WO2022050551A1 - Legal service provision system and method therefor - Google Patents

Abstract

A system for providing legal services related to corporate duties, and a method therefor are provided. A legal service provision system according to some embodiments of the present disclosure may include: an analysis platform, which uses an artificial intelligence model to analyze legal information and standard duty information, and thus derives laws related to specific standard duties; and a service platform for providing legal services for target duties on the basis of the information derived by means of the analysis platform. For example, the service platform can provide legal information related to the target duties, and thus a person in charge of corporate duties can receive useful legal information that should be known when performing duties without the help of a legal expert.

Description

Legal service provision system and method therefor

The present disclosure relates to a system for providing legal services and a method therefor. More particularly, it relates to a system for providing legal services related to corporate duties and a method performed in the system.

Companies must establish in-house rules in consideration of job-related laws, and the person in charge of the company's duties must be familiar with and comply with internal rules when performing their duties. This is because, in case of violation of related laws, corresponding economic or administrative sanctions may be imposed not only on the company but also on the person in charge of the job.

In this regard, some large corporations are establishing and reorganizing their job system and corresponding in-house rules based on job-related laws. However, most companies still do not establish in-house rules in consideration of job-related laws, and the job system does not meet standards or is not clearly differentiated.

In order for the above companies to familiarize themselves with job-related laws, they need the help of an external expert, but this requires a considerable amount of money, which inevitably places a considerable burden on the company. However, it is also very difficult for a person in charge of a job without legal knowledge to directly search for or find job-related laws.

Accordingly, there is a need for a system that can provide job-related legal information or comprehensive legal services to the above companies or job managers.

A technical problem to be solved through some embodiments of the present disclosure is to provide a system capable of providing legal services related to a job and a method performed in the system.

The technical problems of the present disclosure are not limited to the above-mentioned technical problems, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

In order to solve the technical problem, the legal service providing system according to some embodiments of the present disclosure is an analysis platform for deriving a law related to a specific standard job by analyzing legal information and standard job information using an artificial intelligence model; A service platform for providing legal services for a target job based on the information derived by the analysis platform, wherein the analysis platform includes a legal interpreter for interpreting the legal information, a job interpreter for interpreting the standard job information, and the By analyzing the relationship between the standard job and the law based on the analysis result of the law interpreter and the analysis result of the job interpreter, a relationship analyzer for deriving a law related to the specific standard job may be included.

In some embodiments, the standard job information may be information collected from a national job competency standard site.

In some embodiments, the law interpreter interprets the legal information through a Named Entity Recognition (NER) model, wherein the NER model includes a Bidirectional Encoder Representations from Transformers (BERT) model and a Bi-LSTM-CRF (Bidirectional Long Short- Term Memory with a Conditional Random Field Layer) may be implemented based on a model.

In some embodiments, the legal interpreter extracts a legal entity set from the legal information through a Named Entity Recognition (NER) model, the job interpreter extracts a standard job entity set from the standard job information through a NER model, and , the relationship analyzer may derive a law related to the specific standard job based on a similarity between the extracted legal entity set and the extracted standard job entity set.

In some embodiments, the method further comprises: a dictionary interpreter configured to construct a legal dictionary using the extracted legal entity set and to construct a standard job dictionary using the extracted standard job entity set, wherein the relationship analyzer comprises: A law related to the specific standard job may be derived further based on the similarity between the configured legal dictionary and the configured standard job dictionary.

In some embodiments, the relationship analyzer is, in determining the relevance between the specific standard job and the specific law, the specific standard job and Relevance between the specific laws can be determined.

In some embodiments, the relationship analyzer is, in analyzing the relationship between the specific standard job and the specific law, further based on a relationship between the specific law and a higher job or a lower job of the specific standard job, the specific standard job and the relevance of the specific law can be determined.

In some embodiments, the service platform provides visualized information about the target job and related laws based on the information derived by the analysis platform, wherein a space formed by a first axis, a second axis, and a third axis generating the visualized information by arranging a plurality of entities for the target job, the relevant law, and the relevant standard job of the target job, wherein the first axis, the second axis and the third axis are each a target job It can have correspondences with information, legal information, and standard job information.

In some embodiments, the service platform may determine a standard job corresponding to the target job, and provide legal information related to the determined standard job as legal information related to the target job.

Legal service providing method according to some embodiments of the present disclosure for solving the above-described technical problem, in the legal service providing method performed by at least one computing device, legal information and standard duties using an artificial intelligence model Including the steps of deriving a law related to a specific standard job by analyzing information and providing a legal service for a target job based on the derived result, wherein the step of deriving a law related to the specific standard job includes the artificial Analyzing the legal information using an intelligent model, interpreting the standard job information using the artificial intelligence model, and the specific standard job based on the analysis result of the legal information and the analysis result of the standard job information It may include the step of deriving laws related to

A computer program according to some embodiments of the present disclosure for solving the above-described technical problem is combined with a computing device, and derives a law related to a specific standard job by analyzing legal information and standard job information using an artificial intelligence model It may be stored in a computer-readable recording medium in order to execute the step of performing the steps and the steps of providing a legal service for a target job based on the derived result. In this case, the step of deriving the law related to the specific standard job includes the steps of interpreting the legal information using the artificial intelligence model, interpreting the standard job information using the artificial intelligence model, and the legal information It may include deriving a law related to the specific standard job based on the analysis result and the analysis result of the standard job information.

According to some embodiments of the present disclosure described above, a law related to a standard job may be derived using an artificial intelligence model, and a legal service for a corporate job may be provided based on this. Accordingly, the person in charge of the company's job can easily receive job-related legal information without the help of a legal expert. Furthermore, companies can reduce the cost of consulting legal experts and establish internal rules in consideration of job-related laws at a relatively low cost.

In addition, entity sets are extracted from various legal information and standard job information through the Named Entity Recognition (NER) model, which is one of the artificial intelligence models, and the relevance between the standard job and the law is determined based on the similarity between the entity sets. can be Accordingly, the relevance between the standard job and the law can be accurately determined.

In addition, the relevance between the standard job and the law may be determined further based on the prior similarity between the standard job and the law. Accordingly, the relevance between standard duties and laws can be more accurately determined.

In addition, legal information related to the job of the company may be provided based on the standard job. Accordingly, consistent and accurate legal information can be provided even if job titles are different between companies.

In addition, legal information related to the job may be provided as visualized information along with the related standard job. Accordingly, information transfer can be performed more effectively.

Effects according to the technical spirit of the present disclosure are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 illustrates an exemplary service providing environment of a legal service providing system according to some embodiments of the present disclosure.

2 is an exemplary block diagram illustrating a legal service providing system according to some embodiments of the present disclosure.

3 is an exemplary flowchart illustrating a method for analyzing a relationship between standard job information and legal information according to some embodiments of the present disclosure.

4 is an exemplary diagram illustrating a process of extracting a legal entity set from legal information according to some embodiments of the present disclosure.

5 illustrates a structure of a Named Entity Recognition (NER) model according to some embodiments of the present disclosure.

6 and 7 illustrate an entity classification scheme that may be referenced in some embodiments of the present disclosure.

8 illustrates standard job information that may be referenced in some embodiments of the present disclosure.

9 is an exemplary flowchart illustrating a detailed process of the relevance deriving step S300 shown in FIG. 3 .

10 and 11 are exemplary views for explaining a method of pre-configuring a job according to some embodiments of the present disclosure.

12 and 13 are exemplary views for explaining a method for determining the relation between a law and a standard job according to some embodiments of the present disclosure.

14 is an exemplary flowchart illustrating a method of providing legal services for a target job according to some embodiments of the present disclosure.

15 to 19 are exemplary views for explaining a method of visualizing target job-related legal information according to some embodiments of the present disclosure.

20 illustrates an exemplary computing device that may implement a service providing system or a component thereof according to some embodiments of the present disclosure.

Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Advantages and features of the present disclosure, and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the technical spirit of the present disclosure is not limited to the following embodiments, but may be implemented in various different forms, and only the following embodiments complete the technical spirit of the present disclosure, and in the technical field to which the present disclosure belongs It is provided to fully inform those of ordinary skill in the art of the scope of the present disclosure, and the technical spirit of the present disclosure is only defined by the scope of the claims.

In adding reference numerals to the components of each drawing, it should be noted that the same components are given the same reference numerals as much as possible even though they are indicated on different drawings. In addition, in describing the present disclosure, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present disclosure, the detailed description thereof will be omitted.

Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used with the meaning commonly understood by those of ordinary skill in the art to which this disclosure belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless clearly defined in particular. The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present disclosure. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase.

In addition, in describing the components of the present disclosure, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only for distinguishing the elements from other elements, and the essence, order, or order of the elements are not limited by the terms. When a component is described as being “connected”, “coupled” or “connected” to another component, the component may be directly connected to or connected to the other component, but another component is between each component. It should be understood that elements may also be “connected,” “coupled,” or “connected.”

As used herein, “comprises” and/or “comprising” refers to a referenced component, step, operation, and/or component of one or more other components, steps, operations and/or components. The presence or addition is not excluded.

Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

1 illustrates an exemplary service providing environment of a legal service providing system according to some embodiments of the present disclosure.

As shown in FIG. 1 , the legal service providing system 1 may provide various legal services for a job to the service using device 100 . For example, the legal service providing system 1 may provide legal information related to the target job or may provide information of a legal expert who can consult (or advise) on legal issues related to the target job. However, the present invention is not limited thereto. Here, the target job is a job on the service user's side and may mean a job (e.g. an actual job of a company) that is an advisory target of the legal service. Hereinafter, for convenience of description, "legal service providing system 1" will be abbreviated as "service providing system 1".

The service providing system 1 according to the embodiments may include an analysis platform 20 and a service platform 20 . However, this is only a preferred embodiment for achieving the purpose of the present disclosure, and it goes without saying that some components may be added or deleted as needed. The analysis platform 20 may refer to a platform that collects standard job information and legal information and analyzes relationships between them in order to provide legal services, and the service platform 10 includes information analyzed by the analysis platform 20 . It can mean a platform that provides legal services for target jobs based on The detailed configuration and operation principle of each platform 10 and 20 will be described in detail later with reference to the drawings below in FIG. 2 .

The service providing system 1 or the platforms 10 and 20 constituting it may be implemented as one or more computing devices. For example, each of the service platform 10 and the analytics platform 20 may be implemented with one or more computing devices. Alternatively, the service platform 10 and the analysis platform 20 may be implemented in the form of different logic in one or more computing devices. As such, a method for implementing the service providing system 1 may be designed in various ways.

The computing device may be a notebook, desktop, laptop, etc., but is not limited thereto, and may include any type of device equipped with a computing function and a communication function. However, in an environment that provides legal services to a plurality of service using devices 100 , the service providing system 1 may be preferably implemented as a high-performance server-grade computing device. Referring to FIG. 20 for an example of a computing device.

Next, the service using device 100 may mean a device on the side of a service user who receives a legal service from the service providing system 1 . Here, the service user may be, for example, a company or a job manager of the company, but is not limited thereto. The service use device 100 may provide the target job information of the company to the service providing system 1 , request legal services for the target job, and receive legal services for the target job from the service providing system 1 . there is. For example, the service using device 100 may receive legal information related to a target job or information of a legal expert.

The service using device 100 may be implemented as various types of computing devices such as a notebook computer, a desktop computer, a laptop computer, and a smart phone.

As illustrated, the service providing system 1 and the service using device 100 may communicate through a network. Here, the network is implemented as all types of wired/wireless networks such as a local area network (LAN), a wide area network (WAN), a mobile radio communication network, and a Wibro (Wireless Broadband Internet). can be

So far, the service providing system 1 and the service providing environment according to some embodiments of the present disclosure have been schematically described with reference to FIG. 1 . As described above, a legal service for a target job may be provided through the service providing system 1 . Accordingly, the person in charge of the job of the company can easily receive legal information about his/her job without the help of a legal expert.

Hereinafter, the detailed configuration and operation principle of the service providing system 1 will be described in detail with reference to the drawings below in FIG. 2 .

2 is an exemplary block diagram illustrating a service providing system 1 according to some embodiments of the present disclosure. In particular, FIG. 2 shows an example of a data flow of the service providing system 1 together.

As shown in FIG. 2 , the service providing system 1 may include an analysis platform 20 and a service platform 10 . And, each of the analysis platform 20 and the service platform 10 may include one or more components. However, this is only a preferred embodiment for achieving the purpose of the present disclosure, and it goes without saying that some components may be added or deleted as needed. In addition, it is noted that each component of the service providing system 1 shown in FIG. 2 represents functionally separated functional elements, and a plurality of components may be implemented in a form that is integrated with each other in an actual physical environment. .

In addition, in the actual physical environment, each of the components may be implemented in a form separated into a plurality of detailed functional elements. For example, a first function of the service server 11 may be implemented in a first computing device, and a second function may be implemented in a second computing device. Alternatively, a specific function of the service server 11 may be implemented by a plurality of computing devices. Hereinafter, each component of the service provision system 1 is demonstrated.

First, the analysis platform 20 according to the embodiments may include various information DBs 25 to 27 , a law interpreter 22 , a job interpreter 23 , a dictionary interpreter 24 , and a relationship analyzer 21 . .

The various information DBs 25 to 27 may include, for example, a legal information DB 25 , a job information DB 26 , and a dictionary information DB 27 , and the information collected from the data source 30 is stored therein. can be However, the present invention is not limited thereto.

Legal information collected from the legal site 31 and the like may be stored in the legal information DB 25 . Here, the legal information may include, for example, laws, treaties, orders, rules, guidelines, precedents, etc., but is not limited thereto. In addition, the legal information may be collected through the crawling of the legal information collector (not shown) on the legal site 31, etc., but is not limited thereto, and any method of collecting legal information may be used. .

Next, job information collected from a standard job site 32 (e.g. NCS National Job Competency Standards site) may be stored in the job information DB 26 . Here, the job information may include, for example, various information related to the job, such as job system, job content (eg job description, etc.), job difficulty, as well as job related documents (eg report sample, etc.). In addition, the job information may be collected from the standard job site 32 or the like through crawling of the job information collector (not shown), but is not limited thereto, and any method of collecting job information may be used.

In addition, target job information received from the service using device 100 may be stored in the job information DB 26 . The target job information may be, for example, job information customized to fit the characteristics of a company, but is not limited thereto. Some or all of the target job information may be the same as the standard job information.

Next, dictionary information collected from the portal/wiki site 33 or the like may be stored in the dictionary information DB 27 . Here, the dictionary information may include, for example, explanation information such as definitions of terms (e.g. legal terms, job terms), example sentences, similar words, and antonyms, but is not limited thereto. In addition, the dictionary information may be collected from the portal/wiki site 33 or the like through crawling of the dictionary information collector (not shown), but is not limited thereto, and any method of collecting the dictionary information may be used.

Next, the law interpreter 22 may interpret the legal information stored in the legal information DB 25 using the artificial intelligence model. For example, the law interpreter 22 may extract a legal entity set by interpreting legal information through a natural language processing model (e.g. NER model). A legal entity set may include one or more legal entities, for example, an entity related to an actor of a law, an entity related to an act of a law (ie, an act), or an entity related to a name of a law. Entities and other entities representing key keywords of the law may include, and the like. However, the present invention is not limited thereto. In addition, the law interpreter 22 may interpret the relationships between the extracted legal entities. For example, the law interpreter 22 may determine a corresponding relationship between an actor-related entity and an act-related entity, or define a type of relationship.

The legal information interpreted by the law analyzer 22 may be later utilized by the relationship analyzer 21 , and may be stored in the legal information DB 25 and/or the service information DB 12 . The detailed operation of the law interpreter 22 will be described in more detail later with reference to FIGS. 3 to 7 and the like.

Next, the job analyzer 23 may interpret job information stored in the job information DB 26 through the artificial intelligence model. For example, the job interpreter 23 may extract the standard job entity set by interpreting the standard job information through a natural language processing model (e.g. NER model). A standard job entity set may include one or more standard job entities, eg, an entity related to an actor (ie, an actor) of a job, an entity related to an act (ie, an action) of a job, an entity related to a name of the job, and It may include entities representing key keywords of other jobs. However, the present invention is not limited thereto. As another example, the job interpreter 23 may extract the target job entity set by interpreting the target job information.

The job information analyzed by the job analyzer 23 may be later utilized by the relationship analyzer 21 , and may be stored in the job information DB 26 and/or the service information DB 12 . The detailed operation of the job analyzer 23 will be described in more detail later with reference to FIGS. 3 to 8 and the like.

Next, the dictionary interpreter 24 may interpret the dictionary information stored in the dictionary information DB 27 based on the entities extracted by the law interpreter 22 and/or the job interpreter 23 . For example, the dictionary analyzer 24 may generate a dictionary for a specific law or a dictionary for a standard job (or target job) based on previously collected dictionary information. A dictionary for a legal and/or standard job (or target job) may be utilized by the relationship analyzer 21 , and may be stored in the dictionary information DB 27 and/or the service information DB 12 . The detailed operation of the dictionary analyzer 24 will be described in more detail later with reference to FIGS. 3 and 9 to 11 .

Next, the relationship analyzer 21 may derive a relationship between the job and the law by analyzing the information provided from the law interpreter 22 , the job interpreter 23 , and the dictionary interpreter 24 . For example, the relationship analyzer 21 may analyze the relationship between the standard job and the law based on a legal entity set, a standard job entity set, a legal dictionary, a standard job dictionary, and the like. As another example, the relationship analyzer 21 may analyze the relationship between the target job and the law based on a legal entity set, a target job entity set, a legal dictionary, a target job dictionary, and the like.

The analysis result of the relationship analyzer 21 may be stored in the service information DB 12 and/or another DB. The detailed operation of the relationship analyzer 21 will be described in more detail later with reference to FIGS. 3, 12, and 13 .

Hereinafter, the service platform 10 will be described.

The service platform 10 according to embodiments may include a service information DB 12 , a service server 11 , and a management server 13 .

Various information for providing legal services may be stored in the service information DB 12 . For example, the service information DB 12 may store an analysis result of the analysis platform 20 , legal expert information, member information, and the like. However, the present invention is not limited thereto, and various types of information used in the analysis platform 20 may be further stored in the service information DB 12 .

Next, the service server 11 may provide a legal service for a job (or company). Here, the legal service may include, for example, a legal information provision service, a legal expert matching service, a legal information inquiry service, a job-related consulting service, and various information subscription services, but is not limited thereto.

As a specific example, the service server 11 may receive target job information from the service using device 100 or a service user, and may provide legal information related to the target job. At this time, the service server 11 may provide the legal information as described above in a visualized form. This embodiment will be described in more detail later with reference to FIGS. 14 to 19 .

As another example, the service server 11 may provide information of a legal expert related to a target job. The service server 11 may determine a legal expert suitable for consulting a target job based on the history of the legal expert and the degree of relevance to the target job, and may provide information on the determined legal expert. At this time, the degree of relevance is the number (or ratio) of litigation related to the target job, the value (or cost) of litigation, the trend of increase or decrease in the number of litigation, the trend of increase or decrease in the value of litigation, the prevailing rate of litigation, the increase or decrease of the prevailing rate, and the legal expert It can be calculated by comprehensively considering the size of the company to which A belongs, the number (or ratio) of lawsuits related to the target job of the affiliated company, the winning rate, and their increase/decrease trend. In addition, the more the legal expert's recent history information has more litigation information related to the target job (e.g. the number of related litigations increases or increases recently), the higher the degree of relevance can be calculated. According to the present embodiment, the person in charge of the job of the company can easily receive the information of the legal expert related to the job.

As another example, the service server 11 may provide an inquiry service for legal information. Specifically, the service server 11 may provide a function of inquiring legal information related to a job or a function of inquiring a job related to specific legal information. For example, the service server 11 may receive (input) a job keyword or a legal keyword, and provide a search result for the received keyword. Alternatively, the service server 11 receives (inputs) a natural language (eg sentence, etc.) related to a job or law, extracts a keyword from the natural language received through a natural language processing model (eg extracts an entity through NER, etc.), Search results for extracted keywords can be provided. According to the present embodiment, the job manager of the company can easily inquire job-related legal information.

As another example, the service server 11 may provide a subscription service for job information or legal information. As a more specific example, the service server 11 may provide subscribers with revision information of laws related to a specific job, recent precedents, recent dispute cases, legal expert information, and the like. As another example, the service server 11 may provide update information related to the standard job to the subscriber. As another example, the service server 11 may provide subscribers with legal information related to a target job for which legal service requests are increasing, or update information of a standard job related thereto. The service server 11 may provide subscription information as exemplified periodically or aperiodically to the subscriber. Such a subscription service may be provided only to paid members. In this case, a differentiated service may be provided depending on whether or not there is a charge, and the service provider's revenue model may be improved.

In the preceding example, the service server 11 may provide subscription information to non-subscribers. For example, the service server 11 generates and provides customized subscription information (eg, recent disputes related to target job information, legal revision information, etc.) based on the non-subscriber's legal service use history (eg target job information, search keywords, etc.) can do. In this case, the effect of inducing non-subscribers to subscribe to the subscription service may be achieved.

Meanwhile, the service providing interface of the service server 11 (or the service use interface of the service using device 100) may be designed in various ways. For example, the service server 11 may request or provide a legal service through a messenger (e.g. chatbot interface), a web, an e-mail (e-mail), an app (e.g. a mobile app), and the like. However, the present invention is not limited thereto.

Next, the management server 13 may provide various management functions related to the service platform 10 or the service information DB 12 . For example, the management server 13 may provide a management (eg addition, deletion, correction, etc.) function for the information (eg the relationship between job information and legal information) stored in the service information DB 12 , and A management interface for convenience can also be provided.

Each component of FIG. 2 may mean software or hardware such as a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC). However, the components are not limited to software or hardware, and may be configured to be in an addressable storage medium, or configured to execute one or more processors. The functions provided in the components may be implemented by more subdivided components, or may be implemented as one component that performs a specific function by combining a plurality of components.

So far, the service providing system 1 according to some embodiments of the present disclosure has been described with reference to FIG. 2 . As described above, a law related to a standard job can be derived using an artificial intelligence model, and legal services for a corporate job can be provided based on this. Accordingly, the person in charge of the company's job can easily receive job-related legal information without the help of a legal expert. Furthermore, companies can reduce the cost of consulting legal experts and establish internal rules in consideration of job-related laws at a relatively low cost.

Hereinafter, a method of providing legal services according to some embodiments of the present disclosure will be described with reference to the drawings below with reference to FIG. 3 .

Each step of a method for providing legal services to be described below may be performed by a computing device. In other words, each step of the method may be implemented with one or more instructions executed by a processor of a computing device. All steps included in the method may be executed by one physical computing device, or may be distributed and executed by a plurality of physical computing devices. For example, first steps of the method may be performed by a first computing device, and second steps of the method may be performed by a second computing device. Hereinafter, the description will be continued on the assumption that the method is performed by the service providing system 1 illustrated in FIG. 1 or FIG. 2 . Therefore, in the following description, when the subject of a specific operation is omitted, it can be understood that it can be performed by the exemplified system 1 .

A method of providing legal services according to embodiments may be conceptually divided into a method of analyzing a relationship between standard job information and legal information, and a method of providing legal services for a target job based on a result of the relationship analysis. Therefore, in order to provide convenience of understanding, the above methods will be described separately.

3 is an exemplary flowchart illustrating a method for analyzing a relationship between standard job information and legal information according to some embodiments of the present disclosure. However, this is only a preferred embodiment for achieving the purpose of the present disclosure, and it goes without saying that some steps may be added or deleted as needed.

As shown in FIG. 3 , the relationship analysis method may be started in step S100 of collecting legal information and standard job information. For example, the service providing system 1 may collect various legal information and standard job information by crawling a legal site and a standard job site (e.g. NCS National Competency Standards site).

In some embodiments, the service providing system 1 may further collect dictionary information for various terms. For example, the service providing system 1 may collect dictionary information on legal terms and/or job terms by crawling a portal site and/or a wiki site. As mentioned above, the dictionary information may include explanation information such as definitions of terms, example sentences, analogous words, and antonyms. The collected prior information can be used to more accurately determine the relationship between the law and standard duties.

In step S200, the service providing system 1 may interpret the legal information and standard job information collected through the natural language processing model. In more detail, the service providing system 1 may extract a legal entity set and a standard job entity set from legal information and standard job information collected through a Named Entity Recognition (NER) model. In order to provide more convenience of understanding, it will be described in more detail with reference to the example shown in FIG. 4 .

As illustrated in FIG. 4 , the service providing system 1 may extract various legal entities 42 and 43 by applying the NER model 40 to the information 41 of a specific law (eg, the Industrial Product Quality Control Act). . In this case, the NER model 40 may be a deep learning-based model, a dictionary-based model, or other well-known models.

In some embodiments, the NER model 40 may be based on a Bidirectional Long Short-Term Memory with a Conditional Random Field Layer (Bi-LSTM-CRF) model (eg, HighWay-LSTM, etc.). A person skilled in the art will be able to clearly understand the operation method of the Bi-LSTM-CRF model, and a description thereof will be omitted. For an example of the structure of the Bi-LSTM-CRF model, reference is made to FIG. 5 .

In some embodiments, the NER model 40 may be based on a combination of a Bidirectional Encoder Representations from Transformers (BERT) model and a Bi-LSTM-CRF model. Specifically, the BERT model performs a word embedding function that converts words constituting legal information into an embedding vector, and the Bi-LSTM-CRF model receives an embedding vector and outputs a NER result. there is. In this case, due to the performance improvement of the NER model 40, the extraction accuracy of the legal entity may be improved.

In some embodiments, the service providing system 1 may classify the extracted legal entities according to predetermined criteria. 6 shows an exemplary classification system of legal entities, the service providing system 1 may classify the extracted legal entities according to the classification system as illustrated. Specifically, the service providing system 1 may classify the extracted legal entity using the entity classification result (e.g. person, organization, location, misc, etc.) of the NER model. Specifically, when the entity classification result is "person" or "organization", the service providing system 1 may classify the legal entity as an actor entity (e.g. worker, user, etc.). Other legal entities may be classified as act entities.

Also, in some embodiments, the service providing system 1 may hierarchically classify (organize) legal entities based on hierarchical information of laws from which legal entities are extracted. For example, referring to FIG. 7 , the service providing system 1 classifies the first legal entity (eg workers) extracted from the first law (eg the Labor Standards Act) as an upper entity, and the first legal entity (eg workers) in the lower layer of the first law 2 The second legal entity (eg production manager) extracted from the law may be classified as a sub-entity of the first legal entity. The classified upper entity may be designated as a representative entity when the visualized information is generated later. In this regard, refer to the description of FIGS. 18 and 19 .

Meanwhile, the service providing system 1 may extract the standard job entity set from the standard job information in the same manner as described above. That is, various examples related to the legal entity set (e.g. NER model-based extraction, actor/act entity classification, hierarchical classification, etc.) can also be applied to the standard job entity set. As mentioned above, the standard job information may include various job information obtained from the NCS National Competency Standards website. For example, as illustrated in FIG. 8 , various job information such as a specific standard job and its substandard jobs, a job description for each standard job, and job difficulty may be obtained from the NCS National Competency Standards site. In order to exclude duplicate explanations, a description of the detailed process of extracting the standard job entity set will be omitted.

It will be described again with reference to FIG. 3 .

In step S300, the service providing system 1 may analyze the extracted legal entity set and the standard job entity set to derive a relationship between the standard job and the law. The detailed process of this step may be designed in various ways, which may vary depending on the embodiment. Hereinafter, various embodiments related to this step will be described.

In the first embodiment, the relevance between the law and the standard job may be determined based on the similarity between the legal entity set and the standard job entity set. For example, the relevance between the first law (eg Industrial Products Quality Control Act) and the first standard job (eg quality management) depends on the degree of similarity between the entity set of the first law and the entity set of the first standard job (hereinafter, “entity set similarity”). can be judged based on For example, when the entity set similarity between the first law and the first standard job is equal to or greater than the reference value, it may be determined that a relationship exists between the first law and the first standard job.

In the above-described embodiments, a method of calculating the similarity between entity sets may be varied. As an example, the entity set similarity may be calculated based on the number (or weight) of the same or similar entities. Here, whether the entity is a similar entity (ie, entity similarity) may be determined by various keyword similarity calculation techniques. For example, it may be determined based on a degree of similarity between vectors (e.g., cosine similarity, etc.), a degree of relevance predicted through a Neural Tensor Network (NTN) model, and the like. In addition, the entity similarity may be calculated by further considering the difference between the hierarchies of the two entities (e.g. see FIG. 7 ). For example, when two entities are located in the same layer, the entity similarity may be calculated to be higher, and vice versa. As another example, the entity set similarity may be calculated based on the similarity between actor entity sets and the similarity between the act entity sets. That is, the entity set similarity may be calculated based on the similarity between the legal actor entity set and the standard job actor entity set and the similarity between the legal act entity set and the standard job act entity set (e.g. weighted sum, etc.). The similarity between actors and/or act entity sets may be calculated in the same or similar manner as in the above example. As another example, the entity set similarity may be calculated based on a combination of the above-described examples.

In the second embodiment, the relevance between the law and the standard job may be judged (more) based on the degree of similarity between the dictionary of the law and the standard job (hereinafter, "dictionary similarity"). This embodiment will be described in more detail with reference to FIGS. 9 to 12 .

As illustrated in FIG. 9 , the service providing system 1 may construct a dictionary for each of the legal and standard duties ( S310 , S320 ), and may derive a relationship between the legal and standard duties further based on the similarity of the dictionary ( S310 , S320 ) ( S330). For reference, steps S310 and S320 may be performed by the dictionary analyzer 24 , and step S330 may be performed by the relationship analyzer 21 .

An example of configuring a standard job dictionary is shown in FIG. 10 . As illustrated in FIG. 10 , the dictionary 55 of the standard job (A) may be configured based on previously collected dictionary information, and in detail, the synonyms (51), definitions (52), and definitions (52) of the standard job (A), The dictionary 55 of the standard job A may be configured based on explanatory information such as definitions 53 and 54 of the entities a and b extracted from the information of the standard job A.

In some embodiments, the NER model may be applied to construct a standard job dictionary (e.g. 55). For example, the NER model may be applied to extract keywords such as synonyms (e.g. 51) from the collected dictionary information (e.g. example sentences, etc.). Alternatively, the NER model may be applied to extract only keywords from dictionary information ( e.g. definitions 52, 53, 54, etc.) in the form of sentences. In this case, the standard job dictionary (e.g. 55) may be configured in the same form as a keyword set.

Meanwhile, in some embodiments, the standard job dictionary may be corrected using the NTN model. The NTN model is a model for predicting the degree of relevance between two entities, and a person skilled in the art can clearly understand the structure and operation principle of the NTN model, so a description thereof will be omitted. Specifically, as shown in Fig. 11, the first entity (E1; or keyword) belonging to the dictionary 61 of the standard job A and the entity set 62 of the standard job A through the NTN model 60 ), a degree of relevance between the second entities E2 belonging to each other may be predicted. In addition, when the predicted degree of relevance is less than or equal to the reference value, the first entity E1 is removed from the dictionary 61 of the standard job A to configure the corrected dictionary 63 . In this case, the problem that terms unrelated to the standard job are included in the standard job dictionary (e.g. 61) can be prevented in advance. For example, since the standard job dictionary (e.g. 55) is constructed based on general information collected from portal/wiki sites, etc., words or example sentences unrelated to the standard job may be included. For example, when a specific entity (ie, standard job term) belonging to the standard job entity set (eg 62) is used with different meanings depending on context or field (eg polysyllabic, Chinese), the standard job dictionary (eg 61) contains the above Dictionary information related to other meanings may be included, and this problem can be solved according to the present embodiment.

Meanwhile, a legal dictionary may be configured in the same or similar manner as a standard job dictionary. In order to exclude a duplicate description, a detailed description thereof will be omitted.

When the legal dictionary and the standard job dictionary are constructed, the relevance between the law and the standard job dictionary can be determined based on (more) the similarity between the legal dictionary and the standard job dictionary. For example, as illustrated in FIG. 12 , the relevance of law (A) to standard job (A) is a degree of similarity (75) between entityset (72) of law (A) and entityset (71) of standard job (A). and the degree of similarity (76) between the dictionary (74) of law (A) and the dictionary (73) of standard duties (A). In this case, a greater weight may be given to the entity set similarity 75 . Also, the dictionary similarity 76 may be calculated in the same or similar manner as the entity set similarity 75 .

In the third embodiment, the relevance between the law and the standard job may be determined by (further) considering the degree of relevance between the law and the higher and/or lower jobs of the standard job. For example, as illustrated in FIG. 13 , when determining the relevance between the law (A) and the standard job (A), the degree of relevance (81) between the standard job (B) and the law (A), which is the upper job, and the lower job At least one of the degree of relevance 82 between the standard job (C) and the law (A) may be further considered. In this case, the degree of relevance between the standard duties (B, C) and the law (A) may be calculated in the same or similar manner to the above-described relevance determination method.

In a fourth embodiment, the relevance between the law and the standard job may be determined based on (further) the relevance between the legal actor entityset and the job act entityset and/or the relationship between the legal act entityset and the job actor entityset. . In this case, the relationship between the actor entity set and the act entity set may be calculated using the NTN model. For example, the relationship between the actor entity set and the act entity set may be calculated by synthesizing the degree of relationship between the actor entity and the act entity predicted through the NTN model.

In the fifth embodiment, the relationship between the law and standard duties can be derived based on various combinations of the first to fourth embodiments described above. Hereinafter, various combinations of the above-described first to fourth embodiments will be described in more detail.

For example, the relevance between the law and the standard job is to be determined by synthesizing the entity set similarity according to the first embodiment, the prior similarity according to the second embodiment, and the relation between the upper/lower job and the law according to the third embodiment. can For example, the relevance between the law and the standard job may be determined based on a weighted sum of the entity set similarity, the dictionary similarity, and the relevance. In this case, the weight assigned to each degree of similarity (or degree of relevance) may be the same or different. For example, the highest weight may be given to the entity set similarity, and the lowest weight may be given to the relevance.

As another example, when the entity set similarity according to the first embodiment is equal to or greater than the reference value, it may be determined that there is a relationship between the law and the standard job. And, if it is less than the reference value, the relevance between the law and the standard job may be re-determined based on the prior similarity according to the second embodiment. When the prior similarity is less than the reference value, it may be determined that there is no relevance between the corresponding law and the corresponding standard job, or the relevance may be determined again based on the relevance according to the third embodiment.

As another example, the relevance between the law and the standard job may be determined based on the entity set similarity according to the first embodiment, and verification may be performed on the determination result based on other metrics (eg prior similarity, relevance, etc.) there is. For example, verification may be performed on the determined relevance using the prior similarity according to the second embodiment. For example, when the prior similarity is less than the reference value, the relevance between the law and the standard job may be denied, and the relevance may be re-determined through other metrics (e.g. relevance, etc.).

As another example, the relevance between the law and the standard job may be determined based on the entity set similarity according to the first embodiment and the entity set relevance according to the fourth embodiment. In this case, the entity set similarity is, for example, based on whether the legal actor (act) entity and the job actor (act) entity match, and the similarity between the vector for the legal actor (act) entity and the vector for the job actor (act) entity can be calculated by In addition, the entity set relevance may be calculated, for example, based on the first relevance between the legal actor entity and the job act entity and the second relevance between the job actor entity and the legal act entity predicted through the NTN model.

Meanwhile, the service providing system 1 may derive laws related to each standard job by repeatedly performing the above-described steps S100 to S300 for various laws and standard jobs.

For reference, each step of the method shown in FIG. 3 may be performed by the analysis platform 20 among the components of the service providing system 1 . In more detail, step S100 may be performed by a legal information collector (not shown) and a standard job information collector (not shown) of the analysis platform 20 , and step S200 is a legal interpreter 22 and job interpreter 23 . may be performed, and step S300 may be performed by the relationship analyzer 21 . In addition, the pre-configuration of the law and the target job may be performed by the dictionary interpreter 24 .

A method of analyzing a relationship between standard job information and legal information according to some embodiments of the present disclosure has been described with reference to FIGS. 3 to 13 . As described above, complex legal information and standard job information can be accurately interpreted through the natural language processing model, and the relationship between law and standard job can be accurately determined through the similarity between entity sets.

Hereinafter, a method of providing legal services for a target job based on the results analyzed as described above will be described.

14 is an exemplary flowchart illustrating a method of providing legal services for a target job according to some embodiments of the present disclosure. However, this is only a preferred embodiment for achieving the purpose of the present disclosure, and it goes without saying that some steps may be added or deleted as needed.

As shown in FIG. 14 , the method of providing legal services may start in step S400 of acquiring information on a target job. For example, the service providing system 1 may obtain target job information from the service using device 100 . The service providing apparatus 1 may acquire target job information through various interfaces such as web, messenger, e-mail, and the like. In this case, the target job information may include one or more target jobs.

In step S500, the service providing system 1 may determine and provide legal information related to the target job based on the result of analyzing the relationship between the standard job information and the legal information. Alternatively, the service providing system 1 may provide information of a legal expert related to a target job. In this step, a specific method of determining legal information related to a target job may vary, which may vary according to embodiments.

In some embodiments, the service providing system 1 may determine a standard job corresponding to the target job, and determine legal information related to the determined standard job as legal information related to the target job. When a corresponding standard job does not exist, the service providing system 1 may derive and provide legal information related to the target job through the same or similar analysis process as described with reference to FIGS. 3 to 13 .

In some other embodiments, the service providing system 1 does not determine the correspondence between the target job and the standard job, but through the same or similar analysis process as described with reference to FIGS. 3 to 13 , the law related to the target job Information can also be derived and provided.

For reference, each step of the method shown in FIG. 14 may be performed by the service platform 10 among the components of the service providing system 1 .

So far, a method of providing legal services for a target job according to some embodiments of the present disclosure has been described with reference to FIG. 14 . As described above, the person in charge of the job of the company can easily receive job-related legal information without the help of a legal expert. Furthermore, companies can reduce the cost of consulting legal experts and establish internal rules in consideration of job-related laws at a relatively low cost.

Meanwhile, according to some embodiments of the present disclosure, the service providing system 1 may provide target job-related legal information in a visualized form. let me explain

15 to 19 are exemplary views for explaining a method of visualizing target job-related legal information according to some embodiments of the present disclosure.

First, as shown in FIG. 15 , target job-related legal information may be visualized in a graph form in a three-dimensional space formed by three axes. In this case, the X axis may correspond to legal information, the Y axis may correspond to standard job information, and the Z axis may correspond to target job information. However, the corresponding relationship may be changed. In addition, a part on the Z-axis that does not have a corresponding relationship with the target job may have a corresponding relationship with the standard job (e.g. when the target job is not completely established or does not correspond, so a part is replaced with a standard job)

In addition, the correspondence relationship between the X-axis and legal information may be determined based on a hierarchical system of laws. For example, as shown in FIG. 15 , the higher-level laws may be located farther from the origin on the X-axis, and the lower-level laws may be located closer to the origin. As a more specific example, a higher-level law such as a constitution may be located farthest from the origin, and may be located in the order of laws, treaties, orders, rules, and precedents in the direction of the origin.

In addition, a correspondence relationship between the Y-axis and standard job information may be determined based on job difficulty. For example, as shown in FIG. 15 , a job of high difficulty may be located farther from the origin on the Y-axis, and a job of low difficulty may be located closer to the origin on the Y-axis. As a more specific example, the standard job may correspond to the Y-axis based on the job difficulty obtained from the national standard job competency NCS site. In this case, the job performed by the person in charge of the high position is usually located far from the origin.

In addition, a correspondence relationship between the Z-axis and target job information may also be determined based on job difficulty. For example, as shown in FIG. 15 , a job of high difficulty may be located farther from the origin on the Z-axis, and a job of low difficulty may be located closer to the origin on the Z-axis. The difficulty level of the target job may be obtained from the service user side, and may be automatically determined by referring to the difficulty level of standard job information.

Hereinafter, a process in which information visualized in the three-dimensional space illustrated in FIG. 15 is configured will be described with reference to FIGS. 16 to 19 by way of example. As shown, the target job is "in-house wage management", the related standard job is "wage management", and the related law is "Labor Standards Act" as an example.

First, clustering is performed on entities related to the Labor Standards Act and wage management, and one or more clusters 91 and 92 generated as a result may be arranged in a specific area 90 of the XY plane. Here, it may be preferable that the specific region 90 is a region close to the X-axis position of the Labor Standards Act and the Y-axis position of wage management.

For example, one or more clusters 91 and 92 may be constructed by converting legal entities related to the Labor Standards Act and standard job entities related to wage management into vectors (e.g. two-dimensional vectors) and clustering the transformed vectors. In order to transform entities into vectors, an embedding technique widely known in the art, such as Word2Vec, may be used, and a clustering technique well known in the art may also be used to cluster the transformed vector.

Next, as shown in FIG. 17, clustering is also performed on entities related to the Labor Standards Act and in-house wage management, and one or more clusters 111 and 112 generated as a result are a specific region 110 of the XZ plane. can be placed in Clustering may be performed in the same or similar manner as described with reference to FIG. 16 .

Next, a step of adjusting the clusters (e.g. 91, 92, 111, 112) may be performed. The reasons for performing the adjustment are as follows. First, since the clusters ( eg 91, 92, 111, 112) are biased in the XY plane and the XZ plane, it is necessary to adjust the positions, and as shown in FIG. 18 , the same entity (eg wages) is a cluster in different positions This is because there may be duplicates in Hereinafter, it will be described with reference to FIG. 19 .

To coordinate the clusters (e.g. 91, 92, 111, 112), a representative entity within the cluster (e.g. wages) may be determined. The representative entity may be, for example, an entity (or an entity above the reference layer; see FIG. 7 ) extracted from a law above a reference layer (eg, a law of the highest layer, a law of the next highest layer) in the legal system, but the scope of the present disclosure is limited thereto it is not going to be

It is determined whether the representative entity (eg wages) overlaps the cluster in the XY plane and the cluster in the YZ plane, and in response to the overlap determination, the XY coordinates (ie, two-dimensional coordinates; eg 1, 2) of the representative entity (eg wages) , (0)) and XZ coordinates (ie, two-dimensional coordinates; eg 3, (0), 3) XYZ coordinates ( eg 2, 1, 1.5) may be calculated. The XYZ coordinates (ie, three-dimensional coordinates) may be determined in various ways, such as an intermediate point between two coordinates, a point having a minimum distance from a straight line formed of the two coordinates to an origin, and the like.

When the XYZ coordinates (e.g. 2, 1, 1.5) of the representative entity (e.g. wages) are calculated, the clusters (e.g. 91, 92, 111, 112) may be adjusted based on the calculated coordinates. For example, the positions of the first cluster 91 and the second cluster 111 may be adjusted according to the changed coordinates (e.g. 2, 1, 1.5) of the representative entity (e.g. wages). At this time, the first cluster 91 and the second cluster 111 may be simply merged, or may be reconfigured into a new cluster 121, and may be disposed adjacent to the changed coordinates ( eg 2, 1, 1.5) without merging. may be

In some embodiments, after the cluster adjustment step is performed, the cluster position readjustment step may be further performed. For example, the adjusted cluster (e.g. 121) is included within a specific region 120 of the XYZ space, and the position of the entire cluster (e.g. 121) may be globally readjusted so that the position within the region 120 is not biased.

Meanwhile, in some embodiments, entities in the cluster (e.g. 121) may be visualized in the form of a word cloud. That is, it may be visualized in a form in which color, size, and/or arrangement are different according to the importance of each entity. In this case, information transfer can be made more effectively.

Also, in some embodiments, the service providing system 1 may automatically generate and provide consulting information for a company based on the analysis information. Hereinafter, this embodiment will be described in more detail.

For example, the service providing system 1 may be configured between a first correspondence point of the law located on the X-axis, a second correspondence point of a standard job related to a target job located on the Y-axis, and a third correspondence point of the target job located on the Z-axis. Consulting information (or evaluation information) for the system of the target job may be generated based on the positional relationship. For example, when the distances from the origin to the first, second, and third corresponding points are the same or similar (eg, when the shape of the figure connecting the first, second, and third corresponding points is balanced), the service providing system ( 1) can generate consulting information indicating that the target job system is well established. In the opposite case, the service providing system 1 may generate consulting information informing that it is necessary to re-establish the system of the target job with reference to the standard job information. The principle that can generate such consulting information is as follows. Generally, the more difficult the job (eg a high-ranking managerial job), the more abstract the job form tends to be, so it is more likely to be related to the higher-level laws (eg the Labor Standards Act). of specific sub-tasks) tends to take on a more specific form of work, so it is highly likely to be related to lower-level laws (eg rules, precedents, etc.). In addition, since standard jobs are systematically well established, there is a tendency that the difficulty of the job and the level of related laws are generally proportional (eg, standard jobs with high difficulty are usually related to laws of higher classes, and the corresponding points of standard jobs and The corresponding point of the relevant law is located at a similar distance from the origin). Accordingly, when the position of the third correspondence point is compared with the positions of the first correspondence point and the second correspondence point, it can be automatically evaluated whether the target job is systematically well established.

As another example, the service providing system 1 may generate consulting information (or evaluation information) for the system of the target job based on the comparison result between the target job information and the standard job information. Specifically, the service providing system 1 may generate a list of target jobs that do not correspond to the standard job, or generate and provide information on the target job that does not match the system of the standard job.

A method of visualizing target job-related legal information according to some embodiments of the present disclosure has been described with reference to FIGS. 15 to 19 . As described above, the legal information related to the target job can be provided as visualized information together with the related standard job, so that the legal information can be provided more effectively.

Hereinafter, with reference to FIG. 20 , in an exemplary computing device 200 that can implement the service providing system 1 or its components (eg service platform 10, service server 11, etc.) according to some embodiments of the present disclosure. to explain about it.

20 is an exemplary hardware configuration diagram illustrating the computing device 200 .

As shown in FIG. 20 , the computing device 200 includes one or more processors 210 , a bus 230 , a communication interface 240 , and a memory (loading) for loading a computer program executed by the processor 210 . 220 , and a storage 250 for storing the computer program 260 . However, only components related to the embodiment of the present disclosure are illustrated in FIG. 20 . Accordingly, one of ordinary skill in the art to which the present disclosure pertains can know that other general-purpose components other than the components shown in FIG. 20 may be further included. That is, the computing device 200 may further include components other than those illustrated in FIG. 20 . Hereinafter, each component of the computing device 200 will be described.

The processor 210 controls the overall operation of each component of the computing device 200 . The processor 210 includes at least one of a central processing unit (CPU), a micro processor unit (MPU), a micro controller unit (MCU), a graphic processing unit (GPU), or any type of processor well known in the art of the present disclosure. may be included. In addition, the processor 210 may perform an operation on at least one application or program for executing the method/operation according to the embodiments of the present disclosure. The computing device 200 may include one or more processors.

Next, the memory 220 stores various data, commands and/or information. The memory 220 may load one or more programs 260 from the storage 250 to execute methods/operations according to embodiments of the present disclosure. For example, when the computer program 260 is loaded into the memory 220 , a module as shown in FIG. 2 may be implemented on the memory 220 . The memory 220 may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

Next, the bus 230 provides a communication function between components of the computing device 200 . The bus 230 may be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

Next, the communication interface 240 supports wired/wireless Internet communication of the computing device 200 . In addition, the communication interface 240 may support various communication methods other than Internet communication. To this end, the communication interface 240 may be configured to include a communication module well known in the technical field of the present disclosure.

Next, the storage 250 may non-temporarily store the at least one program 260 . The storage 250 is a non-volatile memory such as a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, or well in the art to which the present disclosure pertains. It may be configured to include any known computer-readable recording medium.

Next, the computer program 260 may include one or more instructions that, when loaded into the memory 220 , cause the processor 210 to perform a method/operation according to some embodiments of the present disclosure. there is. That is, the processor 210 may perform the method/operation according to some embodiments of the present disclosure by executing the one or more instructions.

For example, the computer program 260 performs an operation of interpreting legal information using an artificial intelligence model, an operation of interpreting standard job information using an artificial intelligence model, and an analysis result of legal information and an analysis result of standard job information. It may include instructions for performing an operation of deriving a law related to a specific standard job based on it. In this case, the analysis platform 20 according to some embodiments of the present disclosure may be implemented through the computing device 200 .

As another example, the computer program 260 performs an operation of obtaining relationship information between a standard job and a law analyzed using an artificial intelligence model, and an operation of providing a legal service for a target job based on the obtained relationship information. It may include instructions to In this case, the service platform 20 according to some embodiments of the present disclosure may be implemented through the computing device 200 .

As another example, the computer program 260 analyzes legal information and standard job information using an artificial intelligence model to derive a law related to a specific standard job and provides a legal service for a target job based on the derived result Instructions for performing the provided operation may be included. In this case, the service providing system 1 according to some embodiments of the present disclosure may be implemented through the computing device 200 .

The technical idea of the present disclosure described with reference to FIGS. 1 to 20 may be implemented as computer-readable codes on a computer-readable medium. The computer-readable recording medium may be, for example, a removable recording medium (CD, DVD, Blu-ray disk, USB storage device, removable hard disk) or a fixed recording medium (ROM, RAM, computer-equipped hard disk). can The computer program recorded on the computer-readable recording medium may be transmitted to another computing device through a network such as the Internet and installed in the other computing device, thereby being used in the other computing device.

In the above, even though all components constituting the embodiment of the present disclosure are described as being combined or operated in combination, the technical spirit of the present disclosure is not necessarily limited to this embodiment. That is, within the scope of the present disclosure, all of the components may operate by selectively combining one or more.

Although acts are shown in a particular order in the drawings, it should not be understood that the acts must be performed in the specific order or sequential order shown, or that all illustrated acts must be performed to obtain a desired result. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of the various components in the embodiments described above should not be construed as necessarily requiring such separation, and the described program components and systems may generally be integrated together into a single software product or packaged into multiple software products. It should be understood that there is

Although embodiments of the present disclosure have been described with reference to the accompanying drawings, those of ordinary skill in the art to which the present disclosure pertains may practice the present disclosure in other specific forms without changing the technical spirit or essential features. can understand that there is Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. The protection scope of the present disclosure should be interpreted by the following claims, and all technical ideas within the equivalent range should be interpreted as being included in the scope of the technical ideas defined by the present disclosure.

Claims (16)

1. An analysis platform that derives laws related to specific standard jobs by analyzing legal information and standard job information using an artificial intelligence model; and

   A service platform that provides legal services for a target job based on the information derived by the analysis platform,

   The analysis platform is

   a law interpreter for interpreting the legal information;

   a job interpreter for interpreting the standard job information; and

   Comprising a relationship analyzer for deriving a law related to the specific standard job by analyzing the relation between the standard job and the law based on the analysis result of the law interpreter and the analysis result of the job interpreter,

   Legal service delivery system.
2. According to claim 1,

   The standard job information is information collected from the National Competency Standards website,

   Legal service delivery system.
3. According to claim 1,

   The legal interpreter interprets the legal information through a Named Entity Recognition (NER) model,

   The NER model is implemented based on a BERT (Bidirectional Encoder Representations from Transformers) model and a Bi-LSTM-CRF (Bidirectional Long Short-Term Memory with a Conditional Random Field Layer) model,

   Legal service delivery system.
4. According to claim 1,

   The legal interpreter extracts a legal entity set from the legal information through a Named Entity Recognition (NER) model,

   The job interpreter extracts a standard job entity set from the standard job information through the NER model,

   The relationship analyzer is

   Deriving a law related to the specific standard job based on the similarity between the extracted legal entity set and the extracted standard job entity set,

   Legal service delivery system.
5. 5. The method of claim 4,

   Further comprising a dictionary interpreter for constructing a legal dictionary using the extracted legal entity set, and configuring a standard job dictionary using the extracted standard job entity set,

   The relationship analyzer is

   Deriving a law related to the specific standard job further based on the similarity between the configured legal dictionary and the configured standard job dictionary,

   Legal service delivery system.
6. 6. The method of claim 5,

   The dictionary interpreter is

   Construct the legal dictionary based on the explanatory information about the extracted legal entity set,

   Correcting the constructed legal dictionary using a Neural Tensor Network (NTN) model, and correcting the legal dictionary based on the degree of relevance between the explanatory information predicted through the NTN model and the extracted legal entity set,

   Legal service delivery system.
7. 5. The method of claim 4,

   The law interpreter classifies the extracted legal entity set into a legal actor entity set and a legal act entity set using the classification result of the NER model,

   The job interpreter also classifies the extracted standard job entity set into a job actor entity set and a job act entity set using the classification result of the NER model,

   The relationship analyzer is

   deriving a law related to the specific standard job based on a first degree of similarity between the legal actor entity set and the job actor entity set and a second degree of similarity between the legal act entity set and the job act entity set;

   Legal service delivery system.
8. 8. The method of claim 7,

   The relationship analyzer is

   calculating the first degree of similarity based on whether the legal actor entity and the job actor entity match and the degree of similarity between the vector for the legal actor entity and the vector for the job actor entity;

   A law related to the specific standard job further based on a first degree of relevance between the legal actor entity and the job act entity and a second degree of relationship between the job actor entity and the legal act entity predicted through a Neural Tensor Network (NTN) model to derive,

   Legal service delivery system.
9. According to claim 1,

   The relationship analyzer is

   In analyzing the relationship between the specific standard job and the specific law, determining the relevance between the specific standard job and the specific law further based on the relationship between the specific law and a higher job or a lower job of the specific standard job,

   Legal service delivery system.
10. According to claim 1,

    The service platform provides visualized information about the target job and related laws based on the information derived by the analysis platform, the target job on the space formed by the first axis, the second axis, and the third axis; generating the visualized information by arranging a plurality of entities for the relevant law and the relevant standard job of the target job;

    The first axis, the second axis, and the third axis have a corresponding relationship with target job information, legal information, and standard job information, respectively,

    Legal service delivery system.
11. 11. The method of claim 10,

    The correspondence relationship between the first axis and the target job information is determined based on the difficulty level of the target job,

    The correspondence relationship between the second axis and the legal information is determined based on a hierarchical system of laws,

    The correspondence relationship between the third axis and the standard job information is determined based on the difficulty level of the standard job,

    How to provide legal services.
12. 12. The method of claim 11,

    The service platform is

    The user of the legal service based on the positional relationship between the corresponding point of the target job located on the first axis, the corresponding point of the related law located on the second axis, and the corresponding point of the related standard job located on the third axis to create consulting information for

    How to provide legal services.
13. 11. The method of claim 10,

    The service platform is

    clustering and arranging a first plurality of entities for the target job and the related law on a plane formed by the first axis and the second axis;

    Clustering and disposing a second plurality of entities for the relevant laws and the relevant standard duties on a plane formed by the second axis and the third axis,

    determine whether a first representative entity of the first plurality of entities is the same as a second representative entity of the second plurality of entities;

    In response to determining that they are the same, calculating three-dimensional coordinates based on the two-dimensional coordinates of the first representative entity and the two-dimensional coordinates of the second representative entity,

    Adjusting the positions of the first cluster to which the first representative entity belongs and the second cluster to which the second representative entity belongs based on the calculated three-dimensional coordinates;

    How to provide legal services.
14. According to claim 1,

    The service platform is

    determining a standard job corresponding to the target job;

    Providing legal information related to the determined standard job as legal information related to the target job,

    How to provide legal services.
15. A method of providing legal services performed by at least one computing device, the method comprising:

    deriving a law related to a specific standard job by analyzing legal information and standard job information using an artificial intelligence model; and

    Comprising the step of providing legal services for the target job based on the derived result,

    The step of deriving a law related to the specific standard job is,

    interpreting the legal information using the artificial intelligence model;

    interpreting the standard job information using the artificial intelligence model; and

    Comprising the step of deriving a law related to the specific standard job based on the analysis result of the legal information and the analysis result of the standard job information,

    How to provide legal services.
16. combined with a computing device,

    deriving a law related to a specific standard job by analyzing legal information and standard job information using an artificial intelligence model; and

    Execute the step of providing legal services for the target job based on the derived result,

    The step of deriving a law related to the specific standard job is,

    interpreting the legal information using the artificial intelligence model;

    interpreting the standard job information using the artificial intelligence model; and

    Stored in a computer-readable recording medium, comprising the step of deriving a law related to the specific standard job based on the analysis result of the legal information and the analysis result of the standard job information,

    computer program.

Images