CN111708897A - Target information determination method, device and equipment - Google Patents
Target information determination method, device and equipment Download PDFInfo
- Publication number
- CN111708897A CN111708897A CN202010527825.4A CN202010527825A CN111708897A CN 111708897 A CN111708897 A CN 111708897A CN 202010527825 A CN202010527825 A CN 202010527825A CN 111708897 A CN111708897 A CN 111708897A
- Authority
- CN
- China
- Prior art keywords
- target
- user
- information
- resource transfer
- party
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Abstract
The application provides a target information determination method, a target information determination device and target information determination equipment, wherein the method comprises the following steps: collecting a user data set, a third-party user data set and an information set, wherein the information set comprises at least one piece of resource transfer information, and the resource transfer information represents the resource transfer condition of a user and/or a third-party user; extracting a plurality of groups of target data from the user data set, the third party user data set and the information set, wherein each group of target data comprises: entities, attributes, and relationships between entities; constructing a first knowledge graph according to the multiple groups of target data; determining target information in resource transfer information of a target user in the users according to the first knowledge graph; wherein the target information represents resource transfer characteristics between the target user and the third party user. In the embodiment of the application, the first knowledge graph containing the information set can be used for efficiently and accurately screening data, and the efficiency of bank audit is accelerated.
Description
Technical Field
The present application relates to the field of big data processing technologies, and in particular, to a method, an apparatus, and a device for determining target information.
Background
At present, some illegal persons may use the process loopholes in the bank to cooperate with the bank users, so that the risk behaviors such as cheating and loan, money laundering and the like occur, and certain loss risk is brought to the bank.
In the prior art, the approval system of the bank only provides functional support in the process, for example: data entry and data storage, etc. Experience of the relevant business personnel is required to review and screen the user profile to screen out potentially risky data. The business personnel can hardly recognize the cooperative behavior between the user and the illegal personnel only through the data provided by the user, the screening work needs to be carried out with higher cost and time, and the requirements on the working experience and professional quality of the business personnel are higher. Therefore, the technical scheme in the prior art cannot efficiently and accurately mine and screen the data of the user.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the application provides a method, a device and equipment for determining target information, and aims to solve the problem that the data of a user cannot be efficiently and accurately mined and screened in the prior art.
The embodiment of the application provides a target information determining method, which comprises the following steps: collecting a user data set, a third-party user data set and an information set, wherein the information set comprises at least one piece of resource transfer information, and the resource transfer information represents the resource transfer condition of the user and/or the third-party user; extracting a plurality of groups of target data from the user data set, the third party user data set and the information set, wherein each group of target data comprises: entities, attributes, and relationships between entities; constructing a first knowledge graph according to the multiple groups of target data; wherein the first knowledge graph represents a relationship between the user and the third party user; determining target information in resource transfer information of a target user in the users according to the first knowledge graph; wherein the target information represents resource transfer characteristics between the target user and the third party user.
In one embodiment, determining target information in the resource transfer information of a target one of the users based on the first knowledge-graph comprises: acquiring social attribute relations among all entities in the first knowledge graph; converting a graph structure corresponding to the first knowledge graph into a hypergraph structure according to social attribute relations among all entities in the first knowledge graph to obtain a second knowledge graph; and determining target information in the resource transfer information of the target user according to the second knowledge graph.
In one embodiment, determining the target information in the resource transfer information of the target user according to the second knowledge-graph comprises: determining whether a resource transfer relationship exists between the target user and a target third-party user in the third-party users according to the second knowledge graph; under the condition that the resource transfer relationship is determined to exist, acquiring target resource transfer data between the target user and the target third-party user from the second knowledge graph; determining whether the proportion of the resources transferred to the target account by the target user and originated from the target third-party user is within a preset range according to the target resource transfer data; and under the condition that the proportion of the resources transferred to the target account by the target user and originated from the target third-party user is determined to be within a preset range, determining target information in the resource transfer information of the target user.
In one embodiment, after determining the target information in the resource transfer information of the target user among the users, the method further includes: acquiring the relevant information of the target user and the relevant information of the target third-party user from the second knowledge graph; extracting a target relationship sub-graph comprising the target user and the target third-party user from the second knowledge graph; generating target user information according to the relevant information of the target user, the relevant information of the target third-party user and the target relation subgraph; acquiring a processing object corresponding to the target user; and sending the target user information to the processing object.
In one embodiment, extracting sets of target data from the user data set, third party user data set, and information set comprises: extracting user entities, user attributes and social relationships among users from the user data set; extracting the third party user entity, the attributes of the third party user and the social relationship among the third party users from the third party user data set; extracting resource transfer relationship and resource transfer attribute between each entity from the information set; and matching the extracted user entities, the attributes of the users, the social relationship among the users, the third-party user entities, the attributes of the third-party users, the social relationship among the third-party users, the resource transfer relationship among the entities and the resource transfer attributes to obtain a plurality of groups of target data.
In one embodiment, the third party user includes: financial institutions, employees of financial institutions, intermediary employees, and intermediary companies.
An embodiment of the present application further provides a target information determining apparatus, including: the data acquisition module is used for acquiring a user data set, a third-party user data set and an information set, wherein the information set comprises at least one piece of resource transfer information, and the resource transfer information represents the resource transfer condition of the user and/or the third-party user; a data extraction module, configured to extract multiple sets of target data from the user data set, the third-party user data set, and the information set, where each set of target data includes: entities, attributes, and relationships between entities; the construction module is used for constructing and obtaining a first knowledge graph according to the multiple groups of target data; wherein the first knowledge graph represents a relationship between the user and the third party user; a determining module, configured to determine, according to the first knowledge graph, target information in resource transfer information of a target user among the users; wherein the target information represents resource transfer characteristics between the target user and the third party user.
In one embodiment, the determining module comprises: the acquisition unit is used for acquiring social attribute relations and relationships among all entities in the first knowledge graph; the conversion unit is used for converting the graph structure corresponding to the first knowledge graph into a hypergraph structure according to social attribute relations and among all entities in the first knowledge graph to obtain a second knowledge graph; and the determining unit is used for determining target information in the resource transfer information of the target user according to the second knowledge graph.
The embodiment of the application also provides target information determination equipment, which comprises a processor and a memory for storing processor executable instructions, wherein the processor executes the instructions to realize the steps of the target information determination method.
Embodiments of the present application also provide a computer-readable storage medium, on which computer instructions are stored, and when executed, the instructions implement the steps of the target information determination method.
The embodiment of the application provides a target information determining method, wherein a user data set, a third-party user data set and an information set are collected, the information set comprises at least one piece of resource transfer information, and the resource transfer information represents the resource transfer condition of a user and/or a third-party user, so that a first knowledge graph constructed by the resource transfer information comprises information of the third-party user, and target information can be comprehensively mined. Further, a plurality of groups of target data can be extracted from the user data set, the third-party user data set and the information set, and a first knowledge graph is constructed by using entities in the plurality of groups of target data as nodes, wherein each group of target data comprises: entities, attributes, and relationships between entities. Because the first knowledge graph contains all resource transfer information among users, between the users and third-party users and between the third-party users, the target information in the resource transfer information of the target user in the users can be determined according to the first knowledge graph, wherein the first knowledge graph can be used for efficiently and accurately mining data, and the efficiency of bank audit is accelerated.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, are incorporated in and constitute a part of this application, and are not intended to limit the application. In the drawings:
FIG. 1 is a schematic diagram of a target information determination system provided in accordance with an embodiment of the present application;
FIG. 2 is a schematic diagram illustrating steps of a target information determination method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a first knowledge-graph provided in accordance with an embodiment of the present application;
FIG. 4 is a schematic diagram of a second knowledge-graph provided in accordance with an embodiment of the present application;
FIG. 5 is a schematic structural diagram of a target information determination apparatus provided in an embodiment of the present application;
fig. 6 is a schematic structural diagram of a target information determination device according to an embodiment of the present application.
Detailed Description
The principles and spirit of the present application will be described with reference to a number of exemplary embodiments. It should be understood that these embodiments are given solely for the purpose of enabling those skilled in the art to better understand and to practice the present application, and are not intended to limit the scope of the present application in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As will be appreciated by one skilled in the art, embodiments of the present application may be embodied as a system, apparatus, device, method or computer program product. Accordingly, the present disclosure may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.
Although the flow described below includes operations that occur in a particular order, it should be appreciated that the processes may include more or less operations that are performed sequentially or in parallel (e.g., using parallel processors or a multi-threaded environment).
The Knowledge Graph (knowledgegraph) may refer to a semantic network that exposes relationships between entities, where nodes represent entities (entitys) or concepts (concepts) and edges represent various semantic relationships between entities/concepts.
In an example scenario of the present application, there is provided a target information determination system, as shown in fig. 1, which may include: the user can initiate a resource transfer request in a bank system through the terminal device 101, and the bank server 102 can determine target information in the resource transfer information of the user based on the resource transfer request operation submitted by the user and perform risk prompt under the condition that risk data exist in the resource transfer information of the user. Further, the determination result of the target information in the resource transfer information of the user may also be fed back to the terminal device 101.
The terminal device 101 may be a terminal device or software used by a user. Specifically, the terminal device may be a terminal device such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart watch, or other wearable devices, or may be a robot device. Of course, the terminal apparatus 101 may be software that can be run in the above terminal apparatus. For example: application software such as bank system application, payment application, browser, wechat applet and the like.
The bank server 102 may be a single server or a server cluster, and certainly, the functions of the servers may also be implemented by a cloud computing technology. The bank server 102 may be connected to a plurality of terminal devices, or may be a server having a strong bank information set library, and may perform data screening based on a resource transfer application initiated by a user and an information set in the bank information set library.
Referring to fig. 2, the present embodiment may provide a method for determining target information. The target information determining method can be used for auditing resource transfer requests submitted by users on line and screening out target information. The above target information determination method may include the following steps.
S201: the method comprises the steps of collecting a user data set, a third-party user data set and an information set, wherein the information set comprises at least one piece of resource transfer information, and the resource transfer information represents the resource transfer condition of a user and/or a third-party user.
In this embodiment, the user data set may be a set of data related to a user, and may include: the resource information data, the relationship information data and the basic information data of the user, the resource may include: virtual currency, account funds, gold, real estate and other fixed assets, and the like. The resource transfer information may be used to represent resource transfer situations between users, between a user and a third-party user, or between third-party users, and in one embodiment, the resource transfer may include: transfer accounts, borrow, repay, purchase financing products, etc. The user may be a user currently applying for resource transfer or a user having historically performed resource transfer, and specifically, the user may be a user having a loan history or a user who has submitted a loan application to be checked.
In one embodiment, the user data set may include: identity card number, reserved telephone number, work unit, bank account information, loan account number, initial payment amount, loan application date, bank account opening date, examination and approval date of loan application, house information, social relationship attributes among users and the like.
In this embodiment, the third-party user may be a third party that may have resource association or may potentially risk a resource source of the user in a resource transferring process of the user, and the third-party user may be a company, an organization, or an individual user, which is not limited in this application. The third-party user data set may be a set of data related to a third-party user, and may include: company and business data, people credit data, public accumulation fund data, agency wage data, public client information data, private client information data and the like.
The information set may be resource transfer information between users, between users and third-party users, and between third-party users. In one embodiment, the information set may include: the information of the fund flow transaction of the private account, the information of the fund flow transaction of the public account and the like. Of course, in some embodiments, the user data set, the third-party user data set, and the information set may further include other data, which may be determined according to practical situations, and this is not limited in this application.
In this embodiment, the manner of collecting the user data set, the third-party user data set, and the information set may include: the method is obtained by pulling from a preset database or mining from text description by using a rule extraction method in combination with a corpus. The preset database may be a database for storing historical data and data submitted and generated by a user in real time in a bank or other financial institutions.
S202: extracting a plurality of groups of target data from the user data set, the third party user data set and the information set, wherein each group of target data comprises: entities, attributes, and relationships between entities.
In this embodiment, a plurality of sets of target data may be extracted from the user data set, the third-party user data set, and the information set, where each set of target data may include: the multiple groups of target data can be used for constructing a mesh relation network formed by entity-relation-entity triples and converting independent data into a structured knowledge correlation database.
In this embodiment, since data can be simply understood as a symbol, the representation form of the symbol mainly includes characters, diagrams, voice, and the like, information is the content carried or expressed by the data, and knowledge is the integration and abstraction of the information. Therefore, the extraction of the information can be the basis and precursor of knowledge graph construction, and the extraction of the information can comprise: entity extraction, relationship extraction and attribute extraction.
The entity extraction may be referred to as "NER" (named entity recognition) in the art, and refers to automatically recognizing a named entity from an original corpus. And (3) extracting the relation: the entity relationship can be identified by manually constructing semantic rules and templates, or by using a relationship model between entities. The attribute extraction is mainly for the entity, and since the attribute of the entity can be regarded as a name relationship between the entity and the attribute value, the extraction problem of the attribute of the entity can be converted into a relationship extraction problem in some embodiments.
In this embodiment, the entity is a basic unit of the knowledge graph, and is also an important language unit for carrying information in the text, for example: name of person, place name, organization name. The attributes may be used to characterize the entity, and a complete delineation of the entity may be formed through the attributes, and the attributes may include: identity card number, account number, house loan mark, loan account number, initial payment amount, loan amount, application date, account opening date, examination and approval date, house information, resource transfer amount, resource transfer time and the like. The relationship between the entities may be used to solve the problem of semantic links between the entities, and specifically, the relationship may include: work relationships, resource transfer relationships, social relationships, and the like.
The target data may be similar (entity 1, relationship, entity 2) triple data, or similar (entity, attribute value) triple data, for example: (Yaoming, play-in, NBA), or (Yaoming, height, 2.29m), it will be understood that the sets of target data extracted may be in other possible forms, and the specific application is not limited thereto.
In this embodiment, the user data set, the third-party user data set, and the information set may be unstructured data, semi-structured data, or structured data, and thus may be processed for different types of data. In one embodiment, the collected user data set, the third-party user data set and the information set can be preprocessed in a data cleaning and data normalization mode, wherein the preprocessing comprises the steps of identity card verification, identity card cleaning and the like, dirty data are cleaned, and data quality is improved.
Furthermore, word segmentation extraction processing can be performed on the preprocessed unstructured data and semi-structured data (such as text), and then target data can be extracted based on the result of the word segmentation extraction processing. And for the structured data such as the basic information of the user, the related fields can be directly extracted without further processing.
S203: constructing a first knowledge graph according to a plurality of groups of target data; wherein the first knowledge graph represents a relationship between the user and a third party user.
In this embodiment, the first knowledge graph may be constructed according to a plurality of sets of target data, where entities in the plurality of sets of target data are nodes, every two entities in the first knowledge graph are connected through a relationship to obtain an edge, and each node and edge have corresponding attributes, that is, attributes of the entities and attributes of the relationship. The attributes of the entities may include, but are not limited to, at least one of: identity card number, account number, house loan mark, loan account number, initial payment amount, loan amount, application date, account opening date, examination and approval date, house information and the like, and the attributes of the relationship can comprise at least one of the following: resource transfer amount, resource transfer time, social relationship attributes (e.g., spouse, superior/inferior, friends, etc.).
In this embodiment, the first knowledge-graph may be used to represent a relationship between a user and a third-party user, and in a specific embodiment, the first knowledge-graph may be as shown in fig. 3, and may include an entity: company a, employee B, employee C, user a, and user B, it being understood that the above-described fig. 3 is only one example of the present application and is not intended to limit the present application.
In order to effectively store the first knowledge graph for convenient retrieval and calling, the database needs to be selected according to the actual situation of the graph. The types of databases are mainly: relational databases, graph databases, NoSQL databases, etc. Wherein, if the map structure and the relationship are complex and the connection is more, a map database such as Neo4J can be adopted; if the graph focuses on node knowledge, the relationship is simple, and the connection is few, the relational database or ES can meet the requirements; a NoSQL database may be used if map performance, scalability, and distribution are considered. In some embodiments, the above databases may be used in a fusion manner, which may be determined according to actual situations, and this application does not limit this.
S204: determining target information in resource transfer information of a target user in the users according to the first knowledge graph; wherein the target information represents resource transfer characteristics between the target user and the third party user.
In this embodiment, since the first knowledge graph includes all resource transfer information between users, between a user and a third-party user, and between third-party users, target information in resource transfer information of a target user among the users can be determined based on the first knowledge graph.
In this embodiment, the target user may be a user who needs to be checked, and the resource transfer information of the target user may be resource transfer information associated with a resource that needs to be checked. In one embodiment, in the case that the resource to be audited is a loan, the resource transfer information associated with the resource to be audited may include: a source of funds for payment by the target user, a source of funds for payment by the target user for initial payment, etc.
In this embodiment, the target information may be resource transfer characteristics obtained by filtering from the first knowledge graph and used for representing the resource transfer between the target user and the third-party user, and the target information may be data that does not conform to the conventional resource transfer behavior of the target user in the resource transfer information of the target user. The resource transfer characteristics may include time, attributes, and properties of resource transfer between the target user and the third-party user. In one embodiment, the resources of the general users are all from users who issue salaries or have social attribute relations, and then the information that the resources of the target users in the resource transfer information are partially or completely from the third-party users belongs to the target information. For example: the resource transfer feature described above may be such that a third party user transfers 50 ten-thousand dollars to a target user one month before the target user applies for a house credit.
In one embodiment, the prompt message may be sent to the processing object of the target user when the target information in the resource transfer information of the target user is determined to be obtained. In the present embodiment, when it is determined that target information exists in the resource migration information of the target user, it is described that the target user may have a risk, and at this time, it is necessary to perform timely processing on the target user. Because each user has a corresponding processing object, the target user information can be generated according to the relevant information of the target user, the relevant information of the related third-party user and the target relation subgraph containing the target user and the target third-party user in the first knowledge graph, and the generated target user information is sent to the processing object corresponding to the target user.
In this embodiment, the processing target may be a customer manager or other staff responsible for auditing, and the specific application is not limited thereto.
From the above description, it can be seen that the embodiments of the present application achieve the following technical effects: by collecting the user data set, the third-party user data set and the information set, the information set comprises at least one piece of resource transfer information, and the resource transfer information represents the resource transfer condition of the user and/or the third-party user, so that the first knowledge graph constructed by the first knowledge graph contains the information of the third-party user, and the target information can be comprehensively mined. Further, a plurality of groups of target data can be extracted from the user data set, the third-party user data set and the information set, and a first knowledge graph is constructed by using entities in the plurality of groups of target data as nodes, wherein each group of target data comprises: entities, attributes, and relationships between entities. Because the first knowledge graph contains all resource transfer information among users, between the users and third-party users and between the third-party users, the target information in the resource transfer information of the target user in the users can be determined according to the first knowledge graph, wherein the first knowledge graph can be used for efficiently and accurately mining data, and the efficiency of bank audit is accelerated.
In one embodiment, since the third party user may cooperate with the target user, the risk of cheating, money laundering, cash-out, hoarding, and hoarding may occur, the third party user may provide the user with all or part of the resources that need to be transferred to the target account. The third-party user packages the identities of the users who do not reach the loan qualification so that the third-party user can apply for the real estate loan which is not in line with the consumption capacity of the third-party user, or the third-party user applies for a plurality of real estate loans to store by using the identities of a plurality of users who have the loan qualification. Since the user does not have the corresponding initial payment capability or is not actually paying and repayment by the user, the third party user is required to provide some or all of the resources required to be transferred to the target account to the user before and after the loan. Therefore, the information set can effectively reflect the resource transfer condition of the user before and after the loan and between the third-party users, and can effectively track the source of the initial payment or repayment fund. Therefore, the third party user may include: financial institutions, employees of financial institutions, intermediary employees, and intermediary companies.
In this embodiment, the target account may be an account of an opposite party involved in resource transfer, and in some embodiments, the target account may be an account of a bank, for example, an account for which resource transfer is required for monthly repayment after loan of the user, and may also be another account, which may be determined according to practical situations, and the application is not limited to this.
In the case where the third-party users are broker employees and broker companies, the entities, attributes and relationships that may occur in the constructed knowledge-graph may include: 1) the attributes of the user, who has business activity in the bank, include an identification number, a bank account number, a house credit mark, and the like. The house loan mark indicates whether the user has house loan, and if the user has house loan, the attributes of the user also comprise a loan account number, an initial payment amount, a loan amount, an application date, an account opening date, an examination and approval date, house information and the like. 2) The attributes of the intermediary staff comprise identity card numbers, bank account numbers and the like. 3) The intermediary company, the attribute contains the bank account number, etc. 4) Intermediary employee-intermediary company: the relationship type has a work relationship indicating that the intermediary employee works with the company. 5) Intermediary employee-user: the relationship type has a resource transfer relationship, which indicates that the resource of the employee of the intermediary is transferred to the user, and the resource transfer relationship attribute comprises resource transfer amount, resource transfer time and the like. 6) Intermediary company-user: the relationship type has a resource transfer relationship, which indicates that the intermediary company resources are transferred to the user, and the attribute includes a resource transfer amount, a resource transfer time, and the like. 7) User-user: the relationship type comprises a resource transfer relationship and a social relationship, wherein the resource transfer relationship attribute comprises a resource transfer amount, a resource transfer time and the like, the social relationship attribute comprises a label for displaying the social relationship type between the users, and the attribute values comprise 'spouse', 'friend' and the like.
In this embodiment, since there is no direct intermediary inventory data in the preset database, it is necessary to centrally mine from the third-party user data. In one embodiment, an intermediary corpus may be first established, then intermediary companies are mined from the text description by using a rule extraction method in combination with the corpus through fields such as enterprise operation scope in a business data table, so as to obtain an intermediary company list, and account information of intermediary employees and the intermediary employees is mined by combining data such as accumulation fund data, generation wage data and human behavior credit data in a row. The enterprise operation range field may be a text description, for example: the business scope of a company is "enterprise management, computer system services, computer animation design, economic information consulting services …", and it is possible to find out which companies are intermediary companies by these text descriptions, so as to obtain the list of intermediary companies.
In one embodiment, since there may be a case where a third-party user splits funds and transfers the funds to accounts of a plurality of users related to the user, the funds are collected to the user's account finally as a resource to be transferred to a target account. Therefore, other users related to the user can be mined by taking the user as a core. Other users related to the user have certain social attribute relationship with the user, and have resource transfer activities in the row. In one embodiment, an intra-row user relationship table may be used to mine other users related to a user while mining social relationships between the two. In the user relationship table, the relationship between users is stored. In the case where the relationship between users is described in text, the relationship keywords need to be extracted, for example: the text description of the "user A and user B are spouse relations" needs to extract the keywords of the "spouse".
Further, in an embodiment, a relational corpus may be established first, and the corpus includes all relational terms, for example: the terms "couple", "husband", "wife", "classmate", "mother and" spouse "and the like. Then, a regular matching technology can be used to extract the relationship keywords in each relationship text, and after extraction, relationship fusion is performed to merge the same word meaning relationship into the same relationship, for example: both "spouse" and "couple" can be normalized to a "spouse" relationship to eliminate redundant relationship connections.
In one embodiment, in order to avoid a group partaking plan of a third-party user, funds are divided into multiple people, then the multiple people transfer to accounts of multiple users related to the user, and finally the accounts of the users are collected to be used as resources transferred to a target account, so that social attribute relations among all entities in a first knowledge graph can be obtained, and a graph structure corresponding to the first knowledge graph is converted into a hypergraph structure according to the social attribute relations among all the entities in the first knowledge graph to obtain a second knowledge graph, wherein the second knowledge graph can be shown in fig. 4. Further, target information in the resource transfer information of the target user may be determined according to the second knowledge graph.
In this embodiment, one edge of the graph structure can only connect two nodes, and one edge of the hypergraph structure can connect a plurality of nodes. The second knowledge graph may be as shown in fig. 4, where the points within the dotted line are merged into one point at the time of risk pre-warning calculation, and the employees are merged into a point company a 'because they are in the same company, and the users a and B are merged into a user a' because of social connection. After the graph structure corresponding to the first knowledge graph is converted into the hypergraph structure, when the resource transfer condition between the user A and the third-party user is counted, the resource transfer condition can be converted into the resource transfer between the statistical company A 'and the user A', and therefore a fraud scene that the third-party user transfers the resource split to the user account can be accurately and effectively excavated.
In this embodiment, determining target information in the resource transfer information of the target user according to the second knowledge graph may include: and determining whether a resource transfer relationship exists between the target user and a target third-party user in the third-party users according to the second knowledge graph. The target third-party user may be a third-party user who may have a resource transfer relationship with the target user in the second knowledge graph. In the event that a resource transfer relationship is determined to exist, target resource transfer data between the target user and the target third-party user may be obtained from the second knowledge graph.
Further, whether the proportion of the resources transferred to the target account by the target user and originated from the target third-party user is within a preset range or not can be determined according to the target resource transfer data. And under the condition that the proportion of the resources transferred to the target account by the target user and originated from the target third-party user is determined to be within a preset range, determining target information in the resource transfer information of the target user. In some cases, if the amount of money from the target third-party user in the resource transferred to the target account by the target user is small, it may be determined that there is no risk in the target information, and at this time, it is necessary to determine the proportion of the resource transferred to the target account by the target user from the target third-party user. In one embodiment, whether a risk exists in the target information of the target user may be determined according to the following formula:
wherein, transTRepresenting the total amount of resource transfer to the target user by the target third party user within the time range T, baseAmt representing the comparative base amount, such as the initial payment or payment amount (monthly supply, etc.), β and α being threshold parameters, β to α being the above-mentioned predetermined range, β and α being any value greater than 0Numerical values, for example: 0.5, 0.83, 1.0, etc., which can be specifically set according to actual requirements, and the present application is not limited by contrast.
When the calculation result is 1, the risk data exists in the target information of the target user, and if the calculation result is 0, the risk is not existed. In one embodiment, whether the risk early warning calculation scenario is risk of an initial payment source or risk of a repayment fund source can be controlled by the parameter T, for example: when the data of N months before the target user submits the loan application is selected, calculating the risk of the initial payment source; and selecting data of N months after the target user opens an account, calculating the risk of repayment fund source, and generally taking the time range of three months or six months before the target user submits loan application or after the target user opens the account. The formula can show that when the target user receives the resource transfer amount of the target third-party user in the T time range, the resource transfer amount is in the range from beta to alpha times of the fluctuation of the baseAmt amount, and the risk data exists in the target information of the target user.
In one embodiment, the prompting may be performed when it is determined that target information in the resource transfer information of the target user is obtained, and may include: and acquiring the related information of the target user and the related information of the target third-party user from the second knowledge graph, and extracting a target relation subgraph containing the target user and the target third-party user from the second knowledge graph. Further, target user information can be generated according to the relevant information of the target user, the relevant information of the target third-party user and the target relation subgraph. In order to accurately feed back the excavated target user information in real time, a processing object corresponding to the target user may be acquired, and the target user information may be sent to the processing object.
In this embodiment, the target relationship subgraph including the target user and the target third-party user may be a subgraph including two entities of the target user and the target third-party user, attributes of the two entities, and a relationship between the two entities, so that the processing object can intuitively and clearly know the risk related to the target user and the whole process of resource transfer.
In one embodiment, extracting sets of target data from the user data set, the third party user data set, and the information set may include: extracting user entities, user attributes and social relationships among users from the user data set; extracting the entity of the third-party user, the attribute of the third-party user and the social relationship among the third-party users from the third-party user data set; and extracting the resource transfer relationship and the resource transfer attribute among the entities from the information set. Furthermore, the extracted user entities, the attributes of the users, the social relationship among the users, the third-party user entities, the attributes of the third-party users, the social relationship among the third-party users, the resource transfer relationship among the entities and the resource transfer attributes can be matched to obtain a plurality of groups of target data.
In this embodiment, data matching may be performed using a unique ID technique, so that different source data may be associated by a unique ID key, which may be an identification number. The unique ID technology is used for data matching, so that the user and the in-line debit card which is not involved in resource transfer can be associated, all resource transfer information of the user is obtained, related data of a third-party user can be integrated, comprehensiveness of the data is guaranteed, and a data mining result is more accurate.
Based on the same inventive concept, the embodiment of the present application further provides a target information determining apparatus, such as the following embodiments. Because the principle of solving the problem of the target information determining apparatus is similar to that of the target information determining method, the implementation of the target information determining apparatus can refer to the implementation of the target information determining method, and repeated details are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated. Fig. 5 is a block diagram of a structure of a target information determining apparatus according to an embodiment of the present application, and as shown in fig. 5, the target information determining apparatus may include: the data acquisition module 501, the data extraction module 502, the construction module 503, the determination module 504, and the risk prompt module 505 are described below.
The data collection module 501 may be configured to collect a user data set, a third-party user data set, and an information set, where the information set includes at least one piece of resource transfer information, and the resource transfer information indicates a resource transfer condition of a user and/or a third-party user.
The data extraction module 502 may be configured to extract multiple sets of target data from a user data set, a third-party user data set, and an information set, where each set of target data includes: entities, attributes, and relationships between entities.
The constructing module 503 may be configured to construct a first knowledge graph according to multiple sets of target data; wherein the first knowledge graph represents a relationship between the user and a third party user.
A determining module 504, configured to determine target information in the resource transfer information of a target user among the users according to the first knowledge graph; wherein the target information represents resource transfer characteristics between the target user and the third party user.
In one embodiment, the determining module 504 may include: the acquiring unit is used for acquiring social attribute relations and relationships among all entities in the first knowledge graph; the conversion unit is used for converting the graph structure corresponding to the first knowledge graph into a hypergraph structure according to the social attribute relationship and the relationship among the entities in the first knowledge graph to obtain a second knowledge graph; and the determining unit is used for determining target information in the resource transfer information of the target user according to the second knowledge graph.
The embodiment of the present application further provides an electronic device, which may specifically refer to a schematic structural diagram of the electronic device based on the target information determining method provided in the embodiment of the present application shown in fig. 6, and the electronic device may specifically include an input device 61, a processor 62, and a memory 63. The input device 61 may specifically be used for inputting user data sets, third party user data sets and information sets, among others. The processor 62 may be specifically configured to collect a user data set, a third-party user data set, and an information set, where the information set includes at least one piece of resource transfer information, and the resource transfer information indicates a resource transfer condition of a user and/or a third-party user; extracting a plurality of groups of target data from the user data set, the third party user data set and the information set, wherein each group of target data comprises: entities, attributes, and relationships between entities; constructing a first knowledge graph according to a plurality of groups of target data; wherein the first knowledge graph represents a relationship between the user and a third party user; determining target information in resource transfer information of a target user in the users according to the first knowledge graph; wherein the target information represents resource transfer characteristics between the target user and the third party user. The memory 63 may specifically be used for storing parameters such as the first knowledge-graph, the risk data, etc.
In this embodiment, the input device may be one of the main apparatuses for information exchange between a user and a computer system. The input devices may include a keyboard, mouse, camera, scanner, light pen, handwriting input panel, voice input device, etc.; the input device is used to input raw data and a program for processing the data into the computer. The input device can also acquire and receive data transmitted by other modules, units and devices. The processor may be implemented in any suitable way. For example, a processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth. The memory may in particular be a memory device used in modern information technology for storing information. The memory may include multiple levels, and in a digital system, memory may be used as long as binary data can be stored; in an integrated circuit, a circuit without a physical form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.
In this embodiment, the functions and effects specifically realized by the electronic device can be explained by comparing with other embodiments, and are not described herein again.
The embodiment of the present application further provides a computer storage medium based on the target information determination method, where the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the computer storage medium may implement: collecting a user data set, a third-party user data set and an information set, wherein the information set comprises at least one piece of resource transfer information, and the resource transfer information represents the resource transfer condition of a user and/or a third-party user; extracting a plurality of groups of target data from the user data set, the third party user data set and the information set, wherein each group of target data comprises: entities, attributes, and relationships between entities; constructing a first knowledge graph according to a plurality of groups of target data; wherein the first knowledge graph represents a relationship between the user and a third party user; determining target information in resource transfer information of a target user in the users according to the first knowledge graph; wherein the target information represents resource transfer characteristics between the target user and the third party user.
In the present embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard disk (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.
In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer storage medium can be explained by comparing with other embodiments, and are not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the embodiments of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different from that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.
Although the present application provides method steps as described in the above embodiments or flowcharts, additional or fewer steps may be included in the method, based on conventional or non-inventive efforts. In the case of steps where no necessary causal relationship exists logically, the order of execution of the steps is not limited to that provided by the embodiments of the present application. When the method is executed in an actual device or end product, the method can be executed sequentially or in parallel according to the embodiment or the method shown in the figure (for example, in the environment of a parallel processor or a multi-thread processing).
It is to be understood that the above description is intended to be illustrative, and not restrictive. Many embodiments and many applications other than the examples provided will be apparent to those of skill in the art upon reading the above description. The scope of the application should, therefore, be determined not with reference to the above description, but instead should be determined with reference to the pending claims along with the full scope of equivalents to which such claims are entitled.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and it will be apparent to those skilled in the art that various modifications and variations can be made in the embodiment of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method for determining target information, comprising:
collecting a user data set, a third-party user data set and an information set, wherein the information set comprises at least one piece of resource transfer information, and the resource transfer information represents the resource transfer condition of the user and/or the third-party user;
extracting a plurality of groups of target data from the user data set, the third party user data set and the information set, wherein each group of target data comprises: entities, attributes, and relationships between entities;
constructing a first knowledge graph according to the multiple groups of target data; wherein the first knowledge graph represents a relationship between the user and the third party user;
determining target information in resource transfer information of a target user in the users according to the first knowledge graph; wherein the target information represents resource transfer characteristics between the target user and the third party user.
2. The method of claim 1, wherein determining target information in the resource transfer information for a target one of the users based on the first knowledge-graph comprises:
acquiring social attribute relations among all entities in the first knowledge graph;
converting a graph structure corresponding to the first knowledge graph into a hypergraph structure according to social attribute relations among all entities in the first knowledge graph to obtain a second knowledge graph;
and determining target information in the resource transfer information of the target user according to the second knowledge graph.
3. The method of claim 2, wherein determining the target information in the resource transfer information of the target user according to the second knowledge-graph comprises:
determining whether a resource transfer relationship exists between the target user and a target third-party user in the third-party users according to the second knowledge graph;
under the condition that the resource transfer relationship is determined to exist, acquiring target resource transfer data between the target user and the target third-party user from the second knowledge graph;
determining whether the proportion of the resources transferred to the target account by the target user and originated from the target third-party user is within a preset range according to the target resource transfer data;
and under the condition that the proportion of the resources transferred to the target account by the target user and originated from the target third-party user is determined to be within a preset range, determining target information in the resource transfer information of the target user.
4. The method of claim 3, after determining the target information in the resource transfer information of the target one of the users, further comprising:
acquiring the relevant information of the target user and the relevant information of the target third-party user from the second knowledge graph;
extracting a target relationship sub-graph comprising the target user and the target third-party user from the second knowledge graph;
generating target user information according to the relevant information of the target user, the relevant information of the target third-party user and the target relation subgraph;
acquiring a processing object corresponding to the target user;
and sending the target user information to the processing object.
5. The method of claim 1, wherein extracting sets of target data from the user data set, third party user data set, and information set comprises:
extracting user entities, user attributes and social relationships among users from the user data set;
extracting the third party user entity, the attributes of the third party user and the social relationship among the third party users from the third party user data set;
extracting resource transfer relationship and resource transfer attribute between each entity from the information set;
and matching the extracted user entities, the attributes of the users, the social relationship among the users, the third-party user entities, the attributes of the third-party users, the social relationship among the third-party users, the resource transfer relationship among the entities and the resource transfer attributes to obtain a plurality of groups of target data.
6. The method of claim 1, wherein the third party user comprises: financial institutions, employees of financial institutions, intermediary employees, and intermediary companies.
7. An object information determination apparatus characterized by comprising:
the data acquisition module is used for acquiring a user data set, a third-party user data set and an information set, wherein the information set comprises at least one piece of resource transfer information, and the resource transfer information represents the resource transfer condition of the user and/or the third-party user;
a data extraction module, configured to extract multiple sets of target data from the user data set, the third-party user data set, and the information set, where each set of target data includes: entities, attributes, and relationships between entities;
the construction module is used for constructing and obtaining a first knowledge graph according to the multiple groups of target data; wherein the first knowledge graph represents a relationship between the user and the third party user;
a determining module, configured to determine, according to the first knowledge graph, target information in resource transfer information of a target user among the users; wherein the target information represents resource transfer characteristics between the target user and the third party user.
8. The apparatus of claim 7, wherein the determining module comprises:
the acquisition unit is used for acquiring social attribute relations and relationships among all entities in the first knowledge graph;
the conversion unit is used for converting the graph structure corresponding to the first knowledge graph into a hypergraph structure according to social attribute relations and among all entities in the first knowledge graph to obtain a second knowledge graph;
and the determining unit is used for determining target information in the resource transfer information of the target user according to the second knowledge graph.
9. A target information determination device comprising a processor and a memory for storing processor-executable instructions which, when executed by the processor, implement the steps of the method of any one of claims 1 to 6.
10. A computer-readable storage medium having stored thereon computer instructions which, when executed, implement the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010527825.4A CN111708897A (en) | 2020-06-11 | 2020-06-11 | Target information determination method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010527825.4A CN111708897A (en) | 2020-06-11 | 2020-06-11 | Target information determination method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111708897A true CN111708897A (en) | 2020-09-25 |
Family
ID=72539504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010527825.4A Pending CN111708897A (en) | 2020-06-11 | 2020-06-11 | Target information determination method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111708897A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112084348A (en) * | 2020-09-27 | 2020-12-15 | 中国建设银行股份有限公司 | Method and device for determining relevance |
| CN112286979A (en) * | 2020-10-30 | 2021-01-29 | 北京明略软件系统有限公司 | Data screening method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2852111A1 (en) * | 2013-06-21 | 2014-12-21 | Fmr Llc | Methods and systems for expedited trading account funding |
| CN106101192A (en) * | 2016-05-31 | 2016-11-09 | 上海银天下科技有限公司 | Information interacting method and device |
| CN109191281A (en) * | 2018-08-21 | 2019-01-11 | 重庆富民银行股份有限公司 | A kind of group's fraud identifying system of knowledge based map |
| CN109918511A (en) * | 2019-01-29 | 2019-06-21 | 华融融通（北京）科技有限公司 | A kind of knowledge mapping based on BFS and LPA is counter to cheat feature extracting method |
| CN110175825A (en) * | 2019-05-25 | 2019-08-27 | 上海连尚网络科技有限公司 | It is a kind of for providing the method and apparatus of target information |
| CN110458592A (en) * | 2019-06-18 | 2019-11-15 | 北京海致星图科技有限公司 | Knowledge based map and machine learning algorithm excavate the potential credit client method of bank |
-
2020
- 2020-06-11 CN CN202010527825.4A patent/CN111708897A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2852111A1 (en) * | 2013-06-21 | 2014-12-21 | Fmr Llc | Methods and systems for expedited trading account funding |
| CN106101192A (en) * | 2016-05-31 | 2016-11-09 | 上海银天下科技有限公司 | Information interacting method and device |
| CN109191281A (en) * | 2018-08-21 | 2019-01-11 | 重庆富民银行股份有限公司 | A kind of group's fraud identifying system of knowledge based map |
| CN109918511A (en) * | 2019-01-29 | 2019-06-21 | 华融融通（北京）科技有限公司 | A kind of knowledge mapping based on BFS and LPA is counter to cheat feature extracting method |
| CN110175825A (en) * | 2019-05-25 | 2019-08-27 | 上海连尚网络科技有限公司 | It is a kind of for providing the method and apparatus of target information |
| CN110458592A (en) * | 2019-06-18 | 2019-11-15 | 北京海致星图科技有限公司 | Knowledge based map and machine learning algorithm excavate the potential credit client method of bank |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112084348A (en) * | 2020-09-27 | 2020-12-15 | 中国建设银行股份有限公司 | Method and device for determining relevance |
| CN112286979A (en) * | 2020-10-30 | 2021-01-29 | 北京明略软件系统有限公司 | Data screening method and device, electronic equipment and storage medium |
| CN112286979B (en) * | 2020-10-30 | 2024-01-30 | 北京明略软件系统有限公司 | Data screening method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Debreceny et al. | Data mining journal entries for fraud detection: An exploratory study | |
| US10069891B2 (en) | Channel accessible single function micro service data collection process for light analytics | |
| Vaganova et al. | Directions of development of bank technologies applied in the Russian market of retail credit services | |
| CN110852878B (en) | Credibility determination method, device, equipment and storage medium | |
| CN112308710B (en) | Loan data processing method, loan data processing device, computer equipment and storage medium | |
| US10755344B2 (en) | System framework processor for channel contacts | |
| JP2019057160A (en) | Account managing apparatus, account managing method, and account managing program | |
| CN113989019A (en) | Method, device, equipment and storage medium for identifying risks | |
| US20090327036A1 (en) | Decision support systems using multi-scale customer and transaction clustering and visualization | |
| CN110942392A (en) | Service data processing method, device, equipment and medium | |
| CN107679977A (en) | A kind of tax administration platform and implementation method based on semantic analysis | |
| US20220398573A1 (en) | Machine learning classifier based on category modeling | |
| CN111062799A (en) | Method and device for managing family client, electronic equipment and storage medium | |
| CN111708897A (en) | Target information determination method, device and equipment | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| US20170091050A1 (en) | System for aggregation and transformation of real-time data | |
| US11620665B2 (en) | Methods and systems using and constructing merchant communities based on financial transaction data | |
| CN117033431A (en) | Work order processing method, device, electronic equipment and medium | |
| CN117094764A (en) | Bank integral processing method and device | |
| US20170091859A1 (en) | System for real-time data structuring and storage | |
| US9529860B2 (en) | Keyword frequency analysis system | |
| AlWreikat et al. | Business intelligence and data analytics system for mobile money | |
| CN111639910A (en) | Standing book generation method, device, equipment and storage medium | |
| CN113792044A (en) | Data fusion platform and neural network model hosting training method | |
| KR102080769B1 (en) | System and method for mining financial information based on private finanacial code |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220906 Address after: 25 Financial Street, Xicheng District, Beijing 100033 Applicant after: CHINA CONSTRUCTION BANK Corp. Address before: 25 Financial Street, Xicheng District, Beijing 100033 Applicant before: CHINA CONSTRUCTION BANK Corp. Applicant before: Jianxin Financial Science and Technology Co.,Ltd. |