evaluation result.

Description

Personnel risk level obtaining method, terminal and storage device
Technical Field
The invention relates to the technical field of personnel management, in particular to a personnel risk level acquisition method, a terminal and a storage device.
Background
At present, in practical application, risk level assessment needs to be performed on each person one by one, the time consumption is long, the workload is large, the labor cost is high, the assessment is easily affected by the emotion of the assessed person and the external environment, the assessment mode is inaccurate, and risk level assessment errors are easily caused.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a personnel risk level acquisition method, a terminal and a storage device, after the risk indexes of personnel are acquired, effective risk indexes are screened in a characteristic selection mode, and a risk level evaluation model is formed by using the effective risk indexes and the risk level of a first person through supervised learning training, so that the effective risk indexes related to risk evaluation can be screened out, the accuracy of the risk evaluation is improved, the time consumption is short, the efficiency is high, the workload is small, and the labor cost is reduced.
In order to solve the above problems, the present invention provides a method for acquiring a risk level of a person, including: the personnel risk level obtaining method comprises the following steps: s101: acquiring risk information of a first person, and preprocessing the risk information to acquire risk indexes, wherein the risk indexes comprise static risk indexes and dynamic risk indexes; s102: performing feature selection on the risk indexes, and acquiring effective risk indexes in the risk indexes according to feature selection results; s103: forming a known data set and an unknown data set based on the effective risk indexes, and performing supervised learning training through the known data set to form a risk level evaluation model, wherein the known data set comprises a risk level corresponding to the first person, and the unknown data set does not comprise the risk level corresponding to the first person; s104: and obtaining a prediction result of the risk level evaluation model on the data in the unknown data set, optimizing the risk level evaluation model according to the prediction result, and obtaining the risk level of a second person by using the optimized risk level evaluation model.
Further, the step of preprocessing the risk information specifically includes: and sequentially carrying out data extraction, dimensionless quantification and missing value processing on the risk information.
Further, the step of preprocessing the risk information to obtain a risk indicator further includes: and performing data cleaning on the data of the risk indicator.
Further, the step of performing feature selection on the risk indicator specifically includes: and acquiring a pearson correlation coefficient and an information gain of the risk index, and acquiring the Euclidean distance of the risk index according to the pearson correlation coefficient and the information gain.
Further, the step of obtaining the euclidean distance of the risk indicator according to the pearson correlation coefficient and the information gain specifically includes: and taking the pearson correlation coefficient and the information gain as coordinates of the risk indexes, and calculating the Euclidean distance between the risk indexes according to the coordinates.
Further, the step of obtaining an effective risk indicator of the risk indicators according to the feature selection result specifically includes: judging whether the Euclidean distance is larger than a preset value or not; if so, determining the risk index as an effective risk index; if not, determining that the risk indicator is not an effective risk indicator.
Further, the step of forming a known data set and an unknown data set based on the effective risk indicator specifically includes: judging whether a first person corresponding to the effective risk index has a risk level, wherein the data at least comprises the effective index of the first person; if so, putting the data corresponding to the first person into a known data set; and if not, putting the data of the first person into an unknown data set.
Further, the step of performing supervised learning training through the known data set to form a risk level assessment model specifically includes: and dividing the known data set into a training set and a testing set, performing supervised learning training through the training set and the testing set to form a risk level evaluation model, and adjusting training parameters according to the accuracy of the risk level evaluation model.
Based on the same inventive concept, the invention further provides an intelligent terminal, which comprises a processor and a memory, wherein the processor is in communication connection with the memory, the memory stores a computer program, and the processor executes the personnel risk level obtaining method according to the computer program.
Based on the same inventive concept, the invention also proposes a storage device, which stores program data used for executing the personnel risk level acquisition method as described above.
Compared with the prior art, the invention has the beneficial effects that: after the risk indexes of the personnel are obtained, effective risk indexes are screened in a characteristic selection mode, the effective risk indexes and the risk grade of the first personnel are used for supervised learning training to form a risk grade evaluation model, the effective risk indexes related to risk evaluation can be screened out, the accuracy of the risk evaluation is improved, the risk grade evaluation model is trained by using big data to form the risk grade evaluation model for each personnel, the time consumption is short, the efficiency is high, the workload is small, the labor cost is reduced, and the accuracy of the evaluation result is high.
Drawings
FIG. 1 is a flowchart of an embodiment of a person risk level obtaining method of the present invention;
FIG. 2 is a flowchart of another embodiment of a method for obtaining a risk level of a person according to the present invention;
FIG. 3 is a block diagram of an embodiment of an intelligent terminal according to the present invention;
FIG. 4 is a block diagram of a memory device according to an embodiment of the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.
Referring to fig. 1-2, fig. 1 is a flowchart illustrating an embodiment of a method for acquiring a risk level of a person according to the present invention; fig. 2 is a flowchart of another embodiment of a person risk level obtaining method according to the present invention. The person risk level acquisition method of the present invention is explained with reference to fig. 1-2.
In this embodiment, the device for executing the method for acquiring a risk level of a person may be a computer, a server, a control platform, or other intelligent terminals capable of acquiring a risk index of a person and executing the method for acquiring a risk level of a person according to the risk index. The personnel risk level obtaining method comprises the following steps:
s101: acquiring risk information of personnel, and preprocessing the risk information to acquire risk indexes, wherein the risk indexes comprise static risk indexes and dynamic risk indexes.
In this embodiment, the risk information of the person and the risk indicators in the risk information may be obtained by artificial classification and input, or extracted from the risk information of the person according to the features of each risk indicator after the information of the person is collected.
In this embodiment, the preprocessing method performed on the data of the risk indicator includes data extraction, dimensionless quantization, and missing value processing. The data extraction is used for extracting data of risk indexes in the risk information, the dimensionless quantization is used for converting data of different rules into the same specification so as to avoid the dependency on measurement unit data, and the dimensionless quantization can be performed in a standardized or normalized mode. And carrying out missing value processing on the data of the risk index in a mode of filling a machine learning algorithm and discarding the data during the missing value processing.
In this embodiment, after the risk information is preprocessed to obtain the risk indicator, data of the risk indicator may be further cleaned to further remove incomplete or error data in the data.
S102: and performing feature selection on the risk indexes, and acquiring effective risk indexes in the risk indexes according to feature selection results.
In this embodiment, the step of performing feature selection on the risk indicator specifically includes: and acquiring a pearson correlation coefficient and an information gain of the risk index, and acquiring an Euclidean distance of the risk index according to the pearson correlation coefficient and the information gain. The calculation method of the pearson correlation coefficient, the information gain, and the euclidean distance is the prior art, and is not described herein again.
In this embodiment, the step of obtaining the euclidean distance of the risk indicator according to the pearson correlation coefficient and the information gain specifically includes: and calculating the Euclidean distance between the risk indexes according to the coordinates by taking the pearson correlation coefficient and the information gain as the coordinates of the risk indexes.
In a specific embodiment, pearson correlation coefficient (pr) and information gain (ig) of each risk index are calculated, the correlation coefficient and the information gain are used as coordinates (pr, ig) of the risk index, and the Euclidean distance between each risk index is calculated by using the coordinates.
In this embodiment, the step of obtaining an effective risk indicator in the risk indicators specifically includes: judging whether the Euclidean distance is larger than a preset value or not; if so, determining the risk index as an effective risk index; and if not, determining that the risk index is not the effective risk index. The preset value can be set according to user requirements, and only the mutual interference among different effective risk indexes can be avoided.
In this embodiment, the number (depth) n of the stages of the effective risk indicators may be set according to the type of the effective indicators, the associated information with the risk, and other data, for example, the effective indicators of the age include two secondary indicators, i.e., 0-18 and 18-60.
S103: and forming a known data set and an unknown data set based on the effective risk indexes, and performing supervised learning training through the known data set to form a risk grade evaluation model, wherein the known data set comprises the risk grade corresponding to the first person, and the unknown data set does not comprise the risk grade corresponding to the first person.
In this embodiment, the step of forming the known data set and the unknown data set based on the effective risk indicator specifically includes: judging whether a first person corresponding to the effective risk index has a risk level, wherein the data at least comprises the effective index of the first person; if so, putting the data corresponding to the first person into a known data set; if not, the data of the first person is put into the unknown data set.
In this embodiment, the step of performing supervised learning training through a known data set to form a risk level assessment model specifically includes: the known data set is divided into a training set and a testing set, supervised learning training is carried out through the training set and the testing set to form a risk level evaluation model, and training parameters are adjusted according to the accuracy of the risk level evaluation model.
S104: and obtaining a prediction result of the risk level evaluation model on the data in the unknown data set, optimizing the risk level evaluation model according to the prediction result, and obtaining the risk level of the second person by using the optimized risk level evaluation model.
In a specific embodiment, data including effective indexes of people are divided into a known data set and an unknown data set, a supervised learning algorithm is trained through a training set and a test set in the known data set to form a risk level assessment model, whether the accuracy of the risk level assessment model on the prediction result of the data in the test set is greater than a preset probability or not is judged, and training parameters of the risk level assessment model are adjusted when the preset probability is not reached and are trained. And when the preset probability is reached, inputting the data in the position data set into the risk level evaluation model to obtain a prediction result, judging whether the prediction result is accurate or reaches an expected value, if so, determining that the model training is successful, if not, adding the unknown data set and the risk level corresponding to the first person in the unknown data set into the training set in the known data set, and performing retraining to optimize the risk level evaluation model. The expected value can be the risk level judgment information of the first person in the unknown data set by the person, and whether the prediction result is accurate or not is judged according to the information input by the person.
In other embodiments, a risk level that is pre-stored and corresponds to a first person in the unknown data set may be searched for in the obtained prediction result, and it is determined whether the risk level is the same as the prediction result or a deviation is not greater than a preset deviation threshold, if so, the prediction result is determined to be accurate, and if not, the prediction result is determined to be inaccurate.
In this embodiment, the risk level of the second person is obtained by inputting data related to the effective risk indicator of the second person into the risk level assessment model.
In this embodiment, the risk score of the second person may also be obtained, and the risk level of the second person is obtained by combining the risk score and the risk level.
Wherein, the step of obtaining the risk score comprises: and performing AHP hierarchical analysis on each level of the effective risk indexes, and acquiring the weight of each effective risk index according to the analysis result. And performing risk assessment on the second person according to the weight of each effective risk score to obtain a risk score.
In this embodiment, the step of performing AHP hierarchical analysis on each level of effective risk indicators specifically includes: and acquiring a random consistency index and a current matrix consistency index of each level of index, performing consistency check through the random consistency index and the current matrix consistency index, and acquiring an evaluation variable of the effective risk index and a weight of the evaluation variable according to a check result of the consistency check.
In this embodiment, a judgment matrix is generated according to the importance degree judgment information of the personnel on each level of the index, and the current matrix consistency index of each level of the index is obtained by using the judgment matrix.
In a specific embodiment, for an i-level index in an effective risk index with a depth of n, a random consistency index RI and a judgment matrix of the i-level index are respectively generated, a current matrix consistency index CI is generated by using the judgment matrix, and consistency check CR is performed by using the random consistency index RI and the current matrix consistency index CI as CI/RI to obtain a check result CR.
In this embodiment, the step of obtaining the weight of each level of the effective risk indicator according to the verification result of the consistency verification specifically includes: judging whether the consistency check result is smaller than a preset threshold value or not; if so, carrying out hierarchical sorting on the indexes, and acquiring the weight of each level of indexes in the effective risk indexes according to a sorting result; if not, the current matrix consistency index of the index is obtained again, and consistency check is carried out according to the current consistency index until the consistency check result is smaller than the preset threshold value.
In a specific embodiment, the preset threshold is 0.1.
In this embodiment, the step of obtaining the weight of each effective risk indicator according to the analysis result specifically includes: and performing hierarchical total sorting on the weight of each level of index in the effective risk index, and acquiring the weight of each effective risk index according to the result of the total sorting.
In this embodiment, the step of evaluating the risk of the second person by the weight of the effective risk indicator to obtain the risk score specifically includes: and carrying out absolute risk index evaluation and predicted risk index evaluation on the second person based on the weight of the effective risk index and the effective risk index of the second person, and obtaining the risk score of the second person according to the evaluation result.
In this embodiment, data related to the effective risk indicator possessed by the second person is obtained according to the risk information of the person, the weight of the effective risk indicator is obtained, and the weight of the effective risk indicator possessed by the second person to be evaluated is obtained, and the absolute risk index evaluation is performed through the weight.
In a specific embodiment, by formula
Figure RE-GDA0003263845410000081
Obtaining an absolute risk index, wherein R (k) is the absolute risk index, M is the number of effective risk indicators, ωiIs the weight of the ith valid risk indicator, Rk,iIs the risk score of the ith risk indicator.
In this embodiment, the predictive risk index assessment is performed based on the risk rating of the second person. The risk level of the second person can be obtained through a manual evaluation mode, a risk level evaluation model can also be established, and the risk level of the second person is obtained through the risk level evaluation model.
In a specific embodiment, by formula PkE {10,35,60,85} calculating a predicted risk index, where PkIn order to predict the risk index, the predicted risk index P of the second person is 10 when the risk class of the second person is the general risk, the predicted risk index is 35 when the risk class of the second person is the third-level risk, the predicted risk index is 35 when the risk class of the second person is the second-level risk, and the predicted risk index is 85 when the risk class of the first person is the first-level risk.
In this embodiment, the step of obtaining the risk score of the second person through the evaluation result specifically includes: by the formula Y (k) ═ α Ak+βPkObtaining a risk score for the second person, wherein Y (k) is the risk score, PkFor absolute risk index, α, β are fixed parameters.
The invention has the beneficial effects that: after the risk indexes of the personnel are obtained, effective risk indexes are screened in a characteristic selection mode, the effective risk indexes and the risk grade of the first personnel are used for supervised learning training to form a risk grade evaluation model, the effective risk indexes related to risk evaluation can be screened out, the accuracy of the risk evaluation is improved, the risk grade evaluation model is trained by using big data to form the risk grade evaluation model for each personnel, the time consumption is short, the efficiency is high, the workload is small, the labor cost is reduced, and the accuracy of the evaluation result is high.
Based on the same inventive concept, the present invention further provides an intelligent terminal, please refer to fig. 3, fig. 3 is a structural diagram of an embodiment of the intelligent terminal of the present invention, and the intelligent terminal of the present invention is described with reference to fig. 3.
In this embodiment, the intelligent terminal includes a processor and a memory, the processor is in communication connection with the memory, the memory stores a computer program, and the processor implements the method for acquiring the risk level of the person according to the computer program.
The processor is used for controlling the overall operation of the intelligent terminal so as to complete all or part of the steps in the personnel risk level acquisition method. The memory is used to store various types of data to support operation at the smart terminal, which may include, for example, instructions for any application or method operating on the smart terminal, as well as application-related data such as contact data, messaging, pictures, audio, video, and so forth. The Memory may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
Based on the same inventive concept, the present invention further provides a memory device, please refer to fig. 4, fig. 4 is a structural diagram of an embodiment of the memory device of the present invention, and the memory device of the present invention is described with reference to fig. 4.
In the present embodiment, the storage means stores program data used for executing the person risk level acquisition method according to the above-described embodiment.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A personnel risk level obtaining method is characterized by comprising the following steps:
s101: acquiring risk information of a first person, and preprocessing the risk information to acquire risk indexes, wherein the risk indexes comprise static risk indexes and dynamic risk indexes;
s102: performing feature selection on the risk indexes, and acquiring effective risk indexes in the risk indexes according to feature selection results;
s103: forming a known data set and an unknown data set based on the effective risk indexes, and performing supervised learning training through the known data set to form a risk level evaluation model, wherein the known data set comprises a risk level corresponding to the first person, and the unknown data set does not comprise the risk level corresponding to the first person;
s104: and obtaining a prediction result of the risk level evaluation model on the data in the unknown data set, optimizing the risk level evaluation model according to the prediction result, and obtaining the risk level of a second person by using the optimized risk level evaluation model.
2. The personnel risk level acquisition method of claim 1, wherein the step of preprocessing the risk information specifically comprises:
and sequentially carrying out data extraction, dimensionless quantification and missing value processing on the risk information.
3. The method for acquiring the risk level of the person according to claim 1, wherein the step of preprocessing the risk information to acquire the risk index further comprises:
and performing data cleaning on the data of the risk indicator.
4. The method for acquiring the personnel risk level according to claim 1, wherein the step of performing the feature selection on the risk indicator specifically comprises:
and acquiring a pearson correlation coefficient and an information gain of the risk index, and acquiring the Euclidean distance of the risk index according to the pearson correlation coefficient and the information gain.
5. The method for acquiring the personnel risk level according to claim 4, wherein the step of acquiring the Euclidean distance of the risk indicator according to the pearson correlation coefficient and the information gain specifically comprises:
and taking the pearson correlation coefficient and the information gain as coordinates of the risk indexes, and calculating the Euclidean distance between the risk indexes according to the coordinates.
6. The method for acquiring the personnel risk level according to claim 4, wherein the step of acquiring the effective risk indicators in the risk indicators according to the feature selection result specifically comprises:
judging whether the Euclidean distance is larger than a preset value or not;
if so, determining the risk index as an effective risk index;
if not, determining that the risk indicator is not an effective risk indicator.
7. The method for obtaining the personal risk level according to claim 1, wherein the step of forming the known data set and the unknown data set based on the effective risk indicator specifically comprises:
judging whether a first person corresponding to the effective risk index has a risk level, wherein the data at least comprises the effective index of the first person;
if so, putting the data corresponding to the first person into a known data set;
and if not, putting the data of the first person into an unknown data set.
8. The method for obtaining the risk level of the person according to claim 1, wherein the step of performing supervised learning training through the known data set to form the risk level assessment model specifically comprises:
and dividing the known data set into a training set and a testing set, performing supervised learning training through the training set and the testing set to form a risk level evaluation model, and adjusting training parameters according to the accuracy of the risk level evaluation model.
9. An intelligent terminal, characterized in that the intelligent terminal comprises a processor and a memory, the processor is connected with the memory in a communication way, the memory stores a computer program, and the processor executes the personnel risk level obtaining method according to any one of claims 1-8 according to the computer program.
10. A storage device, characterized in that the storage device stores program data for executing the person risk level acquisition method according to any one of claims 1-8.
CN202110528759.7A 2021-05-14 2021-05-14 Personnel risk level obtaining method, terminal and storage device Pending CN113537693A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110528759.7A CN113537693A (en) 2021-05-14 2021-05-14 Personnel risk level obtaining method, terminal and storage device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110528759.7A CN113537693A (en) 2021-05-14 2021-05-14 Personnel risk level obtaining method, terminal and storage device

Publications (1)

Publication Number Publication Date
CN113537693A true CN113537693A (en) 2021-10-22

Family

ID=78095398

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110528759.7A Pending CN113537693A (en) 2021-05-14 2021-05-14 Personnel risk level obtaining method, terminal and storage device

Country Status (1)

Country Link
CN (1) CN113537693A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116862242A (en) * 2023-08-28 2023-10-10 苏州真趣信息科技有限公司 Method and system for evaluating regional risk level by unsafe operation behaviors
CN117634873A (en) * 2023-11-15 2024-03-01 中国人寿保险股份有限公司江苏省分公司 System and method for evaluating risk of sales personnel in insurance industry

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116862242A (en) * 2023-08-28 2023-10-10 苏州真趣信息科技有限公司 Method and system for evaluating regional risk level by unsafe operation behaviors
CN116862242B (en) * 2023-08-28 2023-11-24 苏州真趣信息科技有限公司 Method and system for evaluating regional risk level by unsafe operation behaviors
CN117634873A (en) * 2023-11-15 2024-03-01 中国人寿保险股份有限公司江苏省分公司 System and method for evaluating risk of sales personnel in insurance industry

Similar Documents

Publication Publication Date Title
CN112494952B (en) Target game user detection method, device and equipment
CN117056734B (en) Method and device for constructing equipment fault diagnosis model based on data driving
CN113537693A (en) Personnel risk level obtaining method, terminal and storage device
CN105786711A (en) Data analysis method and device
EP4273750A1 (en) Data processing method and apparatus, computing device, and test simplification device
CN109460474B (en) User preference trend mining method
CN114924203A (en) Battery SOH prediction analysis method and electric automobile
CN117235608B (en) Risk detection method, risk detection device, electronic equipment and storage medium
CN115271282A (en) Customer value determination method and device based on fuzzy logic
CN115729761B (en) Hard disk fault prediction method, system, equipment and medium
CN111340975A (en) Abnormal data feature extraction method, device, equipment and storage medium
CN115936773A (en) Internet financial black product identification method and system
CN113537692A (en) Personnel risk assessment method based on risk indexes, terminal and storage device
CN116384223A (en) Nuclear equipment reliability assessment method and system based on intelligent degradation state identification
CN114862092A (en) Evaluation method and device based on neural network
CN113537694A (en) Personnel risk allocation obtaining method, terminal and storage device
CN112463378B (en) Server asset scanning method, system, electronic equipment and storage medium
CN111026661A (en) Method and system for comprehensively testing usability of software
CN114330090A (en) Defect detection method and device, computer equipment and storage medium
CN117419427B (en) Constant temperature and humidity air cabinet control method and system based on intelligent workshop
CN116051166A (en) List sorting method, device, electronic equipment and medium
CN118245825A (en) Clustering iteration method, clustering iteration device, electronic equipment and computer-readable storage medium
CN117422545A (en) Credit risk identification method, apparatus, device and storage medium
CN115936749A (en) Activity information pushing method and device
CN117350765A (en) Variable determining method and device, storage medium and electronic equipment

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