A method, apparatus, device and medium for determining an object gray list

Abstract

A method, device, equipment and medium for determining an object gray list are disclosed. The method comprises: determining real-time news data associated with at least one white list object; the real-time news data is data authorized for use by the white list object; determining a first risk object from the white list objects based on each real-time news data; the first risk object is an object with potential financial risk; determining at least one second risk object having a risk association with the first risk object; determining a risk probability value of the second risk object, and determining the first risk object and the second risk object with a risk probability value greater than a preset probability threshold as the object gray list. By executing the present scheme, the object with potential financial risk can be predicted, and a reference basis for building a good risk management system for financial institutions is provided.

Description

Technical Field

[0001] This invention relates to the field of financial technology, and in particular to a method, apparatus, device, and medium for determining a gray list of objects. Background Technology

[0002] In the digital risk control system of the financial system, it is a very important step to predict the risks of various customers with potential financial risks and to determine the user blacklist.

[0003] Existing technologies typically utilize internal historical default user data to generate a blacklist of corporate clients who have previously defaulted. Alternatively, expert rules are used to set filtering conditions, listing corporate clients that meet the criteria as potential defaulters for risk propagation analysis. These methods result in inconsistent real-time performance and incompleteness in blacklist determination. Furthermore, unreasonable condition or parameter settings can lead to significant errors, resulting in unsatisfactory risk propagation calculations. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and medium for determining a gray list of objects, which can predict objects with potential financial risks and provide a reference for financial institutions to build a sound risk management system.

[0005] According to one aspect of the present invention, a method for determining an object gray list is provided, the method comprising:

[0006] Identify real-time news data associated with at least one whitelisted object; the real-time news data is data authorized for use by the whitelisted object.

[0007] Based on the real-time news data mentioned above, a first risk object is determined from each of the whitelist objects; the first risk object is an object with potential financial risks.

[0008] Identify at least one second risk object that has a risk association with the first risk object;

[0009] Determine the risk probability value of the second risk object, and define the first risk object and the second risk object whose risk probability value is greater than a preset probability threshold as objects in a gray list.

[0010] According to another aspect of the present invention, an apparatus for determining an object graylist is provided, the apparatus comprising:

[0011] A real-time news data determination module is used to determine real-time news data associated with at least one whitelisted object; the real-time news data is data authorized for use by the whitelisted object.

[0012] The first risk object determination module is used to determine a first risk object from each of the whitelist objects based on the real-time news data; the first risk object is an object with potential financial risk.

[0013] The second risk object determination module is used to determine at least one second risk object that has a risk association with the first risk object;

[0014] The object graylist determination module is used to determine the risk probability value of the second risk object, and to determine the first risk object and the second risk object whose risk probability value is greater than a preset probability threshold as objects in the graylist.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the object graylist determination method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the object graylist determination method according to any embodiment of the present invention.

[0020] The technical solution of this invention involves identifying real-time news data associated with at least one whitelisted object; the real-time news data being data authorized for use by the whitelisted object; determining a first risk object from each whitelisted object based on the real-time news data; the first risk object being an object with potential financial risk; identifying at least one second risk object with a risk association with the first risk object; determining the risk probability value of the second risk object; and defining the first risk object and the second risk object with a risk probability value greater than a preset probability threshold as an object graylist. By implementing the solution provided by this invention, it is possible to predict objects with potential financial risks, providing a reference for financial institutions to build a sound risk management system.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a method for determining an object gray list provided by an embodiment of the present invention;

[0024] Figure 2 This is a flowchart of another method for determining an object gray list provided by an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of an object graylist determination device provided in an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the object graylist determination method of the embodiments of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort 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, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of application, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0030] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application program, server, or storage medium executing the operation of this invention, based on the prompt message.

[0031] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0032] It is understood that the above notification and user authorization process is merely illustrative and does not constitute a limitation on the implementation of the present invention. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present invention.

[0033] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0034] Figure 1 This is a flowchart of a method for determining a gray list of objects provided in an embodiment of the present invention. This embodiment is applicable to situations where users with potential financial risks need to be identified. This method can be executed by a device for determining the gray list of objects, which can be implemented in hardware and / or software. This device can be configured in an electronic device used for determining the gray list of objects. Figure 1 As shown, the method includes:

[0035] S110: Determine real-time news data associated with at least one whitelisted object.

[0036] The real-time news data is data authorized for use by whitelisted entities.

[0037] For example, the whitelisted entities can be at least one of the corporate or group clients already registered with the bank. Real-time news data can be real-time financial news reports obtained by searching for whitelisted entities using them as search keywords. Real-time news data is data authorized for use by whitelisted entities for risk analysis.

[0038] S120: Determine the first risk object from each of the whitelisted objects based on the real-time news data.

[0039] The first risk object is an object that has potential financial risks.

[0040] The first risk object can be an entity with potential financial risk, such as an entity that has only opened an account with this bank without defaulting, but has operational risks and may have already defaulted at another bank or may default in the future; this is a whitelisted entity. This solution can process real-time news data, for example, by using event discovery methods to obtain an event set. Then, based on a pre-built financial dictionary, the attributes of the financial terms contained in each event in the event set are determined, and the event attributes are further determined, such as whether it is a negative event, a positive event, or a neutral event. The entities contained in the negative events are then identified as the first risk objects.

[0041] S130: Identify at least one second risk object that has a risk association with the first risk object.

[0042] The second risk object can be an object that has a risk association with the first risk object. For example, the second risk object can be an object that has a business relationship with the first risk object through a risk propagation chain, such as a related enterprise or a related individual.

[0043] S140: Determine the risk probability value of the second risk object, and define the first risk object and the second risk object whose risk probability value is greater than a preset probability threshold as an object gray list.

[0044] For example, the preset probability threshold can be set according to actual needs. This solution can determine the relationship between whitelisted objects within the same industry based on industry data, and establish a knowledge graph of the whitelisted objects within the same industry based on this relationship. Then, a risk propagation link is constructed based on the first risk object in the knowledge graph and the relationship in the graph, and the propagation damping coefficient of each node in the risk propagation link and the weight coefficient of each edge in the risk propagation link are determined. The risk probability value of the second risk object is determined according to the propagation damping coefficient of each node in the risk propagation link and the weight coefficient of each edge in the risk propagation link. The second risk object with a risk probability value greater than the preset probability threshold is added to the object gray list, and the first risk object determined in the above steps is added to the object gray list. Here, the relationship can be, for example, that the legal representative of enterprise A is B, or that enterprise A has invested in enterprise C.

[0045] The technical solution of this invention involves identifying real-time news data associated with at least one whitelisted object; the real-time news data being data authorized for use by the whitelisted object; determining a first risk object from each whitelisted object based on the real-time news data; the first risk object being an object with potential financial risk; identifying at least one second risk object with a risk association with the first risk object; determining the risk probability value of the second risk object; and adding the first risk object and the second risk object with a risk probability value greater than a preset probability threshold to an object graylist. By implementing the solution provided by this invention, it is possible to predict customers with potential financial risks, providing a reference for financial institutions to build a sound risk management system.

[0046] Figure 2 This is a flowchart of a method for determining an object graylist provided in an embodiment of the present invention. This embodiment is an optimization based on the above embodiment. Figure 2 As shown, the method for determining the gray list of objects in this embodiment of the invention may include:

[0047] S210: Determine real-time news data associated with at least one whitelisted object.

[0048] S220: Cluster the real-time news data to obtain at least one clustering information.

[0049] For example, this solution can utilize text clustering to process real-time news data to determine event clusters and obtain at least one clustering information. Specifically, this solution can first perform word segmentation on the real-time news data, converting the words in the real-time news data into vectors, where the matrix elements represent the vector elements of word j in the i-th news article. Then, text clustering is performed: specifying a range for the number of clusters, the cluster distance for all cases within that range is calculated. The smaller the distance, the better the clustering result, meaning the points within a cluster are closer together, and the points between clusters are farther apart. The cluster number k with the smallest distance is taken as the final cluster number result, and the K-means algorithm is used to calculate the clustering result of the current text into k event clusters. The category to which the news text belongs, i.e., the event category number, is obtained. For example, this solution can perform clustering processing on 10 real-time news articles to obtain two clusters, i.e., two events.

[0050] S230: Determine the sentiment attributes of the clustering information.

[0051] The emotional attribute includes one of positive, negative, or neutral.

[0052] In this embodiment, optionally, determining the sentiment attribute of the clustering information includes: determining the financial terms included in the clustering information and the sentiment attribute of each financial term; if the proportion of positive financial terms in each financial term is greater than the proportion of negative financial terms in each financial term, then the sentiment attribute of the clustering information is determined to be positive; if the proportion of negative financial terms in each financial term is greater than the proportion of positive financial terms in each financial term, then the sentiment attribute of the clustering information is determined to be negative.

[0053] For example, this solution can pre-construct a financial sentiment lexicon, which includes financial terms and their sentiment attributes. For instance, the sentiment attribute of the financial term "positive" is positivity. For each cluster of information, this solution can identify all the financial terms included in that cluster and then compare them with the financial sentiment lexicon to determine the sentiment attribute of each financial term in the cluster. Then, it determines the proportion of negative financial terms and the proportion of positive financial terms in the cluster. If the former is greater than the latter, the sentiment attribute of the cluster is negative. If the former is less than the latter, the sentiment attribute of the cluster is positive.

[0054] Therefore, by identifying the financial terms included in the cluster information and the sentiment attributes of each financial term; if the proportion of positive financial terms is greater than that of negative financial terms, the sentiment attribute of the cluster information is determined to be positive; if the proportion of negative financial terms is greater than that of positive financial terms, the sentiment attribute of the cluster information is determined to be negative. This provides a reliable data foundation for accurately identifying the primary risk-related objects.

[0055] S240: If the emotional attribute is determined to be negative, then the whitelisted objects contained in the clustering information are determined to be the first risk objects.

[0056] In this scheme, if the sentiment attribute of the cluster information is determined to be negative, it means that the whitelist objects in the cluster information have potential financial risks and are regarded as the first risk objects.

[0057] S250: Identify at least one second risk object that has a risk association with the first risk object.

[0058] In this embodiment, optionally, determining at least one second risk object that is risk-associated with the first risk object includes: determining a knowledge graph between the whitelisted objects based on the feature data of each whitelisted object; the knowledge graph includes the association relationships between the whitelisted objects; the association relationships include one of corporate legal persons, actual controllers, investors, and holding companies; the feature data is data stored in a database that the whitelisted objects are authorized to access; the first risk object in the knowledge graph is used as a risk node; the objects corresponding to the nodes of the risk nodes in the knowledge graph with a preset number of hops are used as candidate risk objects; an inducement subgraph of the knowledge graph is constructed based on each candidate risk object; and the objects corresponding to each node in each inducement subgraph are used as second risk objects.

[0059] For example, a knowledge graph can describe real-world "entities" and the "relationships" between them in the form of a relationship graph. Feature data can be business data of whitelisted objects stored in a bank's database. For a graph G = (V, E), a subgraph G′ = (V′, E′), And E′={(u,v)|u,v∈V′,(u,v)∈E}, then G′ is an induced subgraph of G. For V′, if there is an edge in G, then there should also be an edge in G′. That is, the set of points V′ to be included in the subgraph G′ is selected in advance, and V′ should be included in the set of points V of graph G. At the same time, all edges connecting the set of points V in graph G are regarded as the edge set E′. The set of points V′ and the edge set E′ constitute the induced subgraph G. This scheme can determine the knowledge graph based on the feature data of each whitelist object of the bank and the relationship between the whitelist objects. The nodes on the knowledge graph correspond to the whitelist objects in the bank. The directed edges between two nodes can represent the relationship between the whitelist objects, such as one of corporate legal person, actual controller, investor and holding company. The preset number of hops can be set according to actual needs. Assuming that the first risk object in the knowledge graph is D, it is taken as the risk node. The objects corresponding to the first hop number node F and the second hop number node P of node D in the knowledge graph are taken as candidate risk objects. Then, based on nodes D, F, and P, a induced subgraph of the knowledge graph is constructed, and the objects corresponding to each node in the induced subgraph are designated as second-risk objects. This allows for the identification of second-risk objects through the knowledge graph, providing a reliable data source for determining the object graylist.

[0060] S260: Determine the risk probability value of the second risk object, and define the first risk object and the second risk object whose risk probability value is greater than a preset probability threshold as an object gray list.

[0061] In one feasible implementation, optionally, determining the risk probability value of the second risk object includes: determining a risk propagation link with the risk node as the starting node and the second risk object as the ending node; determining the propagation damping coefficient of the object corresponding to each node on the risk propagation link and the weight coefficient of each edge on the risk propagation link; determining the risk probability value of the second risk object based on each weight coefficient and each propagation damping coefficient; the weight coefficient of each edge is determined according to the association relationship between the objects corresponding to the two nodes of the current edge.

[0062] For example, this solution can determine a risk propagation link starting from risk node D and ending at the second risk object P, and determine the propagation damping coefficient for each node in the risk propagation link and the weight coefficient for each edge in the risk propagation link. Specifically, if the nodes in the risk propagation link correspond to individual customers, this solution can divide individual customers into four levels based on their average daily deposits, and set different propagation damping coefficients for each level, with the damping coefficient ranging from 0 to 1. The higher the deposits, the larger the propagation damping coefficient, and the stronger the risk resistance. If the nodes in the risk propagation link correspond to corporate customers, this solution can divide corporate customers into four levels based on their registered capital, and set different propagation damping coefficients for each level, with the propagation damping coefficient ranging from 0 to 1. The higher the registered capital, the larger the propagation damping coefficient, and the stronger the risk resistance.

[0063] Furthermore, risks propagate along the edges of the risk propagation chain; the larger the weight coefficient, the higher the probability of propagation. The weight coefficient of each edge is determined based on the relationship between the objects corresponding to the two nodes of the current edge. The relationship weight coefficients for "actual controller," "legal person," "investor," and "holding company" can be set according to actual needs. The value range of the weight coefficient is 0 to 1.

[0064] After determining the propagation damping coefficients of each node in the risk propagation chain and the weight coefficients of each edge in the chain, this scheme can determine the risk probability value of the second risk object based on these coefficients. Starting with the first risk object, the scheme calculates the risk probability of the second risk object based on the maximum propagation probability within the risk propagation chain. For example, for each node m in the risk propagation chain (i.e., the second risk object), the scheme substitutes the weight coefficients of each edge in the risk propagation chain from the first to the second risk object into Dijkstra's algorithm to calculate all possible probabilities of reaching that node k, and takes the largest probability value as the probability P of node m. m During the calculation, if the propagation damping coefficient of node m is less than P...m If so, the probability value of node k is updated, allowing the risk to propagate to subsequent nodes of node m. If the propagation damping coefficient of node m is greater than or equal to P... m Then the transmission of risk will be interrupted.

[0065] Therefore, by assigning values ​​to the propagation damping coefficient of each node in each risk propagation chain and the weight coefficient of each edge, the risk probability value of the second risk object can be determined. This allows for a description of the actual risk control scenario in the financial system and provides scientific and objective data support for determining the gray list of objects.

[0066] In another feasible implementation, optionally, determining the propagation damping coefficient of each node corresponding to the object in the risk propagation chain and the weight coefficient of each edge in the risk propagation chain includes: if the account type of the object corresponding to the node in the risk propagation chain is determined to be a first object type, then the propagation damping coefficient of the object corresponding to the node is determined according to the first business information of the object; if the account type of the object corresponding to the node in the risk propagation chain is determined to be a second object type, then the propagation damping coefficient of the node is determined according to the second business information of the object.

[0067] The first business information can be set according to actual needs, such as deposit information. The second business information can be set according to actual needs, such as registered capital information. The first object type can be set according to actual needs, such as personal account type. The second object type can be set according to actual needs, such as corporate account type or group account type. If this solution determines that the account type of the object corresponding to the node in the risk propagation chain is the first object type, then this solution can divide the objects associated with the first object type account into four levels according to the average daily deposit, and set different propagation damping coefficients for each level of object. The propagation damping coefficient ranges from 0 to 1. The more deposits, the larger the propagation damping coefficient, and the stronger the risk resistance. The less deposits, the smaller the propagation damping coefficient, and the weaker the risk resistance. If this solution determines that the account type of the object corresponding to the node in the risk propagation chain is the second object type, then this solution can divide the objects associated with the second object type account into four levels according to registered capital, and set different propagation damping coefficients for each level of object. The propagation damping coefficient ranges from 0 to 1. The more registered capital, the larger the propagation damping coefficient, and the stronger the risk resistance. The less registered capital, the smaller the propagation damping coefficient, and the weaker the ability to resist risks.

[0068] Therefore, if the account type of the object corresponding to a node in the risk propagation chain is determined to be the first object type, the propagation damping coefficient of the corresponding object is determined based on the object's first business information; if the account type of the object corresponding to a node in the risk propagation chain is determined to be the second object type, the propagation damping coefficient of the node is determined based on the object's second business information. This allows for the description of actual financial system risk control scenarios and provides a scientific and objective data basis for determining object gray lists.

[0069] In this scheme, when determining the risk propagation path, each node on the path exists in two states: "accessible" and "blocked." If the arrival probability (risk probability value) from the starting node to the current node is greater than the damping coefficient of that node, the current node is in the "accessible" state; otherwise, the current node is in the "blocked" state. Iterative calculations are performed to obtain the risk probability value of the second risk object corresponding to each terminal node. Second risk objects with risk probability values ​​greater than a preset probability threshold are considered risk objects and added to the object gray list. Furthermore, the first risk object determined in the aforementioned steps is added to the object gray list.

[0070] The technical solution provided by this invention involves identifying real-time news data associated with at least one whitelisted object; the real-time news data being data authorized for use by the whitelisted object; clustering each piece of real-time news data to obtain at least one clustering information; determining the sentiment attribute of the clustering information; the sentiment attribute including positive, negative, or neutral; if the sentiment attribute is determined to be negative, then the whitelisted object included in the clustering information is determined as a first risk object. At least one second risk object with a risk association with the first risk object is identified; the risk probability value of the second risk object is determined, and the first risk object and the second risk object with a risk probability value greater than a preset probability threshold are designated as an object graylist. By implementing the solution provided by this invention, it is possible to predict customers with potential financial risks, providing a reference for financial institutions to build a sound risk management system.

[0071] Figure 3 This is a schematic diagram of the device for determining an object graylist provided in an embodiment of the present invention. Figure 3 As shown, the device includes:

[0072] The real-time news data determination module 310 is used to determine real-time news data associated with at least one whitelisted object; the real-time news data is data authorized for use by the whitelisted object.

[0073] The first risk object determination module 320 is used to determine a first risk object from each of the whitelist objects based on the real-time news data; the first risk object is an object with potential financial risk.

[0074] The second risk object determination module 330 is used to determine at least one second risk object that has a risk association with the first risk object;

[0075] The object graylist determination module 340 is used to determine the risk probability value of the second risk object, and to determine the first risk object and the second risk object whose risk probability value is greater than a preset probability threshold as objects in the graylist.

[0076] Optionally, the first risk object determination module 320 includes a clustering information determination unit, used to cluster the real-time news data to obtain at least one clustering information; a sentiment attribute determination unit, used to determine the sentiment attribute of the clustering information; the sentiment attribute includes one of positive, negative or neutral; and a first risk object determination unit, used to determine the whitelisted objects contained in the clustering information as first risk objects if the sentiment attribute is determined to be negative.

[0077] Optionally, the sentiment attribute determination unit is specifically used to determine the financial terms included in the clustering information and the sentiment attribute of each financial term; if the proportion of positive financial terms in each financial term is greater than the proportion of negative financial terms in each financial term, then the sentiment attribute of the clustering information is determined to be positive; if the proportion of negative financial terms in each financial term is greater than the proportion of positive financial terms in each financial term, then the sentiment attribute of the clustering information is determined to be negative.

[0078] Optionally, the second risk object determination module 330 includes a knowledge graph determination unit, used to determine a knowledge graph between the whitelisted objects based on the feature data of each whitelisted object; the knowledge graph includes the association relationship between the whitelisted objects; the association relationship includes one of corporate legal person, actual controller, investor, and holding company; the feature data is data stored in the database that the whitelisted objects are authorized to access; a risk node determination unit, used to take the first risk object in the knowledge graph as a risk node; a candidate risk object determination unit, used to take the object corresponding to the node of the risk node in the knowledge graph with a preset number of hops as a candidate risk object; a induced subgraph determination unit, used to construct an induced subgraph of the knowledge graph based on each candidate risk object; and a second risk object determination unit, used to take the object corresponding to each node in each induced subgraph as a second risk object.

[0079] Optionally, the object graylist determination module 340 includes a risk propagation link determination unit, used to determine a risk propagation link with the risk node as the starting node and the second risk object as the ending node; a coefficient determination unit, used to determine the propagation damping coefficient of each node corresponding to the object on the risk propagation link and the weight coefficient of each edge on the risk propagation link; and a risk probability value determination unit, used to determine the risk probability value of the second risk object based on each of the weight coefficients and each of the propagation blocking coefficients; the weight coefficient of each edge is determined according to the association relationship between the objects corresponding to the two nodes of the current edge.

[0080] Optionally, the coefficient determining unit is specifically used to determine the propagation damping coefficient of the object corresponding to the node based on the first business information of the object if the account type of the object corresponding to the node on the risk propagation chain is determined to be a first object type; and to determine the propagation damping coefficient of the node based on the second business information of the object if the account type of the object corresponding to the node on the risk propagation chain is determined to be a second object type.

[0081] The object graylist determination device provided in the embodiments of the present invention can execute the object graylist determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0082] Figure 4 A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is 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 electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0083] like Figure 4As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded into the RAM 43 from storage unit 48. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0084] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0085] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as the method for determining an object graylist.

[0086] In some embodiments, the method for determining the object graylist may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the object graylist determination method described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the object graylist determination method by any other suitable means (e.g., by means of firmware).

[0087] 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-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0088] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0089] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0090] To provide interaction with an object, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the object; and a keyboard and pointing device (e.g., a mouse or trackball) through which the object provides input to the electronic device. Other types of devices can also be used to provide interaction with the object; for example, feedback provided to the object can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the object can be received in any form (including sound input, voice input, or tactile input).

[0091] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., object computers with a graphical object interface or web browser through which objects can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0092] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0093] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0094] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining an object gray list, characterized in that, include: Identify real-time news data associated with at least one whitelisted object; The real-time news data is data authorized for use by whitelisted entities; The first risk target is determined from each of the whitelisted objects based on the real-time news data described above; The first risk object is an object that has potential financial risks; Identify at least one second risk object that has a risk association with the first risk object; Determine the risk probability value of the second risk object, and define the first risk object and the second risk object whose risk probability value is greater than a preset probability threshold as an object gray list; Wherein, determining at least one second risk object that has a risk association with the first risk object includes: A knowledge graph is determined based on the feature data of each whitelisted object; the knowledge graph includes the relationships between whitelisted objects; the relationships include one of corporate entities, actual controllers, investors, and holding companies; the feature data is data stored in the database that the whitelisted objects are authorized to access; The first risk object in the knowledge graph is taken as the risk node; The objects corresponding to the nodes of the risk nodes in the knowledge graph with a preset number of hops are selected as candidate risk objects. Construct an induced subgraph of the knowledge graph based on each of the candidate risk objects; The objects corresponding to each node in each of the aforementioned induced subgraphs are taken as the second risk objects; The determination of the risk probability value of the second risk object includes: Determine the risk propagation link with the risk node as the starting node and the second risk object as the ending node; The propagation damping coefficients of each node in the risk propagation chain and the weight coefficients of each edge in the risk propagation chain are determined. Specifically, if the node in the risk propagation chain corresponds to a personal account, the propagation damping coefficient is determined based on the account's deposit information, and the propagation damping coefficient increases with increasing deposits. If the node in the risk propagation chain corresponds to a corporate account or group account, the propagation damping coefficient is determined based on the account's registered capital, and the propagation damping coefficient increases with increasing registered capital. The risk probability value of the second risk object is determined based on the weight coefficients and the propagation damping coefficients; the weight coefficient of each edge is determined according to the association relationship between the objects corresponding to the two nodes of the current edge.

2. The method according to claim 1, characterized in that, Based on the aforementioned real-time news data, a first risk target is determined from each of the aforementioned whitelisted objects, including: Clustering of each of the aforementioned real-time news data yields at least one clustering information; Determine the sentiment attribute of the clustering information; the sentiment attribute includes one of positive, negative, or neutral. If the emotional attribute is determined to be negative, then the whitelisted objects contained in the clustering information are determined to be the first risk objects.

3. The method according to claim 2, characterized in that, Determining the sentiment attributes of the clustering information includes: Determine the financial terms contained in the clustering information and the sentiment attributes of each financial term; If the proportion of positive financial terms in each of the financial terms is greater than the proportion of negative financial terms in each of the financial terms, then the sentiment attribute of the clustering information is determined to be positive. If the proportion of negative financial terms in each set of financial terms is greater than the proportion of positive financial terms, then the sentiment attribute of the clustering information is determined to be negative.

4. A device for determining an object gray list, characterized in that, include: The real-time news data determination module is used to determine real-time news data associated with at least one whitelisted object; The real-time news data is data authorized for use by whitelisted entities; The first risk object determination module is used to determine the first risk object from each of the whitelist objects based on the real-time news data. The first risk object is an object that has potential financial risks; The second risk object determination module is used to determine at least one second risk object that has a risk association with the first risk object; The object graylist determination module is used to determine the risk probability value of the second risk object, and to determine the first risk object and the second risk object whose risk probability value is greater than a preset probability threshold as objects graylist; The second risk object determination module includes: The knowledge graph determination unit is used to determine the knowledge graph between the whitelisted objects based on the feature data of each whitelisted object; the knowledge graph includes the association relationships between the whitelisted objects; the association relationships include one of corporate legal persons, actual controllers, investors, and holding companies; the feature data is data stored in the database that the whitelisted objects are authorized to access; A risk node determination unit is used to identify the first risk object in the knowledge graph as a risk node. The candidate risk object determination unit is used to select the objects corresponding to the nodes of the risk nodes in the knowledge graph with a preset number of hops as candidate risk objects. The induced subgraph determination unit is used to construct induced subgraphs of the knowledge graph based on each of the candidate risk objects; The second risk object determination unit is used to take the objects corresponding to each node in each of the induced subgraphs as the second risk objects; The object graylist determination module includes: The risk propagation link determination unit is used to determine the risk propagation link that starts with the risk node and ends with the second risk object. The coefficient determination unit is used to determine the propagation damping coefficient of each node corresponding to the object in the risk propagation chain and the weight coefficient of each edge in the risk propagation chain; wherein, if the object corresponding to the node in the risk propagation chain is a personal account, the propagation damping coefficient of the object corresponding to the node is determined according to the deposit information of the object, and the propagation damping coefficient increases with the increase of deposits; if the object corresponding to the node in the risk propagation chain is a corporate account or a group account, the propagation damping coefficient of the object corresponding to the node is determined according to the registered capital of the object, and the propagation damping coefficient increases with the increase of registered capital; The risk probability value determination unit is used to determine the risk probability value of the second risk object based on each of the weight coefficients and each of the propagation damping coefficients; the weight coefficient of each edge is determined according to the association relationship between the objects corresponding to the two nodes of the current edge.

5. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining the object gray list according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining the gray list of objects according to any one of claims 1-3.

Images