CN112528038B - Method, device and medium for ensuring communication body uniqueness identification based on multilayer graph structure - Google Patents
Method, device and medium for ensuring communication body uniqueness identification based on multilayer graph structure Download PDFInfo
- Publication number
- CN112528038B CN112528038B CN202011436111.9A CN202011436111A CN112528038B CN 112528038 B CN112528038 B CN 112528038B CN 202011436111 A CN202011436111 A CN 202011436111A CN 112528038 B CN112528038 B CN 112528038B
- Authority
- CN
- China
- Prior art keywords
- guarantee
- link
- bodies
- change
- time point
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Computational Linguistics (AREA)
- Finance (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method, equipment and a medium for guaranteeing uniqueness of a connected object based on a multilayer graph structure, wherein the method comprises the following steps: 1: aiming at bank data, establishing a static guarantee relation map based on the guarantee relation between enterprise clients at a single time point, and acquiring mutually independent guarantee link sets at each time point; 2: labeling the link guarantee relationship sides in the guarantee link set independent from each other at each time point and performing quantity statistics; 3: further identifying and classifying the change trend of the secured link in the secured link set; 4: and constructing a link body change map by taking the guarantee link body set with mutually independent time points as a map node according to the result of identifying and classifying the change trend of the guarantee link bodies in the guarantee link body set, and finally generating a second layer of link bodies and unique identification numbers of corresponding dynamic guarantee link bodies to identify bank data. Compared with the prior art, the method has the advantages that the algorithm efficiency is improved by nearly two times, and the like.
Description
Technical Field
The invention relates to the technical field of financial science and technology, in particular to a method, equipment and a medium for guaranteeing uniqueness identification of a communicator based on a multilayer graph structure.
Background
With the increase of the credit asset scale of banking financial institutions, various guarantee loans are increased, and the risk of guarantee link bodies formed by mutual guarantee or interlinked guarantee among clients is highlighted continuously. Due to the complexity, uncertainty and infectivity of the security federation, security federation credit risk management becomes a weak link in commercial bank credit management. Aiming at the risky guarantee link body risk, commercial banks need to establish a long-acting mechanism for risk evaluation of the guarantee link body, loan risk of the loan of the financial of the loan of the insurance of the loan of the insurance of the people of the insurance of the commercial banks of the insurance of the commercial banks of the commercial bank of the insurance of the commercial bank of the insurance of the commercial bank of the insurance of the.
The general process of the risk evaluation of the security communication body is roughly divided into security data analysis, incidence relation depiction, default risk evaluation, security relation modeling and risk blocking application. The purpose of the security data analysis and the incidence relation depiction is to identify a security UNICOM body formed by enterprise customers, and the unique identification of the security UNICOM sample is also a key basic problem of default risk evaluation and security relation modeling. Therefore, how to determine the risk evaluation object, namely the sample unique identification, is the basis for guaranteeing the risk evaluation modeling of the communicator.
The currently commonly adopted guarantee link body recognition algorithm comprises an exhaustive search method based on a guarantee matrix and a depth-first traversal method based on a guarantee map. The exhaustive search method establishes a guarantee relationship matrix of the current time point, ergodic search is carried out on the first elements in the guarantee matrix in sequence, and the sub-guarantee matrix obtained by each search is a closed guarantee communicator. The depth-first traversal method is used for path traversal based on the guarantee relation graph, and all nodes in each traversal subgraph form a guarantee communication body until all the guarantee communication bodies are closed and do not intersect. These two types of methods present two major pain points:
1. the method is only suitable for analyzing the association relation of the static insurance, and cannot meet the requirement of uniqueness identification of the dynamic insurance communicator. Aiming at a static guarantee relation matrix or a guarantee relation map at a fixed time point, an exhaustive search method and a depth-first traversal method can obtain mutually independent guarantee link body sets. However, for a guarantee relationship matrix or a guarantee relationship map time sequence set which dynamically changes along with time, how to identify a unique guarantee link sample based on the guarantee relationship change between enterprise clients is a problem which cannot be solved by the two methods.
2. The exhaustive search method is less efficient. The exhaustive search method needs to traverse the guarantee relation matrix globally every time when the guarantee communication body is generated, and the algorithm complexity is high. In the face of a large amount of guarantee relationship data and a constantly changing guarantee relationship, an exhaustive search method based on a guarantee relationship matrix is difficult to meet the real-time requirement of application.
The graph structure is a non-relational data structure widely applied in the current risk management field, draws a guarantee map based on enterprise client guarantee relations, can visually depict the guarantee network topology structure and boundary scale, and provides technical support for the prevention and solution of guarantee communicator risks. Aiming at the dynamic guarantee map which changes constantly along with time, a graph algorithm is used for quickly identifying all guarantee communication bodies constructed by the same enterprise client set, unique guarantee communication body sample identifications are given, and the dynamic change trend of the guarantee communication bodies is effectively mined.
The combination of depth-first traversal based on a guarantee map and an exhaustive search method based on a connected body matrix is one of the existing technical schemes. Firstly, respectively constructing guarantee maps for the guarantee relations of enterprise clients at different time points, sequentially executing depth-first path traversal, generating guarantee links by each enterprise client connection subgraph, and acquiring mutually independent guarantee link sets at each time point. Secondly, a communicating body matrix is constructed by utilizing the guarantee communicating body change relation of two adjacent time points, all first and last elements in the communicating body matrix are sequentially subjected to forward and reverse exhaustive search, and the same unique identification is given to the mutually associated communicating bodies.
Although the method of combining the guarantee map and the link matrix can solve the problem of unique identification of the dynamic guarantee link, the method has very low efficiency for large-data-volume enterprise customers. Two rounds of exhaustive search are respectively carried out on each head element and tail element of the guarantee connected body matrix in a forward and reverse direction, each time of exhaustive search needs to traverse the connected body matrix globally, in practice, the scale of a large-scale guarantee network of a bank can reach over ten thousands of nodes, and the time complexity of the method cannot be supported. The uniqueness recognition of the security communicator is the basic work of risk evaluation model training and prediction, and the efficiency of the uniqueness recognition of the security communicator directly influences the response speed of the security communicator risk evaluation model application.
Disclosure of Invention
The present invention is directed to overcome the above-mentioned drawbacks of the prior art, and provides a method, an apparatus, and a medium for guaranteeing uniqueness of a link based on a multi-layer graph structure.
The purpose of the invention can be realized by the following technical scheme:
a method for guaranteeing uniqueness of a link based on a multi-layer graph structure comprises the following steps:
step 1: aiming at bank data, establishing a static guarantee relation map based on the guarantee relation between enterprise clients at a single time point, and acquiring mutually independent guarantee link sets at each time point;
step 2: labeling the link guarantee relationship sides in the guarantee link set independent from each other at each time point and performing quantity statistics;
and step 3: further identifying and classifying the change trend of the secured links in the secured link set based on all the labels and the quantity statistical data;
and 4, step 4: and establishing a link body change map according to the result of identifying and classifying the change trend of the guarantee link bodies in the guarantee link body set by taking the guarantee link body sets with mutually independent time points as graph nodes, and finally generating a second-layer link body with the guarantee link body sets with mutually independent time points as new nodes and the unique identification number of the corresponding dynamic guarantee link body to identify bank data.
Further, the step 1 comprises the following sub-steps:
step 101: aiming at the bank data, establishing a static guarantee map for the guarantee relationship among the inline enterprise clients by taking the inline enterprise clients as nodes and the guarantee relationship among the clients as connecting edges;
step 102: respectively executing depth-first path traversal on the static guarantee maps of all time points, ensuring that no node overlap exists between every two static guarantee communication bodies of all time points, and acquiring mutually independent guarantee communication body sets of all time points;
step 103: and respectively numbering the communication bodies aiming at the guarantee communication body set with mutually independent time points.
Further, the step 2 comprises the following sub-steps:
step 201: aiming at the mutually independent guarantee link set of each time point, comparing enterprise clients in the guarantee link at adjacent time points, and labeling the link guarantee relationship;
step 202: and counting the number of guarantee relationship edges in the guarantee link at each time point.
Further, the step 3 specifically includes: and processing, identifying and classifying the communication body change types according to the communication body side label values, the communication body quantity, the communication body inside number and the newly added side ratio statistical analysis of adjacent time points.
Further, the identifying the variation type of the classification includes:
the inner sides of the communicating bodies are the same, and the number of the communicating bodies is the same;
the communicating bodies are reduced, namely the inner edges of the communicating bodies are the same, the number of the communicating bodies is reduced, and the number of the communicating bodies is unchanged;
when the number of the communicating bodies is more than one, the inner edges of the communicating bodies are the same, the number of the communicating bodies is reduced, and the number of the communicating bodies is increased;
the combination is that the inner side of the communicating body is newly increased, the points are the same and the number of the communicating bodies is reduced;
the special change is that the increase and the disappearance of the inner side of the communicating body are both present;
the inner side of the communicating body is newly increased.
Further, the label in step 2 comprises:
an edge label FLAG _ PRE for indicating edge state change of the previous period and the current period;
the edge label FLAG _ AFT is used for indicating the edge state change of the current period and the next period;
the edge label ORI _ CC _ ID is used to indicate the corresponding guaranteed correspondent number of the edge at the previous period.
Furthermore, the statistics included in the quantity statistics in step 2 include the total number of the edges in the current period and the percentage of newly added edges in the current period.
Further, the step 4 comprises the following sub-steps:
step 401: establishing a correlation edge for the guarantee connected object pairs with the same, reduced, one-time-split and multiple-time-combined total four types of changes at adjacent time points by taking the guarantee connected objects at each time point as graph nodes according to the change types of the guarantee connected objects, and constructing a second layer of guarantee connected object change graph;
step 402: performing depth-first path traversal on the second-layer guarantee link change map again, wherein no node is overlapped between every two generated second-layer links, and nodes in the second-layer links are first-layer links which are in mutual change association;
step 403: and giving a unique identifier to the second layer communication body, and taking the minimum value of the serial number of the first layer communication body as the unique identifier of the dynamic security communication body to identify the bank data according to the rule.
The invention also provides a terminal device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of the method for guaranteeing the uniqueness of the link based on the multilayer graph structure when executing the computer program.
The present invention further provides a computer-readable storage medium, which stores a computer program, which, when executed by a processor, implements the steps of the method for guaranteeing link uniqueness based on a multi-layer graph structure.
Compared with the prior art, the invention has the following advantages:
(1) the existing algorithm for identifying uniqueness of a security communication body is used for searching based on a security matrix or performing one-time depth-first traversal based on a security map, so that the algorithm efficiency is low and the analysis requirement of a dynamic security relationship cannot be met. The invention constructs a multilayer atlas structure based on the guarantee relationship among enterprise clients, carries out statistical analysis and change classification on guarantee UNICOM samples, realizes the uniqueness recognition of the dynamic guarantee UNICOM, improves the efficiency by nearly two times compared with the traditional algorithm, and lays a foundation for the risk evaluation work of the guarantee UNICOM.
(2) According to the technical scheme, a multilayer atlas is constructed based on the dynamic relation among enterprise clients, the uniqueness recognition of the security communication body is completed, the recognition efficiency of the security communication body is improved, a solution for the problem of the uniqueness recognition of the dynamic security communication body is provided, and the analysis requirement of security data which changes constantly along with time is met.
(3) The traditional guarantee communication body uniqueness recognition usually adopts a depth-first traversal based on a guarantee map and an exhaustive search method based on a guarantee matrix, and has the problems of low efficiency, incapability of meeting the analysis requirement of a dynamic guarantee relationship and the like. In order to solve the problems, the invention provides a guarantee connected object uniqueness recognition method based on a multilayer graph structure, which can be used for mining graphical features in a guarantee network by means of technical characteristics of a graph database while improving the connected object recognition efficiency, optimizing the response speed of a risk rating model application and meeting the requirements of dynamic guarantee relationship analysis and providing effective feature variables for guarantee connected object risk evaluation modeling.
Drawings
FIG. 1 is a flow chart of a method in an embodiment of the invention;
fig. 2 is a schematic diagram of a communicator identification step based on a static guarantee map in the embodiment of the present invention, wherein fig. 2(a) is a schematic diagram of a data step of a guarantee relationship at each time point, fig. 2(b) is a schematic diagram of a static guarantee map set step, fig. 2(c) is a schematic diagram of a communicator set step at each time point, and fig. 2(d) is a schematic diagram of a static guarantee communicator numbering step;
FIG. 3 is a schematic diagram of a sample analysis procedure of a UNICOM based on a dynamic guarantee relationship in an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating exemplary types of communication link changes in accordance with an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a processing rule for a communication body type change category according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a unique identification step based on a channel variation map in the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
First, abbreviations and key terms in the technical scheme of the present invention are defined as follows:
the load-carrying communication body: the security circle is a network structure formed by linking security relationships of pledge, mortgage, guarantee and the like of two or more legal customers, and is a special interest body generated by mutual security or environmental security of multiple enterprises. The characteristic of 'honor and loss' is presented, the risk of enterprises in the guarantee Union body is increased sharply in the economic downlink period, the development of the enterprises which run well in the guarantee Union body is influenced, the asset safety of commercial banks is seriously threatened, and even regional financial risk is formed.
The specific technical scheme of the invention is as follows:
the guarantee link uniqueness identification method based on the multilayer graph structure comprises the following four main steps:
1. and (3) identifying the connected body based on the static guarantee map:
and establishing a static guarantee relation map based on the guarantee relation among enterprise clients at a single time point. And acquiring a guarantee link set with mutually independent time points by adopting a depth-first path traversal method based on a guarantee map.
2. UNICOM sample analysis based on the DYNAMIC SHORTENING RELATIONS:
analyzing sample of security link at adjacent time points, and identifying the change of security relationship of enterprise clients in the sample of security link at the previous time point and the current time point, wherein the change comprises the characteristics of existing in the previous period, newly increased in the current period, lost in the current period and the like.
3. And (3) analyzing the change trend of the guarantee link body based on the rule:
the change trend of the guarantee communicating bodies is classified, and the change trend comprises six types including completely identical communicating bodies, communication body reduction, one-to-many disassembly, all-in-one, special change of the communicating bodies and completely new communicating bodies. And analyzing the change types of the guarantee link at the adjacent time points based on the rule according to the change characteristics of the guarantee relationship in the link sample at the adjacent time points.
4. Unique identification based on unicom change maps:
and constructing a second-layer guaranteed link body change map by taking the guaranteed link body of each time point as a map node and the change type of the guaranteed link body of the adjacent time point as a map association edge, and obtaining the link body set with the same identification number by applying a depth-first traversal map algorithm to the second-layer map structure again so as to generate the link body unique identification number of the dynamic guaranteed map.
Third, specific embodiments
Fig. 1 is a schematic diagram of the overall process of the method of the present invention, which shows the main steps of the identification process and their dependency relationships, and the calling relationships among the main functions that can be provided by each step.
The data of the guarantee relationship between the enterprise clients in the line are input after the preprocessing steps of data cleaning, statistical analysis and the like, all the steps of the identification process are established on the basis of the link body identification of the static guarantee map, and the output static guarantee link body set is further mined and analyzed.
The guarantee link uniqueness identification method based on the multilayer diagram structure executes the following processes:
1. and (3) identifying the connected body based on the static guarantee map:
1.1, constructing a static guarantee map for the guarantee relationship among the inline enterprise clients by taking the inline enterprise clients as nodes and the guarantee relationship among the clients as connecting edges, as shown in the graph 2/(a) to 2/(b);
1.2, respectively executing depth-first path traversal on the static guarantee maps of each time point, and ensuring that no node is overlapped between every two static guarantee link bodies of each time point, as shown in figure 2/(c);
and 1.3, respectively numbering the communication bodies aiming at the static insurance communication body set at each time point obtained in the previous step, wherein the numbering rule adopts the time point + sequence number, as shown in the graph 2/(d).
2. Analysis of UNICOM samples based on the DYNAMIC SHORTENING RELATIONS, as shown in FIG. 3:
2.1, comparing the enterprise clients in the link guaranteed by adjacent time points, and marking the link guaranteed relation side: wherein the edge label FLAG _ PRE indicates the edge state change of the previous period and the current period; the edge label FLAG _ AFT indicates the edge state change of the current period and the next period; the edge label ORI _ CC _ ID indicates the corresponding vouch-for contact number of the edge at the previous stage, as shown in fig. 3;
2.2, counting the number of guarantee relationship edges in the guarantee link at each time point, wherein the number comprises the total number of the edges at the current period and the percentage of newly added edges at the current period.
3. And (3) analyzing the change trend of the guarantee link body based on the rule:
3.1, classifying the form change of the guarantee link, wherein the form change of adjacent time points is totally divided into 6 change types as shown in the following table and fig. 4;
and 3.2, processing the change type of the communication body according to the label value of the communication body side, the number of the communication bodies, the number of the communication body sides and the proportion of the newly added side at adjacent time points, wherein the processing rule is shown in figure 5.
4. Unique identification based on unicom change maps:
4.1, establishing a correlation edge for the guarantee connected object pairs with the same, reduced, one-time-split and multiple-time-combined total four types of changes at adjacent time points by taking the guarantee connected objects at each time point as graph nodes according to the change types of the guarantee connected objects, and constructing a second-layer guarantee connected object change map;
4.2, performing depth-first path traversal again on the second-layer guarantee link change map, wherein no node is overlapped between every two generated second-layer links, and nodes in the second-layer links are first-layer links with mutual change correlation, as shown in fig. 6;
and 4.3, giving a unique identifier to the second layer of communication body, and taking the minimum value of the number of the first layer of communication body as the unique identifier of the dynamic insurance communication body according to the rule.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. A method for guaranteeing uniqueness of a link based on a multilayer graph structure is characterized by comprising the following steps:
step 1: aiming at bank data, establishing a static guarantee relation map based on the guarantee relation between enterprise clients at a single time point, and acquiring mutually independent guarantee link sets at each time point;
step 2: labeling the link guarantee relationship sides in the guarantee link set independent from each other at each time point and performing quantity statistics;
and step 3: further identifying and classifying the change trend of the secured links in the secured link set based on all the labels and the quantity statistical data;
and 4, step 4: establishing a link body change map according to the result of identifying and classifying the change trend of the guarantee link bodies in the guarantee link body set by taking the guarantee link body set with each time point independent from each other as a map node, and finally generating a second-layer link body with each time point independent from each other as a new node and a unique identification number of a corresponding dynamic guarantee link body so as to identify bank data;
the label in the step 2 comprises:
an edge label FLAG _ PRE for indicating edge state change of the previous period and the current period;
the edge label FLAG _ AFT is used for indicating the edge state change of the current period and the next period;
an edge label ORI _ CC _ ID used for indicating the corresponding guarantee communication body number of the edge in the previous period;
the statistics quantity contained in the quantity statistics in the step 2 comprises the total number of the edges in the current period and the ratio of newly added edges in the current period;
the step 4 comprises the following sub-steps:
step 401: establishing a correlation edge for the guarantee connected object pairs with the same, reduced, one-time-split and multiple-time-combined total four types of changes at adjacent time points by taking the guarantee connected objects at each time point as graph nodes according to the change types of the guarantee connected objects, and constructing a second layer of guarantee connected object change graph;
step 402: performing depth-first path traversal on the second-layer guarantee link change map again, wherein no node is overlapped between every two generated second-layer links, and nodes in the second-layer links are first-layer links which are in mutual change association;
step 403: and giving a unique identifier to the second layer communication body, wherein the rule is to take the minimum value of the serial number of the first layer communication body as the unique identifier of the dynamic security communication body to identify the bank data.
2. The method according to claim 1, wherein the step 1 comprises the following sub-steps:
step 101: aiming at the bank data, establishing a static guarantee map for the guarantee relationship among the inline enterprise clients by taking the inline enterprise clients as nodes and the guarantee relationship among the clients as connecting edges;
step 102: respectively executing depth-first path traversal on the static guarantee maps of all time points, ensuring that no node overlap exists between every two static guarantee link bodies of all the time points, and acquiring mutually independent guarantee link body sets of all the time points;
step 103: and respectively numbering the communication bodies aiming at the guarantee communication body set with mutually independent time points.
3. The method according to claim 1, wherein the step 2 comprises the following sub-steps:
step 201: aiming at each time point mutually independent guarantee unicom set, comparing enterprise clients in adjacent time points guarantee unicom, and labeling the guarantee relationship of the unicom;
step 202: and counting the number of guarantee relationship edges in the guarantee link at each time point.
4. The method according to claim 1, wherein the step 3 specifically comprises: and processing, identifying and classifying the communication body change types according to the communication body side label values, the communication body quantity, the communication body inside number and the newly added side ratio statistical analysis of adjacent time points.
5. The method according to claim 4, wherein the identifying the variation type of the classification comprises:
the inner sides of the communicating bodies are the same, and the number of the communicating bodies is the same;
the communicating bodies are reduced, namely the inner edges of the communicating bodies are the same, the number of the communicating bodies is reduced, and the number of the communicating bodies is unchanged;
when the number of the communicating bodies is more than one, the inner edges of the communicating bodies are the same, the number of the communicating bodies is reduced, and the number of the communicating bodies is increased;
the combination is that the inner side of the communicating body is newly increased, the points are the same and the number of the communicating bodies is reduced;
the special change is that the increase and the disappearance of the inner side of the communicating body are both present;
the inner side of the communicating body is newly increased.
6. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for guaranteeing unicom identification based on multi-layer graph structure according to any one of claims 1 to 5 when executing the computer program.
7. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements the steps of a method for guaranteeing link uniqueness based on multi-layer graph structure according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011436111.9A CN112528038B (en) | 2020-12-10 | 2020-12-10 | Method, device and medium for ensuring communication body uniqueness identification based on multilayer graph structure |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011436111.9A CN112528038B (en) | 2020-12-10 | 2020-12-10 | Method, device and medium for ensuring communication body uniqueness identification based on multilayer graph structure |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112528038A CN112528038A (en) | 2021-03-19 |
CN112528038B true CN112528038B (en) | 2022-07-05 |
Family
ID=74999947
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011436111.9A Active CN112528038B (en) | 2020-12-10 | 2020-12-10 | Method, device and medium for ensuring communication body uniqueness identification based on multilayer graph structure |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112528038B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115310609A (en) * | 2022-10-10 | 2022-11-08 | 中信证券股份有限公司 | Method, device and related equipment for constructing derivative guarantee map |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8799177B1 (en) * | 2010-07-29 | 2014-08-05 | Intuit Inc. | Method and apparatus for building small business graph from electronic business data |
CN108510388A (en) * | 2018-05-24 | 2018-09-07 | 深圳市买买提信息科技有限公司 | A kind of guarantee business marking method and device |
CN110209826A (en) * | 2018-02-06 | 2019-09-06 | 武汉观图信息科技有限公司 | A kind of financial map construction and analysis method towards bank risk control |
CN110378786A (en) * | 2019-07-29 | 2019-10-25 | 中国工商银行股份有限公司 | Model training method, promise breaking conduction Risk Identification Method, device and storage medium |
CN111754340A (en) * | 2020-07-03 | 2020-10-09 | 交通银行股份有限公司 | Guarantee network risk investigation system based on graph database |
CN111784495A (en) * | 2020-06-04 | 2020-10-16 | 江苏常熟农村商业银行股份有限公司 | Guarantee ring identification method and device, computer equipment and storage medium |
-
2020
- 2020-12-10 CN CN202011436111.9A patent/CN112528038B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8799177B1 (en) * | 2010-07-29 | 2014-08-05 | Intuit Inc. | Method and apparatus for building small business graph from electronic business data |
CN110209826A (en) * | 2018-02-06 | 2019-09-06 | 武汉观图信息科技有限公司 | A kind of financial map construction and analysis method towards bank risk control |
CN108510388A (en) * | 2018-05-24 | 2018-09-07 | 深圳市买买提信息科技有限公司 | A kind of guarantee business marking method and device |
CN110378786A (en) * | 2019-07-29 | 2019-10-25 | 中国工商银行股份有限公司 | Model training method, promise breaking conduction Risk Identification Method, device and storage medium |
CN111784495A (en) * | 2020-06-04 | 2020-10-16 | 江苏常熟农村商业银行股份有限公司 | Guarantee ring identification method and device, computer equipment and storage medium |
CN111754340A (en) * | 2020-07-03 | 2020-10-09 | 交通银行股份有限公司 | Guarantee network risk investigation system based on graph database |
Also Published As
Publication number | Publication date |
---|---|
CN112528038A (en) | 2021-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109543925A (en) | Risk Forecast Method, device, computer equipment and storage medium based on machine learning | |
CN112597399B (en) | Graph data processing method and device, computer equipment and storage medium | |
Niu et al. | iConViz: Interactive visual exploration of the default contagion risk of networked-guarantee loans | |
CN111639910A (en) | Standing book generation method, device, equipment and storage medium | |
CN111241153A (en) | Enterprise natural person entity comprehensive judgment alignment method and system | |
CN109903045A (en) | Action trail monitoring method, device, computer equipment and medium | |
CN116541792A (en) | Method for carrying out group partner identification based on graph neural network node classification | |
CN118277739A (en) | Method, system, device, medium and program product for analyzing associated account | |
CN117993915A (en) | Transaction behavior detection method based on metamulti-graph heterogeneous graph neural network | |
CN112528038B (en) | Method, device and medium for ensuring communication body uniqueness identification based on multilayer graph structure | |
CN107527289B (en) | Investment portfolio industry configuration method, device, server and storage medium | |
CN115603955B (en) | Abnormal access object identification methods, devices, equipment and media | |
CN116450847A (en) | Enterprise credit assessment method, enterprise credit assessment device, electronic equipment and readable storage medium | |
CN119648377A (en) | Logistic regression enterprise credit assessment method and system based on additive model | |
CN119939310A (en) | A method, system, medium and program product for classifying Ethereum transaction users based on semantic motif differentiation | |
CN114912927A (en) | Block chain anti-fraud analysis method and system | |
CN115982654B (en) | Node classification method and device based on self-supervision graph neural network | |
Apparao et al. | Financial statement fraud detection by data mining | |
Thirumagal et al. | AI-Enhanced IoT Data Analytics for Risk Management in Banking Operations | |
CN115292274B (en) | Data warehouse topic model construction method and system | |
CN114676266A (en) | Conflict identification method, device, equipment and medium based on multilayer relation graph | |
CN119357710B (en) | Enterprise relevance analysis method and device, computer equipment and storage medium | |
CN112347102A (en) | Multi-table splicing method and multi-table splicing device | |
CN113971406A (en) | Network node semantic information mining method and device, storage medium and electronic equipment | |
Pan et al. | Role-oriented dynamic network embedding |
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 |