CN116051272A

CN116051272A - Enterprise risk analysis method and related equipment

Info

Publication number: CN116051272A
Application number: CN202310116643.1A
Authority: CN
Inventors: 兰桥; 赵彦晖; 耿心伟; 曾源
Original assignee: Shenzhen Weizhong Credit Technology Co ltd
Current assignee: Shenzhen Weizhong Credit Technology Co ltd
Priority date: 2023-02-15
Filing date: 2023-02-15
Publication date: 2023-05-02

Abstract

The embodiment of the application provides an enterprise risk analysis method and related equipment, which are used for analyzing transaction relations among enterprises so as to evaluate credit risks of the enterprises. The method comprises the following steps: acquiring enterprise operation data of a plurality of enterprises to be analyzed, wherein the enterprise operation data at least comprises a plurality of enterprise operation characteristics and invoice data of any enterprise to be analyzed; calculating a target risk value of a target enterprise according to invoice data and a plurality of enterprise operation characteristics, and determining association relations of different enterprise operation characteristics, wherein the target enterprise is any enterprise to be analyzed, and the association relations at least comprise association relations of different enterprises to be analyzed; evaluating association degree values of any two enterprises to be analyzed according to the association relation; and determining risk values of other enterprises to be analyzed after removing the target enterprise according to the association value and the target risk value, so that the banking enterprise manages and controls the other enterprises to be analyzed according to the risk values.

Description

Enterprise risk analysis method and related equipment

Technical Field

The embodiment of the application relates to the technical field of Internet, in particular to an enterprise risk analysis method and related equipment.

Background

At present, the wind control of a bank enterprise is mostly based on transaction flowing water in a row, and tax administration collection management and control is based on tax data, and the wind control and the tax administration collection management and control are relatively independent, so that an optimization space exists in multidimensional analysis of the enterprise.

Meanwhile, the invoice is an important legal evidence of expenditure and income for enterprises, and the pushing of the full-electricity invoice enriches the data dimension of the invoice. However, pushing of "all-electric invoices" also presents challenges to tax auditing risks, e.g., the "all-electric invoices" cancel ticket face limits, whereas "credit total management" schemes are pushed. The billing limit of the scheme can be dynamically adjusted according to tax compliance of tax payers.

Therefore, how to timely find tax compliance problems of enterprises and analyze enterprise risks become an important management and control means.

Disclosure of Invention

The embodiment of the application provides an enterprise risk analysis method and related equipment, which are used for analyzing transaction relations among enterprises so as to evaluate credit risks of the enterprises.

An embodiment of the present application provides a method for analyzing risk of an enterprise, including:

acquiring enterprise operation data of a plurality of enterprises to be analyzed, wherein the enterprise operation data at least comprises a plurality of enterprise operation characteristics and invoice data of any enterprise to be analyzed;

Calculating a target risk value of a target enterprise according to the invoice data and a plurality of enterprise operation characteristics, and determining association relations of different enterprise operation characteristics, wherein the target enterprise is any enterprise to be analyzed, and the association relations at least comprise association relations of different enterprises to be analyzed;

evaluating association degree values of any two enterprises to be analyzed according to the association relation;

and determining risk values of other enterprises to be analyzed after removing the target enterprise according to the association value and the target risk value, so that the banking enterprise manages and controls the other enterprises to be analyzed according to the risk values.

Optionally, the acquiring enterprise operation data of the plurality of enterprises to be analyzed includes:

triggering an authentication request of the enterprise to be analyzed in a credit investigation organization, and acquiring the enterprise operation data of the enterprise to be analyzed according to the authentication request;

analyzing the enterprise operation data to acquire a plurality of enterprise operation characteristics and invoice data of the enterprise to be analyzed; and the enterprise operation characteristics and the invoice data have a corresponding relation.

Optionally, before calculating the target risk value of the target enterprise according to the invoice data and the enterprise operation characteristics, the method further includes:

Constructing a global view according to all the enterprise operation characteristics;

selecting any enterprise operation characteristic from the global view to construct an initial business scene graph;

acquiring target invoice data with corresponding relation with any enterprise operation characteristic in the initial business scene graph;

writing the target invoice data into the initial service scene graph to generate a target service scene graph;

and executing the step of calculating the target risk value of the target enterprise according to the invoice data and the enterprise operation characteristics according to the target business scene graph.

Optionally, the calculating the target risk value of the target enterprise according to the invoice data and the enterprise operation characteristics comprises:

configuring a risk rule;

acquiring target invoice data and target enterprise business characteristics of the target enterprise corresponding to the risk rule, wherein the target invoice data is the invoice data corresponding to the risk rule, and the target enterprise business characteristics are the enterprise business characteristics corresponding to the risk rule;

and calculating the target risk value of the target enterprise according to the target invoice data and the target enterprise operation characteristics.

Optionally, before the calculating the target risk value of the target enterprise according to the target invoice data and the target enterprise operation characteristics, the method further includes:

configuring operation parameters of a risk operation model according to the target invoice data and the target enterprise operation characteristics;

the calculating the target risk value of the target enterprise according to the target invoice data and the target enterprise operating characteristics comprises:

inputting the target invoice data and the target enterprise operation characteristics into the risk operation model to determine the risk degree satisfied by the target enterprise according to the operation parameters, the target invoice data and the target enterprise operation characteristics, wherein the risk degree corresponds to different scale coefficient intervals;

and determining the target risk value according to the risk degree.

Optionally, determining risk values of other enterprises to be analyzed after eliminating the target enterprise according to the association degree and the target risk value includes:

determining a first enterprise to be analyzed which is associated with the target enterprise according to the association relation;

determining the association value of the first enterprise to be analyzed and the target enterprise;

And calculating the association degree value and the target risk value to determine the risk value of the first enterprise to be analyzed.

Optionally, after the calculating the association value and the target risk value to determine the risk value of the first enterprise to be analyzed, the method further includes:

determining the first enterprise to be analyzed as the target enterprise;

and determining a second enterprise to be analyzed which is associated with the target enterprise according to the association relation, and taking the second enterprise to be analyzed as the first enterprise to be analyzed so as to execute the step of determining the association value of the first enterprise to be analyzed and the target enterprise.

A second aspect of an embodiment of the present application provides an enterprise risk analysis system, including:

the system comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring enterprise operation data of a plurality of enterprises to be analyzed, and the enterprise operation data at least comprises a plurality of enterprise operation characteristics and invoice data of any enterprise to be analyzed;

the calculating unit is used for calculating a target risk value of a target enterprise according to the invoice data and a plurality of enterprise operation characteristics, and determining association relations of different enterprise operation characteristics, wherein the target enterprise is any enterprise to be analyzed, and the association relations at least comprise association relations of different enterprises to be analyzed;

The evaluation unit is used for evaluating association degree values of any two enterprises to be analyzed according to the association relation;

and the determining unit is used for determining the risk values of other enterprises to be analyzed after the target enterprise is eliminated according to the relevance value and the target risk value, so that the banking enterprise manages and controls the other enterprises to be analyzed according to the risk values.

A second aspect of the embodiments of the present application provides a method for performing the enterprise risk analysis method described in the first aspect.

A third aspect of the embodiments of the present application provides an enterprise risk analysis device, including:

the device comprises a central processing unit, a memory, an input/output interface, a wired or wireless network interface and a power supply;

the memory is a short-term memory or a persistent memory;

the central processor is configured to communicate with the memory and to execute instruction operations in the memory to perform the enterprise risk analysis method of the first aspect.

A fourth aspect of the embodiments of the present application provides a computer-readable storage medium, where the computer-readable storage medium includes instructions that, when executed on a computer, cause the computer to perform the enterprise risk analysis method according to the first aspect.

From the above technical solutions, the embodiments of the present application have the following advantages: by the enterprise risk analysis method disclosed by the embodiment of the application, enterprise operation data of a plurality of enterprises to be analyzed are acquired; calculating a target risk value of a target enterprise according to the invoice data and a plurality of enterprise operation characteristics, and determining association relations of different enterprise operation characteristics; then, evaluating association values of any two enterprises to be analyzed according to the association relation; and finally, determining the risk values of other enterprises to be analyzed after the target enterprise is removed according to the association value and the target risk value, so that the banking enterprise manages and controls the other enterprises to be analyzed according to the risk values. Therefore, the invoice data is used as an analysis subject of the enterprise, and the transaction relation of different enterprises is analyzed on the basis of considering the business characteristics of the enterprises, so that whether the tax of the enterprises is compliant is determined, and the enterprises are managed and controlled by the banking enterprises.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.

FIG. 1 is a schematic diagram of an enterprise risk analysis system according to an embodiment of the present disclosure;

FIG. 2 is a schematic flow chart of an enterprise risk analysis method disclosed in an embodiment of the present application;

FIG. 3 is a schematic flow chart of another method for enterprise risk analysis disclosed in an embodiment of the present application;

FIG. 4 is a model design diagram of a global view disclosed in an embodiment of the present application;

FIG. 5 is a schematic diagram of enterprise-related risk conduction according to an embodiment of the present disclosure;

FIG. 6 is a diagram of a login interface of an electronic tax bureau according to an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of a relationship between enterprise correspondents disclosed in an embodiment of the present application;

FIG. 8 is a graph of a business transaction according to an embodiment of the present disclosure;

FIG. 9 is a diagram of price change for an enterprise transaction commodity according to an embodiment of the present disclosure;

FIG. 10 is a schematic structural diagram of an enterprise risk analysis system according to an embodiment of the present disclosure;

fig. 11 is a schematic structural diagram of an enterprise risk analysis device according to an embodiment of the present application.

Detailed Description

The terms "first," "second," "third," "fourth" and the like in the description and in the claims of this application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that the description herein of "first," "second," etc. is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implying an indication of the number of technical features being indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be regarded as not exist and not within the protection scope of the present application.

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

The invoice is an important legal evidence of expenditure and income for enterprises, and the data dimension of the invoice is richer along with the pushing of the current 'all-electric invoice'. The invoice is used as a main relation link for complex transaction analysis of enterprises, and has the following advantages:

1. The invoice data can reflect the business upstream and downstream relationship, the transaction amount, the transaction time and commodity information of the enterprise, has high data reliability, and can truly reflect the business condition and the fund flow direction of the enterprise.

2. The whole-electricity invoice is pushed to enable the transaction behavior to be real-time, the electronic invoice platform can be opened at any time and any place, and risk early warning can be rapidly carried out in real time according to abnormal transaction behaviors.

3. The invoice data and the transaction flow of the bank and the tax data of the tax office have natural fusion, the essence of the invoice data and the tax office is surrounding the enterprise fund flow direction, and massive invoice data can be used for constructing enterprise behavior characteristic patterns in real time by using a graph calculation technology, so that reliable service is provided for bank and enterprise wind control and tax office collection management.

Therefore, in the technical scheme, the linkage of the invoice, tax and business multiple data is enhanced based on big data and graph technology, the enterprise risk problem is analyzed in depth, and tax management and control are promoted.

However, it is required to explain in advance that in the technical scheme of the application, the application mainly relates to innovative application of the bank enterprise wind control and local tax platform auxiliary tax collection management. Under the large environment of economic fluctuation and epidemic situation influence, the loan obtaining rate of small and medium-sized micro enterprises is improved for the bank enterprises, and the tax authorities realize the preferential policy to the small and medium-sized micro enterprises and provide help to prevent the tax deception of part of enterprises as much as possible. Therefore, the technical scheme of the application takes invoice transaction data of enterprises as description requirements, deeply fuses industrial and commercial tax data, introduces graph technology to construct enterprise relationship feature graphs, analyzes enterprise hidden risks and provides services for bank and enterprise credit service and local tax platforms.

Referring to fig. 1, fig. 1 is a schematic architecture diagram of an enterprise risk analysis system according to an embodiment of the present disclosure. Comprising the following steps: the system comprises a data acquisition module 101, a business scene graph construction module 102, a relevance evaluation module 103, a risk rule parameter configuration module 105, a risk score real-time calculation module 104 and a black-and-white list module 106.

As can be seen from fig. 1, in the enterprise risk analysis system disclosed in the embodiments of the present application, a data acquisition module 101, a business scenario diagram construction module 102, a relevance evaluation module 103, a risk score real-time calculation module 104, and a black-and-white list module 106 are sequentially in communication connection, and a risk rule parameter configuration module 105 is in communication connection with the risk score real-time calculation module 104. It may be understood that the data acquisition module 101, the association degree evaluation module 103, and the risk rule parameter configuration module 105 may be understood as front-end functions, and the business scenario diagram construction module 102, the risk score real-time calculation module 104, and the black-and-white list module 106 may be understood as back-end functions. Of course, the above is only one specific embodiment, and the functional modules described above may not be executed on the front end or the back end described in the above, for example, the relevance evaluation module 103 may be executed on the back end of the system, which is not limited herein. In order to facilitate understanding of each of the functional modules described in the above, each of the functional modules is described in detail below.

The data acquisition module 101 is mainly used for acquiring data from various channels (or data sources). Specifically, the interface service of the tax platform is accessed by a user authentication and authorization mode, so that data such as invoices, enterprise declarations or financial reports are obtained. And acquiring data such as the running bank checking interface service to acquire the loan order and the like of the enterprise account. Public data such as business, judicial or credit is obtained from a credit bureau interface. In the above, only a few specific embodiments of the data acquisition module 101 acquire data from different channels, it is not easy to understand that the data acquisition module 101 may acquire other data associated with the channel from other channels, which is not described herein in detail.

The business scene graph construction module 102 mainly aims at the characteristics that business analysis scenes are changeable and data types are relatively fixed, and therefore a module of 'global view' mapping 'business scene graph' is adopted. It will be appreciated that a "global view" is a complex relationship that builds an enterprise all around based on all existing data sources. In one embodiment, the "point" and the "face" may be simply understood, where the "point" is an enterprise feature, for example, a commodity, an industry, a commodity type, or a natural person (legal responsible person), and the "face" is an association generated by each enterprise feature, for example, a guarantee type, a provider, or a stock, and details of the content contained in the "point" or the "face" will not be described herein. Correspondingly, the business scenario graph can be a plurality of scenarios, such as an upstream-downstream graph, a share right penetration graph, a transaction risk graph or a commodity analysis graph, and the like. The combination of different "points" and "faces" corresponding to each different service scenario diagram may not be described herein in detail.

The relationship evaluation module is mainly used for evaluating the relationship tightness degree between the entities and is used for conducting the risk values in the relationship links. However, it is understood that it can be considered a degree of silence of the relationship between two enterprises. This will be described in detail later.

The risk score real-time calculation module 104 comprises a front-end service configuration function and a background stream processing application, and calculates the risk value of the enterprise in real time based on the risk rule configured by the front end.

The risk rule parameter configuration module 105 is each parameter configured by the service analyst according to the risk rule on the front-end page.

The black-and-white list module 106 determines whether the enterprise has a risk based on the value output by the risk score real-time calculation module 104. It can be appreciated that the black-and-white list module 106 is formed by running the traffic scene graph according to the total data of day T-1, the black list represents the high-risk enterprises, the white list represents the non-risk enterprises, and the black-and-white list can assist the banking enterprise in the air-controlled admission model.

Referring to fig. 2, fig. 2 is a flow chart of an enterprise risk analysis method according to an embodiment of the present disclosure. Including steps 201-204.

201. And acquiring enterprise operation data of a plurality of enterprises to be analyzed.

Step 201 in this embodiment is similar to the function performed by the data acquisition module in fig. 1, and detailed description thereof is omitted here. However, in this embodiment, since unified analysis needs to be performed on the enterprise and other enterprises associated with the enterprise, enterprise operation data of a plurality of enterprises needs to be acquired.

In one particular embodiment, enterprise business data for an enterprise to be analyzed is acquired from different data sources via a data acquisition module. The enterprise to be analyzed at least comprises any entity enterprise. The plurality of enterprises to be analyzed may be enterprises related to the enterprise, or may be other enterprises not directly related to the enterprise, which is not described herein in detail. For ease of understanding and description, the description of the enterprises to be analyzed follows, in which the enterprises having associations between the enterprises to be analyzed are described in detail.

In another embodiment, the enterprise business data includes at least enterprise business characteristics and invoice data. In particular, an enterprise business trait may be understood as an enterprise attribute or association with an enterprise with other enterprises that are generated during the business process. For example, some of the enterprise business features may be enterprises, natural people, commodities, industries or commodity types, etc., or may be guaranty relationships, clients, suppliers or share ratios, etc., which are not described herein. Correspondingly, the invoice data can be understood as a current common full-electric invoice in the market, at least including an enterprise name, a commodity name or a commodity specification, etc., and the contents included in the full-electric invoice are not limited herein, and are not described in detail later.

202. And calculating a target risk value of a target enterprise according to the invoice data and the enterprise operation characteristics, and determining the association relation of different enterprise operation characteristics.

In this embodiment, step 202 is similar to the functions executed by the business scenario diagram construction module and the risk score real-time calculation module in fig. 1, and detailed descriptions thereof are omitted herein. However, it should be noted that, after the invoice data and the plurality of business operation features are obtained, the target risk value of the target business can be calculated according to the correlation between the invoice data and the plurality of business operation features. It should be understood that the plurality of business operation features at this time are business operation features corresponding to the target business, and the corresponding invoice data may be invoice data related to the target business. Meanwhile, as the invoice data has the data corresponding to different enterprise operation characteristics, the association relationship between different enterprise operation characteristics can be determined according to the invoice data and the enterprise operation characteristics.

Of course, it should be further noted in advance that the target enterprise is one of the enterprises to be analyzed specifically related to the present embodiment, that is, in the present embodiment, the invoice data or the enterprise operation features related to the target enterprise are all associated with the target enterprise. For ease of understanding and description, this will not be described in detail later.

In one specific embodiment, the invoice data includes at least a business name, a commodity name, etc., and the business operation features include a business, a commodity, a purchasing relationship, etc. Thus, in one embodiment, the merchandise purchase relationship that exists between two businesses to be analyzed may be determined based on the invoice data and the business operating characteristics. The commodity purchasing relationship can be understood as the association relationship of enterprise operation characteristics.

203. And evaluating the association degree value of any two enterprises to be analyzed according to the association relation.

In this embodiment, step 203 is similar to the function executed by the association evaluation module in fig. 1, and detailed descriptions thereof are omitted here. However, it should be noted that, as shown in the above step 202, the association relationship specifically describes the association relationship between different enterprise operation features, and further, the enterprise operation features of different enterprises to be analyzed are related to the enterprise operation features.

In one specific embodiment, the association relationship can objectively evaluate the relationship degree between two enterprises, specifically, the association degree between the target enterprise and another enterprise to be analyzed can be evaluated, so that the association degree value between the target enterprise and the other enterprise to be analyzed can be determined. It should be understood that, since the description is given above for the target enterprise, the step of evaluating any two enterprises to be analyzed in this embodiment can be understood as that one enterprise to be analyzed is the target enterprise, and the other enterprise to be analyzed is the enterprise associated with the target enterprise. For ease of understanding and description, this will not be described in detail later.

204. And determining risk values of other enterprises to be analyzed after removing the target enterprise according to the association value and the target risk value, so that the banking enterprise manages and controls the other enterprises to be analyzed according to the risk values.

After the target risk value of the target enterprise and the association degree value of the target enterprise and any enterprise to be analyzed are determined, the risk value of the enterprise to be analyzed can be determined, so that the bank enterprise can conveniently manage and control the enterprise according to the risk value.

In one specific embodiment, the target risk value may be multiplied by the association value, so as to determine the risk value of the enterprise to be analyzed.

Based on the above embodiment, in another specific embodiment, the enterprise to be analyzed may be regarded as the target enterprise again, the risk value of the enterprise to be analyzed is regarded as the target risk value, and the association degree value of the enterprise to be analyzed (which is regarded as the target enterprise at this time) with other enterprises to be analyzed is determined, so that the risk values of other enterprises to be analyzed are gradually calculated, so that the banking enterprise manages and controls all enterprises to be analyzed according to all the obtained risk values.

By the enterprise risk analysis method disclosed by the embodiment, enterprise operation data of a plurality of enterprises to be analyzed are acquired first; calculating a target risk value of a target enterprise according to the invoice data and a plurality of enterprise operation characteristics, and determining association relations of different enterprise operation characteristics; then, evaluating association values of any two enterprises to be analyzed according to the association relation; and finally, determining the risk values of other enterprises to be analyzed after the target enterprise is removed according to the association value and the target risk value, so that the banking enterprise manages and controls the other enterprises to be analyzed according to the risk values. Therefore, the invoice data is used as an analysis subject of the enterprise, and the transaction relation of different enterprises is analyzed on the basis of considering the business characteristics of the enterprises, so that whether the tax of the enterprises is compliant is determined, and the enterprises are managed and controlled by the banking enterprises.

For convenience in describing an enterprise risk analysis method disclosed in the embodiments of the present application in detail, please refer to fig. 3, and fig. 3 is a schematic flow chart of another enterprise risk analysis method disclosed in the embodiments of the present application. Including steps 301-309.

301. Triggering an authentication request of the enterprise to be analyzed at the credit investigation organization, and acquiring enterprise operation data of the enterprise to be analyzed according to the authentication request.

Step 301 in this embodiment is similar to step 201 in fig. 2, and detailed description thereof will be omitted herein. However, it should be understood that in one specific embodiment, the enterprise needs to log in successfully on the front-end page, and after authorization, the enterprise operation data of the corresponding enterprise to be analyzed can be obtained from the electronic tax bureau.

In one embodiment, referring to fig. 6, fig. 6 is a login interface diagram of an electronic tax bureau according to an embodiment of the present application. As shown in fig. 6, the enterprise user performs electronic tax office authentication and authorizes collection of business data of the enterprise.

302. And analyzing the enterprise operation data to acquire a plurality of enterprise operation characteristics and invoice data of the enterprise to be analyzed.

Based on the enterprise business data obtained in step 301, the system may parse the enterprise business data to obtain invoice data and a plurality of enterprise business features. It should be understood that the invoice data and the business operation features have been described in detail in step 201, and detailed descriptions thereof are omitted here.

In another embodiment, referring to table 1, table 1 is an example of one of the value added tax receipts.

It should be understood that the above is merely an example of one type of value-added tax invoice.

Referring to table 2, table 2 is an example of a value added tax special invoice involving merchandise information.

It should be understood that the above is merely an example of a value added tax specific invoice that involves merchandise information. 303. And constructing a global view according to all enterprise operation characteristics, and selecting any enterprise operation characteristic from the global view to construct an initial business scene graph.

Step 303 in this embodiment is similar to the functions described in the foregoing service scenario diagram construction module in fig. 1, and detailed descriptions thereof are omitted here. However, it should be noted that, for the feature that the scene is variable and the data type is relatively fixed for the service analysis, a mode of "global view" mapping "the service scene graph" is adopted. It will be appreciated that a "global view" is a complex relationship that builds an enterprise all around based on all existing data sources.

In one embodiment, referring to fig. 4, fig. 4 is a model design diagram of a global view disclosed in an embodiment of the present application. The point and edge attributes described in FIG. 4 are as follows, please refer to

Table 3, table 3 shows the descriptions and connections corresponding to the points and edges in FIG. 4.

It should be understood that the "name" in table 3 may be understood as an enterprise operation feature, and the attribute may be understood as specific data corresponding to the invoice data, which is not described herein in detail.

Based on the points or edges of the global view, the initial business scene graph can be constructed according to the selected points or edges by selecting the points or edges in the global view through a graph platform tool. For example, for a merchandise analysis map, a "point" may select an enterprise, a merchandise type, and an industry. While "edges" may be selected for type, purchase, sale, etc., and are not limited in particular herein. Correspondingly, the other business scenario diagrams are not described in detail.

304. And acquiring target invoice data corresponding to any enterprise operation characteristic in the initial business scene graph, writing the target invoice data into the initial business scene graph, and generating a target business scene graph.

Since the point or edge has been selected in step 303, i.e., the business operation feature in the initial business scenario diagram, the corresponding invoice data, i.e., the target invoice data, can be found based on the business operation feature selected in the foregoing. It is to be understood that each feature in the enterprise operation features exists in the invoice data, and detailed description is omitted herein, and specific reference may be made to examples of the value added tax invoices in table 1 or table 2. In the process of selecting an initial business scene graph, such as a risk analysis scene of an upstream graph and a downstream graph, points (enterprises), edges (clients, main suppliers, judicial disputes and investments) can be selected as analysis objects, and then a mapping relation is automatically generated according to the points edges which need to be analyzed.

In one specific embodiment, after data acquisition is completed, data source data (invoice data) are collected from a message engine by utilizing big data stream processing, then relevant fields are extracted according to a service scene graph mapping relation configured by a platform visualization and written into a graph in real time, specifically, target invoice data is written into an initial service scene graph, so that a target service scene graph is generated. Thereby facilitating the analysis of each enterprise to be analyzed.

305. And configuring risk rules, and acquiring target invoice data and target enterprise business characteristics of a target enterprise corresponding to the risk rules.

Step 305 in this embodiment is similar to the function described in the risk rule parameter configuration module in fig. 1, and detailed description thereof is omitted here. However, the risk rule includes at least a statistical period, a range interval, a threshold value, or the like of the invoice data, and specifically, the content included in the risk rule is not limited herein.

In one specific embodiment, the risk analysis personnel of the enterprise can configure the risk rule at the front end, so that the background flow processing application can obtain the target invoice data and the target enterprise operation characteristics of the target enterprise corresponding to the risk rule. It should be understood that the target business operating characteristic is the business operating characteristic associated with the target invoice data.

Based on the above embodiment, the risk rule may be configured based on the target business scenario diagram generated in the above step. For easy understanding and description, the risk rules will be described in detail later, and detailed descriptions thereof will be omitted herein.

In another specific embodiment, after the target enterprise business feature and the target invoice data are obtained, the operation parameters of the risk operation model may be further configured, specifically, the operation parameters may be also configured by the service analyst on the front end page, which is not described herein in detail. The risk operation model is used for calculating the risk value of the enterprise.

306. And calculating a target risk value of the target enterprise according to the target invoice data and the target enterprise operation characteristics, and determining the association relation of different enterprise operation characteristics.

After the target invoice data and the target enterprise business characteristics are obtained, the target risk value of the target enterprise can be calculated based on the configured risk rules. Meanwhile, the association relation of different enterprise operation characteristics in different enterprises to be analyzed can be determined based on the enterprise operation characteristics.

In one embodiment, step 306 in this embodiment is similar to the function described in the foregoing real-time risk score calculation module in fig. 1, and detailed descriptions thereof are omitted herein. However, the module includes a front-end service configuration function and a background stream processing application, and is based on risk rules (statistical period, range interval, threshold, etc.) of the front-end configuration. Referring to table 4, table 4 shows risk behaviors and rules thereof.

The middle-high, middle-high and general association parties (the degree of tightness of the relationship) are configured on the front-end page by service analysis personnel, and the background obtains the risk value of the enterprise in real time by utilizing graph calculation (GSQL or graph algorithm) according to the configuration parameters.

In another specific embodiment, the target invoice data and the target enterprise business characteristics may be input into the risk operation model, so as to determine the risk degree of the target enterprise according to the operation parameters, the target invoice data and the target enterprise business characteristics, where the risk degree corresponds to different scale coefficient intervals. It is to be understood that, for example, for a suspected closed-loop transaction, when the calculated risk degree is 0.6, that is, N > 0.5, it is determined that the target enterprise is at a high risk at this time, and meanwhile, the risk value of the target enterprise may also be obtained in real time according to the configuration parameters, which is not described in detail herein in the specific calculation step.

Please refer to fig. 7, 8 and 9. Fig. 7 is a schematic diagram of a relationship between enterprise associated parties according to an embodiment of the present application. Fig. 8 is a transaction diagram spectrum of an enterprise transaction according to an embodiment of the present application. Fig. 9 is a diagram showing a price change of an enterprise transaction commodity according to an embodiment of the present application. It will be appreciated that fig. 7, 8 and 9 are each a visual presentation of the results after calculation.

For fig. 7, fig. 7 is a diagram of a primary counterparty being determined as a primary party based on an investment relationship. FIG. 8 is a diagram of a suspected closed-loop transaction for a business, where both purchasing and selling actions for the same commodity are mined from a transaction map. Fig. 9 is a chart showing the price floating proportion of the commodity of the plurality of transactions of the enterprise. The above cases are visual traceability of enterprise risk scores (risk values). Specific data will not be described in detail herein.

307. And evaluating the association degree value of any two enterprises to be analyzed according to the association relation.

Because the enterprise operation characteristics of different enterprises to be analyzed are determined in the steps, and the risk rule is configured, the association degree value of any two enterprises to be analyzed can be determined according to the association relation between the enterprises to be analyzed, or the association degree can be understood as the relation degree. It should be understood that, in another specific embodiment, if the calculation step is omitted, the association value may be considered to be set by the service personnel according to the experience of the service personnel, and dynamically adjusted according to the service effect, and the specific process of obtaining the association value is not limited herein.

Based on the above embodiments, it may be appreciated that the enterprise to be analyzed includes at least the target enterprise described in the above. Correspondingly, the association degree value of the target enterprise and the enterprise to be analyzed related to the target enterprise can be known.

308. And determining a first enterprise to be analyzed which is associated with the target enterprise according to the association relation, and determining the association degree value of the first enterprise to be analyzed and the target enterprise.

Step 307 in this embodiment is similar to the function of the association evaluation module in fig. 1, and detailed description thereof will be omitted herein. However, it should be noted that the main role of the association relationship assessment is to assess the relationship tightness between entities, and to conduct the risk values in the relationship links. The association relationship can be converted into the association relationship between two different enterprises to be analyzed (the target enterprise and the other enterprise to be analyzed in the step). Referring to fig. 5, fig. 5 is a schematic diagram of risk conduction associated with an enterprise according to an embodiment of the present application. Based on step 307, it may be determined that the target enterprise has a first enterprise to be analyzed associated with the target enterprise according to the association relationship, and in fig. 5, if the enterprise a is the target enterprise, the enterprise B is the first enterprise to be analyzed. For ease of understanding and description, this will not be described in detail later. At this time, the association degree value between the enterprise a and the enterprise B is 0.8.

309. And calculating the association degree value and the target risk value to determine the risk value of the first enterprise to be analyzed.

Based on step 308, in fig. 5, the association value between the enterprise a and the enterprise B and the target risk value 100 of the enterprise a are calculated, specifically, the risk event is triggered by the enterprise a or the current risk score obtained after the calculation in the foregoing step is 100, if the relationship degree between the enterprise a and the enterprise B is 0.8, the risk score of the enterprise B is 80 according to the formula "risk score x relationship degree", and if the relationship degree between the enterprise a and the enterprise B is very close to 1, the risk score of the enterprise B is 100. Specifically, the relevance value here may be obtained in step 307.

In fig. 5, the number smaller than 1 is a conductivity coefficient, i.e., a relevance value, and the number larger than 1 is a risk score (risk value), which may be calculated according to the relevance value, or may be obtained according to the target invoice data and the target enterprise operation characteristics, which will not be described in detail herein.

For the risk value calculated according to the association value, the first enterprise to be analyzed can be used as a target enterprise, the second enterprise to be analyzed which is associated with the target enterprise is determined according to the association relation, and the second enterprise to be analyzed is used as the first enterprise to be analyzed, so that the step of determining the association value of the first enterprise to be analyzed and the target enterprise is executed.

Specifically, in connection with fig. 5, that is, the enterprise B is taken as the target enterprise, and then the enterprise client E associated with the enterprise B is determined according to the association relationship. At this time, the association value between the enterprise B and the enterprise client E is 0.8, and at this time, it can be understood from the above-mentioned enterprise business characteristics and invoice data that the relationship between the enterprise client E and the enterprise B is a guaranteed relationship, and since the risk value of the enterprise B is 80, the risk value of the enterprise client E is 64. It will be understood that the foregoing is by way of example only.

According to the enterprise risk analysis method disclosed by the embodiment, an invoice is used as an analysis main body of a transaction relationship, and industrial and commercial judicial, tax and in-line data are fused, and the service forms an enterprise complex relationship analysis system by modules of data acquisition, basic large graph, service scene graph, relationship evaluation, black and white list and the like, wherein key technologies of large data cleaning, stream processing, graph calculation and the like are introduced, so that the enterprise risk analysis method can be efficiently adapted to each scene of enterprise analysis. Meanwhile, the invoice is used as an important certificate of enterprise transaction, and the reliability of data is more beneficial to improving the accuracy of enterprise risk assessment in credit management and supply chain scenes. And secondly, the method is technically characterized by integrating large data flow calculation and graph calculation, and can improve the complex relation analysis capability of mass data.

Meanwhile, in practical application, the following problems can be solved.

1. Excavating real-time transaction behavior characteristics of enterprises: the full-electricity invoice realizes the instant uploading of enterprise billing data, and the real-time mining transaction behavior characteristics are analyzed through real-time acquisition, big data stream processing and graph model analysis.

2. Enterprise risk timing analysis: based on the transaction time dimension, the complex association relation evolution process of enterprises in different time intervals is dynamically analyzed, and risk traceability is facilitated.

3. The invoice +' establishes a link to drive more application scenes: the invoice data is public data such as enterprise transaction relation as main link, combined with industry and commerce judicial, enterprise credit and the like, tax office side enterprises declare and remit payment data, a high-precision enterprise multidimensional analysis system is constructed, and a plurality of innovative application scenes of banking enterprise wind control and tax office collection management and control are met.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

If the scheme involves sensitive information (e.g., user information, business information), it should be noted that the collection, use and handling of the sensitive information requires compliance with laws and regulations of the relevant country and region, and needs to be performed with approval or consent of the corresponding subject (e.g., user or business, etc.).

Referring to fig. 10, fig. 10 is a schematic structural diagram of an enterprise risk analysis system according to an embodiment of the present disclosure.

An obtaining unit 1001, configured to obtain enterprise operation data of a plurality of enterprises to be analyzed, where the enterprise operation data at least includes a plurality of enterprise operation features and invoice data of any enterprise to be analyzed;

the calculating unit 1002 is configured to calculate a target risk value of a target enterprise according to invoice data and a plurality of enterprise operation features, and determine an association relationship of different enterprise operation features, where the target enterprise is any enterprise to be analyzed, and the association relationship at least includes association relationships of different enterprises to be analyzed;

an evaluation unit 1003, configured to evaluate association values of any two enterprises to be analyzed according to the association relationship;

the determining unit 1004 is configured to determine risk values of other enterprises to be analyzed after the target enterprise is removed according to the relevance value and the target risk value, so that the banking enterprise manages and controls the other enterprises to be analyzed according to the risk values.

Illustratively, the system further comprises: an analysis unit 1005;

the obtaining unit 1001 is specifically configured to trigger an authentication request of an enterprise to be analyzed by the credit investigation organization, and obtain enterprise operation data of the enterprise to be analyzed according to the authentication request;

an parsing unit 1005, configured to parse the enterprise operation data to obtain a plurality of enterprise operation features and invoice data of the enterprise to be analyzed; and the enterprise operation characteristics and the invoice data have a corresponding relation.

Illustratively, the system further comprises: a construction unit 1006, a generation unit 1007, and an execution unit 1008;

a building unit 1006, configured to build a global view according to all enterprise operation features;

the construction unit 1006 is further configured to select any enterprise operation feature from the global view to construct an initial business scenario diagram;

the obtaining unit 1001 is further configured to obtain target invoice data having a corresponding relationship with any enterprise operation feature in the initial service scenario diagram;

a generating unit 1007, configured to write target invoice data into the initial service scene graph, and generate a target service scene graph;

and the execution unit 1008 is configured to execute the step of calculating a target risk value of the target enterprise according to the invoice data and the plurality of enterprise business characteristics according to the target business scenario diagram.

Illustratively, the system further comprises: a configuration unit 1009;

a configuration unit 1009, configured to configure a risk rule;

the obtaining unit 1001 is specifically configured to obtain target invoice data and target business operation characteristics of a target enterprise corresponding to the risk rule, where the target invoice data is invoice data corresponding to the risk rule, and the target business operation characteristics are business operation characteristics corresponding to the risk rule;

the calculating unit 1002 is specifically configured to calculate a target risk value of the target enterprise according to the target invoice data and the target enterprise business characteristics.

Illustratively, the system further comprises: an input unit 1010;

the configuration unit 1009 is further configured to configure operation parameters of the risk operation model according to the target invoice data and the target enterprise operation characteristics;

the input unit 1010 is configured to input target invoice data and target enterprise operation characteristics into a risk operation model, so as to determine a risk degree satisfied by a target enterprise according to operation parameters, the target invoice data and the target enterprise operation characteristics, where the risk degree corresponds to different scale coefficient intervals;

the determining unit 1004 is specifically configured to determine a target risk value according to the risk degree.

Illustratively, the system includes:

A determining unit 1004, configured to determine, according to the association relationship, a first enterprise to be analyzed that has an association with the target enterprise;

the determining unit 1004 is further configured to determine a relevance value between the first enterprise to be analyzed and the target enterprise;

the calculating unit 1002 is specifically configured to calculate the association value and the target risk value to determine a risk value of the first enterprise to be analyzed.

Illustratively, the system further comprises:

the determining unit 1004 is further configured to determine that the first enterprise to be analyzed is a target enterprise;

the determining unit 1004 is further configured to determine, according to the association relationship, a second enterprise to be analyzed that has an association with the target enterprise, and take the second enterprise to be analyzed as the first enterprise to be analyzed, so as to perform the step of determining the association value between the first enterprise to be analyzed and the target enterprise.

Referring to fig. 11, a schematic structural diagram of an enterprise risk analysis device disclosed in an embodiment of the present application includes:

a central processor 1101, a memory 1105, an input-output interface 1104, a wired or wireless network interface 1103, and a power supply 1102;

memory 1105 is a transient memory or persistent memory;

the central processor 1101 is configured to communicate with the memory 1105 and to execute the instructions in the memory 1105 to perform the enterprise risk analysis method of the embodiments shown in fig. 2 or fig. 3 described above.

The embodiment of the application further provides a chip system, which is characterized in that the chip system comprises at least one processor and a communication interface, the communication interface and the at least one processor are interconnected through a line, and the at least one processor is used for running a computer program or instructions to execute the enterprise risk analysis method in the embodiment shown in fig. 2 or fig. 3.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (RAM, random access memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Claims

1. A method of enterprise risk analysis, the method comprising:

2. The enterprise risk analysis method of claim 1, wherein the obtaining enterprise business data for a plurality of enterprises to be analyzed comprises:

3. The business risk analysis method of claim 1, wherein prior to calculating the target risk value for the target business from the invoice data and the plurality of business operations characteristics, the method further comprises:

4. The method of claim 1, wherein calculating a target risk value for a target business from the invoice data and a plurality of the business operations features comprises:

Configuring a risk rule;

5. The business risk analysis method of claim 4, wherein prior to calculating the target risk value for the target business from the target invoice data and the target business operating characteristics, the method further comprises:

And determining the target risk value according to the risk degree.

6. The enterprise risk analysis method according to claim 1, wherein determining risk values of other enterprises to be analyzed after rejecting the target enterprise according to the relevance value and the target risk value includes:

7. The enterprise risk analysis method of claim 6, wherein after calculating the relevance value and the target risk value to determine the risk value for the first enterprise to be analyzed, the method further comprises:

determining the first enterprise to be analyzed as the target enterprise;

8. An enterprise risk analysis system, the system comprising:

9. An enterprise risk analysis device, the device comprising:

The memory is a short-term memory or a persistent memory;

the central processor is configured to communicate with the memory and to execute the instruction operations in the memory to perform the enterprise risk analysis method of any one of claims 1 to 7.

10. A computer readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the enterprise risk analysis method of any one of claims 1 to 7.