KR102596718B1 - Method for managing integrated labor and computing device for executing the method - Google Patents

Abstract

A method for integrated labor management and a computing device for performing the same are disclosed. A computing device according to an embodiment disclosed is a computing device having one or more processors and a memory that stores one or more programs executed by the one or more processors, and collects labor-related cases and collects labor-related cases. A labor case analysis engine that analyzes cases and generates labor case analysis information, a labor risk prediction engine that generates labor risk management information for the workplace based on labor-related cases and labor case analysis information, and provides labor risk management information to the corresponding user. Includes a user service engine provided by the terminal.

Description

Labor integration management method and computing device for performing the same {METHOD FOR MANAGING INTEGRATED LABOR AND COMPUTING DEVICE FOR EXECUTING THE METHOD}

Embodiments of the present invention relate to labor management technology.

Recently, employment promotion measures and expansion of employment insurance have emerged as social concerns due to the increase in unemployment, and many policies are being attempted to support this. However, from the perspective of small and medium-sized companies, there are many difficulties in organizational management and labor issues due to complex labor policies and labor laws. The reality is that there is a lack of solutions to systematically manage it. In other words, human resources and labor-related functions are provided as part of a tax or accounting management solution, leading to a lack of specialized solutions.

In addition, even if government subsidies are available, there are many cases in which they do not receive them because they are not properly aware of them, and in the reality that people are turning away from employment at small and medium-sized companies due to job instability, it is necessary to manage government subsidies tailored to each individual's situation, and systematic personnel and labor management is necessary. A plan is required to reduce social costs by preventing labor disputes in advance.

Korean Patent Publication No. 10-2164413 (2020.10.13)

The purpose of the present invention is to provide an integrated labor management method that can predict and prevent labor-related risks and a computing device for performing the same.

Meanwhile, the technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly apparent to those skilled in the art from the description below. It will be understandable.

A computing device according to an embodiment disclosed is a computing device having one or more processors and a memory that stores one or more programs executed by the one or more processors, and collects labor-related cases and collects the collected labor-related cases. A labor case analysis engine that analyzes labor-related cases and generates labor case analysis information; and a labor risk prediction engine that generates labor risk management information for the workplace based on the labor-related cases and the labor case analysis information.

The labor case analysis information includes one or more of workplace-related information, worker-related information, and labor case-related information, and the labor case-related information includes labor case type information, labor case history information, labor case issue information, and It may contain one or more of the relevant legal information.

The labor risk prediction engine includes an interface module that interfaces with the labor case analysis engine; A policy information management module that collects workplace policy-related information for each workplace based on the workplace-related information for each workplace; And it may include a machine learning module that generates labor risk management information for the workplace by inputting the labor-related cases, the labor case analysis information, the workplace-related information, and the workplace policy-related information.

The labor risk management information includes one or more of an unfair dismissal risk index, an unfair supply risk index, a labor dispute risk index, and an incident accident risk index, and the machine learning module includes the labor-related cases and the labor case analysis information. , When the workplace-related information and the workplace policy-related information are input, it includes a machine learning model that is learned to predict one or more of the unfair dismissal risk index, the unfair supply and demand risk index, the labor dispute risk index, and the incident accident risk index. can do.

The machine learning model is a multi-task learning model, and uses the labor-related cases, the labor case analysis information, the workplace-related information, and the workplace policy-related information as input to determine unfairness against the workplace. a first task unit trained to output a dismissal risk index; a second task unit that learns to output an illegal supply and demand risk index for the relevant workplace by inputting the labor-related cases, the labor case analysis information, the workplace-related information, and the workplace policy-related information; a third task unit that learns to output a labor dispute risk index for the workplace by inputting the labor-related cases, the labor case analysis information, the workplace-related information, and the workplace policy-related information; And it may include a fourth task unit that is trained to output an accident risk index for the relevant workplace by using the labor-related cases, the labor case analysis information, the workplace-related information, and the workplace policy-related information as input.

According to an embodiment of the present invention, by collecting labor-related cases and generating labor risk management information through machine learning technology based on the collected labor-related cases, each workplace or worker can Risks can be managed in advance for hazardous accidents, thereby reducing social costs caused by labor-related disputes or accidents.

Meanwhile, the effects that can be obtained from the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below. You will be able to.

1 is a diagram showing the configuration of an integrated labor management device according to an embodiment of the present invention,
Figure 2 is a block diagram showing the configuration of a labor case analysis engine according to an embodiment of the present invention;
Figure 3 is a diagram schematically showing the configuration of a machine learning module according to an embodiment of the present invention;
Figure 4 is a block diagram showing the configuration of a user service engine according to an embodiment of the present invention;
5 is a block diagram illustrating and illustrating a computing environment including a computing device suitable for use in example embodiments.

Hereinafter, embodiments of the present invention will be described in more detail with reference to the attached drawings. Embodiments of the present invention may be modified in various forms, and the scope of the present invention should not be construed as being limited to the following embodiments. This example is provided to more completely explain the present invention to those skilled in the art. Therefore, the shapes of elements in the drawings are exaggerated to emphasize clearer explanation.

The configuration of the invention to clarify the solution to the problem to be solved by the present invention will be described in detail with reference to the accompanying drawings based on preferred embodiments of the present invention, and the reference numbers to the components in the drawings will be the same. Components are given the same reference numbers even if they are in different drawings, and it is stated in advance that components of other drawings can be cited when necessary when explaining the relevant drawings.

Figure 1 is a diagram showing the configuration of an integrated labor management device according to an embodiment of the present invention.

Referring to FIG. 1 , the integrated labor management device 100 may include a labor case analysis engine 102, a labor risk prediction engine 104, and a user service engine 106.

The labor case analysis engine 102 can collect and analyze labor-related cases. The analyzed information of labor-related cases can be basic data used in the labor integrated management device 100.

Figure 2 is a block diagram showing the configuration of the labor case analysis engine 102 according to an embodiment of the present invention.

Referring to FIG. 2 , the labor case analysis engine 102 may include a data collection module 111, a data processing module 113, and a storage module 115.

In one embodiment, the data collection module 111, data processing module 113, and storage module 115 are implemented using one or more physically separate devices, one or more processors, or a combination of one or more processors and software. It can be implemented by , and unlike the example shown, specific operations may not be clearly distinguished.

The data collection module 111 can collect labor-related cases. Here, labor-related cases may refer to cases of labor-related incidents that have occurred previously (e.g., unfair dismissal, illegal supply, labor disputes, accidents, etc.). The data collection module 111 may collect labor-related cases written by experts in the labor field (for example, labor attorneys or lawyers). Labor-related cases may also include court precedents or decisions of administrative agencies regarding labor cases. Labor-related cases may be written in document files or text format.

In an exemplary embodiment, the data collection module 111 may collect labor-related cases from a website, etc. through crawling. The data collection module 111 may collect labor-related cases at a preset cycle. However, the method of collecting labor-related cases is not limited to this, and labor-related cases may be entered directly by the manager.

The data processing module 113 may generate labor case analysis information by analyzing labor-related cases collected by the data collection module 111. In an exemplary embodiment, the data processing module 113 may extract labor case analysis information from each labor-related case by performing syntax analysis on labor-related cases in document or text form.

Here, labor case analysis information includes business-related information (e.g., business identification information, business size, business sales, and number of employees, etc.), worker-related information (e.g., worker identification information, work details, work period, etc.) and employment patterns, etc.), and information related to labor cases.

Here, labor case-related information may include labor case type information, labor case history information, labor case issue information, and related laws and regulations information. The labor case type information may be information about what type of labor case (e.g., unfair dismissal, unfair disciplinary action, non-payment of wages, strike, salary dispute, etc.) is the labor-related case. Labor case history information may be information representing the history of the relevant labor incident (how the relevant labor incident occurred, how it progressed, how it was concluded, etc.). The labor case issue information may be information about the part that became an issue in the relevant labor case. Related legal information may be information about laws related to the relevant labor case (e.g., Labor Standards Act, Minimum Wage Act, etc.) or administrative interpretation.

That is, the data processing module 113 may serve to classify and systematize labor-related cases collected by the data collection module 111 into a form that can be processed by the integrated labor management device 100.

The storage module 115 may store labor case analysis information generated by the data processing module 113. The storage module 115 can match and store each labor-related case and labor case analysis information. Labor case analysis information can be updated whenever new labor-related cases are collected. Additionally, the storage module 115 may serve as a database of the integrated labor management device 100. The storage module 115 may store various data registered in the integrated labor management device 100.

The labor risk prediction engine 104 can predict labor risks using machine learning technology. The labor risk prediction engine 104 may generate labor risk management information for the relevant workplace by inputting labor-related cases, labor case analysis information, workplace-related information, and workplace policy-related information.

The labor risk prediction engine 104 may include an interface module 121, a policy information management module 123, and a machine learning module 125.

In one embodiment, the interface module 121, the policy information management module 123, and the machine learning module 125 are implemented using one or more physically separate devices, one or more processors, or one or more processors and software. It can be implemented by combination, and unlike the example shown, specific operations may not be clearly distinguished.

The interface module 121 may serve as an interface between the labor case analysis engine 102 and the labor risk prediction engine 104. In an exemplary embodiment, the interface module 121 may extract labor-related cases and labor case analysis information from the storage module 115 and input them into the machine learning module 125.

Additionally, the interface module 121 may serve as an interface between the labor risk prediction engine 104 and the user service engine 106. In an exemplary embodiment, the interface module 121 may transmit labor risk management information output from the machine learning module 125 to the user service engine 106.

The policy information management module 123 provides workplace-related information for each workplace (e.g., business identification information, business industry, workplace size, workplace environment (business location, facilities installed at the workplace, temperature and humidity of the workplace, etc.), workplace History, business sales, number of employees, etc.) can be saved. The policy information management module 123 can collect policy information (workplace policy-related information) related to each workplace based on the workplace-related information of each workplace. For example, if the workplace in question is an urban rail corporation, information related to workplace policies, including laws, policies, and subsidies applicable to the urban railroad corporation, can be collected. The policy information management module 123 can input workplace-related information and workplace policy-related information to the machine learning module 125.

The machine learning module 125 can generate labor risk management information for the relevant workplace by inputting labor-related cases, labor case analysis information, workplace-related information, and workplace policy-related information. Here, the labor risk management information may include an unfair dismissal risk index, a fraudulent supply/demand risk index, a labor dispute risk index, and an accident accident risk index.

The machine learning module 125 is operated when labor-related cases, labor case analysis information, workplace-related information, and workplace policy-related information are input, unfair dismissal risk index, unfair supply and demand risk index, labor dispute risk index, and incident accident risk index. It may include a machine learning model that is trained to predict. In an example embodiment, machine learning module 125 may include a multi-task learning model. Figure 3 is a diagram schematically showing the configuration of the machine learning module 125 according to an embodiment of the present invention.

Referring to FIG. 3, the machine learning module 125 may include a first task unit 125a, a second task unit 125b, a third task unit 125c, and a fourth task unit 125d. .

The first task unit 125a may be a machine learning model that is trained to output an unfair dismissal risk index for the relevant workplace by inputting labor-related cases, labor case analysis information, workplace-related information, and workplace policy-related information.

The second task unit 125b may be a machine learning model that receives labor-related cases, labor case analysis information, workplace-related information, and workplace policy-related information as input and learns to output an illegal supply and demand risk index for the workplace.

The third task unit 125c may be a machine learning model that is trained to output a labor dispute risk index for the workplace by inputting labor-related cases, labor case analysis information, workplace-related information, and workplace policy-related information.

The fourth task unit 125d may be a machine learning model that is trained to output an accident risk index for the workplace by inputting labor-related cases, labor case analysis information, workplace-related information, and workplace policy-related information.

Referring again to FIG. 1, the user service engine 106 may provide services corresponding to various requests or inquiries received from the user terminal (not shown) to the user terminal (not shown). Here, the user terminal (not shown) may be a workplace terminal or a worker's terminal.

Figure 4 is a block diagram showing the configuration of the user service engine 106 according to an embodiment of the present invention. Referring to FIG. 4, the user service engine 106 includes a risk index reporting module 131, an unfair dismissal prevention notification module 133, an unfair supply and demand prevention notification module 135, a labor dispute prevention notification module 137, and an incident/accident notification module. It may include a prevention notification module 139, a labor information notification module 141, a chatbot service module 143, a legal search service module 145, and a labor contract management module 147.

In one embodiment, the risk index reporting module 131, the unfair dismissal prevention notification module 133, the unfair supply and demand prevention notification module 135, the labor dispute prevention notification module 137, the accident prevention notification module 139, and the labor dispute prevention notification module 139. The information notification module 141, chatbot service module 143, legal search service module 145, and employment contract management module 147 are implemented using one or more physically separated devices, one or more processors, or one or more devices. It may be implemented by a combination of a processor and software, and, unlike the example shown, specific operations may not be clearly distinguished.

The risk index reporting module 131 may receive a reporting request from a user terminal (not shown). Reporting requests include business-related information (e.g., business identification information, business industry, business size, business environment (business location, facilities installed at the business, business temperature and humidity, etc.), business history, business sales, and number of employees, etc. ) may be included.

The risk index reporting module 131 may transmit workplace-related information included in the reporting request to the labor risk prediction engine 104 and receive labor risk management information for the workplace from the labor risk prediction engine 104. Here, the labor risk management information may include an unfair dismissal risk index, an unfair supply/demand risk index, a labor dispute risk index, and an accident accident risk index. Since the machine learning module 125 of the labor risk prediction engine 104 has already been learned through previous labor-related cases, etc., when workplace-related information included in the reporting request is input, labor risk management information is provided in response. Can be printed.

The risk index reporting module 131 may calculate the risk index of the relevant business operator based on the unfair dismissal risk index, unfair supply and demand risk index, labor dispute risk index, and incident accident risk index included in the labor risk management information. The risk index reporting module 131 can transmit risk index reporting including the risk index of the relevant workplace to the business operator terminal (not shown). Additionally, risk index reporting may also include the workplace's unfair dismissal risk index, unfair supply and demand risk index, labor dispute risk index, and incident accident risk index.

The unfair dismissal prevention notification module 133 may transmit an unfair dismissal prevention notification to workers registered in the integrated labor management device 100. In an exemplary embodiment, when registering a worker, the integrated labor management device 100 receives worker-related information (e.g., worker identification information, work details, work period, and Work type, etc.) and workplace-related information of the workplace to which the worker belongs can be received and registered.

The unfair dismissal prevention notification module 133 transmits the worker-related information of the registered worker and the business-related information of the business operator to the labor risk prediction engine 104, and receives the unfair dismissal risk index of the worker from the labor risk prediction engine 104. can receive. If the unfair dismissal risk index of the worker exceeds a preset standard (a standard value set to provide notification above a preset threshold), the unfair dismissal prevention notification module 133 is sent to the worker's terminal (not shown). Unfair dismissal prevention notifications can be sent.

The fraudulent supply and demand prevention notification module 135 may generate a fraudulent supply and demand prevention notification based on the fraudulent supply and demand risk index of the workplace registered in the labor integrated management device 100. That is, the labor risk prediction engine 104 can calculate a fraudulent supply and demand risk index for each workplace registered in the integrated labor management device 100. At this time, if the fraudulent supply and demand risk index exceeds the preset standard (a standard value set to provide notification above the preset threshold), the fraudulent supply and demand prevention notification module 135 will generate a fraudulent supply and demand prevention notification for the relevant business site. You can. Fraudulent supply and demand prevention notifications may be transmitted to the server computing device of the relevant organization.

The labor dispute prevention notification module 137 may generate a labor dispute prevention notification based on the labor dispute risk index between workplaces and workers registered in the labor integrated management device 100. In other words, the labor risk prediction engine 104 can calculate the labor dispute risk index between each workplace registered in the integrated labor management device 100 and the workers working at the workplace. At this time, if the labor dispute risk index exceeds the preset standard (a standard value set to provide notification above the preset threshold), the labor dispute prevention notification module 137 provides labor dispute prevention notification to the relevant workplace and workers. It can occur.

The accident prevention notification module 139 may generate an accident prevention notification based on the accident risk index for the workplace registered in the integrated labor management device 100. That is, the labor risk prediction engine 104 can calculate an incident accident risk index for each workplace registered in the integrated labor management device 100. At this time, if the incident accident risk index exceeds the preset standard (a standard value set to provide notification above a preset threshold), the incident accident prevention notification module 139 will generate an incident accident prevention notification for the relevant workplace. You can. Accident prevention notifications may be sent to the workplace terminal of the relevant workplace.

The labor information notification module 141 can monitor laws and policies related to labor. When a labor-related law or policy is revised or newly added, the labor information notification module 141 extracts the workplace to which the relevant law or policy applies, and sends the contents of the revised or newly added law or policy to the workplace terminal of the extracted workplace. Labor information notifications can be sent.

The labor information notification module 141 can monitor whether there is a government subsidy matching the workplace or worker registered in the integrated labor management device 100. In other words, the labor information notification module 141 can monitor whether registered businesses or workers match the conditions of government subsidies. If there is a workplace or worker that matches the conditions of the government subsidy, the labor information notification module 141 can transmit a labor information notification about the contents of the government subsidy to the terminal of the relevant workplace or worker.

When a user inquiry is input from a user terminal (not shown), the chatbot service module 143 can answer the user inquiry. The chatbot service module 143 can analyze user queries and search whether there are similar cases. The chatbot service module 143 can search for whether there is a similar case corresponding to the user inquiry in the labor-related cases collected by the labor case analysis engine 102.

The chatbot service module 143 can extract each keyword from the user query and search for similar cases based on the extracted keywords. Additionally, the chatbot service module 143 can search for similar cases based on user information that made a user inquiry (for example, business-related information for businesses, worker-related information for workers). For example, if the user who made the user inquiry is a business owner, similar cases can be searched based on the business history, business type, number of employees, and business environment among the business-related information of the business operator.

If similar cases cannot be searched for a user's inquiry, the chatbot service module 143 can connect the user's inquiry to a labor expert who can provide real-time consultation. The chatbot service module 143 can transmit the content of the user inquiry as one labor-related case to the labor case analysis engine 102.

When a law-related keyword is input from a user terminal (not shown), the legal search service module 145 may search for laws or policies corresponding to the law-related keyword and transmit them to the user terminal (not shown). In an exemplary embodiment, the legal search service module 145 may search for laws or policies corresponding to law-related keywords among the information collected by the policy information management module 123, but is not limited to this.

The labor contract management module 147 can create a labor contract for workers registered in the integrated labor management device 100. The labor contract management module 147 can automatically create a labor contract based on the labor contract between the worker and the workplace (eg, working period, employment type, salary, bonus, annual leave, etc.).

Additionally, the employment contract management module 147 can create a salary ledger based on each worker's employment contract. The employment contract management module 147 can analyze the working hours in the employment contract and create a salary ledger to pay statutory allowances for overtime work, night work, and holiday work. To this end, the employment contract management module 147 can monitor the attendance status of each worker. Additionally, the employment contract management module 147 may transmit a notification prior to expiration of the contract period based on each worker's employment contract.

According to the disclosed embodiment, by collecting labor-related cases and generating labor risk management information through machine learning technology based on the collected labor-related cases, each workplace or worker manages the risk of labor-related risk accidents in advance. This allows social costs to be reduced due to labor-related disputes or accidents.

In addition, the chatbot service makes it possible to quickly respond to user inquiries by searching for and informing of similar labor-related cases in response to user inquiries. In addition, by matching businesses or workers who match the conditions of government subsidies, it is possible to overcome the information asymmetry of government subsidies and make good use of them.

In this specification, a module may mean a functional and structural combination of hardware for carrying out the technical idea of the present invention and software for driving the hardware. For example, the “module” may mean a logical unit of a predetermined code and hardware resources for executing the predetermined code, and does not necessarily mean a physically connected code or a single type of hardware.

FIG. 5 is a block diagram illustrating and illustrating a computing environment 10 including computing devices suitable for use in example embodiments. In the illustrated embodiment, each component may have different functions and capabilities in addition to those described below, and may include additional components in addition to those described below.

The illustrated computing environment 10 includes a computing device 12 . In one embodiment, computing device 12 may be integrated labor management device 100.

Computing device 12 includes at least one processor 14, a computer-readable storage medium 16, and a communication bus 18. Processor 14 may cause computing device 12 to operate in accordance with the example embodiments noted above. For example, processor 14 may execute one or more programs stored on computer-readable storage medium 16. The one or more programs may include one or more computer-executable instructions, which, when executed by the processor 14, cause computing device 12 to perform operations according to example embodiments. It can be.

Computer-readable storage medium 16 is configured to store computer-executable instructions or program code, program data, and/or other suitable form of information. The program 20 stored in the computer-readable storage medium 16 includes a set of instructions executable by the processor 14. In one embodiment, computer-readable storage medium 16 includes memory (volatile memory, such as random access memory, non-volatile memory, or an appropriate combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash It may be memory devices, another form of storage medium that can be accessed by computing device 12 and store desired information, or a suitable combination thereof.

Communication bus 18 interconnects various other components of computing device 12, including processor 14 and computer-readable storage medium 16.

Computing device 12 may also include one or more input/output interfaces 22 and one or more network communication interfaces 26 that provide an interface for one or more input/output devices 24. The input/output interface 22 and the network communication interface 26 are connected to the communication bus 18. Input/output device 24 may be coupled to other components of computing device 12 through input/output interface 22. Exemplary input/output devices 24 include, but are not limited to, a pointing device (such as a mouse or trackpad), a keyboard, a touch input device (such as a touchpad or touch screen), a voice or sound input device, various types of sensor devices, and/or imaging devices. It may include input devices and/or output devices such as display devices, printers, speakers, and/or network cards. The exemplary input/output device 24 may be included within the computing device 12 as a component constituting the computing device 12, or may be connected to the computing device 12 as a separate device distinct from the computing device 12. It may be possible.

The above detailed description is illustrative of the present invention. Additionally, the foregoing is intended to illustrate preferred embodiments of the present invention, and the present invention can be used in various other combinations, modifications, and environments. That is, changes or modifications can be made within the scope of the inventive concept disclosed in this specification, a scope equivalent to the written disclosure, and/or within the scope of technology or knowledge in the art. The written examples illustrate the best state for implementing the technical idea of the present invention, and various changes required for specific application fields and uses of the present invention are also possible. Accordingly, the detailed description of the invention above is not intended to limit the invention to the disclosed embodiments. Additionally, the appended claims should be construed to include other embodiments as well.

10 Computing environment
12 computing devices
14 processor
16 Computer-readable storage media
18 communication bus
20 programs
22 input/output interface
24 input/output devices
26 network communication interface
100 Labor integrated management device
102 Labor Case Analysis Engine
104 Labor Risk Prediction Engine
106 User Service Engine
111 data acquisition module
113 data processing module
115 storage module
121 interface module
123 Policy Information Management Module
125 machine learning modules
125a first task unit
125b second task unit
125c 3rd task unit
125d 4th Task Department
131 Risk Score Reporting Module
133 Unfair dismissal prevention notification module
135 Fraudulent supply and demand prevention notification module
137 Labor dispute prevention notification module
139 Incident Accident Prevention Notification Module
141 Labor information notification module
143 Chatbot Service Module
145 Legal Search Service Module
147 Employment contract management module

Claims (5)

one or more processors, and
A computing device having a memory that stores one or more programs executed by the one or more processors,
A labor case analysis engine that collects labor-related cases and analyzes the collected labor-related cases to generate labor case analysis information; and
Labor risk prediction that generates labor risk management information for the workplace based on the labor-related cases and the labor case analysis information - the labor case analysis information includes all workplace-related information, worker-related information, and labor case-related information. Includes engine,
The above labor case-related information includes labor case type information, labor case history information, labor case issue information, and related laws and regulations information,
The labor risk prediction engine is,
an interface module that interfaces with the labor case analysis engine;
A policy information management module that collects workplace policy-related information for each workplace based on the workplace-related information for each workplace; and
Labor risk management information for the workplace by inputting the labor-related cases, the labor case analysis information, the workplace-related information, and the workplace policy-related information - the labor risk management information is the unfair dismissal risk index and the unfair supply and demand risk index. , which includes both a labor dispute risk index and an incident accident risk index, and includes a machine learning module that generates,
The policy information management module stores workplace-related information for each workplace - the workplace-related information includes business identification information, business type, workplace size, workplace environment, workplace history, workplace sales, and number of employees - and stores each workplace. Based on the workplace-related information, it is configured to collect workplace policy-related information related to the workplace and input the workplace-related information and the workplace policy-related information into the machine learning module,
The machine learning module is,
When the labor-related cases, the labor case analysis information, the workplace-related information, and the workplace policy-related information are input, the unfair dismissal risk index, unfair supply and demand risk index, labor dispute risk index, and incident accident risk index are all predicted. Contains a machine learning model that is trained,
The machine learning model is a multi-task learning model,
The machine learning model is,
a first task unit that learns to output an unfair dismissal risk index for the workplace by inputting the labor-related cases, the labor case analysis information, the workplace-related information, and the workplace policy-related information;
a second task unit that learns to output an illegal supply and demand risk index for the relevant workplace by inputting the labor-related cases, the labor case analysis information, the workplace-related information, and the workplace policy-related information;
a third task unit that learns to output a labor dispute risk index for the workplace by inputting the labor-related cases, the labor case analysis information, the workplace-related information, and the workplace policy-related information; and
A fourth task unit is learned to output an incident accident risk index for the workplace by inputting the labor-related cases, the labor case analysis information, the workplace-related information, and the workplace policy-related information,
The labor case analysis engine includes a data collection module, a data processing module, and a storage module,
The data collection module crawls the website through labor-related cases - the labor-related cases are labor-related cases that have occurred previously, such as unfair dismissal, illegal supply, labor disputes, accidents, and court precedents on labor cases. and the decisions of administrative bodies, including - are organized to collect;
The data processing module is configured to perform parsing on the labor-related cases in the form of documents or text collected by the data collection module to extract the labor case analysis information from each labor-related case,
The labor case analysis information includes workplace-related information - the workplace-related information includes business identification information, business size, workplace sales, and number of employees - and worker-related information - the worker-related information includes worker identification information, work details, Including work period and work type - and labor case-related information - The labor case-related information includes labor case type information, labor case history information, labor case issue information, and related laws and regulations information,
The above labor case type information includes information on what type of labor case the relevant labor case is, among unfair dismissal, unfair disciplinary action, non-payment of wages, strike, and salary dispute,
The labor incident history information is information representing the history of the labor incident - the history includes how the labor incident occurred, how it progressed, and how it was concluded.
The above labor case issue information is information about the part that became an issue in the relevant labor case,
The relevant legal information includes information on laws and regulations related to the labor case - the laws include the Labor Standards Act and the Minimum Wage Act - and administrative interpretation,
The storage module is configured to store labor case analysis information generated by the data processing module by matching each labor-related case. delete delete delete delete