KR20220168176A - Apparatus, system and method for providing customized management solution for employees based on artificial intelligence - Google Patents

Abstract

The present invention relates to a device, system, and method for providing employee-customized management solutions based on artificial intelligence. More specifically, the present invention relates to a device, system, and method for providing employee-customized management solutions based on artificial intelligence, wherein employee types can be analyzed in consideration of complex influences between diverse employee experiences that occur throughout the employment period and optimal employee-customized management solutions can be provided according to the analysis results.

Description

Apparatus, system and method for providing customized management solution for employees based on artificial intelligence}

The present invention relates to an apparatus, system, and method for providing an artificial intelligence-based employee-customized management solution. It relates to an artificial intelligence-based employee-customized management solution providing device, system, and method capable of providing an optimal employee-customized management solution according to the present invention.

Ever since pioneering retailers have contributed in the past to making customer satisfaction a top business value, most organizations have been focused on customer experience.

However, in recent years, from the perspective of organizational members as stakeholders and partners in delivering value to customers and achieving organizational goals, by creating a workplace environment in which members can immerse themselves, growth of members and the organization is promoted. The consciousness that we must lead together is spreading.

In other words, employees not only support business management and day-to-day operations, but also create products, provide services, fulfill critical customer service and customer support roles, and provide insights, and many companies are embracing the employee experience for future success. is beginning to be accepted as a powerful indicator for measuring

The employee experience is what members think and feel through all touchpoints while engaging in the work of the organization. In addition, it is the perception that members have about what they experience while working while interacting with the organization, and it can be said to be the sum of everything the employee experiences through all the interactions that occur in the workplace from joining the company to leaving the company.

It is being discussed that employee engagement can be improved by tracking these employee experiences and seeking to improve the employee experience based on the tracked data. Employee engagement is a measure of how much passion and dedication employees put into the work they do for pay. Employees who are highly engaged are more productive and make the company appear positive, while less engaged employees are less productive and make the company look negative. Thus, employee engagement is directly linked to productivity and turnover, as well as other important indicators of business success.

Research has shown that when the employee experience index is high, an organization's return on assets (ROA) triples and its return on sales (ROS) doubles.

However, as the needs of members become more and more complex, the types of organizations become more diverse, the size of the organization increases, and the number of members increases, it is difficult to analyze all the employee experiences of so many members with human power, and the conditions of the members or the organization In reality, it is not easy to provide a customized member management solution according to the environment.

In addition, the various experiences experienced as members of an organization tend to operate as precedent and follow-up variables that affect each other.

However, there is a problem that no matter how much an expert is, it is not enough to analyze the employee type of a member in consideration of the relationship and complex influence between these various experiences and provide an optimal solution for managing the member.

The problem to be solved by the present invention is to analyze the employee type of the member in consideration of the complex influence of various experiences experienced as a member in the organization in order to solve the above-mentioned problem, and to provide an optimal employee-customized management solution according to the analysis result. It is intended to provide an artificial intelligence-based employee-customized management solution providing device, system, and method for providing

However, the problem to be solved by the present invention is not limited to those mentioned above, and another problem to be solved that is not mentioned can be clearly understood by those skilled in the art from the description below. will be.

According to an embodiment of the present invention, an artificial intelligence-based employee customized management solution providing device provides a plurality of learning data corresponding to employee experience, employee information, and environmental variables defined for the entire process from joining to leaving the company. Learning data collection unit to collect; An employee analysis unit for learning a multi-task learning model for each employee's first tenancy index, second satisfaction index, and third performance index using the plurality of learning data; an employee type classification unit for classifying employee types based on the first tenancy index, the second satisfaction index, and the third performance index of each employee; And it may include an employee management plan generating unit for generating an employee management plan by classifying and processing the learning data according to the employee type and the employee management solution performed in the past.

According to another embodiment, a method for providing an artificial intelligence-based employee customized management solution collects a plurality of learning data corresponding to employee experience, employee information, and environmental variables defined for the entire process from entry to exit of a plurality of employees. step; learning a multi-task learning model for each employee's first tenancy index, second satisfaction index, and third performance index by using the plurality of learning data; classifying employee types based on the first tenancy index, the second satisfaction index, and the third performance index of each employee; and generating an employee management plan by classifying and processing the learning data according to the employee type and the employee management solution performed in the past.

According to another embodiment, an artificial intelligence-based employee customized management solution providing system includes: an employee terminal providing a plurality of first learning data related to an employee experience defined for the entire process from employees entering the company to leaving the company; an organization terminal providing a plurality of second learning data about employee information and environment variables of the employees; And using the first and second learning data to train a multi-task learning model for each employee's first tenancy index, second satisfaction index, and third performance index, and target employee based on the learned multi-task learning model An employee-customized management solution providing server that classifies the types of employees, determines an employee-customized management solution according to the classified employee types, and provides the customized management solution to the organization terminal.

According to an embodiment of the present invention, by considering the influence of various data collected for employee analysis on each other and adopting a multi-task learning model to reflect the action as a preceding variable, members are classified into the most similar employee types This made it possible to manage strategic and scientific experiences.

According to an embodiment of the present invention, it is possible to classify employee types by considering not only objective employee information but also correlations and influences between employee experience perspectives and environmental variables related to the organization, and based on the analyzed results, improvement plans are derived. We can provide optimized employee-tailored management solutions.

Therefore, in the process of strategic personnel management, employees can have a positive experience as a member of the organization and immerse themselves in the organization at each stage, and further contribute to the establishment of an organizational culture of organizational and individual growth.

In addition, by managing employees based on an optimized employee-customized management solution, organizations can produce maximum results with minimum resource input, positively improve members' experience in the organization, and ultimately reduce turnover. can be an important activity.

1 is a conceptual diagram illustrating an environment in which a method for providing an artificial intelligence-based employee-customized management solution according to an embodiment of the present invention is performed.
Figure 2 is a block diagram showing the configuration of an artificial intelligence-based employee customized management solution providing device according to an embodiment of the present invention.
3 shows an example of learning data related to organizational experience defined for the entire process from entering the company to leaving the company.
4 is an exemplary diagram for explaining a multi-task learning method according to an embodiment of the present invention.
5 is a flowchart of a method for performing multi-task learning for employee analysis and generating an employee management plan according to an embodiment of the present invention.
6 is a flowchart illustrating a method of analyzing a target employee based on a pre-learned multi-task learning model and providing a management solution tailored to the employee according to an analysis result according to an embodiment of the present invention.

Advantages and features of the present invention, and methods for achieving them, will become clear with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention belongs It is provided to fully inform the holder of the scope of the invention, and the present invention is only defined by the scope of the claims.

In describing the embodiments of the present invention, if it is determined that a detailed description of a known function or configuration may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted. In addition, terms to be described below are terms defined in consideration of functions in the embodiments of the present invention, which may vary according to the intention or custom of a user or operator. Therefore, the definition should be made based on the contents throughout this specification.

Hereinafter, an apparatus, system, and method for providing an artificial intelligence-based customized employee management solution according to an embodiment of the present invention will be described in detail with reference to the drawings.

1 is a conceptual diagram illustrating an environment in which a method for providing an artificial intelligence-based employee-customized management solution according to an embodiment of the present invention is performed, and FIG. 2 is an artificial intelligence-based employee-customized management solution according to an embodiment of the present invention. It is a block diagram showing the configuration of the device.

Referring to FIG. 1, the artificial intelligence-based employee customized management solution providing system may include a solution providing server 100, an employee terminal 200, a database 300, and an organization terminal 400 described below. there is.

Here, the solution providing server 100 may also be referred to as an artificial intelligence-based employee customized management solution providing device. As shown in FIG. 2, the artificial intelligence-based employee customized management solution providing device 100 includes a learning data collection unit 110, an employee analysis unit 120, an employee management plan generator 130, and an employee customized management solution. A provision unit 140 may be included.

The learning data collection unit 110 may collect learning data in conjunction with a plurality of employee terminals 200 . 3 shows an example of learning data related to organizational experience defined for the entire process from entering the company to leaving the company.

Each of the employee terminals 200 may have a pre-distributed employee application installed and driven. As the employee application is executed, each of the employee terminals 200 selects a plurality of questionnaires related to the employee's experience during the life cycle as a member of the organization, provides them to the employee who is a user of the employee terminal 200, and answers the employee's questionnaire. can be stored as learning data. For example, the survey may be about education and training reviews, satisfaction with performance compensation, promotion reviews, and the like.

In addition, the learning data collection unit 110 may collect employee information and environmental information corresponding to objective facts generated during a life cycle as a member of an organization from the organization terminal 400 as learning data. As an example, as shown in FIG. 3, the employee information corresponding to objective facts includes selection information, placement department, transfer department, leave information, promotion information, education and training information, career development information, vision strategy information, performance compensation information, and It may include at least one of resignation information, but may not be limited thereto. And, the environment information may include various information about the internal environment and the external environment related to the organization. For example, the external environmental information may include the occurrence of COVID-19, the results of the general election, and the occurrence of natural disasters, and the internal environmental information may include the release of electric vehicles and the development of semiconductor nanoprocesses.

The user of the employee terminal 200 may access the solution providing server 100 using the employee terminal 200 in advance and register user information in the solution providing server 100 through a user authentication procedure. User information may include an employee's name, age, company name, department, position, and the like.

In addition, each of the employee terminals 200 may provide learning data indicating a survey answer result according to a survey provided to the user to the learning data collection unit 110 in real time, at predetermined intervals, or at predetermined times. For example, the survey may be provided to employees every time an event occurs or every quarter, but is not limited thereto.

Specifically, the learning data may mean input results of surveys provided for at least one event generated according to the life cycle of a member of the organization and employee information corresponding to objective facts.

Events that occur according to the life cycle of members in an organization include recruitment, selection, placement, transfer, leave of absence, promotion, training, and resignation, and may have a predetermined order or some may not have an order. For example, with respect to promotion, the promotion process experienced after an employee may be in the order of an assistant manager, a manager, a deputy manager, a manager, and a director. As another example, a predetermined career development training course in an organization is classified into a first level, a second level, ... … , may include a training process classified as the Nth level.

The employee analysis unit 120 may use a plurality of learning data to train the multi-task learning model 124 on a first tenancy index, a second satisfaction index, and a third performance index corresponding to each employee.

Here, the first longevity index may mean information on the number of years of service expected of the employee, the second satisfaction index may mean employee satisfaction with the organization, and the third performance index may mean employee performance in the organization.

Here, the employee performance label can be derived based on at least one of collaboration preference among individual members in the organization, collaboration performance between individuals and organizations, organizational satisfaction, resignation rate, average length of service, and work performance. As described above, collaboration performance and organizational satisfaction can be calculated by questionnaires, resignation rates and average years of service can be acquired from the organization terminal 400 as objective facts, and work performance is information calculated and evaluated by the organization. It can be obtained from the tissue terminal 400 as , and the method of acquiring each information is not limited thereto.

In particular, for performance indicators, elements required to calculate indicators may or may not change according to the flow of time or organizational characteristics, and accordingly, in one embodiment of the present invention, performance indicators reflect these changes and changes. can be calculated.

In addition, the probability of leaving the company, the probability of turnover, the preference for collaboration among individual members in the organization, the preference for collaboration between members and groups in the organization, and the degree of collaboration performance can be added as analysis indicators for employees, which are explained below. do it with

Specifically, the employee analysis unit 120 collects a plurality of past learning data from a plurality of employee terminals 200, and based on the collected past learning data, the first retention index, the second satisfaction index and the second satisfaction index of each employee. The multi-task learning model 122 can be trained for 3 performance indicators.

In addition, each of the first retention index, the second satisfaction index, and the third performance index of the target employee may be predicted through the learned multi-task learning model 122 .

4 is an exemplary diagram for explaining a multi-task learning method according to an embodiment of the present invention.

Multi-task learning means performing learning on a plurality of tasks using one model.

Here, the task refers to a task to be solved through machine learning or a task to be performed through machine learning. In one embodiment of the present invention, the plurality of tasks means a task of predicting the score of each of the first tenancy index, the second satisfaction index, and the third performance index of the employee. To this end, first, the first longevity index, the second satisfaction index, and the third performance index may be set as numerical values within a preset range.

A neural network for the multi-task learning model 124 may be composed of a plurality of generally shared hidden layers 30 and output layers 51 to 5n specialized for each task.

Specifically, each data sample included in the dataset 10 is fed-forward to calculate the error 71 to 7n of each task, and the gradient of each task from each error 71 to 7n gradient) can be calculated. In addition, the weight (learning parameter) of the shared layer 30 may be updated by backpropagating a value obtained by summing the gradients of each task. Here, the error of the task may mean a difference between a prediction of a machine learning model (ie, a neural network) and an actual result.

For example, the first tenancy index 51, the second satisfaction index 52, and the third performance index 53 predicted for an employee output by the multi-task learning model shown in FIG. The difference between the 1st longevity index, the 2nd satisfaction index, and the 3rd performance index investigated for

As an embodiment, the first tenure index as a label may be information about the actual tenure of service of the corresponding employee, and the second satisfaction index as a label may be information obtained from survey results actually accumulated by the corresponding employee, The third performance indicator as a label may be information about achievements actually derived from the employee in the organization. These labels may be obtained from organization terminals or employee terminals of a corresponding organization, or may be obtained through a third party investigation agency.

Here, a neural network is a term encompassing all types of machine learning models designed to imitate neural structures. In one embodiment of the present invention, the neural network may include all types of neural network-based models such as an artificial neural network and a deep neural network (DNN).

The multi-task learning model 124 uses training data consisting of a set of training input values and training output values, and when learning data of a specific employee is received, the first tenancy index 51 corresponding to the specific employee, the second Supervised learning may be performed in advance to output an output value including the satisfaction index 52 and the third performance index 53 .

In this way, the employee analysis unit 120 can improve prediction performance by simultaneously learning tasks related to each other for predicting the first tenancy index, the second satisfaction index, and the third performance index.

Subsequently, the employee analysis unit 120 may classify the employee type based on the predicted first longevity index, the second satisfaction index, and the third performance index.

As an embodiment, the employee analysis unit 120 may set the scores of each of the first tenancy index, the second satisfaction index, and the third performance index as one set, and set matching employee types for each corresponding set.

In one embodiment, the employee type classification unit 124 may classify the employee type into A-type to Z-type employee types, which are a kind of identification symbol, according to the first longevity index, the second satisfaction index, and the third performance index.

For example, if the first tenancy index is predicted to be 67 points, the second satisfaction index is 78 points, and the third performance index is predicted to be 88 points for an employee with employee number 811221, the employee's employee type is matched to the type B employee type. Accordingly, the employee type classification unit 124 may classify the corresponding employee as a B-type employee type. Here, even if the first tenancy index and the second satisfaction index are the same as the employee number 811221, the employee number 130830 whose third performance index is predicted to be 68 points can be classified as a type D employee. Employee types are exemplified as being classified into A-Z type employee types, but are not limited thereto, and may be classified with other types of symbols or other methods.

When the employee type corresponding to each of the employees is determined through the above classification, the employee management plan generation unit 130 manages the employee by classifying and processing the learning data for the employee according to the employee type and the solution performed in the past. plan can be created.

At this time, the employee management plan generation unit 130 may generate an employee management plan by further considering the industry field, company size, employee rank, job type, job type, etc. of the organization to which the employee belongs, and the specific generated in the organization. An employee management plan can be created by further considering variables or environmental variables.

In one embodiment, the staff management plan may include a staff management method including at least one of recommendation personnel, performance compensation, transfer placement, education and training, leave of absence, and counseling.

Here, the created employee management plan is later used as big data to determine an employee-customized management solution for a specific employee (target employee), collects learning data for as many employees as possible, and responds to each employee. By determining the type of employee, it may be desirable to construct an employee management plan based on the largest possible amount of big data.

When the employee management plan is generated through employee type classification, the employee-customized solution providing server 100 may operate to provide a customized solution for a specific employee.

To this end, the employee-customized management solution providing server 100 may receive target learning data from the target employee terminal 200 and the organization terminal 400 among employees, and convert the received target input data to the pre-learned multi-task It is possible to predict the first longevity index, the second satisfaction index, and the third performance index corresponding to the target employee by inputting the input to the learning model 122, and the predicted first longevity index, second satisfaction index, and third performance index Based on this, it is possible to classify the employee type of the target employee.

Here, the target learning data can be obtained in the same way as the above-described method of acquiring the learning data.

The employee customized management solution providing unit 140 may determine a customized employee management solution for the target employee according to the employee type of the target employee based on the employee management plan. Here, the employee-customized management solution may include recommendation personnel, performance compensation, transfer arrangement, education and training, consultation progress, etc., and a solution including a specific time, period, degree, and stage may be determined customized for the employee.

That is, according to the current state of the target employee's schedule, position, affiliation, annual salary, etc., at least one of personnel, performance compensation, transfer arrangement, education and training, counseling, and onboarding may be customized for the employee.

Here, onboarding means helping an employee stay on the job as the next step when it is decided which employee will join the team. Onboarding consists of orientation, a comprehensive process that develops new employees into skilled members of the organization.

In one embodiment, for a target employee classified as an N-type employee type, the employee customized management solution transfers to a certain department at a certain time, promotes to a certain position at a certain time, gives a certain training period, and at which time This could include solutions for how much vacation or compensation to grant.

The employee customized management solution provider 140 may transmit the determined recommended solution to the organization terminal 400 owned by the organization to which the target employee belongs.

Since the organization is provided with an employee-customized management solution that is expected to achieve the highest improvement in the employee type of the target employee through the organization terminal 400, optimal employee management results are achieved by performing employee management according to the employee-customized management solution. chances of doing so may increase.

Meanwhile, if an index to be analyzed for an employee is newly added, a layer learned in response to the new index may be added to the multi-task learning model.

To elaborate, in addition to the first tenancy index, the second satisfaction index, and the third performance index, for example, when you want to predict more employee resignation probability, turnover probability, collaboration preference, and collaboration performance, multi-task To the learning model 122, a layer learned for each prediction of the probability of leaving, turnover probability, collaboration preference, and collaboration performance is added, or a new layer is added to calculate the probability of leaving, turnover probability, collaboration preference, and collaboration performance It is possible to perform multi-task learning in which each prediction for the diagram is added as a task.

In addition, as new indicators to be analyzed are added, the parameters considered by the employee type classifier 124, the employee management plan generator 130, and the employee customized solution provider 140 also change in response to the added indicators. self-explanatory

Various employee experiences, events, and environmental variables as members of an organization act as precedent variables that affect each other, but it is difficult to clearly define and analyze their correlations. Accordingly, in one embodiment of the present invention, by considering the influence of various data collected for employee analysis on each other and by adopting a multi-task learning model to reflect the action as a preceding variable, strategic and scientific analysis on members make this possible

In one embodiment of the present invention, tasks related to each other, that is, the first tenancy index, the second satisfaction index, and the third performance index prediction tasks are simultaneously learned through a multi-task learning model, and the representation of the related tasks is shared, so that all The overall performance of task performance can be improved.

For example, by performing both the satisfaction index and performance index prediction tasks through the multi-task learning model, the performance of the retention index prediction can be improved.

In addition, according to the artificial intelligence-based employee customized management solution providing device according to an embodiment of the present invention, the retention index for the employee is determined with high probability by considering not only objective employee information but also employee experience, environmental variables, and the influence therebetween. Predictable.

In addition, by providing a management solution tailored to the employee according to the predicted results, in each step of the strategic personnel management process, the employee can have a positive experience as a member of the organization and immerse himself in the organization, furthermore, the organizational culture of organizational and individual growth can contribute to building

In addition, by managing employees based on a management solution tailored to employees, organizations can produce maximum results with minimum resource input, positively improve members' experience in the organization, and ultimately reduce turnover. This can be.

So far, each configuration of the artificial intelligence-based employee customized management solution providing device 100 has been described. Hereinafter, the operation of the artificial intelligence-based employee-customized management solution providing device 100 will be described, and redundant descriptions will be omitted.

5 is a flowchart of a method for performing multi-task learning for employee analysis and generating an employee management plan according to an embodiment of the present invention.

Referring to Figure 5, it is possible to first collect learning data on a plurality of employees (S110).

To this end, the learning data collection unit 110 may collect learning data in conjunction with a plurality of employee terminals 200 .

In one embodiment, each of the employee terminals 200 may have a pre-distributed employee application installed and driven. As the employee application is executed, each of the employee terminals 200 selects a plurality of questionnaires related to the employee's experience during the life cycle as a member of the organization, provides them to the employee who is a user of the employee terminal 200, and answers the employee's questionnaire. can be stored as learning data. For example, the survey may be related to a review of education and training, satisfaction with performance compensation, and the like.

In addition, the learning data collection unit 110 may collect employee information and environmental information corresponding to objective facts generated during a life cycle as a member of an organization from the organization terminal 400 as learning data. For example, employee information corresponding to objective facts may include at least one of selection information, placement department, transfer department, leave information, promotion information, education and training information, career development information, vision strategy information, performance compensation information, and resignation information. may be, and may not be limited thereto. And, the environment information may include information about the internal environment and the external environment surrounding the organization.

Each of the employee terminals 200 may provide the learning data collection unit 110 with learning data indicating a survey answer result according to a survey provided to the user in real time, at predetermined intervals, or at predetermined times. For example, the survey may be provided to employees every time an event occurs or every quarter, but is not limited thereto.

Specifically, the learning data may mean input results of surveys provided for at least one event generated according to the life cycle of a member of the organization and employee information corresponding to objective facts. The life cycle of members in an organization is recruitment, selection, placement, transfer, leave of absence, promotion, training, resignation, etc., and may have a predetermined order or some may not have an order. For example, with respect to promotion, the promotion process experienced after an employee may be in the order of an assistant manager, a manager, a deputy manager, a manager, and a director. As another example, a predetermined career development training course in an organization is classified into a first level, a second level, ... … , may include a training process classified as the Nth level.

Next, the multi-task learning model can be trained for the first tenancy index, the second satisfaction index, and the third performance index corresponding to each employee using a plurality of learning data (S120).

To this end, the employee analysis unit 120 collects a plurality of past learning data from a plurality of employee terminals 200, and based on the collected past learning data, the first retention index, the second satisfaction index and the second satisfaction index of each employee. The multi-task learning model 122 can be trained for 3 performance indicators. The learning method of the multi-task learning model has been described in detail with reference to FIG. 4 .

Next, the employee type may be classified based on the first tenancy index, the second satisfaction index, and the third performance index (S130).

To this end, the employee analysis unit 120 may set scores for each of the first tenancy index, the second satisfaction index, and the third performance index as one set, and set matching employee types for each corresponding set.

For example, the employee type classification unit 124 may classify the employee type into A-type to Z-type employee types, which are a kind of identification symbol, according to the first longevity index, the second satisfaction index, and the third performance index.

Next, if the employee type corresponding to each employee is determined through the above classification, the employee management plan can be created by classifying and processing the learning data for the employee according to the employee type and the solution performed in the past. (S140).

To this end, the employee management plan generation unit 130 may generate an employee management plan by further considering the industry, company size, employee rank, job type, job type, etc. of the organization to which the employee belongs, and the specific An employee management plan can be created by further considering variables or environmental variables.

In one embodiment, the staff management plan may include at least one staff management method among recommendation personnel, performance compensation, transfer placement, education and training, leave of absence, and counseling.

Here, the created employee management plan is later used as big data to determine an employee-customized management solution for a specific employee (target employee), collects learning data for as many employees as possible, and responds to each employee. By determining the type of employee, it may be desirable to construct an employee management plan based on the largest possible amount of big data.

Meanwhile, if an index to be analyzed for an employee is newly added, a layer learned in response to the new index may be added to the multi-task learning model.

To elaborate, in addition to the first tenancy index, the second satisfaction index, and the third performance index, for example, when you want to predict more employee resignation probability, turnover probability, collaboration preference, and collaboration performance, multi-task To the learning model 122, a layer learned for each prediction of the probability of leaving, turnover probability, collaboration preference, and collaboration performance is added, or a new layer is added to calculate the probability of leaving, turnover probability, collaboration preference, and collaboration performance It is possible to perform multi-task learning in which each prediction for the diagram is added as a task.

As new indicators to be analyzed are added, functions and roles corresponding to the added indicators may be upgraded in the employee type classification unit 124, the employee management plan generation unit 130, and the employee customized solution provider 140. .

6 is a flowchart illustrating a method of analyzing a target employee based on a pre-learned multi-task learning model and providing a management solution tailored to the employee according to an analysis result according to an embodiment of the present invention.

Referring to FIG. 6 , the employee-customized solution providing server 100 may operate to provide a customized solution for a specific employee.

First, the employee-customized management solution providing server 100 may receive target learning data from the target employee terminal 200 and the organization terminal 400 among employees (S210), and the received target input data may be pre-learned. It is possible to predict the first longevity index, the second satisfaction index, and the third performance index corresponding to the target employee by inputting the input to the multi-task learning model 122 (S220), and the predicted first longevity index, second satisfaction index and Based on the third performance indicator, the employee type of the target employee may be classified (S230).

Next, the employee customized management solution provider 140 may determine a customized employee management solution for the target employee according to the employee type of the target employee based on the employee management plan (S240).

Here, the employee-customized management solution may include recommendation personnel, performance compensation, transfer arrangement, education and training, consultation progress, etc., and a solution including a specific time, period, degree, and stage may be determined customized for the employee. That is, at least one of personnel, performance compensation, transfer arrangement, training, counseling, and onboarding may be determined according to the current state of the target employee's schedule, position, affiliation, annual salary, and the like.

In one embodiment, for a target employee classified as an N-type employee type, the employee customized management solution transfers to a certain department at a certain time, promotes to a certain position at a certain time, gives a certain training period, and at which time This could include how much vacation or compensation to grant.

The employee customized management solution provider 140 may transmit the determined recommended solution to the organization terminal 400 owned by the organization to which the target employee belongs.

Since the organization is provided with an employee-customized management solution that is expected to achieve the highest improvement in the employee type of the target employee through the organization terminal 400, optimal employee management results are achieved by performing employee management according to the employee-customized management solution. chances of doing so may increase.

Various experiences and events as a member of an organization act as precedent variables that affect each other, but it is difficult to clearly define and analyze their correlation. Accordingly, in one embodiment of the present invention, by considering the influence of various data collected for employee analysis on each other and by adopting a multi-task learning model to reflect the action as a preceding variable, the retention index for the employee is determined with high probability. can be predicted with

In addition, by performing the task of predicting satisfaction indicators and performance indicators together through a multi-task learning model, the performance of predicting longevity indicators can be improved.

In addition, by providing a management solution tailored to the employee according to the predicted results, it enables the employee to immerse himself in the organization with a positive experience as a member of the organization at each stage in the process of strategic personnel management, and furthermore, the organizational culture of organizational and individual growth. can contribute to building

In addition, by managing employees based on a management solution tailored to employees, organizations can produce maximum results with minimum resource input, positively improve members' experience in the organization, and ultimately reduce turnover. This can be.

Meanwhile, the above-described multi-task learning device may be implemented by a computing device including at least some of a processor, a memory, a user input device, and a presentation device. Memory is a medium that stores computer-readable software, applications, program modules, routines, instructions, and/or data coded such that when executed by a processor, it performs a particular task. A processor may read and execute computer-readable software, applications, program modules, routines, instructions, and/or data stored in memory.

The user input device may be a means for allowing a user to input a command to execute a specific task to the processor or input data required for execution of the specific task. The user input device may include a physical or virtual keyboard or keypad, key buttons, mouse, joystick, trackball, touch-sensitive input means, or a microphone. The presentation device may include a display, a printer, a speaker, or a vibrator.

Computing devices may include a variety of devices such as smart phones, tablets, laptops, desktops, servers, and clients. A computing device may be a single stand-alone device or may include multiple computing devices operating in a distributed environment consisting of multiple computing devices cooperating with each other over a communications network.

In addition, the above-described method for performing multi-task learning includes a processor, and when executed by the processor, computer-readable software, applications, program modules, and routines coded to perform multi-task learning using an artificial intelligence model. , instructions, and/or data structures, etc. may be executed by a computing device having a memory.

The present embodiments described above may be implemented through various means. For example, the present embodiments may be implemented by hardware, firmware, software, or a combination thereof.

In the case of implementation by hardware, multi-task learning using the artificial intelligence model according to the present embodiments includes one or more ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), It can be implemented by Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), processors, controllers, microcontrollers, or microprocessors.

For example, multi-task learning according to embodiments may be implemented using an artificial intelligence semiconductor device in which neurons and synapses of a deep neural network are implemented as semiconductor devices. At this time, the semiconductor device may be currently used semiconductor devices such as SRAM, DRAM, NAND, etc., next-generation semiconductor devices, RRAM, STT MRAM, PRAM, etc., or a combination thereof.

When multi-task learning according to the embodiments is implemented using an artificial intelligence semiconductor device, the results (weights) of learning the model as software may be transferred to synaptic mimic devices arranged in an array, or learning may be performed on the artificial intelligence semiconductor device. .

In the case of implementation by firmware or software, multi-task learning according to the present embodiments may be implemented in the form of a device, procedure, or function that performs the functions or operations described above. The software codes may be stored in a memory unit and driven by a processor. The memory unit may be located inside or outside the processor and exchange data with the processor by various means known in the art.

Also, the terms "system", "processor", "controller", "component", "module", "interface", "model", or "unit" as described above generally refer to computer-related entities hardware, hardware and software. can mean a combination of, software or running software. For example, but is not limited to, a process driven by a processor, a processor, a controller, a control processor, an object, a thread of execution, a program, and/or a computer. For example, a component can be both an application running on a controller or processor and a controller or processor. One or more components may reside within a process and/or thread of execution, and components may reside on one device (eg, system, computing device, etc.) or may be distributed across two or more devices.

Meanwhile, another embodiment provides a computer program stored in a computer recording medium that performs the aforementioned multi-task learning. In addition, another embodiment provides a computer-readable recording medium on which a program for realizing the aforementioned multi-task learning is recorded.

A program recorded on a recording medium may be read, installed, and executed in a computer to execute the above-described steps. In this way, in order for the computer to read the program recorded on the recording medium and execute the functions implemented by the program, the above-described program is C, C++ that can be read by the computer's processor (CPU) through the computer's device interface. , JAVA, may include a code coded in a computer language such as machine language.

These codes may include functional codes related to functions defining the above-described functions, and may include control codes related to execution procedures necessary for a computer processor to execute the above-described functions according to a predetermined procedure.

In addition, these codes may further include memory reference related codes for which location (address address) of the computer's internal or external memory should be referenced for additional information or media necessary for the computer's processor to execute the above-mentioned functions. .

In addition, when the computer processor needs to communicate with any other remote computer or server in order to execute the above-mentioned functions, the code allows the computer processor to use the computer's communication module to communicate with any other remote computer or server. It may further include communication-related codes for how to communicate with other computers or servers and what information or media to transmit/receive during communication.

A computer-readable recording medium on which the above-described program is recorded includes, for example, ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical media storage device, and the like.

In addition, the computer-readable recording medium is distributed in computer systems connected through a network, so that computer-readable codes can be stored and executed in a distributed manner.

In addition, a functional program for implementing the present invention, codes and code segments related thereto, in consideration of the system environment of a computer that reads a recording medium and executes a program, etc., help programmers in the art to which the present invention belongs It may be easily inferred or changed by

The above-described multi-task learning may be implemented in the form of a recording medium including instructions executable by a computer, such as applications or program modules executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The above-described multi-task learning may be executed by an application basically installed in the terminal (this may include a program included in a platform or operating system basically installed in the terminal), and the user may use an application store server, an application, or a corresponding service. It may be executed by an application (that is, a program) directly installed in the master terminal through an application providing server such as a related web server. In this sense, the above-described multi-task learning is implemented as an application (ie, a program) that is basically installed in a terminal or directly installed by a user, and may be recorded on a computer-readable recording medium such as a terminal.

The above description is merely an example of the technical idea of the present invention, and various modifications and variations can be made to those skilled in the art without departing from the essential qualities of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to explain, and the scope of the technical spirit of the present invention is not limited by these embodiments. The protection scope of the present invention should be interpreted according to the claims below, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

100: Employee customized management solution providing server
110: learning data collection unit
120: employee type classification unit
130: staff management plan generation unit
140: employee customized management solution provider
200: employee terminal
300: database
400: organization terminal

Claims (15)

As an artificial intelligence-based employee customized management solution providing device,
A learning data collection unit that collects a plurality of learning data including employee experience, employee information, and environmental variables defined for the entire process from entry to exit of a plurality of employees;
An employee analysis unit for learning a multi-task learning model for each employee's first tenancy index, second satisfaction index, and third performance index using the plurality of learning data;
an employee type classification unit for classifying employee types based on the first tenancy index, the second satisfaction index, and the third performance index of each employee; and
An artificial intelligence-based employee customized management solution providing device including an employee management plan generation unit for generating an employee management plan by classifying and processing the learning data according to the employee type and the employee management solution performed in the past. According to claim 1,
The learning data collection unit,
An artificial intelligence-based employee-customized management solution providing device that collects survey responses input to questionnaires related to employee experiences during the life cycle as a member of an organization provided to an employee terminal and collects employee information and environment information from the organization terminal. According to claim 1,
The employee analysis department,
Whenever an additional metric to be analyzed for an employee occurs, a layer learned for the additional metric is added to the multi-task learning model, or a new layer is added to add prediction for the additional metric as a task to perform multi-task learning. A device that provides customized employee management solutions based on artificial intelligence. According to claim 1,
The staff management plan creation unit,
An artificial intelligence-based employee customized management solution providing device that generates an employee management plan including at least one of recommendation personnel, performance compensation, transfer placement, training, leave of absence, and consultation. According to claim 1,
The employee-customized management solution providing device,
Receiving target learning data about a target employee, and inputting the target learning data into the learned multi-task learning model to predict a first retention index, a second satisfaction index, and a third performance index corresponding to the target employee, Based on this, an artificial intelligence-based employee customized management solution providing device that classifies the employee type of the target employee. According to claim 5,
Based on the employee management plan, further comprising an employee-customized management solution providing unit for determining an employee-customized management solution according to the employee type of the target employee and providing it to the organization terminal, artificial intelligence-based employee-customized management solution providing device. According to claim 6,
The employee customized management solution provider,
An artificial intelligence-based employee customized management solution providing device that determines at least one of personnel, performance compensation, transfer placement, training, and consultation according to the current status of the target employee, including schedule, position, affiliation, and annual salary. . As a method of providing an artificial intelligence-based employee-customized management solution,
Collecting a plurality of learning data corresponding to employee experience, employee information, and environmental variables of a plurality of employees;
learning a multi-task learning model for each employee's first tenancy index, second satisfaction index, and third performance index by using the plurality of learning data;
classifying employee types based on the first tenancy index, the second satisfaction index, and the third performance index of each employee; and
A method for providing an artificial intelligence-based employee customized management solution comprising the step of generating an employee management plan by classifying and processing the learning data according to the employee type and the employee management solution performed in the past. According to claim 8,
Collecting the learning data,
A method for providing an artificial intelligence-based employee-customized management solution that collects survey answers input to a questionnaire related to an employee's experience during a life cycle as a member of an organization provided to an employee terminal and collects employee information and environment information from the organization terminal. According to claim 8,
The step of learning the multi-task learning model,
Whenever an additional metric to be analyzed for an employee occurs, a layer learned for the additional metric is added to the multi-task learning model, or a new layer is added to add prediction for the additional metric as a task to perform multi-task learning. A method of providing an artificial intelligence-based employee-customized management solution. According to claim 8,
In the step of creating the staff management plan,
A method for providing an artificial intelligence-based employee customized management solution that creates an employee management plan that includes at least one of recommendation personnel, performance compensation, transfer placement, training, leave of absence, and consultation. According to claim 8,
After the staff management plan creation step,
Receiving target learning data about a target employee;
predicting a first tenancy index, a second satisfaction index, and a third performance index corresponding to the target employee by inputting the target learning data into the pre-learned multi-task learning model; and
Further comprising the step of classifying the employee type of the target employee based on the first tenancy index, the second satisfaction index, and the third performance index, artificial intelligence-based employee customized management solution providing method. According to claim 12,
Further comprising the step of determining an employee-customized management solution according to the employee type of the target employee based on the employee management plan and providing it to the organization terminal, artificial intelligence-based employee-customized management solution providing method. According to claim 13,
The step of determining the employee-customized management solution,
A method for providing an artificial intelligence-based employee customized management solution that determines at least one of personnel, performance compensation, transfer placement, training, and counseling according to the current status of the target employee, including schedule, position, affiliation, and annual salary. . As an artificial intelligence-based employee customized management solution providing system,
An employee terminal providing a plurality of first learning data about employee experience of employees;
an organization terminal providing a plurality of second learning data about employee information and environment variables of the employees; and
Using the first and second learning data, a multi-task learning model is trained for each employee's first tenancy index, second satisfaction index, and third performance index, and based on the learned multi-task learning model, the target employee's A method for providing an employee-customized management solution based on artificial intelligence, including an employee-customized management solution providing server that classifies employee types, determines an employee-customized management solution according to the classified employee type, and provides the employee-customized management solution to the organization terminal.

Images