CN111754199A - A business ontology-driven enterprise credit relationship graph coarsening method - Google Patents

Abstract

The invention belongs to the technical field of graph data processing, and particularly relates to a business ontology driven enterprise credit relationship graph coarsening method. The invention provides a novel business ontology driven enterprise credit relational graph coarsening method, which provides a multi-field business ontology model for public credit evaluation in the process of coarsening an enterprise credit relational graph, is based on the multi-field business ontology model, is assisted by enterprise data logical relationship information, adopts an Odgca algorithm, has a relatively great advantage in the aspect of the efficiency of coarsening the enterprise credit relational graph, avoids the blindness of the current majority of graph coarsening methods to a certain extent, and can generate a coarsening graph meeting the requirements of users more quickly.

Description

A business ontology-driven enterprise credit relationship graph coarsening method

technical field

The invention belongs to the technical field of graph data processing, and particularly relates to a business ontology-driven enterprise credit relationship graph coarsening method.

Background technique

Public credit is essentially a special public product provided by specific subjects in the field of public life (such as the government, enterprises, civil organizations, influential individuals, etc.) in the form of fulfilling incomplete contracts or invisible contracts. Data and materials that can be used to identify the basic credit status of commercial entities, public institutions, social organizations and individual citizens (information subjects), which are generated or mastered by the above-mentioned specific subjects in the course of performing their duties. Among them, enterprises are the most active main subjects in the field of public life. Based on social public credit data, using the enterprise credit map model, it is of great significance to provide technical tools for the construction of a new credit-based supervision mechanism, and to provide data support for the government to ensure people's livelihood and develop economic and government affairs decisions.

The corporate credit map is a solidification of expert experience, which can support the accumulation and reuse of knowledge and tools, and has a strong ability to express relationships. , mortgage relationship, affiliated enterprises, and bidding relationship mining credit information, which can support complex risk pattern mining, with better interpretability and display effect. Then, the scale of the enterprise credit graph is large, with more than 200 million enterprise entity nodes alone, and the scale of the relationship is even larger. Therefore, it is necessary to use a graph coarsening algorithm to realize the conversion of large-scale graphs to smaller-scale graphs without losing or as little loss of information as possible, which is an important issue to realize the processing and use of large-scale enterprise credit graphs.

The current graph coarsening methods are mostly aimed at graphs crawled and automatically constructed through Internet data. Through the analysis of graph nodes and relationships, supplemented by algorithms to identify nodes and relationships that can be cut or merged, the graph coarsening process does not take users into account. Due to business requirements, the graph coarsening method may have a certain deviation from the user's business needs; the knowledge of business ontology in specific application scenarios is not fully utilized to reduce the complexity of the graph coarsening algorithm, which affects the graph coarsening algorithm to a certain extent. efficiency.

SUMMARY OF THE INVENTION

In order to solve the problems existing in the prior art, the present invention provides a new business ontology-driven enterprise credit relationship graph coarsening method.

The specific technical scheme of the present invention is as follows:

The present invention provides a method for coarsening an enterprise credit relationship graph driven by a business ontology, comprising the following steps:

S1: Receive the input business ontology set OS: {os1, os2, ..., osn}, the enterprise credit relationship graph g and the concern condition condition, and input the business ontology set OS, the enterprise credit relation graph g and the concern condition condition into the business in the ontology model;

S2: Analyze the attention conditions, and generate virtual nodes in the enterprise credit relationship graph according to the parsed attention conditions, and use the Odgca algorithm to coarsen the enterprise credit relationship graph to obtain the coarsened enterprise credit relationship graph g';

S3: Provide business services based on the roughened enterprise credit relationship graph.

The beneficial effects of the present invention are as follows:

The present invention provides a new business ontology-driven enterprise credit relationship graph coarsening method, and the business ontology-driven enterprise credit relationship graph coarsening method proposes a multi-domain business of public credit evaluation in the process of enterprise credit relationship graph coarsening Ontology model, based on multi-domain business ontology model, supplemented by enterprise data logic relationship information, using Odgca algorithm, has a relatively large advantage in the efficiency of enterprise credit relationship graph coarsening, and avoids most of the current graph coarsening to a certain extent. The blindness of the method can generate a coarse map that meets the user's needs more quickly.

Description of drawings

Fig. 1 is the flow chart of the coarsening method of enterprise credit relation graph driven by business ontology of the present invention;

Fig. 2 is the flow chart of Odgca algorithm in step S2;

Fig. 3 is the flow chart of step S24;

4 is a schematic structural diagram of an enterprise credit evaluation business ontology model of the present invention;

5 is a schematic structural diagram of an enterprise credit evaluation area ontology model of the present invention;

6 is a schematic structural diagram of the enterprise credit evaluation industry ontology model of the present invention;

FIG. 7 is a schematic structural diagram of an ontology model in the field of enterprise credit evaluation according to the present invention.

Detailed ways

The present invention will be described in further detail below in conjunction with the accompanying drawings and the following examples.

The present invention provides a business ontology-driven enterprise credit relationship graph coarsening method, as shown in FIG. 1 , comprising the following steps:

S1: Receive the input business ontology set OS: {os1, os2, ..., osn}, the enterprise credit relationship graph g and the concern condition condition, and input the business ontology set OS, the enterprise credit relation graph g and the concern condition condition into the business in the ontology model;

In the field of enterprise credit evaluation, users need to input business concerns. The business concern is one of the input conditions for graph coarsening, and serves as the guiding information for the graph coarsening algorithm.

S2: Analyze the attention conditions, and generate virtual nodes in the enterprise credit relationship graph according to the parsed attention conditions, and use the Odgca algorithm to coarsen the enterprise credit relationship graph to obtain the coarsened enterprise credit relationship graph g';

Analyze the attention conditions, generate virtual nodes in the coarsening graph according to the attention conditions, use the Odgca algorithm to coarsen the graph, perform traversal and aggregation operations on the nodes in the enterprise credit graph, and realize the coarsening of the enterprise credit relationship graph.

S3: Provide business services based on the roughened enterprise credit relationship graph.

After obtaining the coarsened graph, various operations of the enterprise credit evaluation business can be performed based on the coarsened graph, including various queries and statistics. Due to the large granularity and small scale of the coarsened graph, graph queries and graphs can be greatly shortened. Statistical time overhead.

The present invention provides a new business ontology-driven enterprise credit relationship graph coarsening method, and the business ontology-driven enterprise credit relationship graph coarsening method proposes a multi-domain business of public credit evaluation in the process of enterprise credit relationship graph coarsening Ontology model, based on multi-domain business ontology model, supplemented by enterprise data logic relationship information, using Odgca algorithm, has a relatively large advantage in the efficiency of enterprise credit relationship graph coarsening, and avoids most of the current graph coarsening to a certain extent. The blindness of the method can generate a coarse map that meets the user's needs more quickly.

Different application domains have different business ontology models. The present invention is aimed at the field of enterprise credit evaluation, and firstly, a business ontology model of enterprise credit evaluation should be constructed for this field; the business ontology model describes the objective existence entities in the field of enterprise credit evaluation and the logical relationship between entities, and reflects the enterprise credit evaluation. Business needs.

As shown in Figure 2, the Odgca algorithm (a business ontology-driven graph coarsening algorithm) in step S2 includes the following steps:

S21: Traverse the business ontology set OS:{os1,os2,...,osn} according to the concern condition; the concern condition in this step may be the intersection of multiple business ontology

S22: Traverse the nodes in the enterprise credit relationship graph, and generate a virtual business ontology when the concern condition is the intersection of multiple business ontology, and pay attention to multiple business ontology at the same time;

S23: Initialize the roughened enterprise credit relationship graph g' and its nodes. In the initialization stage, the roughened enterprise credit relationship graph g' only includes root nodes and nodes, and both attributes and edges are empty;

S24: Perform an aggregation operation on the nodes in the enterprise credit relationship graph to obtain a coarsened enterprise credit relationship graph g';

As shown in Figure 3, preferably, step S24 specifically includes the following parts:

S241: Determine the type of each node in the enterprise credit relationship graph;

S242: When the type of the node is a company, shrink all the attribute edges of the connection of the company node to the company node, so as to realize the coarsening of the company attribute node and edge;

S243: Determine whether the node of the enterprise credit relationship graph is connected with the virtual business ontology instance node, and if so, add the node of the enterprise credit relationship graph in the coarsening graph;

Preferably, the step of adding a node of the enterprise credit relationship graph in the roughened graph in step S243 includes copying the edge of the node from the enterprise credit relationship graph g to the roughened graph g' and adding the node from the enterprise credit relationship graph g Copy to coarsened image g'.

This embodiment further defines the Odgca algorithm, and the Odgca algorithm is used to coarsen the graph, traverse and aggregate the nodes in the enterprise credit graph, and realize the coarsening of the enterprise credit graph.

In this embodiment, the business ontology model in step S1 includes an enterprise credit evaluation business ontology model and a plurality of sub-business ontology models associated with the enterprise credit evaluation business ontology model. The enterprise credit evaluation business ontology model consists of several categories and various Relationship building between categories.

The categories include industry categories, regional categories, regional categories, enterprise categories, personal categories, and event categories, where regional categories include national subcategories, provincial subcategories, city subcategories, district/county subcategories, park subcategories, and business circles Class and building sub-category, the industry is divided into 20 sub-categories according to the standard of the National Bureau of Statistics, the field is divided into 14 sub-categories according to the government enterprise supervision function, the enterprise category is divided into large-scale enterprise sub-category, small and medium-sized enterprise sub-category and non-business enterprise sub-category kind.

The relationship between the enterprise credit evaluation business ontology model and various categories includes: the enterprise is located in a certain area, the enterprise belongs to a certain field, the individual plays a certain role in the enterprise, and a certain event occurs in the individual/enterprise/field.

As shown in Figure 4, in this embodiment, the enterprise credit evaluation business ontology model preferably has six categories, namely industry, region, region, enterprise, individual and event;

As shown in Figures 5-7, the corresponding sub-business ontology models constructed for each category include but are not limited to the corporate credit evaluation regional ontology model, the corporate credit evaluation industry ontology model, and the corporate credit evaluation domain ontology model.

In this embodiment, the enterprise credit relationship diagram in step 1 is a full amount of data, including the enterprise's own data and the enterprise external relationship diagram. The enterprise credit relationship graph is the target of the graph coarsening algorithm.

In this embodiment, the enterprise credit relationship graph in step S2 includes a plurality of nodes, and the nodes irrelevant to the condition of interest are searched for in these nodes, and the nodes irrelevant to the condition of interest are generated as virtual nodes. After the virtual nodes are produced, the Odgca algorithm is used to coarsen the graph, and the nodes in the enterprise credit graph are traversed and aggregated to realize the coarsening of the enterprise credit graph.

In step S2 of this embodiment, when the attention conditions target at least two different ontologies, the attention conditions of different ontologies are cross-aggregated, and virtual nodes are generated in the enterprise credit relationship graph according to the cross-aggregated attention conditions.

The graph coarsening method of the present invention introduces a business ontology model in the field of enterprise credit evaluation. According to the concerns of different ontologies in the business model of enterprise credit evaluation and the intersection of different business ontology concerns, the rapid graph nodes and relationships that are drawn by business ontology can be coarsened. Since the original enterprise credit relationship graph includes all company nodes, in different enterprise credit evaluation scenarios, users' concerns are different. For example, some users pay attention to the situation of enterprises in different administrative regions, and some users pay attention to different industries. business situation. Under the condition of a specific concern point, the nodes in the original graph have a lot of redundancy, so the present invention drives the graph coarsening algorithm according to the concern condition of different business scenarios, and finally improves the query efficiency of the enterprise credit graph.

In this embodiment, after the coarsened map is obtained in step S3, various operations of the enterprise credit evaluation service can be performed based on the coarsened map, including various queries and statistics.

The implementations and functional operations of the subject matter described in this specification can be implemented in tangible embodied computer software, computer hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of the foregoing . Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, ie, one or more modules of computer program instructions encoded on one or more tangible non-transitory program carriers, for processing by data The device performs or controls the operation of the data processing device.

The term "data processing apparatus" includes all kinds of apparatus, apparatus and machines for processing data, including, by way of example, computers or servers.

A computer program (which may also be called or described as a program, software, software application, module, software module, script, or code) may be written in any form of programming language, including compiled or interpreted or declarative or A procedural language, and a computer program may be developed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program may be stored in a portion of a file that holds other programs or data, for example, one or more scripts stored in a markup language document; in a single file dedicated to the associated program; or in multiple collaborative In a file, for example, a file that stores one or more modules, subroutines, or portions of code. A computer program can be developed to be executed on one computer or on multiple computers, which are located at one site, or distributed over multiple sites and interconnected by a communication network.

The processes and logic flows described in this specification can be performed by one or more computers executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by special purpose logic circuits.

Computers suitable for the execution of a computer program include personal computers or servers.

Computer readable media suitable for storing computer program instructions and data include all forms of nonvolatile memory, media, and memory devices, including, by way of example, semiconductor memory devices, such as internal hard disks or removable disks.

To transmit interactions with a user, implementations of the subject matter described in this specification can be implemented on a computer having a display device, such as a CRT (Cathode Ray Tube) or LCD (Liquid Crystal Display) monitor, for displaying The user displays information; and a keyboard and pointing device, such as a mouse or trackball, with which the user can send input to the computer. Other kinds of devices may also be used to transmit interactions with the user; for example, feedback provided to the user may be any form of sensory feedback, such as visual feedback, etc.; and input from the user may be received in any form, including keyboards input etc. Additionally, a computer can interact with a user by sending documents to and receiving documents from a device used by the user; for example, by sending web pages to the user's client in response to a request received from a web browser web browser on the device.

Embodiments of the subject matter described in this specification may be implemented in a computing system including back-end components such as data servers, or intermediate components such as application servers, or front-end components such as client computers, The client computer has a graphical user interface or web browser through which a user can interact with implementations of the subject matter described in this specification, or the

A computer system includes any combination of one or more of such back-end components, intermediate components, or front-end components. The components in the system may be interconnected by any form or medium of digital data communication, such as a communication network. Examples of communication networks include local area networks ("LAN") and wide area networks ("WAN"), eg, the Internet. __ A computing system may include clients and servers. Clients and servers are usually remote from each other and usually interact through a communication network. The relationship between client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any invention or on what may be claimed, but as features that may embody particular embodiments of particular inventions illustrate. Certain features that are described in this specification in the context of separate implementations can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations independently or in any suitable subcombination. Furthermore, although features may be described above as acting in combination and even initially claimed as such, one or more features from a claimed combination may in some cases be removed from the combination and the claimed combination may turn into a sub-combination or sub-combination deformed.

Similarly, although operations are depicted in the figures in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in a sequential order, or that all illustrated operations are required to achieve desirable results are executed. In certain situations, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above-described embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that program components and systems may generally be integrated in a single software product or packaged into multiple in software products.

Specific implementations of the subject matter have been described. Other implementations are within the scope of the following claims. For example, the activities recited in the claims can be performed in a different order and still achieve desirable results. As one example, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In certain implementations, multitasking and parallel processing may be advantageous.

Claims (10)

1. an enterprise credit relationship graph coarsening method driven by business ontology, is characterized in that, comprises the steps: S1: Receive the input business ontology set OS: {os1, os2, ..., osn}, the enterprise credit relationship graph g and the concern condition condition, and input the business ontology set OS, the enterprise credit relation graph g and the concern condition condition into the business in the ontology model; S2: Analyze the attention conditions, and generate virtual nodes in the enterprise credit relationship graph according to the parsed attention conditions, and use the Odgca algorithm to coarsen the enterprise credit relationship graph to obtain the coarsened enterprise credit relationship graph g'; S3: Provide business services based on the roughened enterprise credit relationship graph. 2. the enterprise credit relationship graph coarsening method driven by business ontology according to claim 1, is characterized in that, the Odgca algorithm of step S2 comprises the following steps: S21: Traverse the business ontology set OS:{os1,os2,...,osn} according to the concern condition; S22: Traverse the nodes in the enterprise credit relationship graph, and generate a virtual business ontology when the concern condition is the intersection of multiple business ontology, and pay attention to multiple business ontology at the same time; S23: Initialize the roughened enterprise credit relationship graph g' and its nodes. In the initialization stage, the roughened enterprise credit relationship graph g' only includes root nodes and nodes, and both attributes and edges are empty; S24: Perform an aggregation operation on the nodes in the enterprise credit relationship graph to obtain a coarsened enterprise credit relationship graph g'; Preferably, step S24 specifically includes the following parts: S241: Determine the type of each node in the enterprise credit relationship graph; S242: When the type of the node is a company, shrink all the attribute edges of the connection of the company node to the company node, so as to realize the coarsening of the company attribute node and edge; S243: Determine whether the node of the enterprise credit relationship graph is connected with the virtual business ontology instance node, and if so, add the node of the enterprise credit relationship graph in the coarsening graph; Preferably, the step of adding a node of the enterprise credit relationship graph in the roughened graph in step S243 includes copying the edge of the node from the enterprise credit relationship graph g to the roughened graph g' and adding the node from the enterprise credit relationship graph g Copy to coarsened image g'. 3. The business ontology-driven enterprise credit relationship graph coarsening method according to claim 1, wherein the business ontology model in step S1 comprises an enterprise credit evaluation business ontology model and a business ontology model associated with the enterprise credit evaluation business ontology model. A plurality of sub-business ontology models, the enterprise credit evaluation business ontology model is constructed by several categories and the relationship with each category. 4. The business ontology-driven enterprise credit relationship graph coarsening method according to claim 3, wherein the categories include industry categories, regional categories, regional categories, enterprise categories, personal categories and event categories, wherein the regional categories Including national sub-category, provincial sub-category, city sub-category, district/county sub-category, park sub-category, business circle sub-category and building sub-category, the industry is divided into 20 sub-categories according to the standards of the National Bureau of Statistics, and the fields are divided according to the government and enterprise supervision functions There are 14 sub-categories, and the enterprise category is divided into large-scale enterprise sub-category, small and medium-sized enterprise sub-category and non-business enterprise sub-category. 5. The business ontology-driven enterprise credit relationship graph coarsening method according to claim 3, wherein the relationship between the enterprise credit evaluation business ontology model and each category comprises: the enterprise is located in a certain area, the enterprise belongs to a certain The domain, the individual's role in the business, and the occurrence of an event by the individual/business/domain. 6 . The business ontology-driven enterprise credit relationship graph coarsening method according to claim 1 , wherein the enterprise credit relationship graph in step 1 is a full amount of data, including enterprise data and an enterprise external relationship graph. 7 . 7. The enterprise credit relationship graph coarsening method driven by business ontology according to claim 1, is characterized in that, in step S2, the enterprise credit relationship graph includes a plurality of nodes, and searches for nodes irrelevant to the conditions of interest in these nodes , and generate nodes irrelevant to the attention condition as virtual nodes. 8. The business ontology-driven enterprise credit relationship graph coarsening method according to claim 6, characterized in that, in step S2, when the attention conditions are aimed at at least two different ontologies, the attention conditions of different ontologies are cross-collected , and generate virtual nodes in the enterprise credit relationship graph according to the attention conditions after the cross collection. 9. The enterprise credit relationship graph upscaling method driven by business ontology according to claim 1, is characterized in that, after the upscaling graph is obtained in step S3, various operations of enterprise credit evaluation business can be performed based on the upscaling graph, Including various queries and statistics. 10. A business ontology-driven enterprise credit relationship graph coarsening system, the system comprising at least one processor; and a memory storing instructions which, when executed by at least one processor, implement the method according to any of claims 1-9.

Images