KR102418004B1 - Method, device and system for self diagnosis labor risk based on artificial intelligence - Google Patents

Abstract

According to an embodiment, disclosed is a method for artificial intelligence-based labor risk self-diagnosis. The method for artificial intelligence-based labor risk self-diagnosis, performed by an apparatus according to an embodiment, may comprise the steps of: extracting, from an internal network of a corresponding company, a first labor risk keyword for the company; extracting, from an external network, a second labor risk keyword for the company; calculating, through an artificial intelligence module, a risk score for a labor risk of the company based on the first labor risk keyword and the second labor risk keyword; determining whether the company needs labor consulting, based on the risk score and a preset critical score; and transmitting a determination result of whether the labor consulting is necessary, to a terminal of a manager in the company.

Description

Artificial intelligence-based labor risk self-diagnosis method, device and system

The examples below relate to a technology capable of self-diagnosing a company's labor risk based on artificial intelligence.

Companies are experiencing various labor disputes. The root cause of labor disputes is mostly because they miss the signs of labor disputes and do not know the minimum laws to be followed.

Since the management of startups and general companies are all management experts and not labor experts, when a labor dispute arises, they have no choice but to consult with a labor attorney on how to resolve the dispute.

The above method has a problem that only post-processing is possible after a dispute has arisen.

Therefore, in the present specification, it is intended to present a method and system for self-diagnosing the labor risk that may cause a labor dispute in advance.

Korean Patent Registration No. 10-1991881 (June 17, 2019) Korean Patent Registration No. 10-220650 (2021.01.06) Korean Patent No. 10-2287225 (2021.08.02) Korean Patent Registration No. 10-1988353 (2019.06.05)

Embodiments of the present invention are to propose a technology capable of stable corporate management by preventing the possibility of labor disputes occurring in an enterprise in advance.

The object of the present invention is not limited to the object mentioned above, and other objects not mentioned will be clearly understood from the description below.

According to one embodiment, in the artificial intelligence-based labor risk self-diagnosis method performed by a device, extracting a first labor risk keyword for the company from the internal network of the company, the external network for the company Extracting a second labor risk keyword, calculating a risk score for the labor risk of the company based on the first labor risk keyword and the second labor risk keyword through an artificial intelligence module, the risk score and the group It may include the steps of determining whether labor consulting is required of the company based on the set threshold score and transmitting the determination result of whether the labor consulting is necessary to the terminal in charge of the company.

In this case, the internal network may include an e-mail, bulletin board, document, and messenger-related DB used in the internal intra network of the company.

In this case, the external network may include a portal site, a social network service, and an Internet community bulletin board.

In this case, the calculating of the risk score includes calculating a first weight corresponding to the internal network through the artificial intelligence module, calculating a second weight corresponding to the external network through the artificial intelligence module step, calculating a third weight for the labor dispute possibility for each keyword included in the first labor risk keyword and the second labor risk keyword through the artificial intelligence module, the first labor risk keyword, and the second labor risk keyword It may include calculating a risk score for the labor risk of the company based on the risk keyword, the first weight, the second weight, and the third weight.

At this time, the artificial intelligence-based labor risk self-diagnosis method according to an embodiment of the present invention extracts corporate culture keywords related to corporate culture from the first labor risk keyword and the second labor risk keyword through an artificial intelligence module. The method may further include generating evaluation information on the corporate culture (eg, horizontal organization, vertical structure, hierarchical order, free-spiritedness, work-life balance, overtime essential) of the company based on the step and the corporate culture keyword.

At this time, the risk score is calculated by the following formula,

The RP (Risk Point) means the risk score, W1 (Weight1) means the first weight, W2 (Weight2) means the second weight, W3 (Weight3) means the third weight Meaning, int_Keyword_i may mean the number of i-th keywords included in the first no-risk keyword, and ext_Keyword_i may mean the number of i-th keywords included in the second no-risk keyword.

At this time, the artificial intelligence-based labor risk self-diagnosis method according to an embodiment of the present invention is a value obtained by adding the number of clicks of the first labor risk keyword and the number of clicks of the second labor risk keyword, and the first total number of clicks calculating, as a value obtained by dividing the number of clicks of the first no-risk keyword by the first total number of clicks, calculating a first ratio, and dividing the number of clicks of the second no-risk keyword by the first total number of clicks , calculating a second ratio, and correcting the first weight based on the first ratio, and correcting the second weight based on the second ratio.

Advantageous Effects of Invention According to the present invention, it is possible to present a technology capable of stable corporate management by preventing the possibility of labor disputes occurring in an enterprise in advance.

On the other hand, effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those of ordinary skill in the art from the description below.

1 is a configuration diagram for explaining an artificial intelligence-based labor risk self-diagnosis system according to an embodiment.
2 is a flowchart of an artificial intelligence-based labor risk self-diagnosis method according to an embodiment.
3 is a flowchart illustrating a process of calculating a risk score through artificial intelligence according to an embodiment.
4 is an exemplary diagram of a configuration of an apparatus according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes may be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all modifications, equivalents and substitutes for the embodiments are included in the scope of the rights.

Specific structural or functional descriptions of the embodiments are disclosed for purposes of illustration only, and may be changed and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosure form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various elements, these terms should be interpreted only for the purpose of distinguishing one element from another. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected to” another component, it may be directly connected or connected to the other component, but it should be understood that another component may exist in between.

The terms used in the examples are used for the purpose of description only, and should not be construed as limiting. The singular expression includes the plural expression unless the context clearly dictates otherwise. In this specification, terms such as "comprise" or "have" are intended to designate that a feature, number, step, operation, component, part, or a combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

In addition, in the description with reference to the accompanying drawings, the same components are given the same reference numerals regardless of the reference numerals, and the overlapping description thereof will be omitted. In describing the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description thereof will be omitted.

The embodiments may be implemented in various types of products, such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent cars, kiosks, wearable devices, and the like.

Hereinafter, an artificial intelligence-based labor risk self-diagnosis method, apparatus and system will be described with reference to the drawings.

1 is a configuration diagram for explaining an artificial intelligence-based labor risk self-diagnosis system according to an embodiment.

Referring to FIG. 1 , the artificial intelligence-based labor risk self-diagnosis system according to an embodiment of the present invention includes an internal network 200 such as a messenger, a mail system, an internal bulletin board and an internal intranet used in a company, a portal site, and a social Extracting labor risk keywords judged to have a possibility of a labor dispute of the company from the external network 300 such as network service and Internet community bulletin board, and the internal network 200 and the external network 300, and extracting the extracted labor A device 100 capable of self-diagnosing labor risk by calculating a risk score for the labor risk of the corresponding company based on the risk keyword may be included.

In this case, the device 100 may be configured to perform all or part of an arithmetic function, a storage/referencing function, an input/output function, and a control function of a typical computer. The device 100 may include at least one artificial intelligence module that performs an inference function. The device 100 may be configured to communicate with a receiver and a user terminal through wired or wireless, as will be described later.

At this time, the apparatus 100 can achieve the object of the present invention by performing an artificial intelligence-based labor risk self-diagnosis method to be described later, and detailed operations will be described in detail through an artificial intelligence-based labor risk self-diagnosis method.

2 is a flowchart of an artificial intelligence-based labor risk self-diagnosis method according to an embodiment.

The artificial intelligence-based labor risk self-diagnosis method, performed by the device 100 according to an embodiment of the present invention, may extract the first labor risk keyword for the company from the internal network 200 of the company ( S201).

In this case, the internal network 200 may include an e-mail, bulletin board, document, and messenger-related DB used in the internal intra network of the company.

In this case, the first labor risk keyword relates to keywords related to labor disputes, and whether or not to use a title in e-mail or messenger (hey, abusive language, etc.), keywords related to workplace harassment (forced overtime, unfair work instructions etc.), unpaid wages, unfair dismissal, recommended resignation, etc.

In addition, the extraction standard of the first labor risk keyword can be applied by learning the precedent DB on labor disputes through an artificial intelligence module to derive a correlation between labor disputes and specific keywords.

In addition, the artificial intelligence-based labor risk self-diagnosis method, performed by the apparatus 100 according to an embodiment of the present invention, may extract the second labor risk keyword for the company from the external network 300 (S203). ).

In this case, the external network 300 may include a portal site, a social network service, and an Internet community bulletin board.

At this time, the second labor risk keyword relates to a keyword related to labor dispute, and is extracted according to the same criteria as the first labor risk keyword, but since it is an open network, keywords for the corresponding company are applied together and extracted. . For example, if company 'A' is a target company, even if the keyword 'wage arrears' is extracted, it can be extracted as a valid keyword only when the keyword 'company A' is also searched.

In addition, the extraction standard of the second labor risk keyword can be applied by deriving a correlation between labor disputes and specific keywords by learning the precedent DB on labor disputes through the artificial intelligence module.

In addition, the artificial intelligence-based labor risk self-diagnosis method, performed by the apparatus 100 according to an embodiment of the present invention, is based on the first labor risk keyword and the second labor risk keyword through an artificial intelligence module. It is possible to calculate a risk score for the company's labor risk (S205).

The step of calculating the risk score will be described in more detail with reference to FIG. 2 .

In addition, the artificial intelligence-based labor risk self-diagnosis method, performed by the device 100 according to an embodiment of the present invention, can determine whether the company needs labor consulting based on the risk score and a preset critical score. There is (S207).

At this time, the critical score relates to the minimum range of labor risk that can be resolved by the self-correcting action, and the risk score is calculated by extracting the second labor risk keyword for each company based on the precedent DB on labor disputes. Through this, it is possible to calculate the risk scores, calculate the minimum risk score that will not go to litigation, and set it as the critical score.

At this time, if the risk score exceeds the critical score, it is determined that the labor risk is very high, and a follow-up action may be requested from the person in charge.

Accordingly, the artificial intelligence-based labor risk self-diagnosis method, performed by the apparatus 100 according to an embodiment of the present invention, may transmit the determination result of whether the labor consulting is necessary to the terminal in charge of the company (S209) .

If the risk score of the company exceeds the above critical score, it means that the company's labor risk has reached just before the current litigation. is sent to the terminal in charge.

At this time, the terminal in charge is a computer, smart phone, cell phone, tablet PC, digital camera, camcorder, e-book terminal, digital broadcasting terminal, PDA (Personal Digital Assistants), PMP (Portable Multimedia Player), navigation system, MP3 player, wearable device It may include all devices capable of communication, such as a wearable device, an audio device, and a DVD player.

3 is a flowchart illustrating a process of calculating a risk score through artificial intelligence according to an embodiment.

Referring to FIG. 3 , the step (S205) of calculating the risk score of the artificial intelligence-based labor risk self-diagnosis method according to an embodiment of the present invention includes the corresponding internal network 200 through the artificial intelligence module. A first weight may be calculated. In this case, the first weight is a weight of all keywords extracted from the internal network 200 , and is distinguished from the external network 300 , but the correlation between all keywords extracted from the internal network 200 and actual labor disputes It can be calculated through (S301).

In this case, as described above, the first weight may be calculated by learning the precedent DB on labor disputes through the artificial intelligence module.

In addition, in the step (S205) of calculating the risk score of the artificial intelligence-based labor risk self-diagnosis method according to an embodiment of the present invention, the second weight corresponding to the external network 300 through the artificial intelligence module can be calculated (S303).

In this case, the second weight is a weight of all keywords extracted from the external network 300 , and is distinguished from the internal network 200 , but the correlation between all keywords extracted from the external network 300 and actual labor disputes can be calculated through

At this time, as described above, the second weight may be calculated by learning the case DB on labor disputes through the artificial intelligence module.

In addition, the step (S205) of calculating the risk score of the artificial intelligence-based labor risk self-diagnosis method according to an embodiment of the present invention includes the first labor risk keyword and the second labor risk keyword through the artificial intelligence module. It is possible to calculate a third weight for the possibility of labor disputes for each keyword included in ( S305 ).

In this case, the third weight relates to a weight related to labor disputes for each keyword, and may be set based on how each keyword is correlated with labor disputes. For example, the keyword 'wage payment delay' may be set to have a somewhat lower probability of a labor dispute than 'workplace sexual harassment'. As described above, the third weight is to set a weight for each keyword based on the severity of the labor dispute.

In addition, the step (S205) of calculating the risk score of the artificial intelligence-based labor risk self-diagnosis method according to an embodiment of the present invention includes the first labor risk keyword, the second labor risk keyword, the first weight, A risk score for the labor risk of the company may be calculated based on the second weight and the third weight (S307).

In this case, the risk score may be calculated by Equation 1 below.

At this time, the RP (Risk Point) means the risk score, W1 (Weight1) means the first weight, W2 (Weight2) means the second weight, W3 (Weight3) means the second weight 3 means weight, int_Keyword_i may mean the number of i-th keywords included in the first no-risk keyword, and ext_Keyword_i may mean the number of i-th keywords included in the second no-risk keyword.

Through this, it is possible to calculate an accurate risk score by giving an appropriate weight to each number of keywords extracted from the internal network 200 and the external network 300 .

In this case, the artificial intelligence module uses a deep learning technique, which is a field of machine learning, to extract a first labor risk keyword, a second labor risk keyword, a first weight, a second weight, and a third weight. It is possible to learn the case DB related to labor disputes to output calculation standards, etc.

In addition, the artificial intelligence module may calculate the weight of a plurality of inputs in the function through deep learning through learning. In addition, various models such as RNN (Recurrent Neural Network), DNN (Deep Neural Network), and DRNN (Dynamic Recurrent Neural Network) may be used as an AI network model used for such learning.

Here, RNN is a deep learning technique that considers current data and past data simultaneously. Recurrent neural network (RNN) refers to a neural network in which connections between units constituting an artificial neural network constitute a directed cycle. Furthermore, various methods may be used for a structure capable of constructing a recurrent neural network (RNN), for example, a fully recurrent network, a hopfield network, an Elman network, an ESN (Echo). state network), long short term memory network (LSTM), bi-directional RNN, continuous-time RNN (CTRNN), hierarchical RNN, and secondary RNN are representative examples. In addition, as a method for learning a recurrent neural network (RNN), methods such as gradient descent, Hessian Free Optimization, and Global Optimization Method may be used.

In addition, the number of clicks on the labor risk keyword indicates that the keyword expresses people's interest in labor disputes. If there are many clicks, it can be determined that the possibility of labor disputes is high.

Therefore, the artificial intelligence-based labor risk self-diagnosis method according to an embodiment of the present invention calculates the first total number of clicks by adding the number of clicks of the first labor risk keyword and the number of clicks of the second labor risk keyword. can do.

In addition, the artificial intelligence-based labor risk self-diagnosis method according to an embodiment of the present invention calculates a first ratio by dividing the number of clicks of the first labor risk keyword by the first total number of clicks, and the second labor risk By dividing the number of clicks of the risk keyword by the first total number of clicks, the second ratio can be calculated.

In addition, the AI-based labor risk self-diagnosis method according to an embodiment of the present invention may correct the first weight based on the first ratio and correct the second weight based on the second ratio .

Through this, it is possible to more accurately calculate the risk score.

In addition, labor risk does not simply include labor disputes. External perspectives on corporate culture can have an impact on manpower replenishment. Therefore, self-judgment on the corporate culture of the relevant company is necessary.

To this end, the AI-based labor risk self-diagnosis method according to an embodiment of the present invention extracts corporate culture keywords related to corporate culture from the first labor risk keyword and the second labor risk keyword through an artificial intelligence module. can

In this case, the keywords related to the corporate culture may be keywords related to horizontal organization, vertical structure, hierarchical order, work-life balance, etc. You can extract the company culture keywords.

In addition, the artificial intelligence-based labor risk self-diagnosis method according to an embodiment of the present invention is based on the corporate culture keywords based on the corporate culture (ex. horizontal organization, vertical structure, hierarchy, freewheeling, work-life balance, overtime) It is possible to create evaluation information for required, workload).

In more detail, the evaluation information may be generated in the form of a sentence, for example, the evaluation information may be generated in a complex form such as 'excessive workload, horizontal structure'.

In addition, the AI-based labor risk self-diagnosis method according to an embodiment of the present invention may analyze the employment rules and labor contract of the company through the AI module to determine whether it violates current laws and regulations.

The above evaluation information and information on whether or not the current laws and regulations are violated may be collected and transmitted to the terminal in charge of the relevant company.

4 is an exemplary diagram of the configuration of the apparatus 100 according to an embodiment.

The device 100 according to an embodiment includes a processor 410 and a memory 420 . The apparatus 100 according to an embodiment may be the above-described server or terminal. The processor may include at least one of the devices described above with reference to FIGS. 1 to 3 , or may perform at least one method described above with reference to FIGS. 1 to 3 . The memory 420 may store information related to the above-described method or a program in which the above-described method is implemented. The memory 420 may be a volatile memory or a non-volatile memory.

The processor 410 may execute a program and control the device 100 . The code of the program executed by the processor 410 may be stored in the memory 420 . The device 100 may be connected to an external device (eg, a personal computer or a network) through an input/output device (not shown) and exchange data.

The embodiments described above may be implemented by a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the apparatus, methods, and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA) array), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or apparatus, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

As described above, although the embodiments have been described with reference to the limited drawings, those skilled in the art may apply various technical modifications and variations based on the above. For example, the described techniques are performed in an order different from the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (3)

In the artificial intelligence-based labor risk self-diagnosis method performed by the device,
extracting a first labor risk keyword for the company from an internal network including e-mail, bulletin board, document and messenger-related DB used in the internal intra network of the company;
extracting a second labor risk keyword for the company from an external network including a portal site, a social network service, and an Internet community bulletin board;
All the first labor risk keywords extracted from the internal network through the artificial intelligence module and correlations are derived based on the precedent DB on labor disputes, and as the first labor risk keywords are extracted from the internal network, it becomes a labor dispute. calculating a first weight corresponding to the possibility of succession;
All the second labor risk keywords extracted from the external network through the artificial intelligence module and correlations are derived based on the precedent DB on labor disputes, and as the second labor risk keywords are extracted from the external network, labor disputes calculating a second weight corresponding to a possibility of leading to .
Through the artificial intelligence module, a correlation is derived based on the keywords included in the first labor risk keyword and the second labor risk keyword and the precedent DB on labor disputes, and the possibility of leading to labor disputes for each keyword calculating a corresponding third weight;
calculating a risk score for the labor risk of the company based on the first labor risk keyword, the second labor risk keyword, the first weight, the second weight, and the third weight;
Based on the precedent DB on labor disputes, the threshold score set to respond to the minimum risk score that does not proceed to litigation and the above risk score are compared to each other, and whether labor consulting is necessary to respond to the need for labor consulting or the need for labor consulting in the company concerned judging; and
transmitting a result of determining whether the labor consulting is necessary to a terminal in charge of the company; including,
At this time, the risk score is
It is calculated by the formula below,

RP (Risk Point) means the risk score, W1 (Weight1) means the first weight, W2 (Weight2) means the second weight, W3 (Weight3) means the third weight and int_Keyword_i means the number of i-th keywords included in the first labor risk keyword, and ext_Keyword_i means the number of i-th keywords included in the second labor risk keyword. Risk self-diagnosis method.

delete delete

Images