Methods and programs for monitoring bills and legal provisions

Abstract

A method for monitoring bills and legal regulations according to one embodiment of the present invention is a method for monitoring bills and legal regulations performed by a computing system including at least one memory and at least one processor, and includes the steps of storing template information including predetermined items, receiving basic information including reasons for proposing the bill and main contents from a user terminal, storing the basic information in an analysis server, forming extracted information from the basic information through text mining based on the predetermined items, generating regulatory impact analysis data based on the extracted information and the template information, and outputting a regulatory impact analysis interface for the bill or legal regulation to the user terminal based on the generated regulatory impact analysis data.

Description

[Technical field]

[0001] The present invention relates to a method and program for monitoring proposed legislation and legal provisions, and more particularly to techniques for providing regulatory impact analysis data. [Background technology]

[0002] Bills that are amended or proposed include government bills and private member bills.

[0003] When government legislation strengthens regulations, the government manually prepares a regulatory impact analysis to analyze what impact the regulation will have.

[0004] However, when regulations are weakened through government legislation, a separate regulatory impact analysis is not prepared.

[0005] On the other hand, in the case of parliamentary bills, no regulatory impact analysis is prepared, regardless of whether the proposed regulations are to be strengthened or weakened.

[0006] When a government bill is proposed, a Regulatory Impact Analysis is a document manually prepared by the government and provided to the public that contains an analysis of the name of the regulatory matter, regulatory text, delegated statute, type, legislative notice, background to the promotion and need for government intervention, regulatory objectives, regulatory content, regulated groups and stakeholders, cost-benefit analysis, whether or not an impact assessment can be conducted, whether or not sunsetting can be set, whether or not priority approval and ex post facto regulation can be applied, and so on.

[0007] As such, RIAs are currently only prepared when regulations are strengthened or new regulations are established in government legislation; no RIAs are prepared at all for parliamentary proposals, creating the problem that it is difficult to grasp the impact that regulations will have on related industries and companies.

[0008] In addition, currently, RIAs are prepared manually by humans, and the data cannot be said to be highly reliable. In particular, if the preparer is unable to find materials on relevant overseas cases and emergency legislation cases, the RIA will display "not applicable," providing incorrect information to the public. Summary of the Invention [Problem to be solved by the invention]

[0009] It is an object of the present invention to provide a method and program for a computing system to provide regulatory impact analysis data for proposed legislation to monitor legislation or legal provisions.

[0010] The object of the present invention is not limited thereto, and other objects not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0011] The monitoring method for bills or legal regulations according to the present invention is a monitoring method for bills and legal regulations performed by a computing system including at least one memory and at least one processor, and includes the steps of: storing template information including predetermined items; receiving basic information including reasons for proposing the bill and main contents from a user terminal; storing the basic information in an analysis server; forming extracted information from the basic information through text mining based on the predetermined items; generating regulatory impact analysis data based on the extracted information and the template information; and outputting a regulatory impact analysis interface for the bill or legal regulation to the user terminal based on the generated regulatory impact analysis data.

[0012] The step of forming the regulatory impact analysis data includes a step of generating regulatory impact analysis data by making the extracted information correspond to each of the predetermined items on the template information.

[0013] The specified items include the name of the regulated matter, regulatory text, delegated statute, type, legislative notice, promotion background, need for government intervention, regulatory objectives, regulatory content, regulated groups, stakeholders, cost-benefit analysis, whether or not an impact assessment is possible, whether or not sunsetting is possible, priority approval, whether or not ex post regulation is applicable, cost management system, regulated industries, adjacent industries, and related companies.

[0014] The step of generating the regulatory impact analysis data further includes a step of calculating a first relevance between the extracted information corresponding to each of the regulated group and stakeholders, the regulated industry, the adjacent industry, and the related enterprises and the proposed bill based on a predetermined similarity calculation formula, and generating regulatory impact analysis data for the first relevance.

[0015] The monitoring method for bills or legal provisions according to the present invention further includes a step of receiving information of the specific company provided to a corporate information providing server through an API (Application Programming Interface) provided by the corporate information providing server when logging in to the computing system with an account of a specific company, and the step of generating regulatory impact analysis data further includes a step of calculating a second relevance between the specific company and the bill based on a predetermined similarity calculation formula, a step of generating regulatory impact analysis data for the second relevance, a step of converting the second relevance regulatory impact analysis data into a percentage, and a step of outputting the percentage to the user terminal based on the information of the specific company, and the second relevance is included in the predetermined item.

[0016] The monitoring method for a bill or legal provision according to the present invention further includes a step of receiving information of the specific company provided by a corporate information providing server through an API (Application Programming Interface) provided by the corporate information providing server when logging in to the computing system with an account of a specific company, and the step of generating regulatory impact analysis data further includes a step of calculating the risk of the specific company due to the bill based on a predetermined first algorithm, a step of generating regulatory impact analysis data for the risk, a step of converting the risk regulatory impact analysis data into visual data based on the risk corresponding to the regulatory impact analysis data, and a step of outputting the visual data to the user terminal based on the information of the specific company, wherein the risk is included in the predetermined items, and the visual data includes saturation information corresponding to the risk.

[0017] The method for monitoring bills or legal provisions according to the present invention further includes the steps of: performing supervised learning through a learning model based on training data in which basic information of a first proposed bill, basic information of a first past bill, and first past regulatory impact analysis data are linked and stored; forming learning data through machine learning by the learning model; providing the learning data to an artificial intelligence module; when basic information of a second proposed bill, basic information of a second past bill, and second past regulatory impact analysis data are input, outputting second inference data based on the learning data transmitted from the learning model; forming feedback information based on a difference between the second inference data and a pre-stored ground truth set; and modifying parameters of the learning model based on the feedback information.

[0018] The step of generating the regulation impact analysis data includes a step of generating the regulation impact analysis data based on mining data acquired by text mining the basic information and the second inference data.

[0019] The monitoring method for bills or legal provisions according to the present invention further includes the steps of determining related overseas cases and similar legislative cases corresponding to the basic information using a predetermined second algorithm, extracting key content of the related overseas cases and similar legislative cases, transferring the key content to the user terminal, and outputting the key content to the user terminal.

[0020] When the basic information of the second proposed bill includes basic information on a member's bill, the predetermined items further include the political party and legislative inclination of the member who proposed the second bill.

[0021] The method of monitoring legislation or legal provisions according to the present invention is carried out by a computer program stored on a medium. Effect of the Invention

[0022] According to the bill and legal regulation monitoring method and program of the present invention, even when regulations are weakened by government intervention bills, it can act as a new opportunity for related industries or related companies and provide useful information for business operations through regulatory impact analysis data.

[0023] The bill and legal regulation monitoring method and program according to the present invention can provide useful information for operating a business through regulatory impact analysis data when a bill is proposed by a member of parliament or by analyzing the content of the relevant regulation before it is changed.

[0024] The method and program for monitoring bills and legal regulations according to the present invention can provide guidance to industries and businesses affected by the regulations.

[0025] According to the bill and law regulation monitoring method and program therefor of the present invention, it is possible to provide information on the relationship between a specific company and a corresponding regulation and the risk of a specific company due to the regulation.

[0026] According to the bill and legal provision monitoring method and program therefor of the present invention, information on related overseas cases and similar legislative cases can be automatically searched for and provided to a user.

[0027] The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description. [Brief description of the drawings]

[0028] [Figure 1] FIG. 1 is a schematic diagram of components that provide a method for monitoring bills and statutes according to one embodiment. [Diagram 2] FIG. 2 is a diagram for explaining an operation for generating regulation impact analysis data in which extraction information and predetermined template information correspond to each other according to an embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an interface in which template information is output to a user terminal according to an embodiment. [Figure 4] FIG. 4 illustrates a screen showing regulation impact analysis data corresponding to regulated groups and stakeholders, regulated industries, adjacent industries, and related companies generated and output to a user terminal according to one embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an operation of receiving a corporate information API from a corporate information providing server and outputting visual data on relevance and risk when logged in with a corporate account according to an embodiment. [Figure 6] FIG. 6 is a diagram illustrating a process of generating regulatory impact analysis data through artificial intelligence (AI) learning according to one embodiment. [Figure 7]FIG. 7 is a diagram illustrating the operation of generating regulatory impact analysis data through text mining and machine learning according to one embodiment. [Figure 8] FIG. 8 is a diagram illustrating an operation of generating inference data by machine learning according to one embodiment. [Figure 9] FIG. 9 is a diagram illustrating what the output values ​​are depending on whether there are related overseas cases and similar legislative cases according to one embodiment. [Figure 10] FIG. 10 is a diagram illustrating an operation of adding template information when basic information on a member's proposal is received according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0029] The advantages and features of the present invention, and the methods for achieving them, will become clear from the detailed description of the embodiments described below in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, and may be embodied in various different forms. The present embodiments are provided solely for the purpose of making the disclosure of the present invention complete and fully conveying the scope of the present invention to those skilled in the art to which the present invention pertains. The present invention is only defined by the scope of the claims.

[0030] The terms used in this specification are for describing the embodiments and are not intended to limit the present invention. In this specification, the singular form includes the plural form unless otherwise specified in the text. The terms "comprises" and / or "comprising" used in the specification do not exclude the presence or addition of one or more other components in addition to the components mentioned. The same reference numerals throughout the specification refer to the same components, and "and / or" includes each and every combination of one or more of the components mentioned. Even if "first", "second", etc. are used to describe various components, it goes without saying that these components are not limited by these terms. These terms are simply used to distinguish a certain component from another component. Therefore, it goes without saying that the first component mentioned below is also the second component within the technical idea of ​​the present invention.

[0031] Unless otherwise defined, all terms (including technical and scientific terms) used herein are used as commonly understood by those of ordinary skill in the art to which the present invention belongs. Furthermore, terms defined in commonly used dictionaries are not idealized or overly interpreted unless expressly defined otherwise.

[0032] Meanwhile, the "bill" or "legal provision" described in the present invention means various legal types as commonly understood. Specifically, the "bill" or "legal provision" in the present invention means the constitution, law, enforcement decree, ministerial ordinance, enforcement regulations, ordinances, rules, regulations, etc. Also, the "government legislation", "legislator's bill", or "bill" described in the present invention means a matter proposed for the above-mentioned "bill" or "legal provision".

[0033] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0034] FIG. 1 is a diagram illustrating components for providing a monitoring method for bills and legal provisions according to one embodiment of the present invention, and FIG. 2 is a diagram illustrating an operation for generating regulatory impact analysis data in which extracted information and predetermined template information correspond to one embodiment of the present invention.

[0035] As shown in Figures 1 and 2, in the method for monitoring bills and legal regulations performed by a computing system 200 including at least one memory and at least one processor, a template information storage unit 210, a basic information receiving unit 220, an analysis server 230, an extracted information forming unit 240, a regulatory impact analysis data generating unit 250, and a user terminal 100 are provided to perform the operations of the present invention.

[0036] The user terminal 100 includes all kinds of handheld-based wireless communication devices connected to a web server via a network, such as a mobile phone, a smartphone, a PDA (Personal Digital Assistant), a PMP (Portable Multimedia Player), a tablet PC, etc., and is one of the digital devices equipped with memory means, a microprocessor, and computing capabilities, such as a personal computer (e.g., a desktop computer, a notebook computer, etc.), a workstation, a PDA, a web pad, etc.

[0037] Meanwhile, the user terminal 100 includes a display on which an interface is output, a communication module, and at least one processor provided to run applications on the user terminal.

[0038] Computing system 200, on the other hand, generally refers to a computer-related entity, such as hardware, a combination of hardware and software, or software.

[0039] Template information including predetermined items is stored in the template information storage unit 210 in the computing system 200 (S210).

[0040] The template information is updated for one or more items by an authorized administrator within the computing system 200 .

[0041] The template information includes the name of the regulated matter, regulatory text, delegated statute, type, legislative notice, background to the promotion and need for government intervention, regulatory objectives, regulatory content, regulated groups and stakeholders, cost-benefit analysis, whether or not an impact assessment is possible, whether or not sunsetting is possible, whether or not priority approval and ex post regulation can be applied, cost management system, regulated industry, adjacent industries, related companies, relevance, risk level, related overseas cases / similar legislative cases, political party of the relevant lawmaker, legislative inclinations, and related information.

[0042] The basic information receiving unit 220 in the computing system 200 receives basic information including the reasons for proposing the bill and the main contents from the user terminal 100 (S220).

[0043] The main content refers to the revised content of the proposed bill.

[0044] Initiated Bill means a Government bill and / or a Member's bill.

[0045] The basic information received is the basic information provided when a government bill or a member's bill (hereinafter referred to as a "bill") is changed or proposed, and includes the responsible department, person in charge, person in charge's contact information, date of legislative notice, bill name, proposer (date of proposal), standing committee (department in charge), current status of the National Assembly (date of promotion), current resolution status (date of resolution), bill number (alternative number), reasons for proposing the bill / main contents, and contents of the current law and revised law.

[0046] Meanwhile, the received basic information is stored in the analysis server 230 in the computing system 200 (S230).

[0047] The analysis server 230 receives the API provided by the business information providing server 300 .

[0048] The business information providing server 300 refers to a server that provides business information.

[0049] The API provided by the business information providing server 300 is an API provided by the Business Information Electronic Disclosure System (DART).

[0050] The API provided by the business information server 300 is an API provided by Korea evaluation data (KoDATA).

[0051] Meanwhile, the basic information stored in the analysis server 230 is transmitted to the extraction information forming unit 240 .

[0052] The extracted information forming unit 240 performs text mining on the received basic information to generate mining data, and performs machine learning, if necessary, to generate inference data.

[0053] The extracted information forming unit 240 forms extracted information from the data generated by such text mining or machine learning (S240).

[0054] Text mining is the process of mining unstructured data. Mining is the process of extracting statistically significant concepts and characteristics from data and deriving high-quality information such as patterns and trends between them.

[0055] Machine learning refers to methods that enable machines to teach themselves through data.

[0056] The regulation impact data generating unit 250 generates regulation impact analysis data based on the extracted information and the template information.

[0057] The extracted information is matched with predetermined items stored in the template information storage unit 210 (S250).

[0058] In the regulation impact data generating unit 250, the extracted information and the template information are matched to generate regulation impact analysis data (S260).

[0059] The regulation impact analysis data thus generated is output and displayed on the user terminal 100 (S270).

[0060] FIG. 3 is a diagram showing an interface in which template information is output to the user terminal 100 according to an embodiment of the present invention.

[0061] The predetermined items in the template information storage unit 210 shown in the output interface are the name of the regulated business (D310), the regulation article (D320), the delegated act (D330), the type (D340), the legislative notice (D350), the promotion background and the necessity of government intervention (D360), the regulation content (D370), the regulated group and the interested party (D380), the objective of the regulation (D390), the possibility of impact assessment (D3100), and the cost-benefit analysis (D3100). Includes analysis (D3110), whether sunsetting is possible (D3120), whether priority acceptance and ex post regulation are applicable (D3130), cost management system, impact (D3140), regulated industries (D3150), adjacent industries (D3160), related companies (D3170), primary relevance, secondary relevance (D3180), risk (D3190), related overseas cases / similar legislative cases, political party of the relevant lawmaker, legislative inclination, and related information.

[0062] Specifically, the regulated business name (D310) means the business name indicating the content of the regulation.

[0063] Specifically, the regulatory provisions (D320) refer to the names and legal provisions of the laws, regulations, notices, etc. to which the bill pertains.

[0064] Specifically, delegated acts (D330) refer to the name of the higher-level acts that serve as the basis for regulation, and the legal provisions.

[0065] Specifically, the type (D340) indicates whether the proposal will strengthen and / or weaken regulations, or whether the proposal will create and / or abolish regulations.

[0066] Specifically, Legislative Notice (D350) refers to the legislative notice period for the bill.

[0067] Specifically, the promotion background and the need for government intervention (D360) refers to the socio-economic background in which the problem to be solved through the creation or strengthening of regulations arose, and in this case, it indicates the reason why government intervention is necessary.

[0068] Specifically, the content of the regulation (D370) means a summary of the content of the regulatory affairs.

[0069] Specifically, regulated groups and stakeholders (D380) refer to regulated persons, stakeholders, institutions, etc. that are directly subject to regulation.

[0070] Specifically, the regulatory objectives (D390) refer to the goals that are to be achieved through the introduction of regulations.

[0071] Specifically, the impact assessment (D3100) refers to the applicability of technology, competition, and small and medium-sized enterprises.

[0072] Specifically, cost-benefit analysis (D3110) refers to the results of cost calculations.

[0073] Specifically, the sunset setting option (D3120) refers to whether or not a regulation expiration date and a review deadline can be set.

[0074] Specifically, the applicability of priority approval and ex post regulation (D3130) refers to the applicability of comprehensive negative regulation.

[0075] Specifically, the degree of impact (D3140) is an indicator that shows the extent to which the proposed bill will have an impact on industries, based on the size of the industry to be regulated, whether there are a large number of adjacent industries, and whether there are a large number of related companies, as a result of analyzing the extracted information on industries, adjacent industries, and related companies that will be regulated by the proposed bill.

[0076] Specifically, regulated industries (D3150) refers to the group of industries that will be regulated by the proposed bill.

[0077] Specifically, adjacent industries (D3160) refer to industries that are the same as or adjacent to the relevant regulation.

[0078] Specifically, Affiliated Companies (D3170) refers to the list of domestic and overseas affiliated companies within the relevant regulated industry.

[0079] Specifically, the first relevance level means that the relevance between the regulated groups and stakeholders (D380), regulated industries (D3150), adjacent industries (D3160), and related companies (D3170) in the template information and the relevant regulation is converted into a percentage based on the similarity calculation formula.

[0080] Specifically, the second relevance (D3180) means the relevance between the relevant regulation and a specific company (ID) logged in with a corporate account converted into a percentage.

[0081] Specifically, the risk level (D3190) indicates the risk of increased regulation of a specific company (ID) logged in using a corporate account.

[0082] Specifically, cost management refers to the applicability of cost management and cost benefits.

[0083] Specifically, the relevant overseas cases and similar legislative cases refer to the search results of overseas cases related to the relevant regulatory initiative and similar legislative cases.

[0084] Specifically, the political party of the relevant member means the political party of the member who proposed the relevant bill when basic information on the bill is received.

[0085] Specifically, the legislative inclination of a lawmaker in question means that when basic information about a lawmaker's bill is received, the legislative inclination of the lawmaker who proposed the bill is expressed as a regulatory inclination, a regulatory inclination, etc.

[0086] The form of the interface output in FIG. 3 is merely one embodiment of the present invention, and there is no limitation on the form of the modified interface and the operation of the modified interface.

[0087] At least one component is added or deleted in accordance with the performance of the components in Fig. 3. In addition, it will be easily understood by a person having ordinary skill in the art that the relative positions of the components are changed in accordance with the performance or structure of the system.

[0088] FIG. 4 is a diagram showing an interface in which regulatory impact analysis data (D470) corresponding to regulated groups and stakeholders (D430), regulated industries (D440), adjacent industries (D450), and related companies (D460) is generated and output to a user terminal 100 according to one embodiment of the present invention.

[0089] The regulation impact analysis data (D470) on the regulated groups and stakeholders (D430), regulated industries (D440), adjacent industries (D450) and related companies (D460) on the template information includes an extracted information list (D410).

[0090] In addition, the regulatory impact analysis data (D470) on the regulated groups and stakeholders (D430), regulated industries (D440), adjacent industries (D450), and related companies (D460) on the template information includes a conversion of the relevance to the relevant regulation into a percentage based on a similarity calculation formula (D420) (this is referred to as the "first relevance").

[0091] The similarity calculation formula includes, for example, at least one of a mean square difference similarity, a cosine similarity, and a Pearson similarity formula.

[0092] FIG. 5 is a diagram illustrating an operation of receiving a corporate information API from a corporate information providing server and outputting visual data on relevance and risk when logged in with a corporate account according to an embodiment.

[0093] The computing system 200 is connected by logging in with a company account (S510).

[0094] When logging in using a corporate account, the account is ID-ized and managed by the administrator.

[0095] In this case, the administrator can grant permissions to the data. For example, the administrator can block the analysis data of other companies by company ID, or mask data that cannot be disclosed by certain subjects, such as industry groups, legislative bodies, regulating parties, and regulated parties.

[0096] On the other hand, when logging in with a corporate account, domestic and overseas companies are categorized according to their domestic and overseas characteristics and given authority. For example, the characteristics categorized according to domestic and overseas are whether or not they support a business.

[0097] When the user logs in with a corporate account in this manner, the analysis server 200 receives the API provided by the corporate information providing server 300 (S520).

[0098] The API provided by the business information providing server 300 is an API provided by the Business Information Electronic Disclosure System (DART).

[0099] When an API provided by the Digital Asset Management System (DART) is received, the received API is used to search for and collect in real time the digital asset management system (DART)-registered corporate disclosure information.

[0100] The extracted information forming unit 240 forms extracted information for the second relevance level and risk level, and the regulation impact analysis data generating unit 250 generates regulation impact analysis data corresponding to the extracted information and risk level (S530).

[0101] The second relevance is calculated based on a similarity calculation formula.

[0102] The similarity calculation formula includes, for example, at least one of the mean square difference similarity, the cosine similarity, and the Pearson similarity formula.

[0103] The degree of risk is calculated based on a predetermined algorithm.

[0104] The predetermined first algorithm is an algorithm which outputs a "low" risk level when regulations are relaxed or tightened and the second degree of association is between 0% and 30%, outputs a "medium" risk level when regulations are tightened and the second degree of association is between 30% and 60%, and outputs a "high" risk level when regulations are tightened and the second degree of association is 60% or more.

[0105] The regulatory impact analysis data regarding the second relevance is converted into a percentage and displayed (S540).

[0106] On the other hand, the second relevance level is displayed by other numerical values ​​in addition to the percentage conversion according to a predetermined algorithm.

[0107] For example, the impact may be categorized into a range from 1 to 5, with a higher impact indicated by a number closer to 5 and a lower impact indicated by a number closer to 1.

[0108] The risk-related regulatory impact analysis data can be converted into visual data such as icons and figures that are displayed with different color saturation according to the risk (S550).

[0109] For example, if the risk level is "high", it will be displayed using Hue: 0 (red), rgb(255, 51, 51), hex code(#ff3333); if it is "medium", it will be displayed using Hue: 60 (yellow), rgb(255, 255, 51), hex code(#ffff33); if it is "low", it will be displayed using Hue: 225 (blue), rgb(51, 51, 255), hex code(#3333ff).

[0110] The converted visual data is output to the user terminal 100 (S560).

[0111] FIG. 6 is a diagram illustrating a process of generating regulatory impact analysis data through artificial intelligence (AI) learning according to one embodiment.

[0112] The training data is data in which basic information of the first proposed bill, basic information of the first past bill, and the first past regulatory impact analysis data and the first inference data are linked and stored (S610).

[0113] The learning model performs supervised learning using such training data (S620).

[0114] The learning model forms learning data through machine learning and provides it to the artificial intelligence module (S630).

[0115] Thereafter, when basic information of a second proposed bill, basic information of a second past bill, or second past regulatory impact analysis data is input to the artificial intelligence module, the artificial intelligence module outputs second inference data based on the learning data transmitted to the artificial intelligence module (S640).

[0116] The output inference data is compared with a pre-stored ground truth set to form feedback information (S650).

[0117] The feedback information modifies or tunes the parameters of the learning model (S660).

[0118] The parameters of the learning model refer to weight information of each layer included in the learning model, etc.

[0119] Supervised learning is the learning of mapping between input and output, and is applied when input and output pairs are given as data. For example, when a computer is trying to recognize a license plate at the entrance to a parking lot, if the license plate is contaminated, it cannot be recognized properly. In this case, various contaminated license plate examples and normal license plates are trained as input and output pairs to improve the license plate recognition rate.

[0120] The learning model refers to an artificial intelligence model trained based on deep learning, and as an example, refers to a model trained using a Convolutional Neural Network (CNN).

[0121] In addition, the learning model includes at least one algorithm among Natural Language Processing (NLP), Random Forest (RF), Support Vector Machine (SVC), eXtra Gradient Boost (XGB), Decision Tree (DC), Knearest Neighbors (KNN), Gaussian Naive Bayes (GNB), Stochastic Gradient Descent (SGD), Linear Discriminant Analysis (LDA), Ridge, Lasso, and Elastic net.

[0122] FIG. 7 is a diagram for explaining an operation of generating regulation impact analysis data by text mining and machine learning according to an embodiment.

[0123] The basic information receiving unit 220 receives basic information about a proposed bill (S710).

[0124] When the basic information receiving unit 220 receives the basic information, the extracted information forming unit 240 extracts text, which is non-fixed-form data, through text mining to form mined data (S720).

[0125] Meanwhile, when the basic information is received by the basic information receiving unit 220, the extraction information forming unit 240 provides learning data to the artificial intelligence module through machine learning, and when the basic information of the bill is input based on the provided learning data, inference data can be formed (S730).

[0126] The extracted information forming unit 240 obtains the mining data and inference data thus formed (S740).

[0127] When the mining data and inference data are obtained, they are transmitted to the regulation impact data generation unit, which generates regulation impact analysis data (S750) based on predetermined template information (D710).

[0128] FIG. 8 is a diagram illustrating an operation of generating inference data by machine learning according to one embodiment.

[0129] As shown in FIG. 8, the training data is learned by a learning model to form inference data.

[0130] The learning model of the training data (D810) uses Natural Language Processing (NLP) for language processing (tokenization, refinement and normalization, context analysis) (S810), and uses Convolutional Neural Network (CNN) for video / image processing (attached image / diagram analysis, imaged text analysis) (S820).

[0131] Specifically, tokenization is a text preprocessing process and is classified into sentence tokenization and word tokenization. Sentence tokenization refers to the task of separating sentences in a text, and word tokenization refers to the task of separating words into tokens by characters.

[0132] A token, on the other hand, can be defined as a meaningful unit.

[0133] Specifically, refining means removing noise data from a corpus that you have. A corpus, on the other hand, is a collection of text that consists of words and sentences.

[0134] Specifically, normalization means combining words that are expressed differently into the same word.

[0135] Specifically, context analysis refers to the analytical process of grasping the context during natural language processing, expressing words as numbers, and separating them into vectors to make them understandable to machines.

[0136] Specifically, image / chart analysis is an analysis that learns directly from data and uses patterns to classify images / charts, and is particularly useful for looking for patterns to recognize images / charts.

[0137] Specifically, imaged text analysis is a technique that recognizes imaged text using a deep learning-based model, and involves a preprocessing step that changes image metadata such as brightness and color to make the characters more visible, a character detection step that locates the locations of characters and encloses them in bounding boxes, and a character recognition step that determines the content of the characters within the bounding boxes.

[0138] The data that has passed through the natural language processing and video / image processing learning models is then retrieved (S830).

[0139] Such ordered data is formed as inference data (D820).

[0140] FIG. 9 is a diagram for explaining what the output value is depending on whether or not there are related overseas cases and similar legislative cases according to an embodiment.

[0141] The basic information receiving section receives basic information about the bill (S910).

[0142] In the automatic search step for related overseas cases and similar legislative cases, a predetermined second algorithm is used to automatically search for overseas cases and similar legislative cases related to the basic information of the bill received by the basic information receiving unit 220 (S920).

[0143] The predetermined second algorithm in the step of automatically searching for such related overseas cases and similar legislative cases includes at least one of similarity calculation formulas, for example, mean square difference similarity, cosine similarity, and Pearson similarity formula.

[0144] In addition, the second predetermined algorithm for the step of automatically searching for such related overseas cases and similar legislative cases includes an operation of automatically searching for keywords on an Internet server and searching for output values.

[0145] On the other hand, the method of automatically searching and extracting keywords is carried out by using text mining or machine learning natural language processing (NLP) on basic information about the bill.

[0146] Meanwhile, the main contents of related overseas cases include Internet newspaper articles, broadcasting contents, and overseas legislative cases.

[0147] On the other hand, the main contents of similar legislative cases include the legal provisions, the titles of the legal provisions, and the contents of the legal provisions.

[0148] On the other hand, similar legislative cases include both domestic and overseas similar legislative cases.

[0149] Legal provisions include not only provisions of laws but also subordinate laws such as enforcement orders and enforcement regulations.

[0150] In the automatic search for related overseas cases and similar legislative cases, if there are no related overseas cases and similar legislative cases, a message indicating that there is no match is displayed on the user terminal 100 (S930).

[0151] Meanwhile, if there are related overseas cases and similar legislative cases, the main contents of the related overseas cases and similar legislative cases can be calculated and displayed on the user terminal (S940).

[0152] The key content calculation is based on a text summarization model.

[0153] A text summarization model refers to either an extraction model that generates sentences by combining words extracted from a document, or a generative abstraction model that creates sentences by using words or expressions that are not used in the document, as long as the meaning is not changed.

[0154] The server in the computing system 200 receives the API including the main content information thus calculated.

[0155] The API of the main contents thus received is transmitted to and outputted to the user terminal 100 for display.

[0156] FIG. 10 is a diagram illustrating an operation of adding template information when basic information on a member's proposal is received according to an embodiment.

[0157] In the template information storage unit 210 in the computing system 200, predetermined template items are stored by an administrator (S1010).

[0158] The basic information receiving unit 220 receives basic information about the bill.

[0159] The basic information of a bill received by the basic information receiving unit 220 is basic information on a government bill or basic information on a member's bill.

[0160] The basic information receiving unit 220 separates the basic information on the legislative proposals of the government and the legislator, and receives the basic information on the legislator's proposals (S1020).

[0161] When the basic information receiving unit 220 receives basic information on a member's bill, the template storing unit 210 further stores the political party and legislative tendency items of the member who proposed the bill (S1030).

[0162] The extracted information forming unit 240 further performs a process of classifying the party, legislative inclination, and purpose of proposing the bill of the relevant lawmaker through text mining or machine learning based on the lawmaker information of the lawmaker who proposed the bill.

[0163] The extracted information forming unit 240 forms extracted information regarding the political party and legislative inclination of the added legislators (S1040).

[0164] The regulation impact analysis data generating unit 250 generates regulation impact analysis data by associating the extracted information with the political party and legislative tendency template information of the legislator (S1050).

[0165] Alternatively, the operations performed by such methods may be carried out by a computer program stored on a medium.

[0166] According to the present invention, a method or device for monitoring new bills or legal provisions can be provided that can automatically generate a regulatory impact analysis report to provide users with the impact of the relevant regulations not only when a government bill is newly created or strengthened, but also when a government bill is weakened or a private member's bill is proposed, in order to monitor bills or legal provisions.

[0167] The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

[0168] The steps of a method or algorithm described in relation to the embodiments of the present invention may be embodied directly in hardware, in a software module executed by hardware, or in a combination of both, such as a Random Access Memory (RAM), 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, a CD-ROM, or any other form of computer readable storage medium well known in the art to which the present invention pertains.

[0169] Although the embodiments of the present invention have been described above with reference to the accompanying drawings, those skilled in the art to which the present invention pertains will understand that the present invention can be embodied in other specific forms without changing the technical spirit or essential features of the present invention. Therefore, it will be understood that the embodiments described above are merely illustrative and not restrictive in all respects.

Claims

1. 1. A method of monitoring for bills and statutes performed by a computing system including at least one memory and at least one processor, comprising: saving template information including predetermined items; receiving basic information including the reasons for proposing the bill and the main contents of the bill from a user terminal; storing the basic information in an analysis server; forming extracted information from the basic information through text mining based on the predetermined items; generating regulatory impact analysis data based on the extracted information and the template information; and outputting a regulatory impact analysis interface for the bill or legal provision to a user terminal based on the generated regulatory impact analysis data.

2. 2. The method for monitoring bills and legal provisions as described in claim 1, wherein the step of forming the regulatory impact analysis data includes a step of matching the extracted information to each of the predetermined items on the template information to generate regulatory impact analysis data.

3. The method for monitoring bills and legal provisions as described in claim 1, characterized in that the specified items include the name of the regulatory affairs, regulatory provisions, delegated acts, types, legislative notices, promotion background, need for government intervention, regulatory objectives, regulatory content, regulated groups, stakeholders, cost-benefit analysis, whether or not an impact assessment is possible, whether or not sunsetting is possible, priority acceptance, whether or not ex post regulation is applicable, cost management system, regulated industries, adjacent industries, and related companies.

4. The method for monitoring bills and legal provisions as described in claim 3, characterized in that the step of generating the regulatory impact analysis data further includes a step of calculating a first relevance between the extracted information corresponding to each of the regulated groups and stakeholders, the regulated industry, the adjacent industry, and the related companies and the proposed bill based on a predetermined similarity calculation formula, and generating regulatory impact analysis data for the first relevance.

5. The method further includes receiving information on the specific company provided to a corporate information providing server through an API provided by the corporate information providing server when the specific company is logged into the computing system with an account of the specific company; The step of generating regulatory impact analysis data comprises: calculating a second degree of association between the specific company and the bill based on a predetermined similarity calculation formula; generating regulatory impact analysis data for the second relevance; converting the second relevance regulatory impact analysis data into a percentage; and outputting the percentage to the user terminal based on information of the specific company.

4. The method of claim 3, wherein the second relevance is included in the predetermined item.

6. The method further includes receiving information on the specific company provided by a corporate information providing server through an API provided by the corporate information providing server when the specific company is logged into the computing system with an account of the specific company; The step of generating regulatory impact analysis data comprises: calculating a risk level of the particular company due to the bill based on a first predetermined algorithm; generating regulatory impact analysis data for said risk; converting the risk regulation impact analysis data into visual data based on the risk corresponding to the regulation impact analysis data; outputting the visual data to the user terminal based on information of the specific company; The risk level is included in the predetermined item, 4. The method of claim 3, wherein the visual data includes saturation information corresponding to the degree of danger.

7. A step of performing supervised learning through a learning model based on training data in which basic information of the first proposed bill, basic information of the first past bill, and the first past regulatory impact analysis data and the first inference data are stored in cooperation with each other; A step of forming learning data by machine learning the learning model; providing the training data to an artificial intelligence module; When basic information of a second proposed bill, basic information of a second past bill, and second past regulatory impact analysis data are input, outputting second inference data based on the learning data transmitted from the learning model; forming feedback information based on a difference between the second inference data and a pre-stored ground truth data set; 7. The method of claim 5 or 6, further comprising the step of modifying parameters of the learning model based on the feedback information.

8. The method for monitoring bills and legal provisions as described in claim 7, characterized in that the step of generating the regulatory impact analysis data includes a step of generating the regulatory impact analysis data based on mining data obtained by text mining the basic information and the second inference data.

9. determining relevant foreign cases and similar legislative cases corresponding to the basic information using a second predetermined algorithm; extracting the main contents of the relevant overseas cases and similar legislative cases; transferring the main content to the user terminal; 8. The method of claim 7, further comprising the step of: outputting the summary to the user terminal.

10. The method for monitoring bills and legal provisions as described in claim 7, characterized in that when the basic information of the second proposed bill includes basic information on the member's bill, the specified items further include the political party and legislative inclination of the member who proposed the second bill.

11. A computer program stored on a medium for causing the computer to carry out a method according to any one of claims 1 to 10.

Images