A method, device and electronic device for identifying enterprise association relationships

Abstract

The present application discloses a method, device and electronic device for identifying enterprise association relationships. The method includes: obtaining an enterprise relationship map; the enterprise relationship map includes a target enterprise and several non-target enterprises; obtaining the number of paths of the target path between the non-target enterprise and the target enterprise based on the enterprise relationship map; determining the intimacy value corresponding to each of the path numbers based at least on the number of paths and the target first correspondence in the target association model; determining the association value between the non-target enterprise and the target enterprise based at least on the intimacy value; identifying the target associated enterprise associated with the target enterprise based on the association value of each non-target enterprise. In the present application, by obtaining the enterprise relationship map, and then determining the association value based on the enterprise relationship map and the target association model, the target associated enterprise can be quickly and accurately identified based on the association value, and the identification result is more reasonable and accurate.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to a method and device for identifying enterprise association relationships and an electronic device. Background Art

[0002] In order to promote economic growth and increase employment opportunities, local government departments or organizations will attract investment. However, in the existing investment promotion activities, government departments and organizations usually directly introduce some projects or enterprises, and do not combine the development of local enterprises to "attract business with business" and attract enterprises with business connections to settle down. In addition, it is impossible to quickly and accurately determine which enterprises have business relations with local enterprises, and the matching accuracy of enterprise association relationships is poor.

[0003] Therefore, there is an urgent need for a method for identifying corporate relationships, which can quickly and accurately determine the companies that have relationships with local companies, provide direction for attracting investment, and facilitate accurate investment promotion. Summary of the invention

[0004] In view of this, the present invention provides a method, device and electronic device for identifying enterprise association relationships, the main purpose of which is to solve the current problem of being unable to quickly and accurately identify enterprises that have an association relationship with a target enterprise.

[0005] To solve the above problems, the present application provides a method for identifying enterprise association relationships, including:

[0006] Obtaining an enterprise relationship map; the enterprise relationship map includes a target enterprise and a number of non-target enterprises;

[0007] Acquire the number of target paths between the non-target enterprises and the target enterprises based on the enterprise relationship graph;

[0008] Determine the intimacy value corresponding to each of the path numbers based at least on the path numbers and the target first correspondence in the target association model;

[0009] Determining an association value between a non-target enterprise and the target enterprise based at least on the intimacy value;

[0010] Target associated enterprises associated with the target enterprise are identified based on the associated values ​​of the non-target enterprises.

[0011] Optionally, before obtaining the enterprise relationship map, the method further includes constructing the enterprise relationship map, specifically including:

[0012] Obtain information about each enterprise;

[0013] Obtain one or more relationships between enterprises, between enterprises and legal persons, and between legal persons based on information about each enterprise;

[0014] Based on one or more of the relationships between enterprises, enterprises and legal persons, and legal persons and legal persons, an enterprise relationship map is constructed with enterprises and / or legal persons as nodes.

[0015] Optionally, after determining the intimacy value corresponding to the number of paths, the method further includes:

[0016] Determine the type of relationship between the non-target enterprise and the target enterprise;

[0017] Determining a first association value corresponding to the relationship type based on the relationship type and the target second corresponding relationship in the target association model;

[0018] The determining the association value between the non-target enterprise and the target enterprise at least based on the intimacy value specifically includes: obtaining the association value between the non-target enterprise and the target enterprise by calculation based on the intimacy value and the first association value.

[0019] Optionally, the acquiring the number of target paths between non-target enterprises and target enterprises based on the enterprise relationship graph specifically includes:

[0020] Acquire a first path between a non-target enterprise and a target enterprise based on the enterprise relationship graph;

[0021] Screening the first path based on the target path node limit value in the target association model to obtain a target path with a path node number less than the target path node limit value;

[0022] The number of paths is determined based on the number of target paths.

[0023] Optionally, determining the intimacy value corresponding to each of the path numbers based at least on the path numbers and the target first correspondence in the target association model specifically includes:

[0024] Searching for the first corresponding relationship of the target based on the path number, and obtaining a first intimacy value corresponding to the path number;

[0025] Obtain the total number of nodes on the target path;

[0026] Based on the total number of nodes and the correspondence between the number of nodes and the first intimacy weight value, determine the first intimacy weight value corresponding to the total number of nodes;

[0027] The intimacy value is calculated based on the first intimacy weight value and the first intimacy value.

[0028] Optionally, determining the intimacy value corresponding to each of the path numbers based at least on the path numbers and the target first correspondence in the target association model specifically includes:

[0029] Searching for the first corresponding relationship of the target based on the path number, and obtaining a first intimacy value corresponding to the path number;

[0030] Obtaining the number of first nodes of each target path;

[0031] Determine the second intimacy weight value corresponding to each of the first node numbers based on the correspondence between the node number and the second intimacy weight value;

[0032] Calculate a third intimacy weight value based on each of the second intimacy weight values;

[0033] The intimacy value is calculated based on the third intimacy weight value and the first intimacy value.

[0034] Optionally, before obtaining the number of paths of the target path, the method further includes establishing the target correlation model based on the enterprise relationship graph, specifically including:

[0035] Establishing an initial correlation model; the initial correlation model includes: a first correspondence between the number of paths and the initial intimacy value, a second correspondence between the relationship type of the enterprise and the initial first correlation value, and an initial path node restriction value;

[0036] Determine the target enterprise, the sample enterprises, and the actual correlation values ​​between the target enterprise and the sample enterprises based on the enterprise relationship map;

[0037] Determine the number of paths between the target enterprise and the sample enterprise within the initial path node limit value based on the enterprise relationship graph, and determine the target initial intimacy value by searching the first corresponding relationship in the initial association model based on the number of paths;

[0038] Based on the relationship type between the target enterprise and the sample enterprise, searching for a second corresponding relationship in the initial correlation model to determine a target initial first correlation value;

[0039] Calculate and obtain a target initial association value based on the target initial first association value and the target initial intimacy value;

[0040] Based on the difference between the actual association value and the target initial association value, the initial intimacy value, the initial first association value and the initial path node restriction value are adjusted to obtain a target first correspondence between the relationship type and the target first association value, a target second correspondence between the path number and the target intimacy value, and a target path node restriction value to obtain the target association model.

[0041] Optionally, after identifying and obtaining the target affiliated enterprise, the method further includes:

[0042] Based on the order of the relevance values ​​of the target related enterprises, the target related enterprises are displayed in a descending order.

[0043] In order to solve the above technical problems, the present application provides a device for identifying enterprise association relationships, comprising:

[0044] A first acquisition module is used to acquire an enterprise relationship map; the enterprise relationship map includes a target enterprise and a number of non-target enterprises;

[0045] A second acquisition module, configured to acquire the number of target paths between the non-target enterprises and the target enterprises based on the enterprise relationship graph;

[0046] An intimacy value determination module, configured to determine an intimacy value corresponding to each of the path numbers based at least on the path numbers and the target first correspondence relationship in the target association model;

[0047] A correlation value determination module, configured to determine a correlation value between a non-target enterprise and the target enterprise based at least on the intimacy value;

[0048] The identification module is used to identify target associated enterprises associated with the target enterprise based on the associated values ​​of the non-target enterprises.

[0049] In order to solve the above technical problems, the present application provides an electronic device, which at least includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program on the memory, the steps of any of the above-mentioned enterprise association identification methods are implemented.

[0050] The enterprise association relationship identification method, device and electronic device in the present application construct an enterprise relationship map with enterprises and legal persons as nodes, and then determine the intimacy value between each non-target enterprise and the target enterprise according to the number of target paths between each non-target enterprise and the target enterprise in the enterprise relationship map, and determine the association value between each non-target enterprise and the target enterprise according to each intimacy value, so that the target associated enterprises associated with the target enterprise can be quickly and accurately identified from the non-target enterprises according to the association value. The identification result is more reasonable and accurate, which provides direction for subsequent investment promotion and facilitates targeted investment promotion.

[0051] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0053] Figure 1 This is a flow chart of a method for identifying corporate association relationships according to an embodiment of the present application;

[0054] Figure 2 This is a flowchart of a method for identifying corporate association relationships according to another embodiment of the present application;

[0055] Figure 3 This is a schematic diagram of some enterprise relationship maps in the embodiments of this application;

[0056] Figure 4 This is a structural block diagram of the enterprise association relationship identification device in an embodiment of the present application. DETAILED DESCRIPTION

[0057] Various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0058] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but only as an example of an embodiment. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.

[0059] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0060] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0061] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art will be able to readily implement many other equivalent forms of the present application.

[0062] The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.

[0063] Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments applied for are merely examples of the present application, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that obscure the present application. Therefore, the specific structural and functional details applied for herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present application in a variety of ways with substantially any suitable detailed structure.

[0064] This specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present application.

[0065] This application embodiment provides a method for identifying corporate association relationships, such as Figure 1 As shown, the following steps are included:

[0066] Step S101, obtaining an enterprise relationship map; the enterprise relationship map includes a target enterprise and a number of non-target enterprises;

[0067] During the implementation of this step, a corporate relationship map can be pre-constructed. For example, information about each company can be obtained through public information, financial reports, news and public opinion information, or through purchasing corporate databases; then, the relationships around companies and individuals, such as investment relationships, upstream supplier relationships, controlling short messages, legal representative concerns, investor relationships, etc., are mined to construct a corporate relationship map with companies and legal persons as nodes, and the corporate relationship map is obtained when identifying corporate relationships.

[0068] Step S102, obtaining the number of target paths between the non-target enterprises and the target enterprise based on the enterprise relationship graph;

[0069] In this step, after constructing the enterprise relationship map, you can prioritize local leading enterprises with driving effects as target enterprises. Specifically, for example, based on the scale of employees, tax payment status, status of the industrial chain to which the enterprise belongs, and the development plans of the enterprise and the government, you can dig out a list of local leading enterprises and determine the target enterprises. After determining the target enterprises, you can determine the number of paths between each non-target enterprise and the target enterprise based on the enterprise relationship map.

[0070] Step S103, determining the intimacy value corresponding to each of the path numbers based at least on the path numbers and the target first correspondence in the target association model;

[0071] In the specific implementation process of this step, a target correlation model can be established in advance, and the target correlation model at least includes the target first correspondence between the number of paths and the intimacy value. Therefore, after determining the number of paths between each non-target enterprise and the target enterprise, the target first correspondence can be found according to each path number to determine the intimacy value between each non-target enterprise and the target enterprise. The intimacy value is used to characterize the degree of association between the non-target enterprise and the target enterprise. The more the number of paths, the greater the intimacy value, and the more relevant the non-target enterprise is to the target enterprise.

[0072] Step S104, determining the association value between the non-target enterprise and the target enterprise based at least on the intimacy value;

[0073] After determining the intimacy value of each non-target enterprise in this step, the correlation value can be determined based on the intimacy value. The larger the intimacy value, the larger the correlation value, which means that the non-target enterprise is more related to the target enterprise.

[0074] Step S105: identifying and obtaining target associated enterprises associated with the target enterprise based on the associated values ​​of the non-target enterprises.

[0075] In the specific implementation process of this step, a threshold can be set according to the actual situation. After the association value of each non-target enterprise is obtained, each association value can be compared with the threshold. If it is greater than the threshold, the non-target enterprise corresponding to the association value is determined to be the target associated enterprise.

[0076] The enterprise association relationship identification method, device and electronic device in the present application construct an enterprise relationship map with enterprises and legal persons as nodes, and then determine the intimacy value between each non-target enterprise and the target enterprise according to the number of target paths between each non-target enterprise and the target enterprise in the enterprise relationship map, and determine the association value between each non-target enterprise and the target enterprise according to each intimacy value, so that the target associated enterprises associated with the target enterprise can be accurately identified from the non-target enterprises according to the association value. The identification result is more reasonable and accurate, which provides direction for investment promotion and facilitates targeted investment promotion.

[0077] In order to improve the recognition effect of the target associated enterprise, another embodiment of the present application provides a method for identifying the enterprise association relationship, such as Figure 2 As shown, the following steps are included:

[0078] Step S201, obtaining information of each enterprise; obtaining one or more relationships between enterprises, enterprises and legal persons, and legal persons and legal persons based on the information of each enterprise; and constructing an enterprise relationship map with enterprises and / or legal persons as nodes based on the one or more relationships between enterprises, enterprises and legal persons, and legal persons and legal persons.

[0079] During the implementation of this step, the information of each enterprise can be obtained through public information, financial reports, news and public opinion information, or purchasing enterprise databases; then the relationships around enterprises and individuals are explored, such as investment relationships, upstream supplier relationships, controlling short messages, legal representative attention, investor relationships, etc., to build an enterprise relationship map with enterprises and legal persons as nodes.

[0080] Step S202, obtaining the enterprise relationship map;

[0081] Step S203, obtaining a first path between a non-target enterprise and a target enterprise based on the enterprise relationship graph; screening the first path based on a target path node limit value in a target association model to obtain a target path whose number of path nodes is less than the target path node limit value; determining the number of paths based on the number of target paths;

[0082] In this step, after constructing the enterprise relationship map, you can prioritize local leading enterprises with driving effects as target enterprises. Specifically, for example, based on the size of the company's employees, tax payment status, the status of the industry chain to which the company belongs, and the company and government development plans, dig out a list of local leading enterprises and determine the target enterprises. After determining the target enterprises, you can determine the number of first paths between each non-target enterprise and the target enterprise based on the enterprise relationship map, and then filter the first path based on the target path node limit value a in the target correlation model to obtain the target path, thereby determining the number of target paths w x≤a .like Figure 3 As shown, node 3 is the target enterprise node, node 8 is the non-target enterprise node, and nodes 0, 1, 2, 4, 5, 6, and 7 are non-target enterprise nodes or legal person nodes corresponding to target enterprise node 3. Figure 3 It can be determined that the first paths between non-target enterprise 8 and target enterprise 3 are: 3-1-0-2-6-8, 3-1-0-2-5-6-8, 3-1-4-5-6-8, 3-1-4-5-2-6-8, 3-7-4-5-2-6-8, 3-7-4-5-6-8, 3-7-4-1-0-2-6-8, 3-7-4-1-0-2-5-6-8; then according to the target path node limit value a= 7. Then the first paths with more than 7 nodes will be screened out, that is, the paths with less than or equal to 7 nodes are screened as the target paths. The target paths are: 3-1-0-2-6-8, 3-1-0-2-5-6-8, 3-1-4-5-6-8, 3-1-4-5-6-8, 3-1-4-5-2-6-8, 3-7-4-5-2-6-8, 3-7-4-5-6-8, thus determining the path number w of the target path. x≤7 The number of target paths of each non-target enterprise corresponding to the target enterprise can be determined in the same way.

[0083] Step S204, determining the intimacy value corresponding to each of the path numbers based on the path numbers and the target first correspondence relationship in the target association model;

[0084] In the specific implementation process of this step, the target correlation model contains the target first correspondence between the number of paths w and the intimacy value T. Therefore, the number of paths w between each non-target enterprise and the target enterprise is determined. x≤a After that, the intimacy value T(w x≤a ). This intimacy value is used to characterize the degree of association between non-target enterprises and target enterprises. The more paths there are, the greater the intimacy value is, and the more relevant the non-target enterprises are to the target enterprises.

[0085] Step S205, determining the relationship type between the non-target enterprise and the target enterprise;

[0086] The relationship types in this step include any of the following: parent-subsidiary company relationship, shareholder relationship, investment relationship, and upstream-downstream relationship, etc.

[0087] Step S206, determining a first association value corresponding to the relationship type based on the relationship type and the target second corresponding relationship in the target association model;

[0088] In this embodiment, the target association model also includes a target second corresponding relationship between the relationship type z and the first association value P Therefore, after determining the relationship type of each non-target enterprise, the first association value p(z) can be determined according to the second corresponding relationship. For example, if it is a parent-subsidiary relationship, the first association value p(z) is a; if it is a shareholder relationship, the first association value p(z) is b; if it is an investment relationship, the first association value p(z) is c; if it is an upstream and downstream relationship, the first association value p(z) is d; a>b>c>d.

[0089] Step S207: Calculate the association value between the non-target enterprise and the target enterprise based on the intimacy value and the first association value.

[0090] In this step, after determining the intimacy value and the first correlation value, the calculation formula f=p(z)+T(w x≤a ), to calculate the association value f, where z represents the relationship type between the non-target enterprise and the target enterprise, p(z) represents the second association value corresponding to the association type z, and w x≤a Indicates the number of paths in the first path whose node number is less than or equal to the target path node limit value a, T(w x≤a ) represents the intimacy value corresponding to the number of paths. That is, the target association model in this embodiment can be expressed as:

[0091] Step S208: identifying and obtaining target associated enterprises associated with the target enterprise based on the associated values ​​of the non-target enterprises.

[0092] After identifying the target associated enterprises, this embodiment can also display the target associated enterprises in descending order according to the order of their association values, so as to prompt that investment promotion can be prioritized for the target associated enterprises with higher rankings.

[0093] In the specific implementation process of this embodiment, before executing step S202, it is also necessary to establish the target correlation model based on the enterprise relationship map. The process of establishing the target correlation model includes the following steps:

[0094] Step 1: Establish an initial correlation model; the initial correlation model includes: a first correspondence between the number of paths and the initial intimacy value, a second correspondence between the relationship type of the enterprise and the initial first correlation value, and an initial path node restriction value;

[0095] Step 2: determining the target enterprise, the sample enterprises, and the actual correlation values ​​between the target enterprise and the sample enterprises based on the enterprise relationship map;

[0096] In this step, we can dig out a list of local leading enterprises based on the size of their employees, tax payment status, the status of the industrial chain to which the enterprises belong, and the development plans of the enterprises and the government, identify the target enterprises, and then use the known non-target enterprises associated with the target enterprises as sample enterprises. For example, if non-target enterprise B is a subsidiary of target enterprise A, then enterprise B can be used as a sample enterprise, and the actual association value of enterprise B can be determined, for example, the actual association value is 9.5 or 95, etc.

[0097] Step 3: determining the number of paths between the target enterprise and the sample enterprise within the initial path node limit value based on the enterprise relationship graph, and finding the first corresponding relationship in the initial association model based on the number of paths to determine the target initial intimacy value;

[0098] In this step, the calculation depth can be adjusted according to the scale and size of the enterprise relationship map, for example, the initial path node limit value is set to 4 hops or 6 hops. The specific adjustment logic is determined according to the density of the enterprise entity in the space, for example, the initial hop count / initial path node limit value is determined according to the number of enterprise nodes in the enterprise relationship map, for example, the initial path node limit value is determined according to the correspondence between the total number of nodes and the path node limit value. In theory, the denser the enterprise relationship, the shallower the calculation depth, and the looser the enterprise relationship, the deeper the calculation depth; in addition, manual evaluation can be performed according to the effect of the recommendation of the associated enterprise to flexibly adjust the calculation depth parameter. After determining the initial path node limit value, it is also necessary to configure the initial intimacy value for different path numbers to obtain the initial first corresponding relationship. In this way, the number of paths between the sample enterprise and the target enterprise in the enterprise relationship map can be obtained, and then each path can be screened based on the initial path node limit value to obtain the target path, thereby further obtaining the number of paths to the target path; and then the intimacy value corresponding to the number of paths can be determined according to the initial first corresponding relationship.

[0099] Step 4: based on the relationship type between the target enterprise and the sample enterprise, find the second corresponding relationship in the initial correlation model to determine the target initial first correlation value;

[0100] In the specific implementation process of this step, different initial first association values ​​can be configured for each relationship type, thereby obtaining an initial second corresponding relationship. In this way, after determining the relationship type between the sample enterprise and the target enterprise, the target initial first association value can be obtained by searching the second corresponding relationship.

[0101] Step 5: Calculate the target initial association value based on the target initial first association value and the target initial intimacy value;

[0102] In this step, after obtaining the target initial first association value and the target initial intimacy value, the target initial association value can be calculated by a weighted calculation method.

[0103] Step six, based on the difference between the actual association value and the target initial association value, adjust the initial intimacy value, the initial first association value and the initial path node restriction value, obtain the target first correspondence between the relationship type and the target first association value, the target second correspondence between the path number and the target intimacy value, and the target path node restriction value, so as to obtain the target association model.

[0104] In this step, for example, the target initial correlation value is calculated to be 4, while the actual correlation value is 8. Therefore, it is necessary to adjust the initial path node limit value to adjust the calculation depth, and at the same time adjust the initial intimacy value and the initial first correlation value. Finally, the target path node limit value a and the target first corresponding relationship are obtained. And the target second correspondence It is convenient to follow the calculation formula f = p(z) + T(w x≤a ) to calculate the associated value f.

[0105] On the basis of the above embodiments, in order to make the calculated association value reasonable and accurate, in this embodiment, when determining the intimacy value, the intimacy weight value can be further determined, and then the obtained intimacy value is multiplied by the intimacy weight value to obtain the final intimacy value, and finally the final intimacy value and the first association value are used to determine the association value. For example, when the number of target paths between non-target enterprise B and target enterprise A is 5, and the number of target paths between non-target enterprise C and target enterprise A is also 5, but the total number of nodes of the target paths is different, it is not reasonable and accurate to simply determine the intimacy value based on the number of paths. Therefore, the intimacy weight value is introduced, and the final target intimacy value is obtained by combining the intimacy value, so that the finally obtained association value is reasonable and accurate. Therefore, the determination of the intimacy value in this embodiment can also be specifically carried out in the following two ways.

[0106] Method 1: Search the first corresponding relationship of the target based on the number of paths to obtain the first intimacy value corresponding to the number of paths; obtain the total number of nodes of the target path; determine the first intimacy weight value corresponding to the total number of nodes based on the total number of nodes and the corresponding relationship between the number of nodes and the first intimacy weight value; calculate the intimacy value based on the first intimacy weight value and the first intimacy value. That is, in this method, a third corresponding relationship between the total number of nodes and the first intimacy weight value will be established in advance. Therefore, after obtaining the target path, the first number of nodes of each target path can be further obtained, and then the total number of nodes can be obtained by adding the first number of nodes, and then the corresponding first intimacy weight value is determined by searching the third corresponding relationship. Subsequently, the intimacy value can be calculated based on the first intimacy weight value, which provides a guarantee for accurately determining the association value.

[0107] Method 2: Based on the number of paths, the first corresponding relationship of the target is searched to obtain the first intimacy value corresponding to the number of paths; the first number of nodes of each target path is obtained; based on the first number of nodes and the corresponding relationship between the number of nodes and the second intimacy weight value, the second intimacy weight value corresponding to each first number of nodes is determined; based on the second intimacy weight value, the third intimacy weight value is calculated to obtain the intimacy value; based on the third intimacy weight value and the first intimacy value, the intimacy value is calculated to obtain the intimacy value. That is, in this method, a fourth corresponding relationship between the number of nodes and the second intimacy weight value is also established in advance, so that after obtaining the target path, the first number of nodes of each target path can be further obtained, and then the second intimacy weight value corresponding to each first number of nodes is determined by searching the fourth corresponding relationship, and then the average value is calculated according to each second intimacy weight value, thereby obtaining the third intimacy weight value. Subsequently, the intimacy value can be calculated according to the third intimacy weight value, which provides a guarantee for accurately determining the association value.

[0108] Another embodiment of the present application provides a device for identifying enterprise association relationships, such as Figure 4 As shown, including:

[0109] The first acquisition module 1 is used to acquire an enterprise relationship map; the enterprise relationship map includes a target enterprise and a number of non-target enterprises;

[0110] A second acquisition module 2, used for acquiring the number of target paths between the non-target enterprises and the target enterprises based on the enterprise relationship graph;

[0111] An intimacy value determination module 3, configured to determine an intimacy value corresponding to each of the path numbers based on the path numbers and the target first correspondence in the target association model;

[0112] An association value determination module 4, configured to determine an association value between a non-target enterprise and the target enterprise based at least on the intimacy value;

[0113] The identification module 5 is used to identify target associated enterprises associated with the target enterprise based on the associated values ​​of the non-target enterprises.

[0114] Specifically, the enterprise association relationship identification device also includes a construction module for constructing an enterprise relationship map, and the construction module is specifically used to: obtain information of each enterprise; obtain one or more associations between enterprises, enterprises and legal persons, and legal persons and legal persons based on the information of each enterprise; based on the one or more associations between enterprises, enterprises and legal persons, and legal persons and legal persons, construct an enterprise relationship map with enterprises and / or legal persons as nodes.

[0115] Specifically, the enterprise association relationship identification device also includes a first association value determination module, which is used to: determine the relationship type between the non-target enterprise and the target enterprise; based on the relationship type and the target second corresponding relationship in the target association model, determine the first association value corresponding to the relationship type; the association value determination module is specifically used to calculate the association value between the non-target enterprise and the target enterprise based on the intimacy value and the first association value.

[0116] Specifically, the second acquisition module is specifically used to: acquire a first path between a non-target enterprise and a target enterprise based on the enterprise relationship map; filter the first path based on a target path node limit value in the target association model to obtain a target path whose number of path nodes is less than the target path node limit value; and determine the number of paths based on the number of target paths.

[0117] Specifically, the intimacy value determination module is used to: search for the first corresponding relationship of the target based on the path number to obtain the first intimacy value corresponding to the path number; obtain the total number of nodes of the target path; determine the first intimacy weight value corresponding to the total number of nodes based on the total number of nodes and the corresponding relationship between the number of nodes and the first intimacy weight value; calculate the intimacy value based on the first intimacy weight value and the first intimacy value.

[0118] The intimacy value determination module can also be used to: search for the first corresponding relationship of the target based on the path number to obtain a first intimacy value corresponding to the path number; obtain the first node number of each target path; determine the second intimacy weight value corresponding to each first node number based on each first node number and the correspondence between the node number and the second intimacy weight value; calculate and obtain a third intimacy weight value based on each second intimacy weight value; calculate and obtain the intimacy value based on the third intimacy weight value and the first intimacy value.

[0119] Specifically, the enterprise association relationship identification device also includes an establishment module, which is used to: establish an initial association model; the initial association model includes: a first correspondence between the number of paths and the initial intimacy value, a second correspondence between the enterprise relationship type and the initial first association value, and an initial path node limit value; determine the target enterprise, the sample enterprise, and the actual association value between the target enterprise and the sample enterprise based on the enterprise relationship map; determine the number of paths between the target enterprise and the sample enterprise within the initial path node limit value based on the enterprise relationship map, and search the first correspondence in the initial association model based on the number of paths to determine the target initial enterprise; intimacy value; based on the relationship type between the target enterprise and the sample enterprise, searching the second corresponding relationship in the initial correlation model to determine the target initial first correlation value; calculating the target initial correlation value based on the target initial first correlation value and the target initial intimacy value; adjusting the initial intimacy value, the initial first correlation value and the initial path node restriction value based on the difference between the actual correlation value and the target initial correlation value, obtaining the target first corresponding relationship between the relationship type and the target first correlation value, the target second corresponding relationship between the path number and the target intimacy value, and the target path node restriction value, so as to obtain the target correlation model.

[0120] Specifically, the enterprise association relationship identification device further includes a display module, and the display module is used to display each of the target associated enterprises in a descending order based on the order of the association values ​​of each of the target associated enterprises.

[0121] The enterprise association relationship identification device in the present application constructs an enterprise relationship map with enterprises and legal persons as nodes through a construction module, and then uses an intimacy value determination module to determine the intimacy value between each non-target enterprise and the target enterprise according to the number of target paths between each non-target enterprise and the target enterprise in the enterprise relationship map, and uses an association value determination module to determine the association value between each non-target enterprise and the target enterprise according to each intimacy value, so that the target associated enterprises associated with the target enterprise can be accurately identified from the non-target enterprises according to the association value. The identification result is more reasonable and accurate, which provides a direction for investment promotion and facilitates targeted investment promotion.

[0122] Another embodiment of the present application provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the following method steps when executing the computer program on the memory:

[0123] Step 1: Obtain an enterprise relationship map; the enterprise relationship map includes a target enterprise and several non-target enterprises;

[0124] Step 2: obtaining the number of target paths between the non-target enterprises and the target enterprises based on the enterprise relationship graph;

[0125] Step 3: Based on the path numbers and the first target correspondence in the target association model, determine the intimacy value corresponding to each path number;

[0126] Step 4: determining the association value between the non-target enterprise and the target enterprise based at least on the intimacy value;

[0127] Step 5: Identify target associated enterprises associated with the target enterprise based on the associated values ​​of the non-target enterprises.

[0128] The specific implementation process of the above method steps can be found in any of the above-mentioned enterprise association relationship identification method embodiments, and this embodiment will not be repeated here.

[0129] The electronic device in the present application constructs an enterprise relationship map with enterprises and legal persons as nodes, and then determines the intimacy value between each non-target enterprise and the target enterprise according to the number of target paths between each non-target enterprise and the target enterprise in the enterprise relationship map, and determines the association value between each non-target enterprise and the target enterprise according to each intimacy value, so that the target-associated enterprises associated with the target enterprise can be accurately identified from the non-target enterprises according to the association value. The identification result is more reasonable and accurate, which provides a direction for investment promotion and facilitates targeted investment promotion.

[0130] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A method for identifying enterprise association relationships, characterized in that: include: Obtain enterprise relationship map; The enterprise relationship map includes a target enterprise and several non-target enterprises; Acquire the number of target paths between the non-target enterprises and the target enterprises based on the enterprise relationship graph; Determine the intimacy value corresponding to each of the path numbers based at least on the path number, the target first correspondence in the target association model, and the intimacy weight value corresponding to each of the path numbers; the intimacy weight value is determined based on the number of nodes of each target path corresponding to the path number; Determining an association value between a non-target enterprise and the target enterprise based at least on the intimacy value; Identify target associated enterprises associated with the target enterprise based on the associated values ​​of the non-target enterprises; Before obtaining the number of paths of the target path, the method further includes: establishing the target correlation model based on the enterprise relationship graph, specifically including: Establishing an initial correlation model; the initial correlation model includes: a first correspondence between the number of paths and the initial intimacy value; Determine the target enterprise, the sample enterprises, and the actual correlation values ​​between the target enterprise and the sample enterprises based on the enterprise relationship map; Determine the number of paths between the target enterprise and the sample enterprise based on the enterprise relationship graph, and determine the target initial intimacy value by searching the first corresponding relationship in the initial association model based on the number of paths; determining a target initial association value based at least on the target initial intimacy value; The initial intimacy value is adjusted based on the difference between the actual association value and the target initial association value, and a target first corresponding relationship between the number of paths and the target intimacy value is obtained to obtain the target association model.

2. The method according to claim 1, characterized in that Before obtaining the enterprise relationship map, the method further includes constructing the enterprise relationship map, specifically including: Obtain information about each enterprise; Obtain one or more relationships between enterprises, between enterprises and legal persons, and between legal persons based on information about each enterprise; Based on one or more of the relationships between enterprises, enterprises and legal persons, and legal persons and legal persons, an enterprise relationship map is constructed with enterprises and / or legal persons as nodes.

3. The method according to claim 1, characterized in that After determining the intimacy value corresponding to the number of paths, the method further includes: Determine the type of relationship between the non-target enterprise and the target enterprise; Determine a first association value corresponding to the relationship type based on the relationship type and the target second corresponding relationship in the target association model; The determining of the association value between the non-target enterprise and the target enterprise at least based on the intimacy value includes: obtaining the association value between the non-target enterprise and the target enterprise by calculation based on the intimacy value and the first association value.

4. The method according to claim 1, characterized in that The obtaining the number of target paths between non-target enterprises and target enterprises based on the enterprise relationship graph specifically includes: Acquire a first path between a non-target enterprise and a target enterprise based on the enterprise relationship graph; Screening the first path based on the target path node limit value in the target association model to obtain a target path with a path node number less than the target path node limit value; The number of paths is determined based on the number of target paths.

5. The method according to claim 1, characterized in that The determining, based at least on the number of paths and the first corresponding relationship of the target in the target association model, the intimacy value corresponding to each of the number of paths specifically includes: Searching for the first corresponding relationship of the target based on the path number, and obtaining a first intimacy value corresponding to the path number; Obtain the total number of nodes on the target path; Based on the total number of nodes and the correspondence between the number of nodes and the first intimacy weight value, determine the first intimacy weight value corresponding to the total number of nodes; The intimacy value is calculated based on the first intimacy weight value and the first intimacy value.

6. The method according to claim 1, characterized in that The determining, based at least on the number of paths and the first corresponding relationship of the target in the target association model, the intimacy value corresponding to each of the number of paths specifically includes: Searching for the first corresponding relationship of the target based on the path number, and obtaining a first intimacy value corresponding to the path number; Obtaining the number of first nodes of each target path; Determine the second intimacy weight value corresponding to each of the first node numbers based on the correspondence between the node number and the second intimacy weight value; Calculate a third intimacy weight value based on each of the second intimacy weight values; The intimacy value is calculated based on the third intimacy weight value and the first intimacy value.

7. The method according to claim 1, characterized in that The initial correlation model also includes: a second corresponding relationship between the enterprise's relationship type and the initial first correlation value and an initial path node restriction value; Determining the number of paths between the target enterprise and the sample enterprise based on the enterprise relationship graph includes: determining the number of paths between the target enterprise and the sample enterprise within the initial path node limit value based on the enterprise relationship graph; The determining of the target initial association value based at least on the target initial intimacy value comprises: Based on the relationship type between the target enterprise and the sample enterprise, searching for a second corresponding relationship in the initial correlation model to determine a target initial first correlation value; Calculate and obtain a target initial association value based on the target initial first association value and the target initial intimacy value; The establishing of the target association model also includes: adjusting the initial first association value and the initial path node restriction value based on the difference between the actual association value and the target initial association value, obtaining the target second corresponding relationship between the relationship type and the target first association value and the target path node restriction value, so as to obtain the target association model.

8. The method according to claim 1, characterized in that After identifying and obtaining the target affiliated enterprise, the method further includes: Based on the order of the relevance values ​​of the target related enterprises, the target related enterprises are displayed in a descending order.

9. A device for identifying corporate association relationships, characterized in that: include: The first acquisition module is used to acquire the enterprise relationship map; The enterprise relationship map includes a target enterprise and several non-target enterprises; A second acquisition module, configured to acquire the number of target paths between the non-target enterprises and the target enterprises based on the enterprise relationship graph; An intimacy value determination module, configured to determine an intimacy value corresponding to each of the path numbers based at least on the path number, the target first correspondence in the target association model, and the intimacy weight value corresponding to each of the path numbers; the intimacy weight value is determined based on the number of nodes of each target path corresponding to the path number; A correlation value determination module, configured to determine a correlation value between a non-target enterprise and the target enterprise based at least on the intimacy value; An identification module, configured to identify target associated enterprises associated with the target enterprise based on the associated values ​​of the non-target enterprises; The enterprise association relationship identification device further includes an establishment module, which is used to: establish the target association model based on the enterprise relationship map, specifically to: Establishing an initial correlation model; The initial correlation model includes: a first correspondence between the number of paths and the initial intimacy value; Determine the target enterprise, the sample enterprises, and the actual correlation values ​​between the target enterprise and the sample enterprises based on the enterprise relationship map; Determine the number of paths between the target enterprise and the sample enterprise based on the enterprise relationship graph, and determine the target initial intimacy value by searching the first corresponding relationship in the initial association model based on the number of paths; determining a target initial association value based at least on the target initial intimacy value; The initial intimacy value is adjusted based on the difference between the actual association value and the target initial association value, and a target first corresponding relationship between the number of paths and the target intimacy value is obtained to obtain the target association model.

10. An electronic device, characterized in that: The method at least comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the enterprise association relationship identification method according to any one of claims 1 to 8 when executing the computer program on the memory.

Images