Employee abnormal risk monitoring method and system

Abstract

The invention relates to an employee abnormal risk monitoring method and system, and the method comprises the following steps: collecting the historical behavior data of employees to construct an initial employee behavior data set, and carrying out the preprocessing of the initial employee behavior data set, and obtaining a final employee behavior data set; constructing an employee risk scoring model, and inputting the final employee behavior data set into the employee risk scoring model for training to obtain a trained employee risk scoring model; and carrying out risk scoring according to the behavior data of the employees through the trained employee risk scoring model, and when the risk score of the employees is greater than a threshold value, judging that the employees are abnormal and carrying out early warning.

Description

Technical Field

[0001] The invention relates to a method and a system for monitoring abnormal risks of employees, belonging to the technical field of human resource management. Background Art

[0002] Modern enterprises face many challenges in the process of employee management, including but not limited to employee turnover, mood swings, performance decline and other issues; early warning and intervention of these issues can effectively reduce enterprise management costs and improve organizational stability; however, existing employee risk monitoring technology has many shortcomings, which limits the effectiveness of its practical application;

[0003] Traditional methods usually rely on a single data source for risk monitoring, such as:

[0004] Determine abnormal situations by monitoring employee performance indicators (such as task completion rate, KPI);

[0005] Make abnormal judgments based on behavioral patterns such as lateness, absenteeism, and leave frequency;

[0006] The above method is prone to one-sided results due to the single data source and ignores the interaction of multi-dimensional data; risks can often only be identified after problems occur (such as a sharp decline in performance) and lack forward-looking early warning capabilities; it is difficult to capture risk fluctuations and trend changes in the time dimension. Summary of the invention

[0007] In order to solve the above problems existing in the prior art, the present invention proposes a method and system for monitoring employee abnormal risks.

[0008] The technical solution of the present invention is as follows:

[0009] In one aspect, the present invention provides a method for monitoring employee abnormal risk, comprising the following steps:

[0010] Collect employees' historical behavior data to build an initial employee behavior data set, and pre-process the initial employee behavior data set to obtain the final employee behavior data set;

[0011] Construct an employee risk scoring model, input the final employee behavior data set into the employee risk scoring model for training, and obtain a trained employee risk scoring model;

[0012] The trained employee risk scoring model performs risk scoring based on the employee's behavioral data. When the employee's risk score is greater than the threshold, the employee is judged to be abnormal and an early warning is issued.

[0013] As a preferred embodiment of the present invention, an initial employee behavior data set D is constructed in the form of a time series matrix, as shown in the following formula:

[0014]

[0015] Where: n represents the time step; m represents the data sample dimension; each row represents the behavior data vector d at any moment n =[d n,1 ,d n,2 ,…,d n,m ];

[0016] The initial employee behavior data set is filled with missing values, and the missing value filling step is: filling the missing value with the mean of the remaining data of the dimension corresponding to the missing value;

[0017] The employee behavior dataset after missing values ​​are filled is standardized to obtain the final employee behavior dataset.

[0018] As a preferred embodiment of the present invention, the standardization process is specifically shown in the following formula:

[0019]

[0020] Where: d′ n,m represents the m-dimensional data at time n after standardization; d n,m Represents m-dimensional data at time n; μ m Represents the average value of m-dimensional data at all times; σ m Represents the standard deviation of m-dimensional data at all times.

[0021] As a preferred embodiment of the present invention, the employee risk scoring model is constructed based on a machine learning model, as shown in the following formula:

[0022]

[0023] Where: R n represents the risk score of the employee at time n; M represents the total number of dimensions; ω m represents the feature weight; f(d n,m 0 means d n,m The risk function of n represents the volatility at time n; g represents the nonlinear risk implied function; γ represents the impact factor; λ represents the historical risk weight; L n Represents the historical risk accumulation value up to time n;

[0024] The risk score of an employee is obtained by taking the weighted average of the employee's risk scores at all times.

[0025] As a preferred embodiment of the present invention, the calculation formula of the volatility at time b is specifically shown as follows:

[0026]

[0027] Where: T represents the time window length; Represents the mean of all dimensional data at time n.

[0028] As a preferred embodiment of the present invention, the nonlinear risk implication function is specifically shown in the following formula:

[0029]

[0030] Where: β represents the sensitivity adjustment parameter.

[0031] As a preferred implementation of the present invention, the historical risk accumulation value calculation formula is:

[0032]

[0033] Where: δ represents the time decay factor.

[0034] On the other hand, the present invention also provides an employee abnormal risk monitoring system, including a data acquisition module, an employee risk scoring model construction module and an employee risk scoring module;

[0035] The data collection module is used to collect the historical behavior data of employees to construct an initial employee behavior data set, and to obtain a final employee behavior data set after preprocessing the initial employee behavior data set;

[0036] The employee risk scoring model construction module is used to construct an employee risk scoring model, input the final employee behavior data set into the employee risk scoring model for training, and obtain a trained employee risk scoring model;

[0037] The employee risk scoring module is used to perform risk scoring based on employee behavior data through a trained employee risk scoring model, and when an employee's risk score is greater than a threshold, the employee is judged to be abnormal and an early warning is issued.

[0038] On the other hand, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0039] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0040] The present invention has the following beneficial effects:

[0041] 1. The data of the present invention is standardized to eliminate the scale differences between different features and improve the accuracy of risk assessment; a nonlinear risk mapping function is introduced to utilize the exponential amplification effect of the behavioral volatility index to sensitively capture high-risk fluctuations; through the historical cumulative risk and time attenuation factor, the model can perceive the combined impact of long-term trends and short-term anomalies. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0045] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0046] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0047] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0048] Embodiment 1:

[0049] See also Figure 1 , a method for monitoring employee abnormal risk, comprising the following steps:

[0050] The historical behavior data of employees are collected to construct an initial employee behavior data set, and the final employee behavior data set is obtained after preprocessing the initial employee behavior data set. The employee historical behavior data includes attendance records, communication frequency, market economic indicators, team project participation, task completion rate, work result quality and mental health.

[0051] Construct an employee risk scoring model, input the final employee behavior data set into the employee risk scoring model for training, and obtain a trained employee risk scoring model;

[0052] The trained employee risk scoring model performs risk scoring based on the employee's behavioral data. When the employee's risk score is greater than the threshold, the employee is judged to be abnormal and an early warning is issued.

[0053] As a preferred implementation of this embodiment, the initial employee behavior data set D is constructed in the form of a time series matrix, as shown in the following formula:

[0054]

[0055] Where: n represents the time step; m represents the data sample dimension; each row represents the behavior data vector d at any moment n =[d n,1 ,d n,2 ,…,d n,m ];

[0056] The initial employee behavior data set is filled with missing values, and the missing value filling step is: filling the missing value with the mean of the remaining data of the dimension corresponding to the missing value;

[0057] The employee behavior dataset after missing values ​​are filled is standardized to obtain the final employee behavior dataset.

[0058] As a preferred implementation of this embodiment, the standardization process is specifically shown in the following formula:

[0059]

[0060] Where: d′ n,m represents the m-dimensional data at time n after standardization; d n,m Represents m-dimensional data at time n; μ m Represents the average value of m-dimensional data at all times; σ m Represents the standard deviation of m-dimensional data at all times.

[0061] As a preferred implementation of this embodiment, the employee risk scoring model is constructed based on a machine learning model, as shown in the following formula:

[0062]

[0063] Where: R n represents the risk score of the employee at time n; M represents the total number of dimensions; ω m represents the feature weight; f(d n,m 0 means d n,m The risk function of nrepresents the volatility at time n; g represents the nonlinear risk implied function; γ represents the impact factor; λ represents the historical risk weight; L n Represents the historical risk accumulation value up to time n;

[0064] The risk score of an employee is obtained by taking the weighted average of the employee's risk scores at all times.

[0065] As a preferred implementation of this embodiment, the calculation formula of the volatility at time n is specifically shown as follows:

[0066]

[0067] Where: T represents the time window length; Represents the mean of all dimensional data at time n.

[0068] As a preferred implementation of this embodiment, the nonlinear risk implication function is specifically shown in the following formula:

[0069]

[0070] Where: β represents the sensitivity adjustment parameter.

[0071] As a preferred implementation of this embodiment, the historical risk accumulation value calculation formula is:

[0072]

[0073] Where: δ represents the time decay factor.

[0074] Embodiment 2:

[0075] An employee abnormal risk monitoring system includes a data collection module, an employee risk scoring model building module and an employee risk scoring module;

[0076] The data collection module is used to collect the historical behavior data of employees to construct an initial employee behavior data set, and to obtain a final employee behavior data set after preprocessing the initial employee behavior data set;

[0077] The employee risk scoring model construction module is used to construct an employee risk scoring model, input the final employee behavior data set into the employee risk scoring model for training, and obtain a trained employee risk scoring model;

[0078] The employee risk scoring module is used to perform risk scoring based on employee behavior data through a trained employee risk scoring model, and when an employee's risk score is greater than a threshold, the employee is judged to be abnormal and an early warning is issued.

[0079] The system is used to implement the method in Example 1, which will not be described in detail here.

[0080] Embodiment three:

[0081] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0082] Embodiment 4:

[0083] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0084] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0085] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0086] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0087] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0088] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for monitoring employee abnormal risk, characterized in that: The following steps are involved: Collect employees' historical behavior data to build an initial employee behavior data set, and pre-process the initial employee behavior data set to obtain the final employee behavior data set; Construct an employee risk scoring model, input the final employee behavior data set into the employee risk scoring model for training, and obtain a trained employee risk scoring model; The trained employee risk scoring model performs risk scoring based on the employee's behavioral data. When the employee's risk score is greater than the threshold, the employee is judged to be abnormal and an early warning is issued.

2. The employee abnormal risk monitoring method according to claim 1, characterized in that: The initial employee behavior dataset D is constructed in the form of a time series matrix, as shown in the following formula: Where: n represents the time step; m represents the data sample dimension; each row represents the behavior data vector d at any time n1 =[d n,1 ,d n,2 ,…,d n,m ]; The initial employee behavior data set is filled with missing values, and the missing value filling step is: filling the missing value with the mean of the remaining data of the dimension corresponding to the missing value; The employee behavior dataset after missing values ​​are filled is standardized to obtain the final employee behavior dataset.

3. The employee abnormal risk monitoring method according to claim 2, characterized in that: The standardization process is specifically shown in the following formula: Where: d ′ n,m represents the m-dimensional data at time n after standardization; d n,m Represents m-dimensional data at time n; μ m Represents the average value of m-dimensional data at all times; σ m Represents the standard deviation of m-dimensional data at all times.

4. The employee abnormal risk monitoring method according to claim 1, characterized in that: The employee risk scoring model is constructed based on a machine learning model, as shown in the following formula: Where: R n represents the risk score of the employee at time n; M represents the total number of dimensions; ω m represents the feature weight; f(d n,m ) means d n,m The risk function of n represents the volatility at time n; g represents the nonlinear risk implied function; γ represents the impact factor; λ represents the historical risk weight; L n Represents the historical risk accumulation value up to time n; The risk score of an employee is obtained by taking the weighted average of the employee's risk scores at all times.

5. The employee abnormal risk monitoring method according to claim 4 is characterized in that: The calculation formula of the volatility at the nth moment is specifically shown as follows: Where: T represents the time window length; Represents the mean of all dimensional data at time n.

6. The method for monitoring employee abnormal risk according to claim 4, characterized in that: The nonlinear risk implicit function is specifically shown in the following formula: Where: β represents the sensitivity adjustment parameter.

7. The method for monitoring employee abnormal risk according to claim 4, characterized in that: The calculation formula of the historical risk accumulation value is: Where: δ represents the time decay factor.

8. An employee abnormal risk monitoring system, characterized in that: It includes data collection module, employee risk scoring model building module and employee risk scoring module; The data collection module is used to collect the historical behavior data of employees to construct an initial employee behavior data set, and to obtain a final employee behavior data set after preprocessing the initial employee behavior data set; The employee risk scoring model construction module is used to construct an employee risk scoring model, input the final employee behavior data set into the employee risk scoring model for training, and obtain a trained employee risk scoring model; The employee risk scoring module is used to perform risk scoring based on employee behavior data through a trained employee risk scoring model, and when an employee's risk score is greater than a threshold, the employee is judged to be abnormal and an early warning is issued.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images