CN111861120B - Method, device, equipment and computer readable medium for constructing enterprise association graph - Google Patents
Method, device, equipment and computer readable medium for constructing enterprise association graph Download PDFInfo
- Publication number
- CN111861120B CN111861120B CN202010556321.5A CN202010556321A CN111861120B CN 111861120 B CN111861120 B CN 111861120B CN 202010556321 A CN202010556321 A CN 202010556321A CN 111861120 B CN111861120 B CN 111861120B
- Authority
- CN
- China
- Prior art keywords
- association
- target
- enterprise
- enterprises
- nodes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method, a device, equipment and a computer readable medium for constructing an enterprise association graph. The method comprises the following steps: acquiring a target data set, wherein the target data set comprises data of a plurality of target enterprises, and each piece of data comprises an associated characteristic of one target enterprise; dividing enterprises with the same association characteristics in a plurality of target enterprises into the same enterprise group; establishing map nodes for a plurality of target enterprises, and establishing association edges between the nodes for the map nodes in the enterprise group according to association types; and determining the association strength of the association edge by using the association coefficient and the association weight. The application realizes the construction of the enterprise association graph, utilizes the enterprise association graph to represent various association relations existing between enterprises and the association strength between enterprises, and provides a basis for the evaluation of risk propagation between enterprises.
Description
Technical Field
The present application relates to the field of enterprise risk assessment technologies, and in particular, to a method, an apparatus, a device, and a computer readable medium for constructing an enterprise association graph.
Background
With the rapid development of modern society, the threshold of registering and investing enterprises is greatly reduced, and a large number of enterprises are pulled up, wherein a plurality of liability relationships exist for a plurality of enterprises, and the enterprises are not independent individuals and have certain association with personnel and other enterprises. There are various associations between enterprises, but the business association is a kind of association data which is easy to obtain and has higher quality, the enterprises are associated by investment control, personnel job-holding and other business association relations, the association can be direct association or indirect association by other enterprises or personnel, a plurality of enterprises are interwoven together through the explicit or implicit association, and the complex interweaved association also brings propagation and diffusion of risks among the enterprises. For example, because some illegal activities are performed by public security authorities and business administration departments, some enterprises have high risk situations such as fund breakage, bond violations and the like, other enterprises associated with the enterprises may participate in related business activities or benefit transmission exists, and thus risks such as fund loss, personnel suspicion crimes and the like caused by fund breakage of the inauguration enterprises are caused.
At present, in the related art, emotion tendentiousness analysis is performed according to internet text so as to evaluate the risk of an enterprise, but the representation scheme of the association relationship between enterprises is lacking at present, so that the influence of risk transmission on the enterprise cannot be evaluated more accurately from the aspect of the association relationship between enterprises.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The application provides a method, a device, equipment and a computer readable medium for constructing an enterprise association graph, which are used for solving the technical problem of lack of representation of association relations between enterprises.
In a first aspect, the present application provides a method for constructing an enterprise association graph, including: acquiring a target data set, wherein the target data set comprises data of a plurality of target enterprises, and each piece of data in the target data set comprises an associated characteristic of one target enterprise; dividing enterprises with same association characteristics in a plurality of target enterprises into the same enterprise group, wherein the target enterprises in one enterprise group at least have one same association characteristic; establishing map nodes for a plurality of target enterprises, and establishing association edges between the nodes for the map nodes in the enterprise group according to association types, wherein the association types represent association relations among the plurality of target enterprises due to the same association characteristics; and determining the association strength of the association edge by using an association coefficient and an association weight, wherein the association coefficient is used for representing the contribution degree of the association type matched with the association coefficient to risk conduction, and the association weight is used for representing the compactness of the association relationship between enterprises with the association type.
Optionally, before acquiring the target data set, determining the association type, the association coefficient and the association weight according to the following manner is further included: determining the type of the association relation between target enterprises with association characteristics as an association type; and determining the association coefficient and the association weight corresponding to each association type according to the set parameters.
Optionally, building the association edge between the nodes for the graph nodes in the enterprise group according to the association type includes: selecting a target enterprise group from a plurality of enterprise groups, wherein the type of the association relationship between target enterprises in the target enterprise group is a target association type; and establishing association edges of the target association type between every two nodes in the target enterprise group in the map nodes, wherein the association edges comprise two opposite association edges which are opposite to each other.
Optionally, after establishing the association edges of the target association type between every two nodes in the target enterprise group in the map nodes, constructing the association edges between the nodes for nodes in other enterprise groups except the target enterprise group in the following manner: and under the condition that no associated edge exists between any two map nodes in other enterprise groups, constructing associated edges for the two map nodes.
Optionally, in the case that no association edge exists between any two graph nodes in other enterprise groups, after the association edges are constructed for the two graph nodes, the method further includes constructing association edges between nodes for the graph nodes in the multiple enterprise groups simultaneously in the following manner: under the condition that the associated objects pointed by different associated features are the same associated object, determining each enterprise group to which the different associated features belong; and under the condition that no association edge exists between any two map nodes in each enterprise group to which different association features belong, establishing association edges for the two map nodes.
Optionally, determining the association strength of the associated edge using the association coefficient and the association weight includes: and determining the product of the association coefficient matched with the association type of the association edge and the association weight as the association strength of the association edge.
Optionally, determining the association strength of the associated edge using the association coefficient and the association weight further includes: in the case where there are a plurality of association types for one association side, the maximum value among the plurality of association strengths is determined as the association strength of the association side.
In a second aspect, the present application provides a device for constructing an enterprise association graph, including: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring a target data set, the target data set comprises data of a plurality of target enterprises, and each piece of data in the target data set is an associated characteristic of one target enterprise; the grouping module is used for dividing enterprises with the same association characteristics in a plurality of target enterprises into the same enterprise group, and the target enterprises in one enterprise group at least have one same association characteristic; the construction module is used for building map nodes for a plurality of target enterprises, constructing association edges between the nodes for the map nodes in the enterprise group according to association types, wherein the association types represent association relations among the plurality of target enterprises due to the same association characteristics; the association strength determining module is used for determining association strength of the association edge by using an association coefficient and an association weight, wherein the association coefficient is used for representing contribution degree of association type matched with the association coefficient to risk conduction, and the association weight is used for representing closeness of association relation between enterprises with the association type.
In a third aspect, the present application provides a computer device comprising a memory, a processor, the memory having stored thereon a computer program executable on the processor, the processor executing the computer program to perform the steps of any of the methods of the first aspect.
In a fourth aspect, the application also provides a computer readable medium having non-volatile program code executable by a processor, the program code causing the processor to perform any of the methods of the first aspect.
Compared with the related art, the technical scheme provided by the embodiment of the application has the following advantages:
according to the method, the target data set is obtained, the target data set comprises data of a plurality of target enterprises, and each piece of data comprises the associated characteristics of one target enterprise; dividing enterprises with the same association characteristics in a plurality of target enterprises into the same enterprise group; establishing map nodes for a plurality of target enterprises, and establishing association edges between the nodes for the map nodes in the enterprise group according to association types; and determining the association strength of the association edge by using the association coefficient and the association weight. The construction of the enterprise association graph is realized, various association relations existing between enterprises and the association strength between the enterprises are represented by the enterprise association graph, and a basis is provided for the evaluation of risk propagation between enterprises.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it will be apparent to those skilled in the art that other drawings can be obtained according to these drawings without inventive effort.
FIG. 1 is a schematic view of an alternative method for constructing an enterprise association graph according to an embodiment of the present application;
FIG. 2 is a flowchart of an alternative method for constructing an enterprise association graph according to an embodiment of the present application;
fig. 3 is a block diagram of an alternative enterprise association graph construction apparatus according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the following description, suffixes such as "module", "component", or "unit" for representing elements are used only for facilitating the description of the present application, and are not of specific significance per se. Thus, "module" and "component" may be used in combination.
In the related art, emotion tendentiousness analysis is performed according to internet text so as to evaluate the risk of an enterprise, but the enterprise is not a completely independent individual and has certain association with personnel and other enterprises. The enterprises have various relations, such as investment relations, common legal relations and the like, can be direct relations, can be indirect relations through other enterprises or people, are interwoven together through the explicit or implicit relations, and are the complex interleaving relations which bring about propagation and diffusion of risks among the enterprises. In the case that individual enterprises are detected by public security authorities and business administrative departments due to certain illegal activities or high-risk situations such as fund breakage, bond violations and the like occur, the enterprises are called inauguration enterprises. Enterprises associated with the inauguration enterprises may participate in the operation activities of the inauguration enterprises, the beneficial transmission with the inauguration enterprises and the like, and may also be subjected to risks such as funds loss caused by the funds breakage of the inauguration enterprises, crimes of personnel and the like, so that the enterprises associated with the inauguration enterprises also have a certain risk. From the perspective of risk propagation, the closer the association with a inauguration enterprise, the higher the inauguration of the enterprise. Under the knowledge, the technical scheme of the application constructs the enterprise association graph based on the business association relationship, provides a knowledge graph for describing the direct connection and the indirect connection of enterprises through various association relationships, distinguishes and comprehensively considers various association relationships among enterprises from the perspective of risk propagation, and finally determines the association strength, thereby providing a knowledge base for the evaluation of enterprise risk propagation.
According to an aspect of the embodiment of the application, an embodiment of a method for constructing an enterprise association graph is provided.
Alternatively, in the embodiment of the present application, the above method may be applied to a hardware environment composed of the terminal 101 and the server 103 as shown in fig. 1. As shown in fig. 1, the server 103 is connected to the terminal 101 through a network, which may be used to provide services to the terminal or a client installed on the terminal, and a database 105 may be provided on the server or independent of the server, for providing data storage services to the server 103, where the network includes, but is not limited to: a wide area network, metropolitan area network, or local area network, and terminal 101 includes, but is not limited to, a PC, a cell phone, a tablet computer, etc.
The method for constructing the enterprise association graph in the embodiment of the present application may be executed by the server 103, or may be executed by the server 103 and the terminal 101 together, as shown in fig. 2, and the method may include the following steps:
in step S202, a target data set is acquired, where the target data set includes data of a plurality of target enterprises, and each piece of data in the target data set includes an associated feature of a target enterprise.
In the embodiment of the present application, the target data set may be a data set including a large amount of enterprise information, and preferably, the embodiment of the present application is described by using an industrial and commercial data set, which is denoted by D. Each piece of data D in the business data set D may include data of a business name, a legal person, a natural person stakeholder, a high-level manager, a contact phone, a contact mailbox, a business to investment ratio of the business investment, a business to stock ratio of the business stock, and the like. The corporate, natural person stakeholders, high management, contact phones, contact mailboxes and the like can be used as association features, and under the condition of having the same association features, the relationship between enterprises with the same association features is indicated, if an A enterprise and a B enterprise have common natural person stakeholders, the relationship between the A enterprise and the B enterprise exists, and the association features are common natural person stakeholders. For another example, if a person is not only a legal person of the enterprise a but also a high management of the enterprise B, then there is an association relationship between the enterprise a and the enterprise B, and the association features are legal person and high management.
In step S204, the enterprises having the same association characteristics in the multiple target enterprises are divided into the same enterprise group, and the target enterprises in one enterprise group have at least one same association characteristic.
In the embodiment of the application, the enterprises can be grouped according to each association characteristic, one association characteristic is used as an enterprise group, namely, the enterprises with the same association characteristic are combined into the same enterprise group, and because one enterprise has association characteristics such as legal persons, high management, natural person stakeholders, contact phones, contact mailboxes and the like, one enterprise can be simultaneously divided into a plurality of enterprise groups, and all enterprises in the same enterprise group have at least one same association characteristic.
Optionally, the enterprise is recorded as N, the legal person as p, the high tube as sp, the natural person stakeholder as vp, the contact phone as h, and the contact mailbox as m, for example:
the enterprise is divided according to legal persons, and the legal persons are counted in a data set D to obtain (p 1 、p 2 …p n ) Then the enterprises of the same legal person are divided into a group, then the legal person p i The enterprise represented by the juggle may be recorded asAll enterprises in the enterprise group have the same legal person p i ；
The enterprise is partitioned by high pipes, and the high pipes are counted in the data set D to obtain (sp 1 、sp 2 …sp n ) The enterprises with the same height are divided into a group, then the height is sp i The enterprise at pension height can be recorded asAll enterprises in the enterprise group have the same high-pipe sp i ；
Dividing the enterprise according to the natural person stakeholders, and counting the natural person stakeholders in the data set D to obtain (vp) 1 、vp 2 …vp n ) If the enterprises of the same natural stakeholders are divided into a group, the natural stakeholders vp i The enterprise represented by the tenninal natural person stakeholder may be recorded asAll enterprises in the enterprise group have the same natural human stakeholder vp i ；
The enterprise is divided according to the contact phones, and the contact phones are counted in the data set D to obtain (h 1 、h 2 …h n ) If the enterprises of the same contact telephone are divided into a group, the contact telephone is h i Can be recorded as an enterprise ofAll enterprises in the enterprise group have the same contact h i ；
Dividing enterprises according to the contact mailbox, and counting the contact mailbox in the data set D to obtain (m) 1 、m 2 …m n ) If the enterprises of the same contact mailbox are divided into a group, the contact mailbox is m i Can be recorded as an enterprise ofAll enterprises in the enterprise group have the same contact mailbox m i 。
The grouping method aims at the situation of indirect association among enterprises, for example, the enterprises with the indirect association are at least divided into one enterprise group by taking personnel, telephones, mailboxes and the like as the basis for establishing the association.
Optionally, in the embodiment of the present application, the enterprises may be directly associated with each other without grouping, that is, the association relationship between the target enterprise and the inauguration enterprise or multiple target enterprises is a direct association relationship of investment and indicting, and the association features of the direct association relationship may not be grouped, or two directly associated enterprises are independently used as a group, which indicates that the two enterprises have a direct association relationship. For example, if the enterprise a holds a stock for the enterprise B, the enterprise a invests the enterprise B, and the enterprise a directly associates with the enterprise B, the basis for establishing the association relationship is independent of personnel, telephones, mailboxes and the like, and other enterprises do not have the direct association relationship between the enterprise a and the enterprise B at the same time, so that grouping is not needed.
Step S206, establishing graph nodes for a plurality of target enterprises, and establishing association edges between the nodes for the graph nodes in the enterprise group according to association types, wherein the association types represent association relations among the plurality of target enterprises due to the same association characteristics.
In the embodiment of the application, each enterprise is abstracted into nodes, the nodes in the same enterprise group can be constructed into directed edges between the nodes, namely, associated edges, which represent that the enterprises with the same associated characteristics have associated relations, the type of the associated relation, namely, the associated type, namely, the type of the associated characteristics, the associated edges can be represented by E, and the associated type can be represented by T k To represent. For example:
grouping enterprises according to legal persons, and establishing an enterprise N in one enterprise group of the same legal person i And N j The associated edge E between i，j And E is j，i Its association type T (E i，j ) And T (E) j，i ) Are all "common legal persons".
Grouping enterprises according to a high manager, establishing enterprise N in one enterprise group of the same high manager i And N j The associated edge E between i，j And E is j，i Its association type T (E i，j ) And T (E) j，i ) Are all "common high tubes".
Grouping enterprises according to natural person stakeholders, and establishing an enterprise N in one enterprise group of the same natural person stakeholders i And N j The associated edge E between i，j And E is j，i Its association type T (E i，j ) And T (E) j，i ) Are all "common natural stakeholders".
According toThe contact phones group enterprises, and then in an enterprise group of the same contact phone, an enterprise N is established i And N j The associated edge E between i，j And E is j，i Its association type T (E i，j ) And T (E) j，i ) Are all "common telephones".
Grouping enterprises according to the contact mailbox, and establishing enterprise N in one enterprise group of the same contact mailbox i And N j The associated edge E between i，j And E is j，i Its association type T (E i，j ) And T (E) j，i ) Are all "common mailboxes".
In the embodiment of the application, the nodes in different enterprise groups can be also built with the association edges between the nodes, for example, if the legal persons of part of the enterprises and the high-level pipes of other enterprises are the same person, the enterprises with the legal persons and the high-level pipes being the same person can be associated, namely, the nodes which belong to the legal persons and the high-level pipes in the high-level pipe group are the same object are built with the two-way association edges.
In the embodiment of the application, besides establishing the association edges between every two indirect association enterprises (namely, enterprises in the enterprise group because of the indirect association relationship established by personnel, telephones, mailboxes and the like), the association edges between two enterprises can be directly established for investment-oriented enterprises. For example, enterprise N i Invest in enterprise N j Then enterprise N may be established i And N j The associated edge E between i，j And E is j，i ，E i，j Represents N i For N j Controlling the strands, and leading the direction of the related edges to be N i Pointing to N j Its association type T (E i，j ) Is "control of strands", E j，i Represents N j Belonging to N i Is related to the direction of the edge by N j Pointing to N i Its association type T (E j，i ) Is a "subsidiary".
In the embodiment of the application, the association edge between the nodes can be a bidirectional association edge, namely N i Pointing to N j Denoted as E i，j Can alsoTo be composed of N j Pointing to N i Denoted as E j，i 。N i Pointing to N j When N is represented j In association type T (E i，j ) Lower subject N i On the contrary, N j Pointing to N i When N is represented i In association type T (E j，i ) Lower subject N j Is a function of (a) and (b). When it is required to be described, in the embodiment of the present application, the relationship between nodes and the enterprise are not distinguished, that is, the relationship between nodes and the influence between nodes can be actually understood as the relationship between enterprises and the influence between enterprises.
Step S208, determining the association strength of the association edge by using the association coefficient and the association weight, wherein the association coefficient is used for representing the contribution degree of the association type matched with the association coefficient to the risk conduction, and the association weight is used for representing the compactness of the association relationship between enterprises with the association type.
In the embodiment of the application, the association coefficient can be used for representing the contribution degree of the association type of the association edge between two nodes to risk conduction by Cor (T k ) Representation, cor (T) k )∈(0，1]. For example, N i Enterprise pair N j Enterprise control, by N i Pointing to N j Is E at the relevant edge of (2) i，j ，N i And N j With associated type T (E i，j ) For "stock control", the correlation coefficient Cor (T (E i，j ) May be 1, accordingly, because of N i Enterprise pair N j Enterprise controlling, N j The enterprise belongs to N i Subsidiary of the enterprise, made of N j Pointing to N i Is E at the relevant edge of (2) j，i ，N j And N i With associated type T (E j，i ) Is "subsidiary", the association coefficient Cor (T (E j，i ) And) may be 0.9. The association weight is used for representing the compactness of association relation between enterprises with association type, and can be usedTo represent. For example, N i Enterprise pair N j If the enterprise is in control, the enterprise is associated with weight +.>Can be N i For N j In contrast, N j The enterprise belongs to N i Subsidiary of enterprise, associated weight +. >May be 1. The correlation strength can be used to represent the probability that the current enterprise is affected by the enterprise (transfer risk) of risk transfer, and can be represented by S, and N i To N j The risk of transfer, i.e. the associated edge is defined by N i Pointing to N j The association strength can be expressed as +.>Representing the association type as T k Is related to the edge E of (1) i，j The associated strength is possessed.
In the embodiment of the application, N is recorded i And N j Type T of association between them k Is of the correlation strength ofThe correlation strength may be determined by the product of the correlation coefficient and the correlation strength, i.e.: />
In the embodiment of the application, a target data set is obtained, wherein the target data set comprises data of a plurality of target enterprises, and each piece of data comprises the associated characteristics of one target enterprise; dividing enterprises with the same association characteristics in a plurality of target enterprises into the same enterprise group; establishing map nodes for a plurality of target enterprises, and establishing association edges between the nodes for the map nodes in the enterprise group according to association types; the method for determining the association strength of the association edges by using the association coefficients and the association weights realizes that the enterprise association graph is constructed by the association edges among the nodes and the association weights of the association edges, so that the explicit or implicit association relationship among enterprises is represented by using the knowledge graph, and the tightness degree of the association relationship among the enterprises, namely the association strength, can be represented in detail, thereby constructing a foundation for the evaluation of enterprise risk propagation.
Optionally, before acquiring the target data set, the embodiment of the present application further includes determining the association type, the association coefficient and the association weight according to the following manner: determining the type of the association relation between target enterprises with association characteristics as an association type; and determining the association coefficient and the association weight corresponding to each association type according to the set parameters.
In the embodiment of the application, the type of the association relationship between two enterprises can be determined according to the association characteristics between the two enterprises and used as the association type T k From the association type, the association coefficient Cor (T k ) Associated weights
In the embodiment of the present application, the setting parameters may be defined manually, and the setting parameters obtained by the server or the terminal device may be preferably as shown in table 1.
TABLE 1
As can be seen from table 1, the association types of the association relationships between enterprises can include 13 kinds of three kinds, for example:
the association types of the direct association are controlled by two kinds of subsidiary companies, T (E i，j ) For "control" means enterprise N i Invest in enterprise N j . "stock" and "subsidiary" are in opposite relationship to each other, T (E i，j ) For "control strand", then T (E j，i ) Is a "subsidiary" relationship.
The association type based on the personnel is a relation pair consisting of legal personnel, natural personnel stakeholders, high-rise and three types of personnel: (legal person, high pipe), (high pipe, legal person), (legal person, natural person stakeholder), (natural person stakeholder, legal person), (natural person stakeholder, high)Tube), (high tube, natural person stakeholder), T (E i，j ) Is "corporate legal", then represents enterprise N i And enterprise N j There is a common legal person. T (E) i，j ) For "(legal, high-rise)", enterprise N is indicated i The legal person is enterprise N at the same time j High tube. The relationship pairs consisting of legal person, natural person stakeholder and high tube are in opposite relationship to each other, e.g. T (E) i，j ) Is "(legal, high-rise)", then T (E) j，i ) Is a "(high-rise, legal)" relationship. The association type based on personnel in the embodiment of the application belongs to an indirect association type.
Other indirectly associated association types are contact phones and contact mailboxes, T (E i，j ) Representing enterprise N as "Co-telephone i And enterprise N j There is a common contact phone.
Optionally, building the association edge between the nodes for the graph nodes in the enterprise group according to the association type includes: selecting a target enterprise group from a plurality of enterprise groups, wherein the type of the association relationship between target enterprises in the target enterprise group is a target association type; for establishing the association edges of the target association type between every two nodes in the target enterprise group in the map nodes, the association edges comprise two opposite association edges which are in opposite relation with each other.
In the embodiment of the application, the association edges between the nodes can be constructed by selecting one enterprise group and constructing the association edges between every two nodes in the enterprise group. The selected enterprise group is the target enterprise group, and the type of the association relationship in the enterprise group is the target association type.
In the embodiment of the present application, as a preferred manner, the association type of one of the common legal person, the common telephone and the common mailbox may be selected as the target association type, and the enterprise group corresponding to the association type may be performed as the target enterprise group.
Optionally, after establishing the association edges of the target association type between every two nodes in the target enterprise group in the map nodes, constructing the association edges between the nodes for nodes in other enterprise groups except the target enterprise group in the following manner: and under the condition that no associated edge exists between any two map nodes in other enterprise groups, constructing associated edges for the two map nodes.
In the embodiment of the application, after the association edges between every two nodes in the target enterprise group are constructed, the association edges between every two nodes in other enterprise groups can be constructed. Because an enterprise can be divided into multiple enterprise groups, nodes in the multiple target enterprise groups are included in other enterprise groups outside the target enterprise group, and at this time, an association edge is constructed for any two nodes in the other enterprise groups, where no association edge exists between every two nodes. For example, N 1 、N 2 、N 3 Belonging to the same enterprise group, the association type T of the enterprise group k Is "common legal person", N 1 、N 2 、N 3 Two enterprise groups are respectively provided with associated edges, and N is contained 2 、N 3 、N 4 Association type T of the enterprise group k For common high pipe, constructing the associated edge is judging N 2 、N 3 The related edges exist, so that the construction is not repeated, N 2 、N 4 And N 3 、N 4 No associated edge exists between the two, N is 2 、N 4 And N 3 、N 4 And constructing a correlation edge between the two.
Optionally, in the case that no association edge exists between any two graph nodes in the enterprise group, after the association edges are constructed for the two graph nodes, the method further includes constructing the association edges between the nodes for the graph nodes in the multiple enterprise groups simultaneously in the following manner: under the condition that the associated objects pointed by different associated features are the same associated object, determining each enterprise group to which the different associated features belong; and under the condition that no association edge exists between any two map nodes in each enterprise group to which different association features belong, establishing association edges for the two map nodes.
In the embodiment of the application, the legal person, the high-rise person and the natural person stakeholder represent natural persons in reality, so that the legal person of the A enterprise serves as the high-rise person of the B enterprise, and the legal person and the natural person stakeholder exist And under the condition that the high-level, natural person stakeholders are coincident, at this time, the association edges can be constructed for all nodes in two enterprise groups of which the association objects indicated by different association features are the same association object, and the association edges between two nodes can be constructed under the condition that no association edge exists between the two nodes in the two enterprise groups. For example, an association type T of an enterprise group k Is "common legal person", which is p 1 Another enterprise group is associated with type T k Is "common high tube", the high tube is sp 1 If p 1 And sp (sp) 1 All are one person, namely the same object, and association edges are built for the nodes in the two enterprise groups. According to the method, if no associated edges exist between every two adjacent pairs, the associated edges are built.
Alternatively, in the embodiment of the application, for two enterprises directly related, such as two enterprises with a controlled relationship and a controlled relationship, the related edge can be directly constructed.
Optionally, determining the association strength of the associated edge using the association coefficient and the association weight includes: and determining the product of the association coefficient matched with the association type of the association edge and the association weight as the association strength of the association edge.
In the embodiment of the application, after the association edges are constructed for all the nodes in the target enterprise group, corresponding association coefficients and association weights are determined according to association types between every two nodes, specifically referring to the above table 1, and the product of the association coefficients and the association weights is used as the association strength of the association edges.
And determining the association strength of other association edges in the same way, namely determining corresponding association coefficients and association weights according to the association types between every two nodes, and taking the product of the association coefficients and the association weights as the association strength of the association edges.
Optionally, determining the association strength of the associated edge using the association coefficient and the association weight further includes: in the case where there are a plurality of association types for one association side, the maximum value among the plurality of association strengths is determined as the association strength of the association side.
In the embodiment of the application, as the association coefficients and the association weights corresponding to different association types are different, if multiple association types exist between two nodes, the association strength corresponding to each association type is obtained respectively, one with the largest numerical value is selected as the final association strength of the association edge between the two nodes, for example, when the association strength of the association edge between the two nodes with the common high management exists is determined, if the association relationship such as the common legal person exists between the two nodes, the corresponding association coefficient is obtained according to the association type of the common legal person and the like and is 1, the association weight is 1, the association strength corresponding to the common legal person is obtained as the product of the association coefficient and the association weight, namely 1, meanwhile, the corresponding association coefficient is obtained according to the association type of the common high management and is 0.4, the association weight is 1, the association strength corresponding to the common high management is obtained as the product of the association coefficient and the association weight, namely 0.4, and the association strength of the association edge between the two nodes is finally determined as 1.
According to the method, the target data set is obtained, the target data set comprises data of a plurality of target enterprises, and each piece of data comprises the associated characteristics of one target enterprise; dividing enterprises with the same association characteristics in a plurality of target enterprises into the same enterprise group; establishing map nodes for a plurality of target enterprises, and establishing association edges between the nodes for the map nodes in the enterprise group according to association types; and determining the association strength of the association edge by using the association coefficient and the association weight. The construction of the enterprise association graph is realized, various association relations existing between enterprises and the association strength between the enterprises are represented by the enterprise association graph, and a basis is provided for the evaluation of risk propagation between enterprises.
According to still another aspect of the embodiment of the present application, as shown in fig. 3, there is provided an apparatus for constructing an enterprise association graph, including: a data acquisition module 301, configured to acquire a target data set, where the target data set includes data of a plurality of target enterprises, and each piece of data in the target data set is an associated feature of a target enterprise; a grouping module 303, configured to divide enterprises having the same association characteristics in a plurality of target enterprises into the same enterprise group, where the target enterprises in one enterprise group have at least one same association characteristic; the building module 305 is configured to build graph nodes for a plurality of target enterprises, and build association edges between the nodes for the graph nodes in the enterprise group according to association types, where the association types represent association relationships between the plurality of target enterprises due to the same association features; the association strength determining module 307 is configured to determine an association strength of the association edge by using an association coefficient and an association weight, where the association coefficient is used to represent a contribution degree of an association type matched with the association coefficient to risk conduction, and the association weight is used to represent a closeness of an association relationship between enterprises having the association type.
It should be noted that, the data acquisition module 301 in this embodiment may be used to perform step S202 in the embodiment of the present application, the grouping module 303 in this embodiment may be used to perform step S204 in the embodiment of the present application, the building module 305 in this embodiment may be used to perform step S206 in the embodiment of the present application, and the association strength determination module 307 in this embodiment may be used to perform step S208 in the embodiment of the present application.
It should be noted that the above modules are the same as examples and application scenarios implemented by the corresponding steps, but are not limited to what is disclosed in the above embodiments. It should be noted that the above modules may be implemented in software or hardware as a part of the apparatus in the hardware environment shown in fig. 1.
Optionally, the device for constructing the enterprise association graph further includes: the association type determining module is used for determining the type of the association relationship between the target enterprises with the association characteristics as the association type; and the parameter determining module is used for determining the association coefficient and the association weight corresponding to each association type according to the set parameters.
Optionally, the device for constructing the enterprise association graph further includes: the selection module is used for selecting a target enterprise group from a plurality of enterprise groups, and the type of the association relationship between the target enterprises in the target enterprise group is a target association type; the first construction module is used for establishing association edges of the target association type between every two nodes in the target enterprise group in the map nodes, wherein the association edges comprise two opposite association edges which are in opposite relation with each other.
Optionally, the device for constructing the enterprise association graph further includes: and the second construction module is used for constructing the association edge for any two map nodes in the enterprise group under the condition that the association edge does not exist between the two map nodes.
Optionally, the device for constructing the enterprise association graph further includes: the enterprise group determining module is used for determining each enterprise group to which different association features belong under the condition that the association objects pointed by the different association features are the same association object; and the third construction module is used for constructing the association edges for any two map nodes in each enterprise group to which the different association features belong under the condition that the association edges do not exist between the two map nodes.
Optionally, the device for constructing the enterprise association graph further includes: and the calculating module is used for determining the product of the association coefficient matched with the association type of the association edge and the association weight as the association strength of the association edge.
Optionally, the device for constructing the enterprise association graph further includes: and the comparison determining module is used for determining the maximum value of the plurality of association strengths as the association strength of the association edge under the condition that a plurality of association types exist in one association edge.
According to yet another aspect of the embodiments of the present application, there is also provided a computer device including a memory, a processor, the memory storing a computer program executable on the processor, the processor implementing the above steps when executing the computer program.
The memory and the processor in the computer device communicate with the communication interface through a communication bus. The communication bus may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The communication bus may be classified as an address bus, a data bus, a control bus, or the like.
The memory may include random access memory (Random Access Memory, RAM) or non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
There is also provided in accordance with yet another aspect of an embodiment of the present application a computer readable medium having non-volatile program code executable by a processor.
Optionally, in an embodiment of the present application, the computer readable medium is arranged to store program code for the processor to:
step S202, acquiring a target data set, wherein the target data set comprises data of a plurality of target enterprises, and each piece of data in the target data set comprises an associated feature of one target enterprise;
step S204, dividing enterprises with same association characteristics in a plurality of target enterprises into the same enterprise group, wherein the target enterprises in one enterprise group at least have one same association characteristic;
step S206, establishing graph nodes for a plurality of target enterprises, and establishing association edges between the nodes for the graph nodes in the enterprise group according to association types, wherein the association types represent association relations among the plurality of target enterprises due to the same association characteristics;
step S208, determining the association strength of the association edge by using the association coefficient and the association weight, wherein the association coefficient is used for representing the contribution degree of the association type matched with the association coefficient to the risk conduction, and the association weight is used for representing the compactness of the association relationship between enterprises with the association type.
Alternatively, specific examples in this embodiment may refer to examples described in the foregoing embodiments, and this embodiment is not described herein.
When the embodiment of the application is specifically implemented, the above embodiments can be referred to, and the application has corresponding technical effects.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the processing units may be implemented within one or more application specific integrated circuits (Application Specific Integrated Circuits, ASIC), digital signal processors (Digital Signal Processing, DSP), digital signal processing devices (DSP devices, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field-Programmable Gate Array, FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented by means of units that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
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, and are not repeated herein.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple modules 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 the embodiments 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 functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the embodiments of the present application may be embodied in essence or a part contributing to the prior art or a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing 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 method described in the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc. It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is only a specific embodiment of the application to enable those skilled in the art to understand or practice the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The method for constructing the enterprise association graph is characterized by comprising the following steps of:
acquiring a target data set, wherein the target data set comprises data of a plurality of target enterprises, and each piece of data in the target data set comprises an associated feature of one target enterprise;
dividing enterprises with the same association characteristics in the target enterprises into the same enterprise group, wherein the target enterprises in one enterprise group have at least one same association characteristic;
establishing a graph node for the plurality of target enterprises, and establishing an association edge between nodes for the graph node in the enterprise group according to an association type, wherein the association type represents an association relationship between the plurality of target enterprises due to the same association characteristic;
Determining the association strength of the association edge by using an association coefficient and an association weight, wherein the association coefficient is used for representing the contribution degree of the association type matched with the association coefficient to risk conduction, and the association weight is used for representing the compactness of association relation among enterprises with the association type;
constructing the association edge between the nodes for the graph nodes in the enterprise group according to the association type comprises:
selecting a target enterprise group from a plurality of enterprise groups, wherein the type of the association relationship between the target enterprises in the target enterprise group is a target association type;
establishing association edges of the target association type between every two nodes in the target enterprise group in the map nodes, wherein the association edges comprise two opposite association edges which are in opposite relation;
and under the condition that the association edges do not exist between any two map nodes in other enterprise groups except the target enterprise group, constructing the association edges for the two map nodes.
2. The method of claim 1, further comprising, prior to obtaining a target data set, determining the association type, the association coefficient, and the association weight as follows:
Determining the type of the association relationship between the target enterprises with the association characteristics as the association type;
and determining the association coefficient and the association weight corresponding to each association type according to the set parameters.
3. The method of claim 1, wherein in the absence of the associated edge between any two of the graph nodes in the other enterprise groups, after constructing associated edges for two of the graph nodes, further comprising simultaneously constructing the associated edges between nodes for the graph nodes in the plurality of enterprise groups as follows:
under the condition that the associated objects pointed by different associated features are the same associated object, determining each enterprise group to which the different associated features belong;
and under the condition that the association edges do not exist between any two map nodes in each enterprise group to which the different association features belong, constructing the association edges for the two map nodes.
4. A method according to any one of claims 1 to 3, wherein determining the association strength of the associated edge using an association coefficient and an association weight comprises:
The product of the association coefficient and the association weight, which are matched with the association type of the association edge, is determined as the association strength of the association edge.
5. The method of claim 4, wherein determining the association strength of the associated edge using an association coefficient and an association weight further comprises:
in the case where there are a plurality of association types for one of the association sides, a maximum value among a plurality of association strengths is determined as the association strength of the association side.
6. The device for constructing the enterprise association graph is characterized by comprising the following components:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring a target data set, the target data set comprises data of a plurality of target enterprises, and each piece of data in the target data set comprises an associated characteristic of one target enterprise;
the grouping module is used for dividing enterprises with the same association characteristics in the plurality of target enterprises into the same enterprise group, wherein the target enterprises in one enterprise group at least have one same association characteristic;
the construction module is used for building map nodes for the target enterprises, and building association edges between the nodes for the map nodes in the enterprise group according to association types, wherein the association types represent association relations among the target enterprises due to the same association characteristics;
The association strength determining module is used for determining association strength of the association edges by using association coefficients and association weights, wherein the association coefficients are used for representing contribution degrees of association types matched with the association coefficients to risk conduction, and the association weights are used for representing closeness of association relations among enterprises with the association types;
the building module is further configured to select a target enterprise group from a plurality of enterprise groups, where a type of association relationship between the target enterprises in the target enterprise group is a target association type;
establishing association edges of the target association type between every two nodes in the target enterprise group in the map nodes, wherein the association edges comprise two opposite association edges which are in opposite relation;
and under the condition that the association edges do not exist between any two map nodes in other enterprise groups except the target enterprise group, constructing the association edges for the two map nodes.
7. A computer device comprising a memory, a processor, the memory having stored therein a computer program executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the method of any of the preceding claims 1 to 5.
8. A computer readable medium having non-volatile program code executable by a processor, the program code causing the processor to perform the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010556321.5A CN111861120B (en) | 2020-06-17 | 2020-06-17 | Method, device, equipment and computer readable medium for constructing enterprise association graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010556321.5A CN111861120B (en) | 2020-06-17 | 2020-06-17 | Method, device, equipment and computer readable medium for constructing enterprise association graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111861120A CN111861120A (en) | 2020-10-30 |
| CN111861120B true CN111861120B (en) | 2023-10-13 |
Family
ID=72986216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010556321.5A Active CN111861120B (en) | 2020-06-17 | 2020-06-17 | Method, device, equipment and computer readable medium for constructing enterprise association graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111861120B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819353A (en) * | 2021-02-07 | 2021-05-18 | 撼地数智(重庆)科技有限公司 | Risk analysis method based on enterprise graph and computer equipment |
| CN113688287A (en) * | 2021-08-24 | 2021-11-23 | 撼地数智(重庆)科技有限公司 | Enterprise risk infection path analysis method, device, equipment and storage medium |
| CN115170271B (en) * | 2022-09-09 | 2023-05-12 | 中证数智科技(深圳)有限公司 | Clustering method, device, equipment and storage medium for risk associated enterprises |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107665252A (en) * | 2017-09-27 | 2018-02-06 | 深圳证券信息有限公司 | A kind of method and device of creation of knowledge collection of illustrative plates |
| CN108647981A (en) * | 2018-05-17 | 2018-10-12 | 阿里巴巴集团控股有限公司 | A kind of target object incidence relation determines method and apparatus |
| CN109271426A (en) * | 2018-10-10 | 2019-01-25 | 中科鼎富（北京）科技发展有限公司 | Enterprise's association relationship analysis method, device and computer readable storage medium |
| CN109670944A (en) * | 2018-12-19 | 2019-04-23 | 信雅达系统工程股份有限公司 | A kind of rating business credit method and system based on map relational network |
| CN110738388A (en) * | 2019-09-02 | 2020-01-31 | 深圳壹账通智能科技有限公司 | Method, device, equipment and storage medium for risk conduction of associated map evaluation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100169134A1 (en) * | 2008-12-31 | 2010-07-01 | Microsoft Corporation | Fostering enterprise relationships |
-
2020
- 2020-06-17 CN CN202010556321.5A patent/CN111861120B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107665252A (en) * | 2017-09-27 | 2018-02-06 | 深圳证券信息有限公司 | A kind of method and device of creation of knowledge collection of illustrative plates |
| CN108647981A (en) * | 2018-05-17 | 2018-10-12 | 阿里巴巴集团控股有限公司 | A kind of target object incidence relation determines method and apparatus |
| CN109271426A (en) * | 2018-10-10 | 2019-01-25 | 中科鼎富（北京）科技发展有限公司 | Enterprise's association relationship analysis method, device and computer readable storage medium |
| CN109670944A (en) * | 2018-12-19 | 2019-04-23 | 信雅达系统工程股份有限公司 | A kind of rating business credit method and system based on map relational network |
| CN110738388A (en) * | 2019-09-02 | 2020-01-31 | 深圳壹账通智能科技有限公司 | Method, device, equipment and storage medium for risk conduction of associated map evaluation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111861120A (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111861120B (en) | Method, device, equipment and computer readable medium for constructing enterprise association graph | |
| CN106952159B (en) | Real estate collateral risk control method, system and storage medium | |
| CN107767262B (en) | Information processing method, apparatus and computer readable storage medium | |
| CN109918454B (en) | Method and device for embedding nodes into relational network graph | |
| Scholl et al. | Detecting spatial clustering using a firm-level cluster index | |
| US10325177B1 (en) | System, device, and method for image anomaly detection | |
| US20140358805A1 (en) | Illegal Activity Detection through Interpersonal Relationship Resolution | |
| CN110135978B (en) | User financial risk assessment method and device, electronic equipment and readable medium | |
| CN111861119B (en) | Enterprise risk data processing method and device based on enterprise risk association graph | |
| CN110378575B (en) | Overdue event refund collection method and device and computer readable storage medium | |
| WO2023185539A1 (en) | Machine learning model training method, service data processing method, apparatuses, and systems | |
| Popli et al. | Educational attainment and wage inequality in Turkey | |
| CN110807699B (en) | Overdue event payment collection method and device and computer readable storage medium | |
| Major et al. | No WAN's land: Mapping US broadband coverage with millions of address queries to ISPs | |
| CN110135684A (en) | A kind of capability comparison method, capability comparison device and terminal device | |
| CN110119979A (en) | House property assessment system recommended method, device and server based on data analysis | |
| CN111144673A (en) | Method, device and equipment for evaluating structure of organization personnel and computer readable medium | |
| CN111105064A (en) | Method and device for determining suspected information of fraud event | |
| WO2020000768A1 (en) | Real estate appraisal method and apparatus, computer device and computer readable storage medium | |
| US11348115B2 (en) | Method and apparatus for identifying risky vertices | |
| CN107767278B (en) | Method and device for constructing community hierarchy | |
| CN109685129A (en) | A kind of multiclass social application subject information cluster association method based on smart phone | |
| CN111709472B (en) | Method for dynamically fusing rules to fraud behavior recognition model | |
| CN112419050B (en) | Credit evaluation method and device based on telephone communication network and social behavior | |
| US20100228792A1 (en) | System for Conducting Persistent Periodic Common Weighted Background Investigations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |