KR20210155501A - Receivable recovery support system for medium-small enterprise account receivable bond decrease and bad debt prevention based on big data - Google Patents

Abstract

The present invention relates to a big data-based trade receivable recovery support system for preventing reduction and weakness of trade receivables of small and medium-sized businesses, which comprises: a collection/security/storage unit (122) for allowing collected data to be completed with a security and de-identification process so as to be stored; and a trade receivable recovery predicting module (123b) including a company financial data analysis module and a company transaction data analysis module (123b-2).

Description

Big data-based trade receivable recovery support system for medium-small enterprise account receivable bond decrease and bad debt prevention based on big data

The present invention relates to a big data-based trade receivable recovery support system for reducing trade receivables of SMEs and preventing insolvency. It is about a big data-based trade receivable collection support system for reducing trade receivables of small and medium-sized enterprises and preventing insolvency by providing meaningful analysis information to customers.

For SMEs, efficient asset management and stabilization of cash flow are very important issues.

SMEs need to systematize work management for the maintenance and repair of their real assets, such as factories and buildings.

At the same time, management of cash assets such as trade receivables has more important management value than real assets from the standpoint of corporate bankruptcy management and permanence maintenance.

However, the system for managing assets such as trade receivables of such companies is usually not systematized, and it is not easy for managers to understand the detailed management of large-scale corporate assets. Managers usually receive brief reports, and the reality is that it is not possible to specifically analyze the cost or time spent for the company.

Accordingly, in the technical field, it is required to develop a technology that can effectively respond to the reduction of the receivables collection time and cost by using analysis information that can prepare for the reduction of trade receivables and insolvency.

The present invention is to solve the above problems, and a big data-based trade receivable recovery support system for reducing trade receivables of SMEs and preventing insolvency in order to provide a predictive analysis model of trade receivables collection based on corporate finance, transaction, and trade receivable data. is to provide

In addition, the present invention is to provide an industry-independent corporate transaction pattern analysis model to provide a big data-based account receivable recovery support system for reducing the receivables of SMEs and preventing insolvency.

In addition, the present invention is to provide a big data-based trade receivable collection support system for reducing the trade receivables of small and medium-sized enterprises and preventing insolvency so as to provide a prediction of trade receivables collection based on a corporate transaction pattern.

In addition, the present invention is to provide an intelligent trade receivable collection support service and system to provide a big data-based trade receivable support system for reducing trade receivables of small and medium-sized enterprises and preventing insolvency.

However, the objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned will be clearly understood by those skilled in the art from the following description.

In order to achieve the above object, the big data-based trade receivable collection support system for reducing trade receivables of small and medium-sized enterprises and preventing insolvency according to an embodiment of the present invention is, In the trade receivable collection support system that collects corporate financial data, corporate transaction data, and external (public) data 112 as customer location data, court case data, and other public data as ), the data collected for analysis a collection/security/storage unit 122 that stores the collected data through security and de-identification processes by performing pre-processing; and a receivables collection prediction module (123b); Including, the accounts receivable collection prediction module (123b) collects corporate financial data, performs basic sales and purchase analysis, and corporate financial data analysis module (123b-) for performing additional data analysis related to corporate finance One); and a corporate transaction data analysis module (123b-2) for modularizing an analysis algorithm so that information on a transaction pattern and transaction volume can be calculated using a network analysis technique for corporate transaction data; It is characterized in that it includes.

In this case, in the big data-based trade receivable recovery support system for reducing trade receivables of small and medium-sized enterprises and preventing insolvency according to another embodiment of the present invention, the trade receivables collection prediction module 123b is the start data for generating sales among the corporate transaction data. a bond data analysis module (123b-3) for classifying as bonds until payment collection, analyzing them as bond management data, and classifying and analyzing them as non-performing bonds when the scheduled collection date is exceeded; It is characterized in that it further comprises.

In addition, in the big data-based trade receivable recovery support system for reducing trade receivables and preventing insolvency of small and medium-sized enterprises according to another embodiment of the present invention, the trade receivables prediction module 123b is, When it is collected through legal acts (such as registration of default or court litigation) for this reminder and collection, the collection data analysis module 123b-4 modularizes so as to analyze the collection case and collection pattern; It is characterized in that it further comprises.

In addition, in the big data-based trade receivable collection support system for reducing trade receivables and preventing insolvency of SMEs according to another embodiment of the present invention, the trade receivables collection prediction module 123b classifies whether the receivables match the collection pattern. Thus, the recovery grade calculation module (123b-5) for calculating the recovery grade according to the state of each bond; It is characterized in that it further comprises.

In addition, the big data-based trade receivable recovery support system for reducing trade receivables and preventing insolvency of SMEs according to another embodiment of the present invention is (1) corporate financial data analysis, (2) corporate transaction data analysis, (3) bonds In addition to the receivables collection prediction module 123b that performs data analysis, (4) recovery data analysis, (1) spatiotemporal pattern analysis, (2) relationship pattern analysis, (3) financial ratio pattern analysis, ( 4) a big data pattern analysis model 123a for performing recovery pattern analysis; It is characterized in that it further comprises.

In addition, the big data-based trade receivable recovery support system for reducing trade receivables and preventing insolvency of SMEs according to another embodiment of the present invention is a customer search, customer monitoring, business insolvency analysis, and collection in order to perform a trade receivable recovery support service Receivables collection support service module 124a that performs predictive analysis, case classification, CRUD (Create, Read, Update, Delete), standard information management, statistical information management a service unit 124 having a manager portal module 124c for performing a bond collection case management module 124b, authentication/authorization management, user management, service management, and API management; It is characterized in that it further comprises.

The big data-based trade receivable collection support system for reducing trade receivables of small and medium-sized enterprises and preventing insolvency according to an embodiment of the present invention has an effect of providing an analysis model for predicting trade receivables collection based on corporate finance, transaction, and trade receivable data.

In addition, the big data-based trade receivable recovery support system for reducing trade receivables of SMEs and preventing insolvency according to another embodiment of the present invention is for reducing trade receivables of SMEs and preventing insolvency in order to provide an industry-independent corporate transaction pattern analysis model It is possible to provide a big data-based trade receivable collection support service. In addition, the big data-based trade receivable collection support system for reducing trade receivables and preventing insolvency of small and medium-sized enterprises according to another embodiment of the present invention, corporate transaction pattern-based trade receivables collection It is possible to provide a big data-based trade receivable collection support service for reducing trade receivables of SMEs to provide prediction and preventing insolvency. The data-based trade receivable collection support system may provide an intelligent trade receivable collection support service.

1 is a view showing a big data-based account receivable recovery support system 100 for reducing and preventing insolvency of trade receivables of small and medium-sized enterprises according to an embodiment of the present invention.
2 is a view showing a service concept by the big data-based trade receivable collection support system 100 for reducing and preventing insolvency of trade receivables of small and medium-sized enterprises according to an embodiment of the present invention.
FIG. 3 is a hierarchical diagram illustrating the big data-based trade receivable collection support system 100 for reducing trade receivables of small and medium-sized enterprises and preventing insolvency according to an embodiment of the present invention as a platform.
4 is a signal and data transmission system diagram between each component in the platform of the big data-based trade receivable collection support system 100 for reducing trade receivables of small and medium enterprises and preventing insolvency of FIG. 3, and existing components, new components, and advanced It is a diagram showing the components separately.
5 to 8 are diagrams for explaining an analysis model and a service model in the big data-based account receivable collection support system 100 for reducing the trade receivables of small and medium enterprises and preventing insolvency according to an embodiment of the present invention.

Hereinafter, a detailed description of a preferred embodiment of the present invention will be described with reference to the accompanying drawings. In the following description of the present invention, if it is determined that a detailed description of a related well-known function or configuration may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted.

In the present specification, when any one component 'transmits' data or signal to another component, the component may directly transmit the data or signal to another component, and through at least one other component This means that data or signals can be transmitted to other components.

1 is a diagram illustrating a big data-based trade receivable collection support system 100 for reducing and preventing insolvency of trade receivables of small and medium-sized enterprises according to an embodiment of the present invention. The big data-based trade receivable collection support system 100 for reducing trade receivables of small and medium-sized enterprises and preventing insolvency uses analysis information that can prepare for the reduction and insolvency of trade receivables for efficient management of corporate assets and stabilization of cash flows. It corresponds to a big data management information system developed to effectively respond to recovery time and cost reduction.

To this end, referring to FIG. 1 , the big data-based trade receivable collection support system 100 for reducing trade receivables and preventing insolvency of small and medium-sized enterprises according to an embodiment of the present invention includes internal/public data 110, collection/security/storage unit 122 , an analysis unit 123 , a service unit 124 , a user terminal 125 , a DB/File module 126 , and an Open Stack cloud infrastructure (Level1) 127 .

First, the big data-based trade receivable collection support system 100 for reducing trade receivables of SMEs and preventing insolvency is internal data 111 corresponding to internal/public data 110, corporate financial data, corporate transaction data, and external ( As the public) data 112 , customer location data, court case data, and other public data are collected. That is, when data is collected, corporate financial data and corporate transaction data generated from corporate work, customer location data, court precedent data, and other public data, which are public data areas, are collected.

Thereafter, the collection/security/storage unit 122 performs pre-processing of the collected data. More specifically, the collected data is stored through security and de-identification processes, and a pre-processing process is performed to be utilized for analysis. .

Here, the collection/security/storage unit 122 may be divided into a security module 122a, a data collection module 122b, and a big data storage and processing module 122c. The security module 122a is a management means 122a -1) and the security I/F 122a-2, and the data collection module 122b is composed of an external (public) data collector 122b-1 and an internal data collector 122b-2, The source data required for analysis is collected through Processing techniques and big data storage techniques are applied.

The analysis unit 123 is a big data pattern analysis model 123a that performs (1) spatiotemporal pattern analysis, (2) relationship pattern analysis, (3) financial ratio pattern analysis, and (4) recovery pattern analysis to build an analysis model. , (1) corporate financial data analysis, (2) corporate transaction data analysis, (3) receivable data analysis, and (4) receivables collection prediction module 123b for performing collection data analysis.

That is, the analysis unit 123 is ported by modularizing the big data pattern analysis model 123a and the accounts receivables collection prediction module 123b corresponding to the big data analysis model for big data analysis.

In other words, in the big data pattern analysis model 123a, modules for spatiotemporal pattern analysis, relationship pattern analysis, financial ratio pattern analysis, and collection pattern analysis are ported, and in the accounts receivable collection prediction module 123b, corporate financial data analysis, Modules for corporate transaction data analysis, bond data analysis, collection data analysis, and collection grade calculation will be ported.

The service unit 124 includes a receivable collection support service module 124a that performs a customer search, customer monitoring, corporate insolvency analysis, and collection prediction analysis in order to perform a trade receivable collection support service, case classification, CRUD (Create), Receivable collection case management module (124b) that performs Read, Update, Delete), standard information management, statistical information management, authentication/authorization management, user management, service management, and API management and an administrator portal module 124c.

Accordingly, the service unit 124 utilizes the analysis result by the analysis unit 123 to service the receivable recovery support service portal, and search for clients, monitor clients, and analyze corporate insolvency by the receivables recovery support service module 124a. , constitute a service for recovery prediction analysis.

The bond collection case management module 124b provides case classification, existing information management, and statistical information management service as a management service for the bond collection case, and the administrator portal module 124c is, through the administrator portal, authentication and authority management, user It is to service management, service management, and API management.

On the other hand, by providing the DB/File module 126 and the Open Stack cloud infrastructure (Level1) 127 as a file system, an environment for utilizing network data analysis technology using Spark in a Hadoop-based distributed file system is established. , it can be constructed by distinguishing it as a file system for mounting a general DBMS.

2 is a view showing a service concept by the big data-based trade receivable collection support system 100 for reducing the trade receivables of small and medium-sized enterprises and preventing insolvency according to the above-described embodiment of the present invention. That is, through the configuration of FIG. 1, the big data-based trade receivable collection support system 100 for reducing trade receivables and preventing insolvency of SMEs according to the embodiment of the present invention is a trade receivable collection support service, ① customer monitoring, ② corporate insolvency Analysis, ③ Search for cases of accounts receivable collection, and ④ Predictive analysis of accounts receivable collection can be provided as main services.

① In customer monitoring, the transaction network is visualized using sales data, and the growth/decrease trend of future sales based on the past and present data of the customer is confirmed, and the estimated profit and loss statement using the sales percentage method to determine the current status. Based on forecasting information.

② For corporate insolvency analysis, classification is provided as sound and insolvent companies using existing financial statements (loans, profit and loss, cash), and information on sound and insolvency analysis according to the number of employees, sales, business type, etc. of the company is provided. It provides a prediction rate for the possibility that the customer will become sound or insolvent in the future.

③ In the search for trade receivable collection cases, it collects and stores court precedents and cases of success and failure of debt collection to build a receivable collection DB, provides a user-customized search function centered on keywords related to trade receivables, It provides prior information about whether debt collection activities have been carried out.

④ In the forecast analysis of trade receivables collection, information in the form of a scenario that can provide a guide on what methods are available when establishing a collection plan suitable for my situation is provided, and the recovery rate, collection period, and required according to the collection procedure Perform analysis on cost, singularities, and key points.

FIG. 3 is a hierarchical diagram showing the big data-based trade receivable collection support system 100 for reducing the trade receivables of small and medium enterprises and preventing insolvency according to an embodiment of the present invention as a platform. And FIG. 4 is a signal and data transmission system diagram between each component in the platform of the big data-based account receivable collection support system 100 for reducing trade receivables of small and medium-sized enterprises and preventing insolvency of FIG. 3, and existing components, new components, and advancement It is a diagram showing the divided components.

3 and 4, the data collection module 122b is based on purchase/sales data generated during corporate business in the corporate financial data area, card slips, bankbook transfer details, electronic tax invoice issuance and Receive details are collected by web scraping based on public certificates. Then, the data collection module 122b collects the data of the electronic tax invoice that has been transmitted to the National Tax Service for the corporate transaction data area through the corporate certificate to configure the database. In addition, the data collection module 122b manages the address data of the customer based on the new address and the old address for the customer location data area, and consists of data necessary to output it to an accurate geographic information system through the above longitude information.

In addition, the data collection module 122b configures a database for court case analysis and court precedent search through court case data scraping for the court case data area, and for other public data areas, such as Statistics Korea, the Bank of Korea, the National Tax Service, etc. Among the statistical information, data of the area to be analyzed convergence is collected and configured as a database.

Thereafter, the accounts receivable collection support service module 124a provides a portal service consisting of customer search, customer monitoring, corporate insolvency analysis, collection case search, collection prediction analysis, and debt collection market.

As a lower layer of the trade receivable collection support service module 124a, the trade receivable collection case management module 124b provides a trade receivable collection case management service as a service, but includes the classification management of trade receivable cases, and management of trade receivable collection cases (CRUD). ), management service consisting of standard information management of accounts receivable collection case, and statistical information management of accounts receivable collection case can be provided.

In addition, as a lower layer of the accounts receivable collection support service module 124a, the manager portal module 124c is a service and provides a manager portal service, but consists of authentication/authorization management, user management, service management, API management, and dashboard. It can provide a portal service that can be used.

Meanwhile, a layer between the above-described data collection and service provision layer will be described. The accounts receivable collection prediction module 123b is based on the receivables collection prediction model. to provide.

And, the big data pattern analysis module 123a is a time series pattern analysis, relationship pattern analysis (node, graph), financial ratio pattern analysis (balance balance, profit and loss, cash flow), collection pattern analysis (type, status, response method, etc.) It provides a pattern analysis management system composed of

On the other hand, the data collection module 122b provides a collection system composed of an external data collector 122b-1 and an internal company data collector 122b-1 as described above, and a big data storage and processing module (Spark ) (122c) provides a system composed of an Apache Spark-based big data processing module and a big data storage module, and the security module 122a includes a management means 122a-1, a security means 122a-3, and an external interworking API. (122a-4) and security I/F (122a-2) is a security system that manages data de-identification and encryption, and handles the security of the network section.

DB/File module 126 is a database composed of Hadoop-based distributed file system (EXT4) (126a), general file system (126b), DBMS (MS-SQL, MariaDB, etc.) (126c), other libraries (126d) and Provides a file system.

Meanwhile, FIGS. 5 to 8 are diagrams for explaining an analysis model and a service model in the big data-based trade receivable collection support system 100 for reducing trade receivables of SMEs and preventing insolvency according to an embodiment of the present invention.

First, referring to FIG. 5A , the accounts receivable collection prediction module 123b includes a corporate financial data analysis module 123b-1, a corporate transaction data analysis module 123b-2, a bond data analysis module 123b-3, and collection It may be divided into a data analysis module 123b-4 and a recovery grade calculation module 123b-5.

First, the corporate financial data analysis module 123b-1 collects corporate financial data, performs basic sales and purchase analysis, and performs additional data analysis related to corporate finance.

The corporate transaction data analysis module 123b-2 modularizes the analysis algorithm so that information on the transaction pattern and transaction volume can be calculated using the network analysis technique of the enterprise transaction data.

The bond data analysis module (123b-3) classifies the start data that generates sales among corporate transaction data as bonds until payment collection, and analyzes them as bond management data. do.

The collection data analysis module 123b-4 analyzes the collection case and collection pattern when the bond is normally collected, or when the non-performing loan is collected through a legal action (debt default registration or court litigation, etc.) modularize so that

The collection grade calculation module 123b-5 classifies whether the bonds are suitable for a collection pattern, and calculates a collection grade according to the state of each bond.

The collection pattern analysis (type, state, response method, etc.) by the trade receivables collection prediction module 123b is shown in FIG. 5b, and data is evaluated based on company information and receivable information in (data evaluation), The data evaluation element is based on the analysis of the company's basic information (current status of the company, past financial status, etc.) is structured to learn the bond information, and each standard predictive evaluation index is quantified and managed, and in (receipt collection prediction evaluation), bond ratings, credit ratings, and score sections are managed, and non-collectible bonds The pattern for recoverable bonds, except for

On the other hand, the portal service of the accounts receivable collection support service module 124a is as shown in FIG. 6A , and the accounts receivable collection support service module 124a is a list of recipients included in the transaction relationship for customer monitoring in (customer search). , and makes it easy to search for recently traded companies and companies with large transaction amounts and recovery rates.

In addition, in the account receivable collection support service module 124a (customer monitoring), the current contract relationship and sales scale in terms of business site management of the searched customer. It monitors the soundness of bonds and provides a monitoring function that can detect whether bonds may fall into a bad state in advance.

In addition, the receivables collection support service module 124a provides an analysis result for informing the sales person whether there are signs of insolvency of the company due to the analysis of the company's transaction relationship and other environmental factors in (corporate insolvency analysis). .

In addition, the trade receivables collection support service module 124a provides a precedent search result to infer a collection pattern for non-performing loans of a similar pattern by searching court precedent cases for receivables in (recovery case search). .

In addition, the trade receivables collection support service module 124a provides the collection probability and the collection scale as prediction results based on the recovery rate according to the pattern of the receivables in (collection prediction analysis).

When the enterprise transaction pattern analysis algorithm model is provided by the big data pattern analysis model 123a, data collection and graph data construction for enterprise transaction pattern analysis are performed, and the transaction data is analyzed in real time and the entire transaction is performed as shown in FIG. The feature is that network analysis is possible. Since it is necessary to build a data processing system for the collection and integration of transaction data stored in individual companies, node data is established based on each company identifier for standardized transaction data analysis, and relationship data between identifiers is established. In addition, relational data is constructed so that relational analysis is possible, including attributes such as amount, date, and item.

Accordingly, it is possible to explore the flow of real and bonds through corporate transaction pattern analysis by the big data pattern analysis model 123a. , can be used as a basis for industrial ecosystem analysis through transaction structure analysis provides

On the other hand, it is possible to analyze and visualize trade patterns between industries by the big data pattern analysis model (123a) (based on sample data, extract specific industries and regions), and it is possible to identify major industries by understanding the structure of transactions between industries according to the standard industry classification; It provides the advantage of measuring the degree of influence of the industry according to the industry-related relationship.

8A shows a direct transaction importance-based analysis (based on real flow data) by the big data pattern analysis model 123a, and FIG. 8B shows an intermediary role importance-based analysis (based on real flow data) by the big data pattern analysis model 123a. ) is indicated.

As described above, preferred embodiments of the present invention have been disclosed in the present specification and drawings, and although specific terms are used, these are only used in a general sense to easily explain the technical content of the present invention and help the understanding of the present invention. , it is not intended to limit the scope of the present invention. It will be apparent to those of ordinary skill in the art to which the present invention pertains that other modifications based on the technical spirit of the present invention can be implemented in addition to the embodiments disclosed herein.

100: Big data-based trade receivable collection support system for reducing trade receivables of small and medium-sized enterprises and preventing insolvency
110: internal/public data
122: collection/security/storage
123: analysis unit
124: service department
125: user terminal
126: DB/File module
127: Open Stack Cloud Infrastructure

Claims (1)

Internal/public data (110) to internal data (111) generated in corporate work, corporate financial data, corporate transaction data, and external (public) data (112) to collect customer location data, court case data, and public data In the trade receivable collection support system,
A collection/security/storage unit 122 that stores the collected data through security and de-identification processes by performing pre-processing of the collected data to be utilized for analysis; In addition, the analysis unit 123; Including, the analysis unit 123,
"Big data pattern analysis model 123a" that performs (1) spatiotemporal pattern analysis, (2) relationship pattern analysis, (3) financial ratio pattern analysis, and (4) recovery pattern analysis to build an analysis model;
(1) corporate financial data analysis, (2) corporate transaction data analysis, (3) receivables data analysis, (4) "receivables collection forecasting module 123b" for performing collection data analysis; and
A receivable collection support service module 124a that performs customer search, customer monitoring, corporate insolvency analysis, and collection prediction analysis to perform trade receivable collection support service, case classification, CRUD (Create), Read, Update,
Delete (delete)), standard information management, and a bond collection case management module 124b that performs statistical information management, and corresponds to an administrator portal module 124c that performs authentication/authorization management, user management, service management, and API management a “service unit 124” consisting of a plurality of modules 124a to 124c; includes,
"Trade receivables collection prediction module 123b" is,
a corporate financial data analysis module (123b-1) for collecting corporate financial data, analyzing sales and purchases, and analyzing additional data related to corporate finance;
a corporate transaction data analysis module (123b-2) for modularizing an analysis algorithm so that information on a transaction pattern and transaction volume can be calculated using a network analysis technique for enterprise transaction data;
Bond data analysis module (123b-3) that classifies start data that generates sales among corporate transaction data as bonds until payment collection and analyzes them as bond management data ;
Collection data analysis module (123b-) that is modularized to analyze collection cases and collection patterns when receivables are normally collected, or when bad receivables are collected through legal acts (registration of default or court action) for dunning and collection 4); and
a collection grade calculation module (123b-5) for classifying bonds matching the collection pattern and calculating a collection grade according to the state of each bond; includes,
In the (data evaluation) by the trade receivables collection prediction module 123b, data is evaluated based on company information and receivables information, and company information (current status of the company, past financial status) is analyzed in the data evaluation element, ( In the accounts receivable collection prediction model), the company transaction information and corporate financial information are configured so that the receivable items and collection patterns can be learned through matrix analysis, and the predictive evaluation index is digitized and managed by deriving the receivable information items, In (receipt collection prediction evaluation), the bond rating, credit rating, and score section are managed, and patterns, collection predictions and recovery rates are presented for recoverable bonds excluding non-collectible bonds,
In the portal service of the accounts receivable collection support service module 124a, the accounts receivable collection support service module 124a manages a list of recipients included in the transaction relationship for client monitoring in (customer search), and recent transactions Allows you to search for companies, transaction amounts and recovery rates,
In the (customer monitoring), the trade receivable collection support service module 124a monitors the current contract relationship, the size of sales, and the soundness of the receivables in terms of managing the sales site of the searched customer, and uses the sales data to create a transaction network. Visualize, confirm the growth/decrease trend of future sales based on past and present data of the customer, and provide forecast information based on the estimated profit and loss statement using the percentage of sales method to determine the current status of the bond. Provides monitoring function for detection,
In the (corporate insolvency analysis), the trade receivables collection support service module 124a provides analysis results for informing the sales manager whether there are signs of insolvency of the company due to the analysis of the company's transaction relationship and environmental factors,
The trade receivables collection support service module 124a searches for court precedents for receivables in (recovery case search), and searches for precedents so as to infer a recovery pattern for non-performing loans of a pattern matching the searched court case cases. The results are provided to the accounts receivable collection prediction module 123b,
The trade receivables collection support service module 124a provides (receipt forecast analysis), the recovery probability and the collection scale as a prediction result based on the recovery rate according to the pattern of receivables,
When the enterprise transaction pattern analysis algorithm model is provided by the big data pattern analysis model 123a, data collection and graph data construction for enterprise transaction pattern analysis are performed, and the transaction data can be analyzed in real time and transaction network analysis is possible, and individual companies In order to establish a data processing system for the collection and integration of transaction data stored in Data is built to enable relational analysis, including amount, date, and item attributes,
Provides analysis and visualization of trade patterns between industries by the big data pattern analysis model (123a) (based on sample data, specific industries and regions) Big data-based trade receivable collection support system for reducing trade receivables of SMEs and preventing insolvency, characterized in that it measures the degree of influence of the industry according to the relationship.

Images