CN114881801A - Group stock right penetration conduction method and system based on knowledge graph - Google Patents
Group stock right penetration conduction method and system based on knowledge graph Download PDFInfo
- Publication number
- CN114881801A CN114881801A CN202210644357.8A CN202210644357A CN114881801A CN 114881801 A CN114881801 A CN 114881801A CN 202210644357 A CN202210644357 A CN 202210644357A CN 114881801 A CN114881801 A CN 114881801A
- Authority
- CN
- China
- Prior art keywords
- enterprises
- matrix
- stock
- enterprise
- degrees
- 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.)
- Pending
Links
Images
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a knowledge graph-based group stock right penetration and transmission method and a knowledge graph-based group stock right penetration and transmission system, which comprises the following steps of: extracting the equity investment relationship of an enterprise, and constructing an enterprise equity relationship map; obtaining an enterprise list within any 5 degrees through a relation map, obtaining the direct stock holding proportion of all enterprises within the current 5 degrees, and forming a matrix M 1 (ii) a Calculating the stock right transfer matrix P of all enterprises within 5 degrees currently according to the stock right transfer function defined by the second point; calculating transition probability matrix M of 2, 3, 4 and 5 degrees respectively 2 、M 3 、M 4 And M 5 (ii) a Accumulating and summing to obtain result matrix, where result is M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 +C 4 *M 5 (ii) a And acquiring the direct or indirect stock holding ratio among all enterprises within 5 degrees from the result matrix. The invention considers the real control person and the relative relation of enterprises through self-defining the stock right transfer functionThe stock right improves the identification capability of the hidden stock right penetrating relationship, and the shareholder relationship among enterprises and the enterprise composition of each group are visually displayed by combining the relationship map, so that auditors can quickly and efficiently consult.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a knowledge graph-based group stock right penetration conduction method and system.
Background
The group is a multi-element and multi-level joint organization composed of a plurality of companies, and is mainly characterized in that member companies are directly or indirectly controlled by a common third party on the equity or operation decision, and the like. In supervision and audit work, the major inspection of abnormalities such as multi-head credit granting, excessive credit granting, improper credit allocation and the like is often required, and the abnormalities are one of the monitoring difficulties in the credit granting process.
The existing group association audit model is a traditional audit model constructed on a relational database, and the relational database has limitations in expression and searching for association relations. For example, first, relational databases are fundamentally unsuitable for representing associations, and for association-type data, associations are the essence of data, and the relationships themselves can be directly stored with respect to a graph database, and relational databases can only indirectly represent associations between data via a two-dimensional table. Secondly, the complexity of the relational database is increased exponentially along with the increase of the relation quantity when searching the incidence relation, that is, the complex relation needs to be searched by connecting for many times, and the useless connection is probably more due to the paradigm design; more importantly, the relational database cannot be directly used for searching the graph and cannot conveniently obtain the associated community. In view of these limitations, existing auditing models have great defects in mining group association, one model result in depth only represents one-to-two layer relationships, and group community mining integrating multiple relationships in breadth needs a great deal of manpower consumed by auditors.
In view of the above-mentioned drawbacks, the prior invention document (application No. 202010183474.X, name: an enterprise affiliation attribution analysis method and system based on equity penetration) describes that all stakeholders of an enterprise to be analyzed are determined by calculating the upwardly diverging equity link ratio of each enterprise to be analyzed, and final affiliation data is generated by retrieving the associated enterprise to be analyzed related to the final stakeholder. However, the technical scheme still has the defects that firstly, the method only simply conducts the equity according to the equity link product, and the equity attenuation problem caused by overlong links is not considered. Secondly, the method is not combined with a knowledge graph platform, and the visualization function is deficient.
Therefore, it is necessary to provide a knowledge graph-based group equity penetration transmission method and system to calculate the direct and indirect equity holding ratio of all enterprises within 5 degrees and improve the accuracy and recall rate of group association relationship investigation.
Disclosure of Invention
The invention aims to provide a knowledge graph-based group stock right penetration and transmission method and a knowledge graph-based group stock right penetration and transmission system, so that the direct and indirect stock holding proportion of enterprises within 5 degrees can be calculated, and the accuracy and the recall rate of group association relation investigation can be improved.
In order to solve the problems in the prior art, the invention provides a knowledge graph-based group stock right penetration conduction method, which comprises the following steps:
extracting the equity investment relationship of an enterprise, and constructing an enterprise equity relationship map by using a knowledge map platform;
obtaining an enterprise list within any 5 degrees through a relation map, obtaining the direct stock holding proportion of all enterprises within the current 5 degrees, and forming a matrix M 1 Matrix M 1 The ith row and the jth column in the matrix represent the direct stock holding ratio of i enterprises to j enterprises, wherein the ith row represents any row in the matrix, and the jth column represents any column in the matrix;
and calculating a stock right transfer matrix P of all enterprises within 5 degrees at present according to the stock right transfer function defined by the second point, wherein the stock right transfer function defined by the second point is as follows:
wherein f (x) is the right to stockData in the conduction matrix P, x being the matrix M 1 F (x) and x are in one-to-one correspondence;
calculating transition probability matrix M of 2, 3, 4 and 5 degrees respectively 2 、M 3 、M 4 And M 5 Wherein M is 2 ＝PM 1 ，M 3 ＝P 2 M 1 ，M 4 ＝P 3 M 1 ，M 5 ＝P 4 M 1 ；
Accumulating and summing to obtain result matrix, where result is M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 +C 4 *M 5 In which C is 1 、C 2 、C 3 And C 4 Setting according to the actual penetration distance;
and acquiring direct or indirect stock holding proportion among all enterprises within 5 degrees from the result matrix, wherein the data in the ith row and the jth column represents the direct or indirect stock holding proportion of the i enterprise to the j enterprise.
Optionally, in the knowledge-graph-based group share right penetration conduction method, 1 degree represents a direct holding relationship; 2, representing an indirect stock holding relation, and holding stocks only through one enterprise; 3, representing an indirect stock holding relation, and holding stocks through two enterprises; 4-degree represents the indirect stock holding relationship, and stock holding is carried out through three enterprises; the 5-degree represents the indirect stock holding relationship, and stock holding is carried out through four enterprises.
Optionally, in the knowledge-graph-based group stock right penetration and transmission method, if there are only 2-degree enterprises, only M is calculated 2 ，result＝M 1 +C 1 *M 2 (ii) a If there are only 3-degree enterprises, only M is calculated 2 And M 3 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 (ii) a If there are only 4-degree enterprises, only M is calculated 2 、M 3 And M 4 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 。
Optionally, in the knowledge-graph-based group stock right penetration conduction method, the matrix M 1 Total number of rows and total number of columns ofAnd the like, and is equal to the number of enterprises within 5 degrees currently.
Optionally, in the knowledge-graph-based group stock right penetration conduction method, C 1 、C 2 、C 3 And C 4 The value range of (a) is not less than 0 and not more than 1.
The invention also provides a knowledge graph-based group stock right penetrating and conducting system, which comprises the following modules:
the information acquisition module is used for extracting the equity investment relationship of the enterprise;
the map construction module is used for constructing an enterprise stock right relation map by using a knowledge map platform;
the stock right calculation module is used for acquiring an enterprise list within any 5 degrees through the relationship map, acquiring the direct stock holding proportion of all enterprises within the current 5 degrees and forming a matrix M 1 Matrix M 1 The ith row and the jth column in the matrix represent the direct stock holding ratio of i enterprises to j enterprises, wherein the ith row represents any row in the matrix, and the jth column represents any column in the matrix;
and calculating a stock right transfer matrix P of all enterprises within 5 degrees at present according to the stock right transfer function defined by the second point, wherein the stock right transfer function defined by the second point is as follows:
wherein f (x) is data in the strand-conducting matrix P, x is the matrix M 1 F (x) and x are in one-to-one correspondence;
calculating transition probability matrix M of 2, 3, 4 and 5 degrees respectively 2 、M 3 、M 4 And M 5 Wherein M is 2 ＝PM 1 ，M 3 ＝P 2 M 1 ，M 4 ＝P 3 M 1 ，M 5 ＝P 4 M 1 ；
Accumulating and summing to obtain result matrix, where result is M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 +C 4 *M 5 In which C is 1 、C 2 、C 3 And C 4 According to the actual penetration distanceSetting the device away;
and the group identification module is used for acquiring the direct or indirect stock holding proportion between all enterprises within 5 degrees from the result matrix, and the data in the ith row and the jth column represents the direct or indirect stock holding proportion of the i enterprise to the j enterprise.
Optionally, in the knowledge-graph-based group equity penetration transfer system, 1 degree represents a direct holding relationship; 2, representing an indirect stock holding relation, and holding stocks only through one enterprise; 3, representing an indirect stock holding relation, and holding stocks through two enterprises; 4-degree represents the indirect stock holding relationship, and stock holding is carried out through three enterprises; the 5-degree represents the indirect stock holding relationship, and stock holding is carried out through four enterprises.
Optionally, in the knowledge-graph-based group equity penetration transfer system, if there are only 2-degree enterprises, only M is calculated 2 ，result＝M 1 +C 1 *M 2 (ii) a If there are only 3-degree enterprises, only M is calculated 2 And M 3 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 (ii) a If there are only 4-degree enterprises, only M is calculated 2 、M 3 And M 4 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 。
Optionally, in the knowledge-graph-based group stock right penetration transmission system, the matrix M 1 The total number of rows and the total number of columns of (a) are equal to the number of enterprises in the current 5 degrees.
Optionally, in the knowledge-graph-based group equity penetration transmission system, C 1 、C 2 、C 3 And C 4 The value range of (a) is not less than 0 and not more than 1.
Compared with the prior art, the invention has the following advantages:
(1) the invention considers the stock right attenuation problem caused by the overlong stock right transmission link, and the enterprise real control person and the relative stock right are considered by customizing the stock right transmission function defined by the second point, thereby improving the identification capability of hiding the stock right penetrating relationship.
(2) The invention utilizes the technical advantages of the knowledge graph, makes up the defects of the original audit model, breaks through the model limitation that only 2-degree incidence relation can be seen originally, and calculates the direct and indirect stock holding proportion of the stock enterprises in all 5-degree relations by adding the stock right penetration algorithm to find out the hidden relation among the enterprises, thereby improving the accuracy and recall rate of group incidence relation investigation and providing data support for predicting the capital relation.
(3) The invention combines the knowledge map platform to visually display the stockholder relationship among enterprises and the enterprise composition of each group, so that auditors can quickly and efficiently consult.
Drawings
Fig. 1 is a block flow diagram of a group rights penetration transmission system according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating an example of direct enterprise holdings provided by the first embodiment of the present invention;
fig. 3 and fig. 4 are schematic diagrams of the transfer strand weight optimization function provided by the embodiment of the present invention when a takes values of 1 and 3.8, respectively.
Detailed Description
The following describes in more detail embodiments of the present invention with reference to the schematic drawings. The advantages and features of the present invention will become more apparent from the following description. It is to be noted that the drawings are in a very simplified form and are not to precise scale, which is merely for the purpose of facilitating and distinctly claiming the embodiments of the present invention.
If the method described herein comprises a series of steps, the order in which these steps are presented herein is not necessarily the only order in which these steps may be performed, and some of the described steps may be omitted and/or some other steps not described herein may be added to the method.
The stockholder stock holding ratio is one of the most important group characteristics, part of enterprises control another enterprise in an indirect stock holding mode, the traditional audit model cannot automatically calculate the indirect stock holding ratio of all stockholders in batches, the accuracy of the model cannot be improved by limiting the threshold value of the indirect stock holding ratio, and the difficulty can be solved by the knowledge-graph technology.
Therefore, it is necessary to provide a method for conducting group stock right penetration based on knowledge graph, as shown in fig. 1, fig. 1 is a block flow diagram of a group stock right penetration conducting system provided by an embodiment of the present invention, and the method includes the following steps:
extracting the equity investment relationship of an enterprise, and constructing an enterprise equity relationship map by using a knowledge map platform;
obtaining an enterprise list within any 5 degrees through a relation map, obtaining the direct stock holding proportion of all enterprises within the current 5 degrees, and forming a matrix M 1 Matrix M 1 The ith row and the jth column in the matrix represent the direct stock holding ratio of i enterprises to j enterprises, wherein the ith row represents any row in the matrix, and the jth column represents any column in the matrix;
and calculating a stock right transfer matrix P of all enterprises within 5 degrees at present according to the stock right transfer function defined by the second point, wherein the stock right transfer function defined by the second point is as follows:
wherein f (x) is data in the strand-weight-conduction matrix P, and x is the matrix M 1 F (x) and x are in one-to-one correspondence;
calculating transition probability matrix M of 2, 3, 4 and 5 degrees respectively 2 、M 3 、M 4 And M 5 Wherein M is 2 ＝PM 1 ，M 3 ＝P 2 M 1 ，M 4 ＝P 3 M 1 ，M 5 ＝P 4 M 1 ；
Accumulating and summing to obtain result matrix, where result is M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 +C 4 *M 5 In which C is 1 、C 2 、C 3 And C 4 Setting according to the actual penetration distance;
and acquiring direct or indirect stock holding proportion among all enterprises within 5 degrees from the result matrix, wherein the data in the ith row and the jth column represents the direct or indirect stock holding proportion of the i enterprise to the j enterprise.
The invention utilizes the technical advantages of the knowledge graph, makes up the defects of the original audit model, breaks through the model limitation that only 2-degree association relation can be seen originally, and calculates the direct and indirect stock holding proportion of the stock enterprises in all 5-degree relation by adding the stock right penetration algorithm to find out the hidden relation among the enterprises, thereby improving the accuracy and recall rate of group association relation investigation. The invention realizes two innovations of stock right penetration calculation and deep level group association relation investigation by using the knowledge map, and overcomes the defect that the original audit model can only investigate the shallow level group association relation.
In the present invention, 1 degree represents a direct holdings relationship; 2, representing an indirect stock holding relation, and holding stocks only through one enterprise; 3, representing an indirect stock holding relation, and holding stocks through two enterprises; 4-degree represents the indirect stock holding relationship, and stock holding is carried out through three enterprises; the 5-degree represents the indirect stock holding relationship, and stock holding is carried out through four enterprises. If there are only 2-degree enterprises, only M is calculated 2 ，result＝M 1 +C 1 *M 2 (ii) a If there are only 3-degree enterprises, only M is calculated 2 And M 3 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 (ii) a If there are only 4-degree enterprises, only M is calculated 2 、M 3 And M 4 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 。
Further, the second point defines a stock right transfer function for purposefully optimizing the situation of the largest holder of all the holders of a business by:
if the maximum share ratio is less than 0.2, the share ratio is not modified in consideration that the share ratio among all the shareholders is not greatly different.
If the maximum share ratio is greater than 0.5, which means that the shareholder has absolute control over the enterprise, the share ratio is set to 1 in subsequent share conduction calculations to eliminate the effect of the share decay.
If the maximum share ratio is between 0.2 and 0.5, no one shareholder has absolute control right, but the shareholder still has a larger share right, so that a larger influence is obtained, and the influence of share right attenuation is reduced by using a function for all shareholders. For the case that the maximum stockholder stock-control ratio is between 0.2 and 0.5, the invention provides an adjustable parameter a in the optimization function, and the value range of the adjustable parameter a is [1, 3.8 ]. As a increases, the rate of change of the optimized value is greater for the case of a larger stock right relative to the case of a smaller stock right. a as a parameter for controlling the change rate can be adjusted according to actual conditions. Fig. 3 and 4 are schematic diagrams of the transfer strand weight optimization function when a takes values of 1 and 3.8, respectively.
When calculating the matrix P, the second point defines the strand weight transfer function with the object determined as the matrix M 1 The data of (1).
Preferably, in this scheme, the matrix M 1 The total number of rows and the total number of columns of (a) are equal to the number of enterprises in the current 5 degrees.
Preferably, C 1 、C 2 、C 3 And C 4 The value range of (A) is greater than or equal to 0 and less than or equal to 1, and under the default condition, C 1 、C 2 、C 3 And C 4 Get 1, if the service has low requirement for penetration distance, C can be properly reduced 1 、C 2 、C 3 And C 4 The value of (a). C 1 、C 2 、C 3 And C 4 To limit the threshold value of the indirect stock holding ratio, the accuracy of the method is improved.
In the first embodiment, please refer to fig. 2, fig. 2 is a diagram of an example of enterprise direct holdings provided by the first embodiment of the present invention, S1: obtaining the direct stock control ratio of all enterprises within 5 degrees, and forming a matrix M because there are 5 enterprises in FIG. 2 and only 2 degrees of relation 1 The following were used:
s2: according to the right transfer function defined by the second point, calculating the right transfer matrix P of all enterprises within 5 degrees currently, and calculating M 1 The data in the step (2) is substituted into a stock right transfer function defined by a second point to obtain a matrix P;
s3: calculating transition probability matrix M of 2, 3, 4 and 5 degrees respectively 2 、M 3 、M 4 And M 5 ，M 2 ＝PM 1 ，M 3 ＝P 2 M 1 ，M 4 ＝P 3 M 1 ，M 5 ＝P 4 M 1 Since there is only a 2 degree connection in FIG. 2, only M is calculated 2 ；
S4: finally, the data in the result matrix is calculated, in this embodiment, the value of C1 is 1, and therefore, the data is not represented in the calculation formula, and the calculation formula and the calculation result are as follows:
therefore, the direct and indirect stock control ratios of the enterprise A to the enterprise B, C, D are respectively 0.6, 0.7 and 0.6, and the model result is consistent with the manual calculation result.
If the strand weight conduction function defined by the second point is not applied, the calculation formula is: result is M 1 +M 2 ，M 2 ＝M 1 2 And the calculation result is as follows: the indirect stock holding ratio of the enterprise A to the enterprise D is 0.39, which is less than the stock holding ratio of the enterprise E to the enterprise D, which is 0.4. In practice, however, because the direct holdings of business a to business B, C exceeds 0.5, i.e., business a has absolute control over both businesses, the equity of business B, C to business D should be passed to business a in its entirety. In this case, the indirect stock holding ratio of the enterprise a to the enterprise D reaches 0.6, that is, the enterprise a has implicit absolute control right to the enterprise D, which is also in accordance with the real situation. It can be seen that the hair is adoptedThe clear group stock right penetration conduction method is more accurate in calculation.
The invention also provides a knowledge graph-based group stock right penetrating and conducting system, as shown in fig. 1, comprising the following modules:
the information acquisition module is used for extracting the equity investment relationship of the enterprise;
the map construction module is used for constructing an enterprise stock right relation map by using a knowledge map platform;
the stock right calculation module is used for acquiring an enterprise list within any 5 degrees through the relationship map, acquiring the direct stock holding proportion of all enterprises within the current 5 degrees and forming a matrix M 1 Matrix M 1 The ith row and the jth column in the matrix represent the direct stock holding ratio of i enterprises to j enterprises, wherein the ith row represents any row in the matrix, and the jth column represents any column in the matrix;
and calculating a stock right transfer matrix P of all enterprises within 5 degrees at present according to the stock right transfer function defined by the second point, wherein the stock right transfer function defined by the second point is as follows:
wherein f (x) is data in the strand-weight-conduction matrix P, and x is the matrix M 1 F (x) and x are in one-to-one correspondence;
calculating transition probability matrix M of 2, 3, 4 and 5 degrees respectively 2 、M 3 、M 4 And M 5 Wherein M is 2 ＝PM 1 ，M 3 ＝P 2 M 1 ，M 4 ＝P 3 M 1 ，M 5 ＝P 4 M 1 ；
Accumulating and summing to obtain result matrix, where result is M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 +C 4 *M 5 In which C is 1 、C 2 、C 3 And C 4 Setting according to the actual penetration distance;
and the group identification module is used for acquiring the direct or indirect stock holding proportion between all enterprises within 5 degrees from the result matrix, and the data in the ith row and the jth column represents the direct or indirect stock holding proportion of the i enterprise to the j enterprise.
Wherein 1 degree represents a direct holdings relationship; 2-degree represents an indirect stock keeping relationship, and the stock keeping is carried out only through one enterprise; 3, representing an indirect stock holding relation, and holding stocks through two enterprises; 4-degree represents the indirect stock holding relationship, and stock holding is carried out through three enterprises; the 5-degree represents the indirect stock holding relationship, and stock holding is carried out through four enterprises. If there are only 2-degree enterprises, only M is calculated 2 ，result＝M 1 +C 1 *M 2 (ii) a If there are only 3-degree enterprises, only M is calculated 2 And M 3 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 (ii) a If there are only 4-degree enterprises, only M is calculated 2 、M 3 And M 4 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 。
In general, the matrix M 1 The total number of rows and the total number of columns of (a) are equal to the number of enterprises in the current 5 degrees.
Preferably, C 1 、C 2 、C 3 And C 4 The value range of (A) is greater than or equal to 0 and less than or equal to 1, and under the default condition, C 1 、C 2 、C 3 And C 4 Get 1, if the service has low requirement for penetration distance, C can be properly reduced 1 、C 2 、C 3 And C 4 The value of (a).
As a large-scale relation mining graph computing system facing individuals and enterprises, the knowledge graph provides multi-dimensional and deep incidence relation analysis capability by constructing a multi-type entity relation network, breaks through the limitation of a traditional two-dimensional table, and has remarkable advantages in incidence relation identification. The invention mainly realizes two innovations of stock right penetration calculation and deep level group association relation investigation by using the knowledge map, and overcomes the defect that the original audit model can only investigate the shallow level group association relation.
The above description is only a preferred embodiment of the present invention, and does not limit the present invention in any way. It will be understood by those skilled in the art that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A group stock right penetration conduction method based on knowledge graph is characterized by comprising the following steps:
extracting the equity investment relationship of an enterprise, and constructing an enterprise equity relationship map by using a knowledge map platform;
obtaining an enterprise list within any 5 degrees through a relation map, obtaining the direct stock holding proportion of all enterprises within the current 5 degrees, and forming a matrix M 1 Matrix M 1 The ith row and the jth column in the matrix represent the direct stock holding ratio of i enterprises to j enterprises, wherein the ith row represents any row in the matrix, and the jth column represents any column in the matrix;
and calculating a stock right transfer matrix P of all enterprises within 5 degrees at present according to the stock right transfer function defined by the second point, wherein the stock right transfer function defined by the second point is as follows:
wherein f (x) is data in the strand-weight-conduction matrix P, and x is the matrix M 1 F (x) and x are in one-to-one correspondence;
calculating transition probability matrix M of 2, 3, 4 and 5 degrees respectively 2 、M 3 、M 4 And M 5 Wherein, M is 2 ＝PM 1 ，M 3 ＝P 2 M 1 ，M 4 ＝P 3 M 1 ，M 5 ＝P 4 M 1 ；
Accumulating and summing to obtain result matrix, where result is M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 +C 4 *M 5 In which C is 1 、C 2 、C 3 And C 4 Setting according to the actual penetration distance;
and acquiring direct or indirect stock holding proportion among all enterprises within 5 degrees from the result matrix, wherein the data in the ith row and the jth column represents the direct or indirect stock holding proportion of the i enterprise to the j enterprise.
2. The knowledge-graph-based corporate equity penetration transfer method of claim 1, wherein 1 degree represents a direct holdings relationship; 2, representing an indirect stock holding relation, and holding stocks only through one enterprise; 3, representing an indirect stock holding relation, and holding stocks through two enterprises; 4-degree represents the indirect stock holding relationship, and stock holding is carried out through three enterprises; the 5-degree represents the indirect stock holding relationship, and stock holding is carried out through four enterprises.
3. The knowledge-graph-based corporate shareholdings penetration propagation method of claim 2, wherein if there are only 2-degree enterprises, only M is calculated 2 ，result＝M 1 +C 1 *M 2 (ii) a If there are only 3-degree enterprises, only M is calculated 2 And M 3 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 (ii) a If there are only 4-degree enterprises, only M is calculated 2 、M 3 And M 4 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 。
4. The knowledge-graph-based corporate shareholder penetration propagation method of claim 2, wherein the matrix M is a matrix M 1 The total number of rows and the total number of columns of (a) are equal to the number of enterprises in the current 5 degrees.
5. The knowledge-graph-based corporate shareholder penetration propagation method of claim 1, wherein C is 1 、C 2 、C 3 And C 4 The value range of (a) is not less than 0 and not more than 1.
6. A knowledge-graph-based group equity penetration transfer system, comprising the following modules:
the information acquisition module is used for extracting the equity investment relationship of the enterprise;
the map construction module is used for constructing an enterprise stock right relation map by using a knowledge map platform;
the stock right calculation module is used for acquiring an enterprise list within any 5 degrees through the relationship map, acquiring the direct stock holding proportion of all enterprises within the current 5 degrees and forming a matrix M 1 Matrix M 1 The ith row and the jth column in the matrix represent the direct stock holding ratio of i enterprises to j enterprises, wherein the ith row represents any row in the matrix, and the jth column represents any column in the matrix;
and calculating a stock right transfer matrix P of all enterprises within 5 degrees at present according to the stock right transfer function defined by the second point, wherein the stock right transfer function defined by the second point is as follows:
wherein f (x) is data in the strand-weight-conduction matrix P, and x is the matrix M 1 F (x) and x are in one-to-one correspondence;
calculating transition probability matrix M of 2, 3, 4 and 5 degrees respectively 2 、M 3 、M 4 And M 5 Wherein M is 2 ＝PM 1 ，M 3 ＝P 2 M 1 ，M 4 ＝P 3 M 1 ，M 5 ＝P 4 M 1 ；
Accumulating and summing to obtain result matrix, where result is M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 +C 4 *M 5 In which C is 1 、C 2 、C 3 And C 4 Setting according to the actual penetration distance;
and the group identification module is used for acquiring the direct or indirect stock holding ratio of all enterprises within 5 degrees from the result matrix, and the data in the ith row and the jth column represents the direct or indirect stock holding ratio of the i enterprise to the j enterprise.
7. The knowledge-graph-based group equity penetration delivery system of claim 6, wherein 1 degree represents a direct holdings relationship; 2, representing an indirect stock holding relation, and holding stocks only through one enterprise; 3, representing an indirect stock holding relation, and holding stocks through two enterprises; 4-degree represents the indirect stock holding relationship, and stock holding is carried out through three enterprises; the 5-degree represents the indirect stock holding relationship, and stock holding is carried out through four enterprises.
8. The knowledge-graph-based group equity penetration delivery system of claim 7, wherein only M is calculated if there are only 2 degree businesses, and wherein M is calculated if there are only 2 degree businesses 2 ，result＝M 1 +C 1 *M 2 (ii) a If there are only 3-degree enterprises, only M is calculated 2 And M 3 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 (ii) a If there are only 4-degree enterprises, only M is calculated 2 、M 3 And M 4 ，result＝M 1 +C 1 *M 2 +C 2 *M 3 +C 3 *M 4 。
9. The knowledge-graph-based corporate shareholder penetration delivery system of claim 7, wherein the matrix M is a matrix 1 The total number of rows and the total number of columns of (a) are equal to the number of enterprises in the current 5 degrees.
10. The knowledge-graph-based group equity penetration delivery system of claim 6, wherein C 1 、C 2 、C 3 And C 4 The value range of (a) is not less than 0 and not more than 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210644357.8A CN114881801A (en) | 2022-06-09 | 2022-06-09 | Group stock right penetration conduction method and system based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210644357.8A CN114881801A (en) | 2022-06-09 | 2022-06-09 | Group stock right penetration conduction method and system based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114881801A true CN114881801A (en) | 2022-08-09 |
Family
ID=82681306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210644357.8A Pending CN114881801A (en) | 2022-06-09 | 2022-06-09 | Group stock right penetration conduction method and system based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114881801A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117273954A (en) * | 2023-11-21 | 2023-12-22 | 中证数智科技(深圳)有限公司 | Stock right relation penetration method, device and equipment based on large-scale relation map |
-
2022
- 2022-06-09 CN CN202210644357.8A patent/CN114881801A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117273954A (en) * | 2023-11-21 | 2023-12-22 | 中证数智科技(深圳)有限公司 | Stock right relation penetration method, device and equipment based on large-scale relation map |
| CN117273954B (en) * | 2023-11-21 | 2024-03-12 | 中证数智科技(深圳)有限公司 | Stock right relation penetration method, device and equipment based on large-scale relation map |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lin et al. | Evaluation of CART, CHAID, and QUEST algorithms: a case study of construction defects in Taiwan | |
| Bergh | Problems with repeated measures analysis: Demonstration with a study of the diversification and performance relationship | |
| Kaur et al. | Ranked set sampling: an annotated bibliography | |
| CN107368700A (en) | Based on the microbial diversity interaction analysis system and method for calculating cloud platform | |
| CN112700319A (en) | Enterprise credit line determination method and device based on government affair data | |
| Ma et al. | Does communist party membership bring a wage premium in China? a meta-analysis | |
| CN110738527A (en) | feature importance ranking method, device, equipment and storage medium | |
| Guimarães et al. | Measuring the localization of economic activity: a parametric approach | |
| EP4080429A1 (en) | Technology readiness level determination method and system based on science and technology big data | |
| EP4068173A1 (en) | System and method for analyzing cause of product defect and computer-readable medium | |
| CN116089495A (en) | Self-service analysis platform based on big data | |
| Radlinski et al. | On predicting software development effort using machine learning techniques and local data | |
| Landerretche et al. | The Union Effect on Wages in C hile: A Two‐Stage Approach Using Panel Data | |
| CN114881801A (en) | Group stock right penetration conduction method and system based on knowledge graph | |
| Feranecová et al. | Measuring the performance of universities through cluster analysis and the use of financial ratio indexes | |
| CN116050831A (en) | Agricultural irrigation water quality early warning method and system | |
| Di Giacinto et al. | The agglomeration of knowledge-intensive business services firms | |
| Rytova et al. | Assessing the Maturity Level of Saint Petersburg’s Digital Government. | |
| Yamada et al. | Distribution of industrial growth in Nagoya Metropolitan Area, Japan: an exploratory analysis using geographical and technological proximities | |
| CN112711585A (en) | Expressway green traffic credit management system based on big data technology | |
| CN104794234A (en) | Data processing method and device for benchmarking | |
| Hegerty | Inflation volatility, monetary policy, and exchange-rate regimes in central and eastern europe: Evidence from parametric and nonparametric analyses | |
| CN114881394A (en) | Big data processing system and method for intelligent evaluation of enterprise growth | |
| Cope | Modeling operational loss severity distributions from consortium data | |
| Okello | Influence of entrepreneurial management on the growth of micro and small furniture manufacturing enterprises in Kenya |
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 |