CN115689705A

CN115689705A - Object identification method, device, equipment and medium

Info

Publication number: CN115689705A
Application number: CN202211231315.8A
Authority: CN
Inventors: 王晓宇; 朱丹
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2022-10-09
Filing date: 2022-10-09
Publication date: 2023-02-03

Abstract

The present disclosure provides an object recognition method, apparatus, device and medium, which can be applied to the technical field of computers and the technical field of artificial intelligence. The object recognition method includes: generating an object network diagram of the plurality of objects based on the property attribution information of the plurality of objects; determining a target object network map from the object network map based on the network density of the object network map; determining a target object from the target object network graph based on the point centrality of the target object network graph; and determining evaluation results of a plurality of objects in the target object network graph based on the attribute information of the target object.

Description

Object identification method, device, equipment and medium

Technical Field

The present disclosure relates to the field of computer technology and the field of artificial intelligence technology, and more particularly, to a method, apparatus, device, medium, and program product for object recognition.

Background

The related loan is a huge loan which is far beyond the liability capability of the enterprise and is obtained by constructing an enterprise group with multi-level equity relations and forming a loan guarantee chain by utilizing the complex and intricate related relations. Lending enterprises need to heavily manage the risk of associated loans.

In implementing the disclosed concept, the inventors found that there are at least the following problems in the related art: the employees of the lending enterprise usually determine the credit line of the associated loan, the loan risk and other problems according to experience, and this way is not only greatly influenced by the subjective factors but also has low operation efficiency.

Disclosure of Invention

In view of the above, the present disclosure provides an object recognition method, apparatus, device, medium, and program product.

One aspect of the present disclosure provides an object recognition method, including:

generating an object network graph of a plurality of objects based on property attribution information of the plurality of objects, wherein the object network graph comprises a plurality of object nodes and a plurality of associated edges, the object nodes are used for representing the objects, and the associated edges are used for representing the association relationship between the two objects;

determining a target object network graph from the object network graph based on the network density of the object network graph, wherein the network density is used for representing the correlation degree between a plurality of objects in the object network graph;

determining a target object from the target object network graph based on the point centrality of the target object network graph; and

and determining the evaluation results of the plurality of objects in the target object network graph based on the attribute information of the target object.

According to an embodiment of the present disclosure, the determining a target object network map from the object network map based on the network density of the object network map includes:

taking the object network graph as the target object network graph when the network density is determined to be greater than or equal to a predetermined network density threshold value; and

and under the condition that the network density is determined to be smaller than the preset network density threshold value, determining the target object network graph from the object network graph by using a clustering analysis method.

According to an embodiment of the present disclosure, the object recognition method further includes, before determining a target object network map from the object network map based on the network density of the object network map:

determining the number of the plurality of object nodes and the number of the plurality of associated edges in the object network graph; and

determining the network density of the object network graph based on the number of the plurality of object nodes and the number of the plurality of associated edges.

According to an embodiment of the present disclosure, the determining a target object from the target object network graph based on the point centrality of the target object network graph includes:

determining respective point centralities of the plurality of object nodes in the target object network graph, wherein the respective point centralities of the plurality of object nodes are used for representing importance degrees of the plurality of object nodes in the target object network graph;

determining the point centrality of the target object network graph based on the point centrality of each of the plurality of object nodes; and

and determining the target object from the target object network graph based on the point centrality of the target object network graph.

According to an embodiment of the present disclosure, the determining the respective point centrality of the plurality of object nodes in the target object network graph includes:

for each object node of the plurality of object nodes,

determining at least one associated edge associated with the object node; and

determining a point centrality of the object node based on at least one associated edge of the object node, the plurality of associated edges of the target object network graph, and the plurality of object nodes of the target object network graph.

According to an embodiment of the present disclosure, the determining the respective point centralities of the plurality of object nodes in the target object network graph includes:

repeatedly executing the following operations until the point centrality of each of the plurality of object nodes in the target object network graph is determined;

determining an object node i from the object nodes, wherein i is greater than or equal to 1 and i is less than or equal to n, and the total number of the object nodes is n;

repeatedly executing the following operations until the association degree between the object node i and any two object nodes in the target object network graph is determined;

determining a plurality of associated paths jk between an object node j and an object node k in the target object network graph, wherein the associated paths jk are used for representing paths which connect the object node j and the object node k through the associated edges and the object node, k is greater than or equal to 1 and k is less than or equal to n, j is greater than or equal to 1 and j is less than or equal to n, i is not equal to k and k is not equal to j;

determining a target associated route jki passing through the object node i from the plurality of associated routes jk;

the degree of association between the target node i, the target node j, and the target node k is determined based on the plurality of relevant routes jk and the target relevant route jki.

According to an embodiment of the present disclosure, the attribute information includes a plurality of attribute sub information;

the determining evaluation results of the plurality of objects in the target object network graph based on the attribute information of the target object includes:

for each of the plurality of attribute sub-information,

determining the type information of the attribute sub-information;

determining the weight of the attribute sub-information based on the type information of the attribute sub-information;

determining an analysis value of the attribute information based on a weight of each of the plurality of attribute sub information and a predetermined analysis value of the attribute sub information;

and determining the evaluation results of the plurality of objects in the target object network graph based on the analysis value of the attribute information.

According to an embodiment of the present disclosure, the generating an object network map of a plurality of objects based on the property attribution information of each of the plurality of objects includes:

determining an association relationship between the plurality of objects based on the title attribution information of each of the plurality of objects; and

and generating an object network graph of the plurality of objects based on the association relationship.

According to an embodiment of the present disclosure, the attribute sub-information includes at least one of: business scope information, available resource holding information, mobile resource flow information, and fixed resource holding information.

Another aspect of the present disclosure provides an object recognition apparatus including:

an object network graph generating module, configured to generate an object network graph of a plurality of objects based on property attribution information of each of the plurality of objects, where the object network graph includes a plurality of object nodes and a plurality of associated edges, where the object nodes are used to represent the objects, and the associated edges are used to represent an association relationship between two of the objects;

a target object network graph determining module, configured to determine a target object network graph from the object network graph based on a network density of the object network graph, where the network density is used to characterize a degree of association between a plurality of objects in the object network graph;

the target object determining module is used for determining a target object from the target object network graph based on the point centrality of the target object network graph; and

and the object evaluation result determining module is used for determining the evaluation results of the objects in the target object network graph based on the attribute information of the target object.

Yet another aspect of the present disclosure provides an electronic device including:

one or more processors;

a memory to store one or more instructions that,

wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to implement the method as described above.

Yet another aspect of the present disclosure provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to implement a method as described above.

Yet another aspect of the disclosure provides a computer program product comprising computer executable instructions for implementing the method as described above when executed.

According to the embodiment of the disclosure, an object network graph of a plurality of objects is generated based on the property attribution information of each of the plurality of objects, wherein the object network graph comprises a plurality of object nodes and a plurality of associated edges, the object nodes are used for representing the objects, and the associated edges are used for representing the association relationship between the two objects; determining a target object network diagram from the object network diagram based on the network density of the object network diagram, wherein the network density is used for representing the association degree of a plurality of objects in the object network diagram; determining a target object from the target object network graph based on the point centrality of the target object network graph; and a technical means for determining evaluation results of a plurality of objects in the target object network graph based on the attribute information of the target object, wherein the object network graph of the plurality of objects is generated based on the property attribution information of each of the plurality of objects, the association relationship between the plurality of objects and the plurality of objects can be expressed in the form of the object network graph, the analysis of the association degree between the plurality of objects is converted into the analysis of the object network graph, the target object network graph is determined from the object network graph based on the network density of the object network graph, the target object network graph with a closer association degree can be determined from the object network graph, the target object is determined from the target object network graph based on the point centrality of the target object network graph, the more important object can be determined as the target object from the target object network graph, the evaluation results of the plurality of objects in the target object network graph are determined based on the attribute information of the target object, so that the evaluation of the plurality of objects in the target object network graph is more based on, and the accuracy and the reliability of the evaluation results are improved.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure with reference to the accompanying drawings, in which:

fig. 1 schematically illustrates an exemplary system architecture to which an object recognition method may be applied, according to an embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow chart of an object recognition method according to an embodiment of the present disclosure;

FIG. 3 schematically illustrates an object network diagram according to an embodiment of the disclosure;

fig. 4 schematically shows a block diagram of an object recognition arrangement according to an embodiment of the present disclosure; and

fig. 5 schematically shows a block diagram of a computer system adapted to implement an object recognition method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.

Where a convention analogous to "A, B and at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include, but not be limited to, systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a convention analogous to "A, B or at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B or C" would include, but not be limited to, systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

At present, the management method of the risk of the associated loan is mainly to manually inquire the public information of the enterprise needing the loan by enterprise staff and judge the loan risk of the enterprise needing the loan by combining the experience of the enterprise staff. This approach is not only significantly affected by subjective factors but is inefficient. Based on this, embodiments of the present disclosure provide an object recognition method, apparatus, device, medium, and program product.

An embodiment of the present disclosure provides an object identification method, including:

generating an object network graph of a plurality of objects based on property attribution information of the plurality of objects, wherein the object network graph comprises a plurality of object nodes and a plurality of association edges, the object nodes are used for representing the objects, and the association edges are used for representing association relations between the two objects; determining a target object network diagram from the object network diagram based on the network density of the object network diagram, wherein the network density is used for representing the association degree of a plurality of objects in the object network diagram; determining a target object from the target object network graph based on the point centrality of the target object network graph; and determining evaluation results of a plurality of objects in the target object network graph based on the attribute information of the target object.

According to the embodiment of the disclosure, by generating the object network graphs of the plurality of objects based on the property attribution information of the plurality of objects, the plurality of objects and the association relationship among the plurality of objects can be expressed in the form of the graph, and the analysis of the association degree among the plurality of objects is converted into the analysis of the object network graph, the target object network graph is determined from the object network graph based on the network density of the object network graph, the target object network graph generated by the object with the closer association degree can be determined from the object network graph, the target object is determined from the target object network graph based on the point centrality of the target object network graph, the target object which is the more important object can be determined from the target object network graph, the evaluation results of the plurality of objects in the target object network graph are determined based on the attribute information of the target object, so that the evaluation of the plurality of objects in the target object network graph is more based, and the accuracy and the reliability of the evaluation results are improved.

Fig. 1 schematically illustrates an exemplary system architecture 100 to which an object recognition method may be applied, according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, the system architecture 100 according to this embodiment may include

terminal devices

101, 102, 103, a network 104 and a server 105. Network 104 is the medium used to provide communication links between

terminal devices

101, 102, 103 and server 105. Network 104 may include various connection types, such as wired and/or wireless communication links, and so forth.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have installed thereon various communication client applications, such as a shopping-like application, a web browser application, a search-like application, an instant messaging tool, a mailbox client, and/or social platform software, etc. (by way of example only).

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the

terminal devices

101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the object identification method provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the object recognition apparatus provided by the embodiments of the present disclosure may be generally disposed in the server 105. The object identification method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Accordingly, the object recognition apparatus provided in the embodiments of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Alternatively, the object identification method provided by the embodiment of the present disclosure may also be executed by the

terminal device

101, 102, or 103, or may also be executed by another terminal device different from the

terminal device

101, 102, or 103. Accordingly, the object recognition apparatus provided in the embodiments of the present disclosure may also be disposed in the

terminal device

101, 102, or 103, or in another terminal device different from the

terminal device

101, 102, or 103.

For example, in the case where a plurality of objects in the object network diagram represent a plurality of enterprises, attribute information representing the business conditions of the enterprises may be originally stored in any one of the

terminal devices

101, 102, or 103 (for example, but not limited to, the terminal device 101), or may be stored on an external storage device and may be imported into the terminal device 101. Then, the terminal device 101 may locally execute the object identification method provided by the embodiment of the present disclosure, or send the object to be identified to another terminal device, a server, or a server cluster, and execute the object identification method provided by the embodiment of the present disclosure by another terminal device, a server, or a server cluster that receives the object to be identified.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Fig. 2 schematically shows a flow chart of an object recognition method according to an embodiment of the present disclosure.

As shown in fig. 2, the method includes operations S201 to S204.

In operation S201, an object network graph of a plurality of objects is generated based on property attribution information of each of the plurality of objects, wherein the object network graph includes a plurality of object nodes and a plurality of associated edges, wherein the object nodes are used for characterizing the objects, and the associated edges are used for characterizing an association relationship between two objects.

According to embodiments of the present disclosure, a plurality of objects may characterize a plurality of businesses. Title assignment information may characterize information of a person who has actual control over the enterprise. For example, the title attribution information may be information of enterprise legal persons, enterprise shareholders and the like.

According to embodiments of the present disclosure, there may be common title attribution information among multiple objects. For example, there may be a corporate identity across multiple enterprises and a shareholder identity across multiple enterprises.

According to the embodiment of the disclosure, under the condition that the plurality of objects have the same property attribution information, the association relationship among the plurality of objects can be represented, the object network graph can be generated based on the plurality of objects and the association relationship among the plurality of objects, and the plurality of objects and the association relationship among the plurality of objects can be represented in the form of the graph.

In operation S202, a target object network graph is determined from the object network graph based on a network density of the object network graph, wherein the network density is used to characterize a degree of association between a plurality of objects in the object network graph.

According to the embodiment of the disclosure, the larger the network density of the object network graph is, the more closely the association degree of the plurality of objects in the object network graph is illustrated. The target object network graph can represent the object network graph generated by a plurality of objects with higher network density and closer association degree and the association relation among the objects in the object network graph.

According to the embodiment of the disclosure, the target object network graph may be an object network graph or a part of the object network graph, and the structure of the target object network graph is determined according to the network density of the object network graph.

In operation S203, a target object is determined from the target object network map based on the point centrality of the target object network map.

According to the embodiment of the disclosure, based on the point centrality of the target object network graph, a key object in the target object network graph can be determined, the key object can be used as the target object, and then the whole target object network graph can be analyzed based on the target object. According to an embodiment of the present disclosure, the degree of point-centric of the target object network graph characterizes the degree of importance of the target object in the target object network graph. The larger the point centrality is, the more important the target object in the target object network graph is.

In operation S204, evaluation results of a plurality of objects in the target object network map are determined based on the attribute information of the target object.

According to an embodiment of the present disclosure, the attribute information of the target object may be information representing a business condition of the target object. The business situation information may include information such as financial situation and business development situation of the industry to which the target object belongs.

According to the embodiment of the disclosure, the attribute information of the target object may be analyzed first, and the evaluation results of the plurality of objects in the target object network graph may be determined according to the analysis results.

According to the embodiment of the disclosure, by generating the object network graphs of the plurality of objects based on the property attribution information of the plurality of objects, the plurality of objects and the association relationship among the plurality of objects can be expressed in the form of the object network graphs, and the analysis of the association degree among the plurality of objects is converted into the analysis of the object network graphs, the target object network graphs can be determined from the object network graphs based on the network density of the object network graphs, the target object network graphs with the closer association degree can be determined from the object network graphs, the target objects can be determined from the target object network graphs based on the point centrality of the target object network graphs, the more important objects can be determined from the target object network graphs as the target objects, the evaluation results of the plurality of objects in the target object network graphs can be determined based on the attribute information of the target objects, so that the evaluation of the plurality of objects in the target object network graphs is more based, and the accuracy and the reliability of the evaluation results can be improved. When the target object is an enterprise, the credibility of the credit granting amount for a plurality of loan enterprises can be improved, and excessive credit granting for the loan enterprises can be avoided.

According to an embodiment of the present disclosure, operation S201 includes: determining an association relation between the plurality of objects based on the property attribution information of the plurality of objects; and generating an object network graph of the plurality of objects based on the incidence relation.

According to the embodiment of the disclosure, in the case that a plurality of objects represent a plurality of enterprises, the respective title attribution information on the plurality of objects disclosed on the network can be automatically acquired by using a related technology, the extracted respective title attribution information on the plurality of objects is stored in an original database, data in the original database is processed, a relation matrix on the plurality of objects is constructed, the data in the relation matrix can represent the association relation among the plurality of objects, and an object network graph is determined according to the data in the relation matrix.

According to the embodiment of the present disclosure, for example, in a case where a plurality of objects represent a plurality of enterprises, it may be automatically obtained from the network that the names of the shareholder names in the title attribution information of the enterprise 1 are zhang, the names of the shareholder names in the title attribution information of the enterprise 2 are zhang and li, respectively, and the names of the shareholder names in the title attribution information of the enterprise 3 are zhao. The data for enterprise 1, enterprise 2, enterprise 3, zhang san, li si and Zhao Wu may be stored in the raw database.

According to the embodiment of the disclosure, a relationship matrix of the enterprise and the property ownership information can be established according to the data stored in the original database, and the relationship matrix of the enterprise and the property ownership information is shown in table 1.

TABLE 1

	Zhang San	Li Si	Zhao Wu
				Enterprise 1	1	0	0
Enterprise 2	1	1	0
				Enterprise 3	0	0	1

According to an embodiment of the present disclosure, the column values in table 1 may characterize all businesses that need to be identified, and the row values may characterize the names of the stockholders of all businesses obtained from the information published on the web. If a shareholder is included in one of the enterprises, a 1 is filled at the intersection of the row of the enterprise and the column of the shareholder name. Otherwise, 0 is filled. For example, the first column in the first row of Table 1 has a value of 1, representing Zhang three as acting as a stockholder in Enterprise 1, and the second column in the first row is 0, representing Lily four as not acting as a stockholder in Enterprise 1.

In accordance with an embodiment of the present disclosure, in the case where multiple objects characterize multiple enterprises, an object network graph may be generated using the data in table 1. The specific generation method may be, for example: and connecting a plurality of enterprises with numerical values of 1 in the same column in the table 1 by using line segments, wherein the enterprises have all association relations, and the enterprises need to be connected by using the line segments.

According to the embodiment of the disclosure, in order to more clearly indicate the association relationship between enterprises, the relationship matrix of the enterprise and the property attribution information in table 1 is converted into the relationship matrix of the enterprise and the enterprise. The specific conversion method is to convert all the row information and column information in table 1 into enterprises. The value 1 in the relationship matrix of the converted enterprise and the enterprise represents that a common stockholder exists between the enterprises, and the value 0 represents that the common stockholder does not exist between the enterprises. The converted enterprise-to-enterprise relationship matrix is shown in table 2.

TABLE 2

	Enterprise 1	Enterprise 2	Enterprise 3
				Enterprise 1	1	0	0
Enterprise 2	1	1	0
				Enterprise 3	0	0	1

In accordance with an embodiment of the present disclosure, an object network graph may be generated using the data in table 2 where multiple objects characterize multiple enterprises. The specific generation method may be, for example: two enterprises with a value of 1 in table 2 are connected by a line segment. Two businesses with a value of 0 do not have a shareholder in common and therefore do not have line segment connections.

The relationship matrix between enterprises obtained according to the above method can be shown in table 3.

In table 3, A, B, C, D, E, F, G may each represent a different enterprise, in accordance with embodiments of the present disclosure. Enterprise a has a shareholder with enterprises D, F and G, enterprise B has a shareholder with C, D, F and G, enterprise E has a shareholder with enterprise C, D, F and G, and enterprise F has a shareholder with enterprise A, B, E and G.

In the case where multiple objects characterize multiple enterprises, an object network graph generated according to table 3 is shown in fig. 3, according to an embodiment of the present disclosure. Fig. 3 schematically illustrates an object network diagram according to an embodiment of the disclosure. Each point in fig. 3 represents a business, and the line between the points represents that the businesses have shareholders, i.e., have stock-holding relationships.

TABLE 3

Name of an enterprise	A	B	C	D	E	F	G
								A	1	0	0	1	0	1	1
B	0	1	1	1	0	1	1
								C	0	1	1	0	0	0	0
D	1	1	0	1	0	0	0
								E	0	0	1	1	1	1	1
F	1	1	0	0	1	1	1
								G	1	1	0	0	1	1	1

According to the embodiment of the disclosure, the association relationship between the objects is determined based on the property attribution information of each object, the object network graph of the objects is generated based on the association relationship, the relationship between the objects on the property attribution information can be expressed in the form of the object network graph, the relationship expression between the objects on the property attribution information is clearer, and the analysis of the relationship compactness between the objects is converted into the analysis of the object network graph.

According to an embodiment of the present disclosure, the object identifying method further includes, before determining the target object network graph from the object network graph based on the network density of the object network graph: determining the number of a plurality of object nodes and the number of a plurality of associated edges in the object network graph; and determining the network density of the object network graph based on the number of the plurality of object nodes and the number of the plurality of associated edges.

According to embodiments of the present disclosure, the network density may be solved according to equation (1).

Wherein n in formula (1) represents the number of object nodes in the object network graph, and l represents the number of associated edges in the object network graph.

According to the embodiment of the present disclosure, for example, the number n of object nodes in the object network graph in fig. 3 is 7, the number l of associated edges is 13, and the network density of the object network graph in fig. 3 can be found to be 0.69 according to formula (1).

According to the embodiment of the disclosure, the network density of the object network graph is determined based on the number of the plurality of object nodes and the number of the plurality of associated edges, so that accurate data capable of evaluating the network density can be obtained, and a reliable basis is provided for determining the target object network from the object network graph based on the network density of the object network graph subsequently.

According to an embodiment of the present disclosure, operation S202 includes: and in the case that the network density is determined to be greater than or equal to the predetermined network density threshold value, taking the object network graph as a target object network graph. And determining a target object network graph from the object network graphs by using a cluster analysis method under the condition that the network density is determined to be less than a preset network density threshold value.

According to the embodiment of the disclosure, under the condition that the network density is determined to be greater than or equal to the predetermined network density threshold value, the degree of association between the objects in the representation object network graph is relatively close, so that the object network graph can be directly taken as a whole for subsequent analysis, and the object network graph is taken as a target object network graph.

According to the embodiment of the present disclosure, when it is determined that the network density is less than the predetermined network density threshold, and the representation evaluates the object network graph as a whole, the degree of association of the objects in the object network graph is not tight enough, and therefore, it is necessary to further search for objects with a tight association relationship from the object network graph, and generate the target object network graph by using the objects with a tight association relationship and the association relationship thereof.

According to the embodiment of the disclosure, in the case that the object in the object network diagram represents the enterprise, the greater the network density is, the tighter the holding relationship between the loan enterprises which need to be identified is represented, and the loan enterprises need to be credited and evaluated as a whole by the loan enterprises. On the contrary, the representative loan enterprises to be identified are not closely related, and the loan enterprises need to be further narrowed in accordance with the analysis results of the network subgroups in the target network diagram.

According to the embodiment of the disclosure, the predetermined network density threshold value can be determined according to actual conditions, and the value range of the predetermined network density threshold value is not limited by the embodiment of the disclosure.

According to the embodiment of the present disclosure, the value of the network density of the object network map is between 0 and 1, in the practical application process, the predetermined network density threshold value may be, for example, 0.7, and if the network density is greater than or equal to 0.7, the network map is said to have a larger density.

According to the embodiment of the disclosure, the target object network graph representation is determined from the object network graph by using a cluster analysis method, and the target object network graph with the network density larger than or equal to the preset network density threshold value is determined from the object network graph by using the cluster analysis method.

According to the embodiment of the present disclosure, the cluster analysis method may be, for example, an iterative correlation convergence method (CONCOR), and the embodiment of the present disclosure does not limit the specific cluster analysis method, and is applicable to the embodiment of the present disclosure as long as the method for determining the target object network diagram from the object network diagram can be implemented.

According to the embodiment of the present disclosure, for example, in a case where an object in the object network graph represents an enterprise and the predetermined network density threshold is set to 0.7, the network density 0.69 of the object network graph in fig. 3 is less than 0.7, at this time, the target object network graph may be determined from the object network graph in fig. 3 by using the CONCOR method, the target object network graph determined by the CONCOR method is composed of enterprises A, B, E and F, and the network density of the target object network graph is calculated to be 0.833,0.833 greater than the predetermined network density threshold 0.7 by using formula (1).

According to the embodiment of the disclosure, under the condition that the network density is determined to be greater than or equal to the predetermined network density threshold value, the object network graph is taken as the target object network graph, and under the condition that the network density is determined to be less than the predetermined network density threshold value, the target object network graph is determined from the object network graph by using a cluster analysis method, the association degree of the objects in the target object network graph can be further controlled by using the predetermined network density threshold value, and the target object network graph formed by the objects with the relatively close association degree is obtained.

According to an embodiment of the present disclosure, operation S203 includes: determining the respective point centrality of a plurality of object nodes in the target object network graph, wherein the respective point centrality of the plurality of object nodes is used for representing the importance degree of the plurality of object nodes in the target object network graph; determining the point centrality of the target object network graph based on the respective point centrality of the plurality of object nodes; and determining the target object from the target object network graph based on the point centrality of the target object network graph.

According to an embodiment of the present disclosure, the importance degree of the object node in the target object network graph may refer to: and the relevance of the object node and other object nodes except the object node in the target object network graph.

According to the embodiment of the present disclosure, in a case that the point centrality of each of the plurality of object nodes in the target object network graph is determined, a value of the maximum point centrality among the point centralities of each of the plurality of object nodes may be determined as the point centrality of the target object network graph, and a point centrality meeting a point centrality threshold among the point centralities of each of the plurality of object nodes may also be determined as the point centrality of the target object network graph, where the point centrality threshold may be selected according to an actual situation, for example, the point centrality threshold may be 0.15, 0.16, 0.17, and the like. According to the embodiment of the disclosure, the determination method of the point centrality of the target object network graph is not limited, and the determination method can be selected according to actual conditions.

According to an embodiment of the present disclosure, in a case where a value of a maximum centrality among point centralities of each of a plurality of object nodes is determined as a point centrality of a target object network graph, an object equal to the point centrality of the target object network graph may be determined as a target object.

In the case where the value of the maximum centrality among the point centralities of each of the plurality of object nodes is determined as the point centrality of the target object network graph, an object whose point centrality is equal to or greater than the point centrality of the target object network graph may be determined as the target object.

According to the embodiment of the disclosure, the point centrality of each of a plurality of object nodes in the target object network graph is determined, and the point centrality of the target object network graph is determined based on the point centrality of each of the plurality of object nodes, so that the centrality of the target object which needs to be determined subsequently in the target object network graph can be controlled according to actual conditions, the centrality of the object with the importance degree meeting the requirement is determined as the point centrality of the target object network graph, and further, the target object can be determined from the target object network graph based on the point centrality of the target object network graph, and further, the object which is closer to other objects in the target object network graph in association degree and is considered as more important can be obtained.

According to an embodiment of the present disclosure, determining respective point centralities of a plurality of object nodes in a target object network graph comprises: determining, for each object node of a plurality of object nodes, at least one associated edge associated with the object node; and determining a point centrality of the object node based on the at least one associated edge associated with the object node, the plurality of associated edges of the target object network graph, and the plurality of object nodes of the target object network graph.

According to an embodiment of the present disclosure, determining a point centrality of an object node based on at least one associated edge associated with the object node, a plurality of associated edges of a target object network graph, and a plurality of object nodes of the target object network graph may include: determining a point centrality of an object node based on a number of at least one associated edge associated with the object node, a number of a plurality of associated edges of a target object network graph, and a number of a plurality of object nodes of the target object network graph

According to the embodiment of the present disclosure, taking the object node a as an example, if there are associated edges between the object node a and each of the object node B, the object node C, and the object node D, the number of associated edges associated with the object node a is 3.

According to the embodiment of the present disclosure, taking the target object network graph a including the object node a as an example, the point centrality of the object node a may be determined based on the number of associated edges of the object node a, the number of associated edges of the target object network graph a, and the number of object nodes of the target object network graph.

For example, the average number of associated edges for each object node in the target object network graph a is determined based on the number of associated edges of the target object network graph a and the number of object nodes of the target object network graph, e.g., using the number of associated edges of the target object network graph a divided by the number of object nodes of the target object network graph. And determining the point centrality of the object node A based on the number and the average number of the associated edges of the object node A. And determining the object node A as a first predetermined point centrality when the number of the associated edges of the object node A is determined to be greater than or equal to the average number. And under the condition that the number of the associated edges of the object node A is determined to be less than the average number, determining the object node A to be the second predetermined point centrality.

But the manner of determining the point centrality of the object node is not limited thereto. Determining a point centrality of the object node based on the at least one associated edge associated with the object node, the plurality of associated edges of the target object network graph, and the plurality of object nodes of the target object network graph, may further include: determining the association degree between the object node and any two object nodes except the object node in the target object network graph based on at least one association edge of the object node, a plurality of association edges of the target object network graph and a plurality of object nodes of the target object network graph; and determining the point centrality of the object node based on the relevance of the object node.

According to an optional embodiment of the present disclosure, determining the respective point centrality of a plurality of object nodes in a target object network graph may specifically include:

repeatedly executing the following operations until the point centrality of each of a plurality of object nodes in the target object network graph is determined;

determining an object node i from a plurality of object nodes, wherein i is greater than or equal to 1 and i is less than or equal to n, and the total number of the plurality of object nodes is n;

determining a plurality of associated paths jk between an object node j and an object node k in a target object network graph, wherein the associated paths jk are used for representing paths which connect the object node j and the object node k through associated edges and the object node, k is greater than or equal to 1 and k is less than or equal to n, j is greater than or equal to 1 and j is less than or equal to n, i is not equal to k and k is not equal to j;

determining a target associated path jki passing through the object node i from the plurality of associated paths jk;

and determining the association degree between the object node i and the object node j and the object node k based on the plurality of association paths jk and the target association path jki.

According to the embodiment of the present disclosure, the dot centrality may be calculated according to formula (2).

Wherein i is not equal to k and k is not equal to j and i is not equal to j and j is less than k, C _ABi Characterizing the point centrality of object node i, j characterizing object node j, k characterizing object node k, g _jk Characterizing multiple associative paths jk, g between object node j and object node k _jk (i) A target associated path jki that passes through the object node i among the plurality of associated paths jk is characterized.

According to the embodiment of the present disclosure, for example, in the case where the plurality of objects in the target object network graph represent a plurality of enterprises, and the predetermined network density threshold is set to 0.5, the network density 0.69 of the object network graph in fig. 3 is greater than 0.5, at this time, the object network graph in fig. 3 may be determined as the target object network graph, and the respective point centrality of each enterprise node in fig. 3 may be calculated using equation (2). The respective degrees of point centrality of the respective enterprise nodes are shown in table 4.

TABLE 4

	A	B	E	F	G	D	C
								Degree of center of point	0.179	0.179	0.179	0.143	0.143	0.107	0.071

According to the embodiment of the disclosure, the point centrality of enterprises A, B and E in table 4 is 0.179, the point centrality of enterprises F and G is 0.143, the point centrality of enterprise D is 0.107, and the point centrality of enterprise C is 0.071.

According to the embodiment of the present disclosure, as can be seen from table 4, the point centralities of the enterprises A, B and E are both 0.179, and are the maximum values of the point centralities in table 4, so that it can be considered that the influence of the enterprises A, B and E in the target enterprise network in fig. 3 is large, and therefore, in the case of evaluating the credit line of the enterprise in the target object network in fig. 3, the business, financial and industrial conditions of three key enterprises, namely the enterprises A, B and E, should be considered with emphasis, and the whole credit line is determined based on the above.

According to an embodiment of the present disclosure, the attribute information includes a plurality of attribute sub information.

According to an embodiment of the present disclosure, the attribute information of the target object may characterize: and if the target object is an enterprise, the business state information of the enterprise.

According to an embodiment of the present disclosure, the attribute sub information includes at least one of: business scope information, available resource holding information, mobile resource flow information, and fixed resource holding information.

According to the embodiment of the disclosure, the operation range information can represent that under the condition that the target object represents the enterprise, the state allows the commodity category, variety and service item of the enterprise production and operation, and reflects the content and production and operation direction of the enterprise legal business activity. For example, the business scope information of enterprise a may be: and providing oil drilling technical service and selling the oil pressure gauge.

According to embodiments of the present disclosure, holding available resource information may characterize resources that a business has realized or was consumed during a business period of one year or more, in which case the target object characterizes the business. For example, the information of holding available resources for enterprise a may be: cash, bank deposits, short term loans, accounts receivable and prepaid, expenses to be amortized, inventory, etc. of business a.

According to the embodiment of the disclosure, the flowing resource flowing information can represent the dynamic turnover condition of resources in aspects of enterprise finance, real objects and the like under the condition that the target object represents an enterprise. For example, enterprise a provides a petroleum pressure gauge to enterprise B, and the condition of the petroleum pressure gauge provided to enterprise B within one year by enterprise a may be used as the flowing resource flowing information of enterprise a.

According to embodiments of the present disclosure, the fixed resource holding information may characterize, in the case of a target object characterizing an enterprise, the life of the enterprise exceeds one year of premises, buildings, machines, machinery, transportation, and other production, business related equipment, appliances, tools, and the like. The fixed resource holding information of enterprise a may be, for example: the A enterprise produces the factory of oil pressure gauge, the A enterprise produces the machine of oil pressure gauge etc..

Operation S204 includes: determining type information of the attribute sub-information for each of the plurality of attribute sub-information; determining the weight of the attribute sub-information based on the type information of the attribute sub-information; determining an analysis value of the attribute information based on the respective weights of the plurality of attribute sub-information and a predetermined analysis value of the attribute sub-information; based on the analysis value of the attribute information, an evaluation result of a plurality of objects in the target object network graph is determined.

According to the embodiment of the disclosure, the predetermined analysis value represents a plurality of preset scoring levels which can be used for evaluating the attribute sub-information containing the business condition information of the enterprise when a plurality of objects in the target object network diagram represent a plurality of enterprises.

According to the embodiments of the present disclosure, for example, in the case where the predetermined analysis value of the attribute sub information is fully divided into 10 points, the predetermined analysis value of the attribute sub information may be divided into four scoring steps of 3 points, 6 points, 9 points, and 10 points.

According to an embodiment of the disclosure, the analytical values characterize: and under the condition that a plurality of objects in the target object network diagram represent a plurality of enterprises, calculating the obtained enterprise scoring values according to the respective weights of a plurality of attribute sub-information related to each object in the plurality of objects and the scoring grades of the preset analysis values of the attribute sub-information. The higher the analysis value is, the better the business condition of the enterprise is represented, and the credibility of the enterprise is high.

According to an embodiment of the disclosure, the evaluation results characterize: and when the plurality of objects in the target object network graph represent the enterprises, whether the operation conditions of the enterprises are good or not and whether the credibility of the enterprises meets the loan-capable requirement or not are judged.

According to the embodiment of the disclosure, the preset value can be set to evaluate the analysis value, and the evaluation results of the plurality of objects in the target object network graph are determined according to the preset value range of the analysis value. For example, the maximum value of the analysis value may be 10, the preset value may be 6, and when the analysis value is greater than 6, it is considered that, when a plurality of objects in the target object network map are a plurality of enterprises, the enterprises have good business conditions and high credibility, and may loan the enterprises.

According to the embodiment of the disclosure, for example, in the case that the target object represents the enterprise, the attribute information of the enterprise can be divided into the financial type information and the industry development type information according to the financial status of the enterprise and the industry development status of the industry to which the enterprise belongs. The financial type information may include information of available resources held, flowing resource flowing information, and fixed resource holding information, and the industry development type information may include information of business conditions of the enterprise. According to the embodiments of the present disclosure, the weight of the attribute sub information may be determined according to the degree of importance of the type information of the attribute sub information. For example, in the case that the target object represents an enterprise, the financial type information of the enterprise can directly reflect the current profit and loss conditions of the enterprise, the industry development type information directly reflects the future development conditions of the enterprise, and the industry development type information can only infer the future revenue and earning conditions of the enterprise from the side, so the financial type information is considered to be more important than the industry development type information, and therefore the weight of the financial type information is greater than that of the industry development type information. The financial type information may be weighted by 0.6, for example, and the industry development type information may be weighted by 0.4, for example.

According to the embodiment of the disclosure, for example, in the case where the target object characterizes a business, in the business a, the weight of the financial type information may be 0.6, for example, the weight of the business development type information may be 0.4, for example, and the predetermined analysis value of the attribute sub information is divided into four scoring steps of 3 points, 6 points, 9 points, and 10 points. The fixed asset holding information in the financial type information of enterprise a has a score of 3, the mobile resource has a score of 9, and the holding available resource information of enterprise a has a score of 6, so that the average analysis value of the financial type information may be (3 +9+ 6)/3 + 0.6, that is, the average analysis value of the financial type information may be 3.6. The operation range information score in the industry development type information is 10, and the average analysis value of the industry development type information may be 10 × 0.4, i.e., 4. The analysis value of the attribute information calculated from the average analysis value of the financial type information and the average analysis value of the industry development type information may be 3.6+4, i.e., the analysis value of the attribute information may be 7.6.

According to the embodiment of the disclosure, the preset value of the evaluation analysis value can be set to 6, and when the analysis value is greater than 6, the business condition of an enterprise is good and the credibility of the enterprise meets the loan-capable requirement under the condition that a plurality of objects in the target object network graph represent a plurality of enterprises. The analysis value of the enterprise A is 7.6 which is more than 6, so that the business condition of the enterprise A is considered to be good, and the credibility of the enterprise A meets the loan requirement.

According to the embodiment of the disclosure, the evaluation results of a plurality of objects in the target object network graph are determined based on the analysis value of the attribute information, and whether the business condition of an enterprise is good and whether the credibility of the enterprise meets the loan-capable requirement or not can be determined based on the analysis value of the attribute information under the condition that a plurality of objects represent a plurality of enterprises, so that the accuracy of the evaluation results of the enterprise is improved.

According to the embodiment of the disclosure, evaluation results of a plurality of objects in the target object network graph are determined based on the analysis value of the attribute information, and under the condition that the plurality of objects represent a plurality of enterprises, the automatic evaluation of the operation condition of the enterprises by using the analysis value of the attribute information can be realized, the loan risk of the enterprises needing loan is judged without depending on the experience of enterprise staff, the evaluation of the enterprises is not influenced by subjective factors, and the identification efficiency of risk enterprises is improved.

According to the embodiment of the disclosure, the evaluation results of a plurality of objects in the target object network graph are determined based on the analysis value of the attribute information, so that evaluation basis is provided for evaluating the target object, and the accuracy of the evaluation results is improved. According to embodiments of the present disclosure, enterprise a may be, for example, a private enterprise hosting the business of providing oil drilling technology services and selling oil pressure gauges. Recently, the owner of the business has applied for a floating fund loan from the lending business. Through the method, it can be determined that the enterprise A and the enterprise B have an association relationship, namely the enterprise A and the enterprise B are associated enterprises, the stakeholder relationship of the enterprise B is a couple, and the enterprise B has transacted the floating fund loan at the lending enterprise. Although enterprise a is listed in the list of suppliers for the heavy petroleum enterprises, the major business revenue comes mainly from enterprise B.

The lending enterprise is generally popular in enterprises in the oil industry because the lending enterprise analyzes the operation condition and the financial condition of the enterprise B and is influenced by global new crown epidemic situation and oil price sudden drop. The business of enterprise B continues to decline. The loan enterprise is based on a careful credit concept, excessive credit risk is avoided, the loan enterprise refuses the loan application of the enterprise A, the post-loan management of the enterprise B is enhanced, credit risk management and control work is practically performed, and the credit fund safety of the loan enterprise is ensured.

Fig. 4 schematically shows a block diagram of an object recognition apparatus according to an embodiment of the present disclosure.

As shown in fig. 4, the object recognition apparatus 400 includes an object network map generating module 410, a target object network map determining module 420, and target

object determining modules

430 and 440.

An object network graph generating module 410, configured to generate an object network graph of a plurality of objects based on the property attribution information of each of the plurality of objects, where the object network graph includes a plurality of object nodes and a plurality of associated edges, where an object node is used to represent an object, and an associated edge is used to represent an association relationship between two objects.

And a target object network graph determining module 420, configured to determine a target object network graph from the object network graph based on a network density of the object network graph, where the network density is used to characterize a degree of association between a plurality of objects in the object network graph.

And the target object determining module 430 is configured to determine the target object from the target object network graph based on the point centrality of the target object network graph.

And an object evaluation result determining module 440, configured to determine evaluation results of the plurality of objects in the target object network graph based on the attribute information of the target object.

According to an embodiment of the present disclosure, the target object network graph determining module includes:

and the target object network graph first determining submodule is used for taking the object network graph as the target object network graph under the condition that the network density is determined to be greater than or equal to the preset network density threshold value.

And the second determining submodule of the target object network graph is used for determining the target object network graph from the object network graph by utilizing a cluster analysis method under the condition that the network density is determined to be smaller than the preset network density threshold value.

According to the embodiment of the present disclosure, the training apparatus of the text feature extraction model further includes:

and the object node number and association edge number determining module is used for determining the number of the plurality of object nodes and the number of the plurality of association edges in the object network graph before determining the target object network graph from the object network graph based on the network density of the object network graph.

And the network density determining module is used for determining the network density of the object network graph based on the number of the object nodes and the number of the associated edges.

According to an embodiment of the present disclosure, the target object determination module includes:

and the centrality determining submodule of the object node is used for determining the point centrality of each of a plurality of object nodes in the target object network graph, and the point centrality of each of the plurality of object nodes is used for representing the importance degree of each of the plurality of object nodes in the target object network graph.

And the point centrality determining submodule of the network graph is used for determining the point centrality of the target object network graph based on the respective point centrality of the object nodes.

And the target object determining submodule is used for determining a target object from the target object network graph based on the point centrality of the target object network graph.

According to an embodiment of the present disclosure, the centrality determination submodule of the object node includes:

an associated edge determining unit, configured to determine, for each object node of the plurality of object nodes, at least one associated edge associated with the object node.

A first point centrality determination unit for determining a point centrality of an object node based on at least one associated edge associated with the object node, a plurality of associated edges of the target object network graph and a plurality of object nodes of the target object network graph. According to the embodiment of the present disclosure, the centrality determining submodule of the object node includes:

a second point centrality determining unit configured to repeatedly perform the following operations until the point centrality of each of the plurality of object nodes in the target object network graph is determined;

the evaluation result determination module for the subject includes:

a type information and weight determining unit configured to determine type information of the attribute sub information for each of the plurality of attribute sub information. Based on the type information of the attribute sub information, the weight of the attribute sub information is determined.

An analysis value determination unit configured to determine an analysis value of the attribute information based on a weight of each of the plurality of attribute sub information and a predetermined analysis value of the attribute sub information.

An evaluation result determination unit configured to determine an evaluation result of the plurality of objects in the target object network map based on the analysis value of the attribute information.

According to an embodiment of the present disclosure, the object network graph generating module includes:

and the association relation determining unit is used for determining the association relation among the objects based on the property attribution information of the objects.

And the object network graph generating unit is used for generating the object network graphs of the objects based on the incidence relation.

It should be noted that, unless explicitly stated that a sequence of execution exists between different operations or a sequence of execution exists in technical implementation of different operations, an execution sequence between multiple operations may not be sequential, and multiple operations may also be executed at the same time in the flowchart in the embodiment of the present disclosure.

Any number of modules, sub-modules, units, sub-units, or at least part of the functionality of any number thereof according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, sub-modules, units, sub-units according to the embodiments of the present disclosure may be implemented by being split into a plurality of modules. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in any other reasonable manner of hardware or firmware by integrating or packaging a circuit, or in any one of or a suitable combination of software, hardware, and firmware implementations. Alternatively, one or more of the modules, sub-modules, units, sub-units according to embodiments of the disclosure may be at least partially implemented as a computer program module, which when executed may perform the corresponding functions.

For example, any plurality of the object network map generation module 410, the target object network map determination module 420, the target object determination module 430, and the object evaluation result determination module 440 may be combined and implemented in one module/unit/sub-unit, or any one of the modules/units/sub-units may be divided into a plurality of modules/units/sub-units. Alternatively, at least part of the functionality of one or more of these modules/units/sub-units may be combined with at least part of the functionality of other modules/units/sub-units and implemented in one module/unit/sub-unit. According to the embodiment of the present disclosure, at least one of the object network diagram generation module 410, the target object network diagram determination module 420, the target object determination module 430, and the object evaluation result determination module 440 may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementation manners of software, hardware, and firmware, or implemented by a suitable combination of any several of them. Alternatively, at least one of the object network graph generating module 410, the target object network graph determining module 420, the target object determining module 430 and the evaluation result determining module 440 of the object may be at least partially implemented as a computer program module, which may perform a corresponding function when executed.

It should be noted that the object identification apparatus part in the embodiment of the present disclosure corresponds to the object identification method part in the embodiment of the present disclosure, and the description of the object identification apparatus part specifically refers to the object identification method part, which is not described herein again.

Fig. 5 schematically shows a block diagram of a computer system adapted to implement an object recognition method according to an embodiment of the present disclosure. The computer system illustrated in FIG. 5 is only one example and should not impose any limitations on the scope of use or functionality of embodiments of the disclosure.

As shown in fig. 5, a computer system 500 according to an embodiment of the present disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. The processor 501 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 501 may also include onboard memory for caching purposes. Processor 501 may include a single processing unit or multiple processing units for performing different actions of a method flow according to embodiments of the disclosure.

In the RAM 503, various programs and data necessary for the operation of the system 500 are stored. The processor 501, the ROM 502, and the RAM 503 are connected to each other by a bus 504. The processor 501 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM 502 and/or the RAM 503. Note that the program may also be stored in one or more memories other than the ROM 502 and the RAM 503. The processor 501 may also perform various operations of method flows according to embodiments of the present disclosure by executing programs stored in one or more memories.

According to an embodiment of the present disclosure, system 500 may also include an input/output (I/O) interface 505, input/output (I/O) interface 505 also being connected to bus 504. The system 500 may also include one or more of the following components connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. A drive 510 is also connected to the I/O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.

According to embodiments of the present disclosure, method flows according to embodiments of the present disclosure may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable storage medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program, when executed by the processor 501, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.

According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. Examples may include, but are not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

For example, according to embodiments of the present disclosure, a computer-readable storage medium may include ROM 502 and/or RAM 503 and/or one or more memories other than ROM 502 and RAM 503 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method provided by the embodiments of the present disclosure, when the computer program product is run on an electronic device, the program code being adapted to cause the electronic device to carry out the object recognition method provided by the embodiments of the present disclosure.

The computer program, when executed by the processor 501, performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal on a network medium, downloaded and installed through the communication section 509, and/or installed from the removable medium 511. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims

1. An object recognition method, comprising:

generating an object network graph of a plurality of objects based on property attribution information of the objects, wherein the object network graph comprises a plurality of object nodes and a plurality of association edges, the object nodes are used for representing the objects, and the association edges are used for representing association relations between the two objects;

determining a target object network graph from the object network graph based on the network density of the object network graph, wherein the network density is used for characterizing the association degree of a plurality of objects in the object network graph;

and determining evaluation results of a plurality of objects in the target object network graph based on the attribute information of the target object.

2. The method of claim 1, wherein the determining a target object network graph from the object network graphs based on the network density of the object network graphs comprises:

in the event that it is determined that the network density is greater than or equal to a predetermined network density threshold, treating the object network graph as the target object network graph; and

determining the target object network graph from the object network graphs using a cluster analysis method if it is determined that the network density is less than the predetermined network density threshold.

3. The method of claim 2, further comprising, prior to said determining a target object network graph from the object network graphs based on the network densities of the object network graphs:

determining a number of the plurality of object nodes and a number of the plurality of associated edges in the object network graph; and

4. The method of claim 1, wherein the determining a target object from the target object network graph based on the point centrality of the target object network graph comprises:

determining the point centrality of the target object network graph based on the respective point centrality of the plurality of object nodes; and

determining the target object from the target object network graph based on the point centrality of the target object network graph.

5. The method of claim 4, wherein the determining the respective point centralities of the plurality of object nodes in the target object network graph comprises:

for each object node of the plurality of object nodes,

determining at least one associated edge associated with the object node; and

determining a point centrality of the object node based on at least one associated edge associated with the object node, the plurality of associated edges of the target object network graph, and the plurality of object nodes of the target object network graph.

6. The method of claim 5, wherein the determining the respective point centralities of the plurality of object nodes in the target object network graph comprises:

repeatedly performing the following operations until the respective point centralities of the plurality of object nodes in the target object network graph are determined;

and determining the association degree between the object node i and the object node j and the object node k based on the plurality of associated paths jk and the target associated path jki.

7. The method of claim 1, wherein the attribute information includes a plurality of attribute sub-information;

the determining evaluation results of a plurality of objects in the target object network graph based on the attribute information of the target object comprises:

for each attribute sub-information of the plurality of attribute sub-information,

determining type information of the attribute sub-information;

determining a weight of the attribute sub information based on type information of the attribute sub information;

and determining evaluation results of a plurality of objects in the target object network graph based on the analysis value of the attribute information.

8. The method of claim 1, wherein generating an object network map of the plurality of objects based on the title assignment information for each of the plurality of objects comprises:

determining an association relation between the plurality of objects based on the property attribution information of the plurality of objects; and

and generating an object network graph of the plurality of objects based on the incidence relation.

9. The method of claim 7, wherein the attribute sub-information comprises at least one of: management scope information, held available resource information, mobile resource flow information, fixed resource holding information.

10. An object recognition apparatus comprising:

the object network graph generating module is used for generating an object network graph of a plurality of objects based on the property attribution information of the objects, wherein the object network graph comprises a plurality of object nodes and a plurality of associated edges, the object nodes are used for representing the objects, and the associated edges are used for representing the association relationship between the two objects;

a target object network map determining module, configured to determine a target object network map from the object network map based on a network density of the object network map, where the network density is used to characterize a degree of association between a plurality of objects in the object network map;

and the evaluation result determining module of the object is used for determining the evaluation results of the plurality of objects in the target object network graph based on the attribute information of the target object.

11. An electronic device, comprising:

one or more processors;

a memory to store one or more instructions that,

wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-9.

12. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to carry out the method of any one of claims 1 to 9.

13. A computer program product comprising computer executable instructions for implementing the method of any one of claims 1 to 9 when executed.