Loan object determination method and device, equipment, medium and program product

Abstract

The embodiment of the invention discloses a loan object determination method and device, equipment, a medium and a program product. Comprising the steps of obtaining operation state information of at least one current loan object; performing data consanguinity analysis on each piece of operation state information, and determining an object relation network; carrying out clustering analysis on the object relation network, and determining the object which is located in the same cluster as each current loan object as a potential loan object; wherein the operation state information comprises supply chain data and fund flow data. Enterprises located upstream and downstream of a current loan object market are added into a consideration range of potential loan objects, an object relation network including fund flow directions and commercial exchange among the enterprises in the market is generated, and objects having similar financial health states and commercial potentials with the current loan object are used as potential loan objects. The rapid change of the market state is fully considered in the screening process, the comprehensiveness and accuracy of loan object screening are ensured, and the dynamic property of screening potential loan objects is improved.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a method, device, equipment, medium and program product for determining a loan object. Background Art

[0002] Lending to enterprises is a common scenario in the working environment of banks and other financial institutions. In this scenario, banks and financial institutions usually rely on a series of assessment methods to determine the loan amount, interest rate and the recipient of the loan. These methods include but are not limited to credit scoring models, financial analysis, review of historical transaction records, and market and industry analysis. Credit scoring models assess loan risks by analyzing factors such as the credit record and debt repayment ability of enterprises. Financial analysis focuses on reviewing the financial statements of enterprises and assessing their financial health. Review of historical transaction records helps banks understand the payment habits and cash flow of enterprises, while market and industry analysis provides a macro perspective of the operating environment and potential risks of enterprises.

[0003] However, although the above methods can assist in the evaluation of loan objects to a certain extent, they can often only conduct surface analysis, and it is difficult to deeply understand the complex business relationships and capital flow patterns between enterprises, and it is impossible to accurately reflect the financial status of enterprises and changes in the market environment, which makes it difficult for loan evaluation methods based on the above methods to adapt to the rapid changes in the market and enterprise status. At present, when banks and other financial institutions are facing the problem of how to expand their loan business when the existing corporate user groups are not enough to support the expansion of loan business, the original evaluation methods for loan objects cannot effectively identify and attract more high-quality enterprises to become loan objects, which seriously affects the scale expansion of loan business and is not conducive to the risk management of loan asset quality. Summary of the invention

[0004] The present invention provides a method, apparatus, device, medium and program product for determining loan objects. Based on the capital flows and business dealings between enterprises associated with the current loan objects to which loans have been provided, potential loan objects similar to the current loan objects in the market are mined and evaluated, thereby improving the accuracy and dynamism of screening potential loan objects and expanding the potential market for loan services.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining a loan object, comprising:

[0006] Obtaining the operating status information of at least one current loan object;

[0007] Conduct data lineage analysis on each business status information to determine the object relationship network;

[0008] Perform cluster analysis on the object relationship network, and determine the objects in the same cluster as the current loan objects as potential loan objects;

[0009] Among them, operating status information includes supply chain data and capital flow data.

[0010] In a second aspect, an embodiment of the present invention further provides a loan object determination device, comprising:

[0011] An information acquisition module, used to acquire the operating status information of at least one current loan object;

[0012] The relationship network determination module is used to perform data lineage analysis on each business status information and determine the object relationship network;

[0013] A loan object determination module is used to perform cluster analysis on the object relationship network and determine objects in the same cluster as each current loan object as potential loan objects;

[0014] Among them, operating status information includes supply chain data and capital flow data.

[0015] In a third aspect, an embodiment of the present invention further provides a loan object determination device, the loan object determination device comprising:

[0016] at least one processor; and a memory communicatively coupled to the at least one processor;

[0017] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can implement the loan object determination method of any embodiment of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the loan object determination method of any embodiment of the present invention.

[0019] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which is used to execute the loan object determination method of any embodiment of the present invention when executed by a processor.

[0020] The embodiments of the present invention provide a method, device, equipment, medium and program product for determining loan objects, which obtains the business status information of at least one current loan object; performs data lineage analysis on each business status information to determine an object relationship network; performs cluster analysis on the object relationship network, and determines the objects in the same cluster as each current loan object as potential loan objects; wherein the business status information includes supply chain data and capital flow data. By adopting the above technical solution, based on the supply chain data and capital flow data corresponding to the current loan object to which the loan has been provided, the enterprises located in the upstream and downstream of the current loan object market are added to the consideration scope of potential loan objects, and an object relationship network containing the capital flow and business transactions between enterprises in the market is generated by data lineage analysis, and objects with similar financial health status and business potential as the current loan object are determined as potential loan objects, so that the screening process fully considers the rapid changes in the market and enterprise status, ensures the comprehensiveness and accuracy of loan object screening, improves the accuracy and dynamics of screening potential loan objects, and expands the potential market of loan services.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A schematic diagram of a flow chart of a method for determining a loan object provided in the first embodiment of the present invention;

[0024] Figure 2 A flowchart of a method for determining a loan object provided in Embodiment 2 of the present invention;

[0025] Figure 3 A schematic diagram of the structure of a device for determining a loan object provided in Embodiment 3 of the present invention;

[0026] Figure 4 This is a structural diagram of a loan object determination device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 The flowchart of a loan object determination method provided in the first embodiment of the present invention is applicable to the situation where other potential loan objects in the market are determined based on the current loan objects of the financial institution. The method can be executed by a loan object determination device, which can be implemented by software and / or hardware, and the loan object determination device can be configured in a loan object determination device. Optionally, the loan object determination device can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, a mobile terminal, etc., and the embodiment of the present invention does not limit this.

[0031] like Figure 1 As shown, a method for determining a loan object provided by an embodiment of the present invention specifically includes the following steps:

[0032] S101. Obtaining operating status information of at least one current loan object.

[0033] Among them, operating status information includes supply chain data and capital flow data.

[0034] In this embodiment, the current loan object can be specifically understood as an object that has been evaluated and provided with a loan by a financial institution. For example, the current loan object can be an enterprise. The operating status information can be specifically understood as information used to characterize the actual operating conditions of the current loan object in the market, which may include information such as the capital flow of the current loan object in the market, the transactions performed, and commercial dealings. Supply chain data can be specifically understood as all activity information of the current loan object in the supply chain, which may include data on raw material procurement, product production, distribution, and other links. Fund flow data can be specifically understood as data that records the current loan object's capital income and expenditure, which can be used to reflect the current loan object's financial health and cash management capabilities. Optionally, the fund flow data can be composed of the current loan object's public financial reports and transaction records within the financial institution, and may also include other types of fund flow related data, which is not limited by the embodiment of the present invention.

[0035] It is understandable that supply chain data can provide financial institutions with important clues to a company’s operational efficiency and market position, while cash flow data can serve as a basis for financial institutions to assess a company’s credit risk and loan amount.

[0036] Specifically, when a financial institution faces the problem that the corporate user group is not enough to support the expansion of loan business, it will try to mine new loan objects based on the current loan objects to which it has provided loans. At this time, the enterprises and other objects to which loans have been provided are identified as current loan objects, and the supply chain data and capital flow data generated by each current loan object in the market when conducting business interactions with upstream and downstream enterprises are obtained. The obtained supply chain data and capital flow data are used as operating status information that can reflect the operating status of the current loan object.

[0037] In an embodiment of the present invention, the basic data used to determine the loan object is expanded from the surface financial data and credit score of the object selected in the traditional loan object screening process to business status information consisting of supply chain data and capital flow data that includes deep-level business relationships and financial health status between enterprises. Based on the business status information, it is possible to have a deeper understanding of the complex business relationships and capital flow patterns between enterprises, reflect the current financial status of the enterprise and changes in the market environment, and reduce the risk of obtaining loan objects based on such mining.

[0038] S102: Perform data lineage analysis on each business status information to determine the object relationship network.

[0039] In this embodiment, data lineage analysis can be specifically understood as a process of tracking the flow of data from source to destination, analyzing the source of data, the processing process it has undergone, and the final storage location. In this embodiment of the present invention, data lineage analysis can be used to help financial institutions that have obtained business status information understand and analyze the current loan object and its corresponding financial transactions and business connections between upstream and downstream enterprises, thereby evaluating the credit risk and loan capacity of the enterprise. The object relationship network can be specifically understood as a graph structure data based on the current loan object and the objects located upstream and downstream in the current loan object market, including business connections between different objects, which can be used for graph computing.

[0040] Specifically, by performing data lineage analysis on each operating status information, the financial transactions and business connections of each current loan object in the market can be clarified, that is, the objects upstream and downstream of the current loan object in the market, as well as the business connections between the current loan object and its upstream and downstream objects can be clarified. At this time, different objects can be used as nodes in the graph structure, and the business connections between them can be used as edges between the nodes in the graph structure to generate an object relationship network that can be used for graph computing.

[0041] S103: Perform cluster analysis on the object relationship network, and determine objects in the same cluster as the current loan objects as potential loan objects.

[0042] In this embodiment, cluster analysis can be specifically understood as a statistical method for grouping data sets, aiming to group objects with similar characteristics together to form clusters. In this embodiment of the present invention, cluster analysis can be used to group objects with similar financial status and business models in an object relationship network together, so that financial institutions can identify objects that are similar to the current loan object in terms of financial status and can be provided with loans. Potential loan objects can be specifically understood as loan objects in the current market that are similar to the current loan object in terms of financial health status and business potential, and can be explored by financial institutions as potential markets and expanded to become new customers.

[0043] Specifically, based on the business connections between different nodes in the object relationship network, multiple clusters are obtained by clustering each node in the object relationship network. For the cluster in which the current loan object exists, it can be considered that other nodes in the same cluster as the current loan object have similar financial health status and business potential as the current loan object. On the basis that the financial institution can provide loans to the current loan object, objects similar to it can be considered as potential customers of the financial institution in the market who can develop loan business. At this time, the objects in the same cluster as the current loan objects are determined as potential loan objects, which expands the potential market of loan services of financial institutions.

[0044] The technical solution of this embodiment obtains the business status information of at least one current loan object; performs data lineage analysis on each business status information to determine the object relationship network; performs cluster analysis on the object relationship network, and determines the objects in the same cluster as each current loan object as potential loan objects; wherein the business status information includes supply chain data and capital flow data. By adopting the above technical solution, based on the supply chain data and capital flow data corresponding to the current loan object to which the loan has been provided, the enterprises located in the upstream and downstream of the current loan object market are added to the consideration scope of potential loan objects, and an object relationship network containing the capital flow and business transactions between enterprises in the market is generated by data lineage analysis, and objects with similar financial health status and business potential as the current loan object are determined as potential loan objects, so that the screening process fully considers the rapid changes in the market and enterprise status, ensures the comprehensiveness and accuracy of the loan object screening, improves the accuracy and dynamics of the screening of potential loan objects, and expands the potential market of loan services.

[0045] Embodiment 2

[0046] Figure 2 A flow chart of a method for determining a loan object provided in the second embodiment of the present invention. The embodiment of the present invention is further optimized on the basis of the above-mentioned optional technical solutions, by tracking the supply chain data and capital flow data to determine the upstream objects and downstream objects corresponding to each current loan object, and inputting them as raw data into the pre-trained business risk identification model to determine the transaction relationships such as the transaction pattern, risk level and capital relationship between each adjacent object, so as to realize the construction of an object relationship network with each object as a node and the transaction relationship between adjacent objects as an edge. The cluster analysis method is used to iteratively identify densely connected subgraphs of the object relationship network, and nodes of the same type are divided into the same densely connected subgraph. A densely connected subgraph is considered to be a cluster, and then the corresponding objects of other nodes in the target densely connected subgraph containing the current loan object are identified as potential loan objects with similar financial health status and business potential as the current loan object, and loan plans similar to the current loan object can be provided to the potential loan objects, so that the screening process fully considers the rapid changes in the market and enterprise status, ensures the comprehensiveness and accuracy of loan object screening, improves the precision and dynamics of screening potential loan objects, improves the convenience and accuracy of determining loan plans, and expands the potential market for loan services.

[0047] like Figure 2 As shown, a method for determining a loan object provided by an embodiment of the present invention specifically includes the following steps:

[0048] S201. Obtain operating status information of at least one current loan object.

[0049] Among them, operating status information includes supply chain data and capital flow data.

[0050] S202: Track each supply chain data and each capital flow data to determine at least one upstream object and at least one downstream object.

[0051] In this embodiment, the upstream object can be specifically understood as an object that is located in the upstream market of the current loan object in the industrial chain and can provide raw materials, parts, technology or services to the current loan object. The downstream object can be specifically understood as an object that is located in the downstream market of the current loan object in the industrial chain and can process the raw materials, parts, technology or services provided by the current loan object into final products or services.

[0052] Specifically, the supply chain data and capital flow data are tracked through blockchain and data tracking algorithms to ensure that the capital flow and business transaction data are traceable and cannot be tampered with. The objects in the market that are upstream and downstream of the current loan object are clearly identified and used as the upstream and downstream objects corresponding to the current loan object, respectively.

[0053] S203: Determine the transaction relationship between each upstream object, each downstream object and each current loan object according to each supply chain data and each capital flow data.

[0054] Specifically, based on the supply chain data and the capital flow data, the capital flow between each upstream object and the corresponding current loan object, as well as between each current loan object and the corresponding downstream object, can be determined. At the same time, the type and risk of their business transactions can be evaluated based on the capital flow situation, and the above information can be comprehensively determined as the transaction relationship between different objects.

[0055] It is understandable that there may be multiple upstream objects in the upstream market for the current loan object, and there may also be multiple downstream objects in the downstream market. There may also be transaction relationships between different upstream objects and between different downstream objects. The determination method is the same as the above method, and the embodiment of the present invention does not limit this.

[0056] Optionally, based on each supply chain data and each capital flow data, the transaction relationship between each upstream object, each downstream object and each current loan object is determined, including:

[0057] Input each supply chain data and each capital flow data into the pre-trained business risk identification model to determine the transaction pattern and risk level of each upstream object, each downstream object, and each adjacent object in the current loan object;

[0058] The transaction pattern, risk level, and capital relationship of each adjacent object determined based on the corresponding supply chain data and capital flow data are determined as the transaction relationship corresponding to the adjacent objects.

[0059] In this embodiment, the business risk identification model can be specifically understood as a machine learning model for extracting and analyzing features of the capital flow data and supply chain data related to market business information, and realizing pattern recognition and risk assessment for the capital flow data and supply chain data containing inter-enterprise capital flows and business transactions. Adjacent objects can be specifically understood as two objects that directly interact with each other in the market. The transaction pattern can be specifically understood as the transaction and cooperation pattern between different objects in the market. The risk level can be specifically understood as the transaction between different objects in the market, which may lead to transaction failure or the rating of the transaction parties' ability to bear risks for the transaction.

[0060] Specifically, each supply chain data and each capital flow data are used as input parameters of the pre-trained business risk identification model, and the business risk identification model determines the transaction mode and risk level between any two adjacent objects that have direct commercial interactions in the market among each upstream object, each downstream object, and each current loan object. After the transaction mode and risk level of each adjacent object are determined, the capital relationship that generates capital interaction between different adjacent objects can also be determined based on the supply chain data and capital flow data, and the above-mentioned transaction mode, risk level and capital relationship are jointly determined as the transaction relationship corresponding to the adjacent objects.

[0061] S204: construct an object relationship network with each upstream object, each downstream object and each current loan object as nodes and transaction relationships between adjacent objects as edges.

[0062] Specifically, since the data needs to be processed into a corresponding graph structure when the graph data processing technology is used for calculation, the graph structure contains nodes and edges. In the embodiment of the present invention, each upstream object, each downstream object and the current loan object can be used as an object for a financial institution to make a loan. When modeling the graph structure based on this, each object can be used as a node in the graph structure, and the transaction relationship between adjacent objects can be used as an edge between nodes with an associated relationship. The constructed graph structure is determined as an object relationship network.

[0063] S205 , iteratively identifying densely connected subgraphs on the object relationship network, so that the edge density within each densely connected subgraph is maximized and the edge density between each densely connected subgraph is minimized.

[0064] It is understandable that cluster analysis includes various types of algorithms. In the embodiments of the present invention, clustering of an object relationship network by using a community discovery algorithm in cluster analysis is used as an example for explanation.

[0065] In this embodiment, the densely connected subgraph can be specifically understood as a subgraph that satisfies both density and connectivity in graph theory, that is, a subgraph that satisfies both that the edges in the graph are far more than randomly distributed edges and that there is a path between any two vertices in the graph.

[0066] Specifically, a community discovery algorithm is used to identify densely connected subgraphs in an object relationship network. There are close transaction relationships or similar capital flow patterns between the internal nodes of each densely connected subgraph, that is, they have similar transaction relationships. Since the core idea of ​​the community discovery algorithm is to maximize the density of edges within the community in the network and minimize the density of edges between communities. In an embodiment of the present invention, by iterating each densely connected subgraph, the attribution of nodes in the object relationship network in different densely connected subgraphs is adjusted until the edge density within each densely connected subgraph is maximized and the edge density between each densely connected subgraph is minimized, it can be considered that the state of dense connections within the community and sparse connections between communities in the community discovery algorithm has been reached, that is, the state of clustering completion.

[0067] S206: Determine the densely connected subgraph containing the current loan object as the target densely connected subgraph, and determine the objects corresponding to the nodes in the target densely connected subgraph as potential loan objects corresponding to the current loan object.

[0068] Specifically, for the densely connected subgraph that includes the current loan object, it can be considered that the nodes in the densely connected subgraph have a close business relationship and similar financial characteristics with the current loan object; while for the densely connected subgraph that does not include the current loan object, it can be considered that the nodes in the densely connected subgraph have a low correlation with the objects for which the current financial institution can provide loan services, and the possibility of becoming potential loan customers of the financial institution is not high. At this time, the densely connected subgraph that includes the current loan object can be determined as the target densely connected subgraph, and the objects corresponding to the nodes in the target densely connected subgraph except the current loan object can be determined as potential loan objects corresponding to the current loan object.

[0069] Optionally, after determining the objects in the same cluster as the current loan objects as potential loan objects, the method further includes: providing the potential loan objects with loan plans similar to the current loan objects corresponding to the potential loan objects.

[0070] Specifically, since the potential loan recipients and their corresponding current loan recipients have close business relationships and similar financial characteristics, that is, the loan plan applicable to the current loan recipients may also be applicable to the potential loan recipients. Therefore, after the financial institutions identify the potential loan recipients, they do not need to re-formulate loan plans for them. Instead, they can adopt loan plans similar to those of the current loan recipients, thereby reducing the difficulty of determining the loan plans.

[0071] Optionally, when the operating status information of any current loan object changes, the loan object determination method further includes:

[0072] Adjust the loan plan corresponding to the current loan object according to the updated business status information, and re-determine the potential loan object corresponding to the current loan object;

[0073] The loan plan of the potential loan object corresponding to the current loan object is adjusted to the updated loan plan of the current loan object.

[0074] Specifically, since the market is changing dynamically, the capital flow and supply chain of the current loan objects in the market may change dynamically over time. In order to ensure the dynamic evaluation capability determined for the loan objects, when the operating status information of any current loan object changes, the financial institution may re-formulate a loan plan for the current loan object based on its changed operating status information. At the same time, data lineage analysis may be re-performed based on the updated operating status information to complete the update of the object relationship network, and then the potential loan object corresponding to the current loan object may be re-determined based on the updated object relationship network through cluster analysis. After completing the update for the potential loan object, the loan plan for the potential loan object may be synchronously updated to the loan plan corresponding to the updated current loan object.

[0075] The technical solution of this embodiment determines the upstream and downstream objects corresponding to each current loan object by tracking the data of each supply chain and the capital flow data, and inputs them as raw data into the pre-trained business risk identification model to determine the transaction relationship such as the transaction mode, risk level and capital relationship between each adjacent object, so as to realize the construction of an object relationship network with each object as a node and the transaction relationship between adjacent objects as an edge. The object relationship network is iteratively identified by the cluster analysis method, and the nodes belonging to the same type are divided into the same dense connected subgraph, and a dense connected subgraph is considered to be a cluster cluster, and then the corresponding objects of each other node in the target dense connected subgraph containing the current loan object are determined as potential loan objects with similar financial health status and business potential as the current loan object, and a loan plan similar to the current loan object can be provided to the potential loan object, so that the screening process fully considers the rapid changes in the market and enterprise status, ensures the comprehensiveness and accuracy of the loan object screening, improves the accuracy and dynamics of the screening of potential loan objects, improves the convenience and accuracy of the loan plan determination, and expands the potential market of loan services.

[0076] Embodiment 3

[0077] Figure 3 A schematic diagram of a loan object determination device provided in Embodiment 3 of the present invention is shown in FIG. Figure 3 As shown, the loan object determination device includes an information acquisition module 31 , a relationship network determination module 32 and a loan object determination module 33 .

[0078] Among them, the information acquisition module 31 is used to obtain the operating status information of at least one current loan object; the relationship network determination module 32 is used to perform data lineage analysis on each operating status information and determine the object relationship network; the loan object determination module 33 is used to perform cluster analysis on the object relationship network and determine the objects in the same cluster cluster as each current loan object as potential loan objects; wherein the operating status information includes supply chain data and capital flow data.

[0079] The technical solution of the embodiment of the present invention adds enterprises located upstream and downstream of the current loan object market to the consideration scope of potential loan objects based on the supply chain data and capital flow data corresponding to the current loan object to which a loan has been provided, generates an object relationship network including the capital flow and business dealings between enterprises in the market by means of data lineage analysis, and determines objects with similar financial health status and business potential to the current loan object as potential loan objects from the network, so that the screening process fully considers the rapid changes in the market and enterprise status, ensures the comprehensiveness and accuracy of the loan object screening, improves the accuracy and dynamics of the screening of potential loan objects, and expands the potential market for loan services.

[0080] Optionally, the relationship network determination module 32 includes:

[0081] An object determination unit, used to track each supply chain data and each capital flow data, and determine at least one upstream object and at least one downstream object;

[0082] A transaction relationship determination unit, used to determine the transaction relationship between each upstream object, each downstream object and each current loan object according to each supply chain data and each capital flow data;

[0083] The relationship network construction unit is used to construct an object relationship network with each upstream object, each downstream object and each current loan object as nodes and the transaction relationship between adjacent objects as edges.

[0084] Optionally, the transaction relationship determination unit is specifically used to:

[0085] Input each supply chain data and each capital flow data into the pre-trained business risk identification model to determine the transaction pattern and risk level of each upstream object, each downstream object, and each adjacent object in the current loan object;

[0086] The transaction pattern, risk level, and capital relationship of each adjacent object determined based on the corresponding supply chain data and capital flow data are determined as the transaction relationship corresponding to the adjacent objects.

[0087] Optionally, the loan object determination module 33 is specifically used for:

[0088] Iteratively identify densely connected subgraphs of the object relationship network so that the edge density within each densely connected subgraph is maximized and the edge density between each densely connected subgraph is minimized;

[0089] The densely connected subgraph containing the current loan object is determined as the target densely connected subgraph, and the objects corresponding to the nodes in the target densely connected subgraph are determined as potential loan objects corresponding to the current loan object.

[0090] Optionally, the loan object determination device further includes:

[0091] The solution determination module is used to provide the potential loan object with a loan solution similar to the current loan object corresponding to the potential loan object after determining the object in the same cluster as each current loan object as the potential loan object.

[0092] Optionally, the loan object determination device further includes:

[0093] The update module is used to adjust the loan plan corresponding to the current loan object according to the updated business status information when the business status information of any current loan object changes, and re-determine the potential loan object corresponding to the current loan object; adjust the loan plan of the potential loan object corresponding to the current loan object to the updated loan plan of the current loan object.

[0094] The loan object determination device provided in the embodiment of the present invention can execute the loan object determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0095] Embodiment 4

[0096] Figure 4 A schematic diagram of a loan object determination device provided in Embodiment 4 of the present invention. The loan object determination device 40 may be intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The loan object determination device 40 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0097] like Figure 4As shown, the loan object determination device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a programmable program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the programmable program stored in the read-only memory (ROM) 42 or the programmable program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the loan object determination device 40 can also be stored. The processor 41, the ROM 42 and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44. Optionally, the processor can be an FPGA.

[0098] Multiple components in the loan object determination device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the loan object determination device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0099] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as the loan object determination method.

[0100] In some embodiments, the loan object determination method may be implemented as a programmable program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the programmable program may be loaded and / or installed on the loan object determination device 40 via the ROM 42 and / or the communication unit 49. When the programmable program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the loan object determination method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the loan object determination method in any other appropriate manner (e.g., by means of firmware).

[0101] Optionally, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the loan object determination method provided by any embodiment of the present invention.

[0102] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more programmable programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0103] Programmable programs for implementing the method of the present invention may be written in any combination of one or more programming languages. These programmable programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the programmable program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The programmable program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0104] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a programmable program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0105] To provide interaction with a user, the systems and techniques described herein may be implemented on a loan object determination device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which a user can provide input to the loan object determination device. Other types of devices may also be used to provide interaction with a user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0106] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0107] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by programmable programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0108] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0109] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a loan object, characterized in that: include: Obtaining the operating status information of at least one current loan object; Performing data lineage analysis on each of the business status information to determine an object relationship network; Performing cluster analysis on the object relationship network, and determining objects in the same cluster as the current loan objects as potential loan objects; The operating status information includes supply chain data and capital flow data.

2. The loan object determination method according to claim 1, characterized in that: The performing of data lineage analysis on each of the business status information to determine an object relationship network includes: Performing data tracking on each of the supply chain data and each of the capital flow data to determine at least one upstream object and at least one downstream object; Determining the transaction relationship between each of the upstream objects, each of the downstream objects, and each of the current loan objects according to each of the supply chain data and each of the capital flow data; An object relationship network is constructed with each of the upstream objects, each of the downstream objects and each of the current loan objects as nodes and the transaction relationships between adjacent objects as edges.

3. The loan object determination method according to claim 2, characterized in that: Determining the transaction relationship between each of the upstream objects, each of the downstream objects, and each of the current loan objects according to each of the supply chain data and each of the capital flow data includes: Input each of the supply chain data and each of the capital flow data into a pre-trained business risk identification model to determine the transaction pattern and risk level of each of the upstream objects, each of the downstream objects, and each of the adjacent objects in the current loan objects; The transaction pattern, risk level, and capital relationship determined according to the corresponding supply chain data and capital flow data of each of the adjacent objects are determined as the transaction relationship corresponding to the adjacent objects.

4. The loan object determination method according to claim 1, characterized in that: The performing cluster analysis on the object relationship network to determine objects in the same cluster as the current loan objects as potential loan objects includes: Iteratively identifying densely connected subgraphs of the object relationship network so that the edge density within each of the densely connected subgraphs is maximized and the edge density between the densely connected subgraphs is minimized; The densely connected subgraph including the current loan object is determined as a target densely connected subgraph, and objects corresponding to nodes in the target densely connected subgraph are determined as potential loan objects corresponding to the current loan object.

5. The method for determining a loan object according to any one of claims 1 to 4, characterized in that: After determining the objects in the same cluster as the current loan objects as potential loan objects, the method further includes: The potential loan recipient is provided with a loan plan that is similar to the current loan recipient corresponding to the potential loan recipient.

6. The loan object determination method according to claim 5, characterized in that: Also includes: When the business status information of any of the current loan objects changes, the loan plan corresponding to the current loan object is adjusted according to the updated business status information, and the potential loan object corresponding to the current loan object is re-determined; The loan plan of the potential loan object corresponding to the current loan object is adjusted to the updated loan plan of the current loan object.

7. A device for determining a loan object, characterized in that: include: An information acquisition module, used to acquire the operating status information of at least one current loan object; A relationship network determination module, used to perform data lineage analysis on each of the business status information to determine an object relationship network; A loan object determination module, used for performing cluster analysis on the object relationship network, and determining objects in the same cluster as each of the current loan objects as potential loan objects; The operating status information includes supply chain data and capital flow data.

8. A loan object determination device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a programmable program executable by the at least one processor, and the programmable program is executed by the at least one processor so that the at least one processor can execute the loan object determination method according to any one of claims 1 to 6.

9. A storage medium containing computer executable instructions, characterized in that: The executable instructions are used to execute the loan object determination method according to any one of claims 1 to 6 when executed by a programmable processor.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for determining a loan object according to any one of claims 1 to 6 is implemented.

Images