Risk information identification method and identification device, electronic equipment and storage medium

By calculating the data distance between the target unit information of the target applicant and the associated unit information, it can identify its risk, and solve the problems of low manual review efficiency and difficult to identify information forgery in the existing technology, and achieve rapid and accurate risk information identification .

CN118916762APending Publication Date: 2024-11-08北京中关村科金技术有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411049986.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

In the prior art, the work unit information in the resource application request can only be manually reviewed, and the identification efficiency is low and the information cannot be quickly and effectively identified, resulting in incomplete identification of risk information.

Method used

By obtaining the target unit information of the target applicant, determining its associated application entity, and obtaining multiple associated unit information of the associated application entity, and calculating the data distance between unit attribute data with the same attribute category to identify whether the target unit information is Risk information realizes a comprehensive risk assessment from the industry perspective and address perspective.

Benefits of technology

The rapid and accurate risk information identification of the target unit information of the target applicant is achieved, the efficiency and accuracy of risk information identification is improved, and the subjectivity and error of manual review are reduced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118916762A_ABST
    Figure CN118916762A_ABST
Patent Text Reader

Abstract

The invention provides a risk information identification method and device, electronic equipment and a storage medium, and belongs to the technical field of computers. The method comprises the steps of obtaining target unit information of a target application subject, and determining an associated application subject corresponding to the target unit information; acquiring multiple pieces of association unit information of the association application subject; unit attribute data corresponding to each piece of associated unit information is determined, and the unit attribute data comprises industry class attribute data of which the attribute class is an industry class and / or address class attribute data of which the attribute class is an address class; and calculating data distances among a plurality of unit attribute data with the same attribute category, and identifying whether the target unit information is risk information or not according to the data distances. According to the embodiment of the invention, comprehensive risk assessment can be carried out on the target unit information in an industry perspective and / or an address perspective, and rapid and accurate risk information identification can be carried out on the target unit information of the target application subject.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a risk information identification method, an identification device, an electronic device, and a computer-readable storage medium. Background Art

[0002] Risk information refers to information that presents potential risks. In actual application scenarios, by inspecting and analyzing the information contained in resource application requests, such as loan applications, and identifying the risk information contained therein, it is possible to timely grasp the potential risks in resource application requests and make corresponding decisions.

[0003] However, in the existing technical solutions, the work unit information in the resource application request can only be manually reviewed to determine whether it is risk information. Not only is the recognition efficiency low, but it is also difficult to review and discover information forgery, making it impossible to achieve fast and effective risk information identification. Summary of the invention

[0004] The present application provides a risk information identification method, a risk information identification device, an electronic device, and a computer-readable storage medium, which can perform a comprehensive risk assessment on target unit information from an industry perspective and / or an address perspective, and quickly and accurately identify risk information on the target unit information of the target applicant.

[0005] In a first aspect, the present application provides a method for identifying risk information, which includes: obtaining target unit information of a target applicant, and determining an associated applicant corresponding to the target unit information; obtaining multiple associated unit information of the associated applicant; respectively determining unit attribute data corresponding to each associated unit information, wherein the unit attribute data includes: industry attribute data whose attribute category is an industry category and / or address attribute data whose attribute category is an address category; calculating a data distance between multiple unit attribute data having the same attribute category, and identifying whether the target unit information is risk information based on the data distance.

[0006] In the second aspect, the present application provides a device for identifying risk information, which includes: a first acquisition module, used to acquire the target unit information of the target applicant, and determine the associated applicant corresponding to the target unit information; a second acquisition module, used to acquire multiple associated unit information of the associated applicant; a determination module, used to respectively determine the unit attribute data corresponding to each associated unit information, wherein the unit attribute data includes: industry attribute data whose attribute category is industry category and / or address attribute data whose attribute category is address category; an identification module, used to calculate the data distance between multiple unit attribute data with the same attribute category, and identify whether the target unit information is risk information based on the data distance.

[0007] In a third aspect, the present application provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores one or more computer programs executable by the at least one processor, and one or more of the computer programs are executed by the at least one processor so that the at least one processor can execute the above-mentioned risk information identification method.

[0008] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the above-mentioned risk information identification method when executed by a processor / processing core.

[0009] The embodiment provided by the present application first obtains the target unit information of the target applicant, determines the associated applicant corresponding to the target unit information, then obtains multiple associated unit information of the associated applicant, thereby respectively determining the industry attribute data and / or address attribute data corresponding to each associated unit information, and finally, calculates the data distance between multiple unit attribute data with the same attribute category, that is, calculates the data distance between multiple industry attribute data of different associated unit information and / or the data distance between multiple address attribute data. As the name suggests, the data distance between the above-mentioned industry attribute data and the data distance between the address attribute data can reflect the industry correlation and address correlation between different associated unit information, that is, industry changes and address changes. Therefore, according to the data distance, it is possible to identify whether the target unit information of the target applicant is risk information, thereby realizing a comprehensive risk assessment of the target unit information of the target applicant from an industry perspective and / or an address perspective, and can quickly and accurately identify risk information of the target unit information of the target applicant.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to provide a further understanding of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. The above and other features and advantages will become more apparent to those skilled in the art by describing detailed example embodiments with reference to the accompanying drawings. In the accompanying drawings:

[0012] Figure 1 A flowchart of a method for identifying risk information provided in an embodiment of the present application;

[0013] Figure 2 A flowchart of a method for identifying risk information provided in an embodiment of the present application;

[0014] Figure 3 A block diagram of a risk information identification device provided in an embodiment of the present application;

[0015] Figure 4 A block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the technical solution of the present application, the exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0017] In the absence of conflict, the embodiments of the present application and the features therein may be combined with each other.

[0018] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0019] The terms used herein are only used to describe specific embodiments and are not intended to limit the present application. As used herein, the singular forms "a" and "the" are also intended to include plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "including" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded. "Connected" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

[0020] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this application, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined herein.

[0021] In the relevant technology, the work unit information contained in the resource application request of the applicant can only be judged by manual review to determine whether it is risk information. Not only is the recognition efficiency low, but it is also difficult to review and discover information forgery, making it impossible to achieve fast and effective risk information identification.

[0022] According to the risk information identification method of the embodiment of the present application, first, the target unit information of the target applicant is obtained to determine the associated applicant corresponding to the target unit information, and then multiple associated unit information of the associated applicant is obtained, so as to respectively determine the industry attribute data and / or address attribute data corresponding to each associated unit information. Finally, the data distance between multiple unit attribute data with the same attribute category is calculated, that is, the data distance between multiple industry attribute data of different associated unit information and / or the data distance between multiple address attribute data are calculated. As the name suggests, the data distance between the above-mentioned industry attribute data and the data distance between the address attribute data can reflect the industry correlation and address correlation between different associated unit information, that is, industry changes and address changes. Therefore, according to the data distance, it is possible to identify whether the target unit information of the target applicant is risk information, thereby realizing a comprehensive risk assessment of the target unit information of the target applicant from an industry perspective and / or an address perspective, and being able to quickly and accurately identify the risk information of the target unit information of the target applicant.

[0023] The risk information identification method according to the embodiment of the present application can be performed by an electronic device such as a terminal device or a server, and the terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The method can be implemented by a processor calling a computer-readable program instruction stored in a memory. The server can be an independent physical server, a server cluster composed of multiple servers, or a cloud server capable of cloud computing.

[0024] Figure 1 A flowchart of a method for identifying risk information provided by an embodiment of the present application. Figure 1 , the method comprising:

[0025] Step S110: Acquire the target unit information of the target applicant, and determine the associated applicant corresponding to the target unit information.

[0026] The target applicant is the applicant who makes a resource application request. The resource application request refers to the application demand for specific resources made by the applicant to the relevant institution or platform during the business handling process. For example, in the financial business scenario, the target applicant applies for resources from the transaction service agency.

[0027] The target unit information is the unit information provided by the target application subject when making a resource application request. The information content contained in the target unit information can be adaptively set according to the actual application needs. For example, the target unit information can include the unit name, unit address, unit type, business scope, etc., which is not limited in this embodiment of the application.

[0028] Among them, the associated applicant corresponding to the target unit information refers to the applicant who has an associated relationship with the target unit corresponding to the target unit information. The associated relationship can be a labor relationship between the applicant and the unit, or a corresponding relationship between the applicant and the unit in the same resource application request. The embodiment of the present application does not limit this.

[0029] For example, if the unit information of an applicant's current employer is consistent with the target unit information, then the applicant is an associated applicant corresponding to the target unit information. For another example, if the unit information of an applicant's historical employer is consistent with the target unit information, then the applicant is an associated applicant corresponding to the target unit information.

[0030] It should be noted that the number of associated applicants can be adaptively set according to actual needs. The associated applicants can be all applicants corresponding to the target unit information. In this case, the target applicant can also be the associated applicant corresponding to the target unit information. The number of associated applicants corresponding to the target unit information can also be controlled within the number threshold range by setting the number threshold range. The embodiment of the present application does not limit this.

[0031] Step S120: Acquire information of multiple associated units of the associated application entity.

[0032] The associated unit information of the associated applicant refers to the information of the associated unit that has an associated relationship with the associated applicant. For example, the associated unit information may be the unit information corresponding to the unit where the associated applicant has worked and the unit information corresponding to the unit where the associated applicant currently works.

[0033] In some possible implementations, in order to achieve accurate risk identification of target unit information, a preset time range can be set to obtain multiple associated unit information of an associated applicant. Accordingly, obtaining multiple associated unit information of an associated applicant includes: obtaining multiple unit information corresponding to the associated applicant and a first association time corresponding to the associated applicant and the unit information; determining a second association time corresponding to the associated applicant and the target unit information from the first association time corresponding to the associated applicant and the unit information; determining an associated time interval based on the second association time and the preset time range; and using the unit information whose first association time is within the association time interval as the associated unit information of the associated applicant.

[0034] Among them, the first association time is the start time or end time of the association relationship between the associated application subject and the associated unit corresponding to the unit information, and the embodiment of the present application does not limit this.

[0035] Among them, the second association time is the start time or end time of the association relationship between the association applicant and the target unit corresponding to the target unit information, and this embodiment of the application does not limit this.

[0036] Among them, the preset time range refers to the time interval used to screen related applicants. For example, the preset time range is set to two years, five years, etc., and this embodiment of the present application does not limit this.

[0037] The associated time interval is a time interval determined by the second associated time and the preset time range. For example, the second associated time can be used as the end time of the time interval, and the preset time range can be used as the time difference between the start time and the end time of the time interval. For another example, the second associated time can be used as the middle value of the time interval, and the preset time range can be used as the time difference between the start time and the end time of the time interval. The embodiments of the present application are not limited to this.

[0038] By setting a preset time range, the associated unit information that meets the preset time range can be screened out, thereby improving the time correlation between the associated unit information and the target unit information, thereby making the risk information identification results obtained based on the analysis of the associated unit information more accurate.

[0039] Step S130: respectively determining the unit attribute data corresponding to each associated unit information, wherein the unit attribute data includes: industry attribute data whose attribute category is industry category and / or address attribute data whose attribute category is address category.

[0040] The unit attribute data corresponding to the associated unit information refers to the attribute information of the unit corresponding to the associated unit information. The unit attribute data can be directly obtained from the associated unit information or retrieved from the data source, which is not limited in the present embodiment.

[0041] Among them, the attribute category refers to the data category corresponding to the unit attribute data. The attribute category can be divided according to the attribute content corresponding to the unit. For example, the attribute content corresponding to the unit includes industry information, address information, business status information, and identity information. The attribute category can be divided into industry category, address category, business status category, identity category, etc.

[0042] Among them, industry attribute data whose attribute category is industry category refers to attribute data containing industry information of the unit. For example, if the unit name information contains industry vocabulary, then the unit name information can be used as industry attribute data. For another example, the unit's main business activity information reflects the industry background corresponding to the unit, then the unit's main business activity information can be used as industry attribute data.

[0043] The address attribute data whose attribute category is the address category refers to attribute data containing the geographical location information of the unit, for example, the unit registration address information, the unit communication address information, etc.

[0044] Step S140: Calculate the data distance between multiple unit attribute data with the same attribute category, and identify whether the target unit information is risk information based on the data distance.

[0045] Among them, the data distance between multiple unit attribute data with the same attribute category can represent the attribute correlation between the multiple unit attribute data. For example, the data distance between multiple industry attribute data can reflect the correlation of their industry attributes. For example, the data distance between multiple address attribute data can reflect the correlation of their address attributes.

[0046] The size of the data distance reflects the correlation between multiple unit attribute data. For example, for the data distance between multiple industry attribute data, the smaller the data distance, the higher the correlation between the industry attributes, and the larger the data distance, the lower the correlation between the industry attributes.

[0047] According to the data distance, the industry correlation and address correlation of multiple related unit information of the related applicant can be reflected. Therefore, according to the size of the data distance, it is possible to identify whether the target unit information has potential risks, that is, whether it is risk information.

[0048] In some possible implementations, in order to improve the calculation accuracy of the data distance between multiple industry attribute data, the industry category can be extracted from the industry attribute data through a sequence annotation model, so as to compare the industry categories corresponding to different industry attribute data to obtain the data distance between the industry attribute data. Accordingly, in the case where the same attribute category is the industry category, the data distance between multiple unit attribute data with the same attribute category is calculated, including: according to the sequence annotation model, the industry category data corresponding to each industry attribute data is determined respectively; from the industry category data corresponding to each industry attribute data, the first industry category data and the second industry category data to be compared are determined; the industry category data distance between the first industry category data and the second industry category data is calculated; according to the industry category data distance, the data distance between multiple industry attribute data is determined.

[0049] Among them, industry category data reflects the industry categories corresponding to the industry attribute data, such as the catering industry, financial industry, leasing industry, etc.

[0050] The first industry category data and the second industry category data are industry category data to be compared selected from the industry category data corresponding to each industry class attribute data.

[0051] It should be noted that multiple groups of first industry category data and second industry category data to be compared can be determined from the industry category data corresponding to each industry category attribute data, or only one group of first industry category data and second industry category data to be compared can be determined from the industry category data corresponding to each industry category attribute data. The embodiments of the present application are not limited to this.

[0052] It should also be noted that, when multiple groups of first industry category data and second industry category data to be compared are determined, the industry category data distance can be calculated for each group of first industry category data and second industry category data respectively, so as to determine the data distance between multiple industry attribute data based on the industry category data distance of each group; when only one group of first industry category data and second industry category data to be compared is determined, the industry category data distance of this group can be directly used as the data distance between multiple industry attribute data.

[0053] Among them, the sequence labeling model is trained according to different industry attribute training data. Since the industry attribute data can contain a variety of data information such as unit name information and unit main business activity information, in order to improve the accuracy of the sequence labeling model in extracting industry categories for industry attribute data, the sequence labeling model can be trained in the following ways: for different industry attribute data, an industry classification vocabulary is constructed; the industry attribute training data and the corresponding industry classification vocabulary are input into the sequence labeling model to be trained to obtain the training word vectors of the industry attribute training data and the label word vectors of different industry categories in the industry classification vocabulary; according to the similarity of the training word vectors and the label word vectors of different industry categories, the predicted industry category corresponding to the industry attribute training data is determined; according to the predicted industry category corresponding to the industry attribute training data and the label industry category corresponding to the industry attribute data, the parameters of the sequence labeling model to be trained are adjusted to obtain the trained sequence labeling model.

[0054] Among them, for different industry attribute data, the corresponding industry classification word library may be different. For example, for the unit name information, the corresponding industry category can be reflected in the name keyword. Therefore, the industry classification word library can be adaptively constructed. For example, for the real estate industry, the corresponding industry classification words can be "real estate development", "property management", etc., and for the financial industry, the corresponding industry classification words can be "bank", "securities", etc. For another example, for the main business activity information of the unit, the corresponding industry classification word library may include: accommodation and catering industry, the industry classification words are "hotel operation", "homestay operation", "restaurant operation", information transmission, software service industry, the industry classification words are "computer", "software development", etc.

[0055] Among them, the similarity between the training word vector and the label word vector of different industry categories can be obtained by calculating the cosine similarity between the two, or the Euclidean distance between the two, etc., which is not limited in this embodiment of the present application.

[0056] Among them, according to the similarity between the training word vector and the label word vector of different industry categories, the category probability that the training word vector belongs to different industry categories can be determined, so as to select the industry category with the largest category probability as the predicted industry category corresponding to the industry attribute data.

[0057] The training parameters of the sequence labeling model are adjusted according to the predicted industry category and the label industry category to minimize the difference between the predicted industry category and the label industry category, thereby obtaining a trained sequence labeling model.

[0058] In an embodiment of the present application, an industry classification vocabulary is constructed for different industry attribute data, and the predicted industry category of the industry attribute training data is determined based on the similarity between the word vectors of the industry classification vocabulary and the word vectors of the industry attribute training data. Thus, a sequence labeling model is trained based on the predicted industry category and the label industry category. During the training process, the similarity between the word vectors of the industry attribute training data and the word vectors of the corresponding industry categories is improved, thereby improving the industry category recognition effect of the sequence labeling model for different industry attribute data.

[0059] In some possible implementations, in order to improve the calculation accuracy of the industry category data distance between the first industry category data and the second industry category data, the degree of difference between the industry categories can be determined through a preset industry difference evaluation table, so as to convert the degree of difference into the industry category data distance according to a preset industry distance conversion rule. Accordingly, calculating the industry category data distance between the first industry category data and the second industry category data includes: based on the first industry category data and the second industry category data, querying the preset industry difference evaluation table to determine the difference value between the first industry category data and the second industry category data; converting the difference value into the industry category data distance between the first industry category data and the second industry category data according to the preset industry distance conversion rule.

[0060] Among them, the preset industry difference evaluation table contains the difference values ​​between different industry categories. Among them, the difference values ​​between different industry categories can be adaptively divided according to the business scenarios of different industries. Through the business scenarios of different industries, the difficulty of industry conversion between different industries can be determined, thereby determining the difference values ​​between different industries. For example, the difference value between the retail industry and the accommodation and catering industry is set to 2, the difference value between the real estate industry and the tourism industry is set to 3, the difference value between the logistics industry and the financial industry is set to 6, etc., and the embodiment of the present application does not limit this.

[0061] The preset industry distance conversion rule includes the corresponding relationship between different difference values ​​and industry distances. The industry distance can be expressed in numerical form, such as 50, 100, or in grade form, such as first-level, second-level, third-level, etc., which is not limited in the present embodiment of the application.

[0062] It should be noted that when determining the industry distances corresponding to different difference values, a difference interval can be set so that the difference values ​​within the interval correspond to the same industry distance. A finer-grained division can also be performed so that different difference values ​​correspond to different industry distances. The embodiments of the present application are not limited to this.

[0063] By setting a preset industry difference assessment table, the difference values ​​between different industry categories can be determined according to the actual business scenarios of different industry categories. Then, according to the preset industry distance conversion rules, the difference values ​​can be converted into industry category data distances, thereby improving the accuracy of data distance calculation for industry category data.

[0064] In some possible implementations, in order to improve the calculation accuracy of the data distance between multiple address-type attribute data, the administrative district information of the address-type attribute data can be extracted through a preset address resolution model, so as to compare according to the administrative district information and obtain the data distance between the address-type attribute data. Accordingly, in the case where the same attribute category is the address category, the data distance between multiple unit attribute data with the same attribute category is calculated, including: extracting the administrative district information contained in each address-type attribute data according to the preset address resolution model; determining the first administrative district information and the second administrative district information to be compared from the administrative district information of each address-type attribute data; comparing the first administrative district information with the second administrative district information, matching the comparison result with the preset address distance rule, and determining the address distance corresponding to the first administrative district information and the second administrative district information; determining the data distance between multiple address-type attribute data according to the address distance corresponding to the first administrative district information and the second administrative district information.

[0065] The preset address parsing model is a parsing model trained with address attribute training data and administrative district label data corresponding to the address attribute training data. The administrative district information contained in the address attribute data can be extracted through the preset address parsing model.

[0066] The administrative district information is the text data corresponding to different administrative district levels contained in the address attribute data. For example, for a certain address attribute data: Province A, City B, District C, the address parsing model can be used to extract the text data corresponding to the provincial, municipal, and district levels of Province A, City B, and District C.

[0067] Among them, when determining the first administrative district information and the second administrative district information to be compared from the administrative district information of each address attribute data, multiple groups of the first administrative district information and the second administrative district information to be compared can be extracted, so as to achieve a comprehensive comparison of the administrative district information of different address attribute data. For example, for the administrative district information 1, 2, and 3 corresponding to the address attribute data 1, 2, and 3, respectively, the administrative district information 1 and the administrative district information 2 can be used as the first administrative district information and the second administrative district information to be compared, respectively, or the administrative district information 1 and the administrative district information 3, and the administrative district information 2 and the administrative district information 3 can be used as the first administrative district information and the second administrative district information to be compared.

[0068] Among them, comparing the first administrative district information with the second administrative district information means: comparing the text data corresponding to the same administrative district level in the first administrative district information and the second administrative district information, for example, comparing the text data corresponding to the provincial administrative district level in the first administrative district information and the second administrative district information, so as to determine whether the text data corresponding to the provincial administrative district level in the first administrative district information and the second administrative district information match.

[0069] The comparison result between the first administrative district information and the second administrative district information represents the matching result of text data corresponding to different administrative district levels in the first administrative district information and the second administrative district information.

[0070] The preset address distance rule includes the correspondence between the matching address type and the industry distance of the administrative district information. The address distance can be expressed in numerical form, such as 5, 10, or in hierarchical form, such as level 1, level 2, level 3, etc., which is not limited in the present embodiment of the application.

[0071] In some possible implementations, in order to achieve an accurate match between the comparison result of the first administrative district information and the second administrative district information and the preset address distance rule, the matching address type of the first administrative district information and the second administrative district information can be determined based on the comparison result, so as to match the preset address distance rule based on the matching address type. Accordingly, the comparison result is matched with the preset address distance rule to determine the address distance corresponding to the first administrative district information and the second administrative district information, including: determining the matching address type of the first administrative district information and the second administrative district information based on the comparison result, wherein the matching address type is divided according to the administrative district level; determining the address distance corresponding to the matching address type in the preset address distance rule; and using the address distance corresponding to the matching address type as the address distance corresponding to the first administrative district information and the second administrative district information.

[0072] The matching address type can be divided according to the administrative district level, so that the text data matching the first administrative district information and the second administrative district information can be divided into corresponding matching address types according to the administrative district level corresponding to the text data. For example, the matching address type is set to be a provincial matching type, a municipal matching type, and a county matching type.

[0073] Among them, when determining the matching address type of the first administrative district information and the second administrative district information based on the comparison results, it is necessary to determine the minimum administrative district level corresponding to the matching text data in the first administrative district information and the second administrative district information, so as to determine the corresponding matching address type according to the minimum administrative district level.

[0074] For example, the text data corresponding to the provincial administrative districts and the municipal administrative districts in the first administrative district information and the second administrative district information are successfully matched. Therefore, the lowest administrative district level, that is, the municipal administrative district, can be selected as the matching administrative district level corresponding to the text data, thereby determining the corresponding matching address type as the municipal matching type based on the administrative district level.

[0075] It should be noted that when there is no matching text data between the first administrative district information and the second administrative district information, the address distance corresponding to the unmatched type can be set in the preset address distance rule to indicate that the geographical locations corresponding to the first administrative district information and the second administrative district information are less correlated.

[0076] It should also be noted that the level or value of the address distance needs to be divided according to the administrative district level corresponding to the matching address type, so that the correlation of the geographical location corresponding to the matching address type can be indicated by the change in level or the difference in value.

[0077] Exemplarily, the address distance corresponding to the county-level matching type is set to 0, the address distance corresponding to the city-level matching type is set to 1, the address distance corresponding to the provincial-level matching type is set to 2, and the address distance corresponding to the unmatched type is set to 3, so that the change in the geographic location correlation of the matching address type can be represented by the change in the numerical value of the address distance.

[0078] After determining the address distance between the first administrative district information and the second administrative district information, the data distance between the plurality of address attribute data may be determined based on the address distance between the first administrative district information and the second administrative district information.

[0079] When there are multiple sets of first administrative district information and second administrative district information, the data distance between multiple address attribute data may be determined based on the address distance corresponding to each set of first administrative district information and second administrative district information.

[0080] Exemplarily, the average distance between the address distances corresponding to multiple groups of first administrative district information and second administrative district information can be calculated as the data distance between multiple address-type attribute data; or, based on the numerical value or level of the address distance, one address distance can be selected from the address distances corresponding to each group of first administrative district information and second administrative district information as the data distance between multiple address-type attribute data. The embodiments of the present application are not limited to this.

[0081] In an embodiment of the present application, first, the target unit information of the target applicant is obtained, and the associated applicant corresponding to the target unit information is determined. Then, multiple associated unit information of the associated applicant is obtained, so as to respectively determine the industry attribute data and / or address attribute data corresponding to each associated unit information. Finally, the data distance between multiple unit attribute data with the same attribute category is calculated, that is, the data distance between multiple industry attribute data of different associated unit information and / or the data distance between multiple address attribute data are calculated. As the name suggests, the data distance between the above-mentioned industry attribute data and the data distance between the address attribute data can reflect the industry correlation and address correlation between different associated unit information, that is, industry changes and address changes. Therefore, according to the data distance, it is possible to identify whether the target unit information of the target applicant is risk information, thereby realizing a comprehensive risk assessment of the target unit information of the target applicant from an industry perspective and / or an address perspective, and being able to quickly and accurately identify risk information of the target unit information of the target applicant.

[0082] In addition, those skilled in the art may also make various modifications and variations to the method in this application:

[0083] In some possible implementations, the inventors found that the target unit information may correspond to multiple associated applicants. Therefore, in order to identify the risk information of the target unit information in combination with the data distances corresponding to the multiple associated applicants, when the number of associated applicants is multiple, the average data distance between the data distances corresponding to each associated applicant can be calculated to identify whether the target unit information is risk information. Correspondingly, if the number of associated applicants is multiple, identifying whether the target unit information is risk information based on the data distance includes: determining the first data distance corresponding to each associated applicant from the data distance; determining multiple second data distances with the same attribute category from the first data distance corresponding to each associated applicant according to the attribute category corresponding to the first data distance; calculating the average data distance between the multiple second data distances, and identifying whether the target unit information is risk information based on the average data distance and a preset distance threshold.

[0084] The first data distance refers to the data distance corresponding to the associated application subject. When determining the first data distance corresponding to each associated application subject from the data distance, the data distance corresponding to the associated application subject can be determined by querying the binding relationship between the data distance and the associated application subject.

[0085] Specifically, after calculating the data distances between multiple unit attribute data corresponding to the associated applicants, the binding relationship between the associated applicants and their corresponding data distances can be stored, so that by querying the binding relationship, the first data distance corresponding to each associated applicant can be determined from the data distances.

[0086] The first data distance corresponding to each associated application entity may include data distances between multiple industry attribute data and data distances between multiple address attribute data.

[0087] For example, for a certain associated applicant 1, the data distance between its corresponding industry attribute data is A1, and the data distance between its address attribute data is B1. Therefore, by binding and storing the associated applicant 1 with the data distances A1 and B1, the data distance corresponding to the associated applicant 1 can be queried based on the binding relationship.

[0088] The attribute category corresponding to the first data distance is the attribute category of the unit attribute data corresponding to the first data distance. For example, for industry attribute data whose attribute category is industry category, when the first data distance is the data distance between multiple industry attribute data, according to the attribute category of the industry attribute data corresponding to the first data distance, it can be determined that the attribute category corresponding to the first data distance is the industry category.

[0089] The second data distance refers to the first data distance having the same attribute category.

[0090] Among them, when the first data distance includes the data distance between multiple industry attribute data and the data distance between multiple address attribute data, the average industry data distance between multiple second data distances corresponding to the industry category and the average address data distance between multiple second data distances corresponding to the address category can be calculated respectively, so as to identify whether the target unit is risk information based on the average industry data distance, the average address data distance and the preset distance threshold.

[0091] In some possible implementations, when calculating the average data distance between multiple second data distances, since the importance of the associated application entities corresponding to different second data distances may be different, the weight value of the second data distance can be determined according to the importance of the associated application entity corresponding to the second data distance, and thus the average data distance between the multiple second data distances can be calculated according to the weight value of the second data distance.

[0092] The importance of the associated application subject is used to characterize the degree of relevance between the associated application subject and the unit corresponding to the target unit information. Specifically, the importance of the associated application subject can be determined according to the association duration or association start time of the association relationship between the associated application subject and the unit corresponding to the target unit information, and this embodiment of the application does not limit this.

[0093] Among them, the preset distance threshold is used to evaluate the risk level corresponding to the average data distance.

[0094] It should be noted that when the average data distance corresponding to the industry category and the average data distance corresponding to the address category are calculated respectively, a unified preset distance threshold can be set for the above-mentioned average data distance, or a corresponding preset distance threshold can be set according to different attribute categories. The embodiments of the present application are not limited to this.

[0095] Exemplarily, when the average data distance includes the average industry data distance and the average address data distance, corresponding preset industry distance thresholds and preset address distance thresholds can be set for the average industry data distance and the average address data distance, respectively, so as to identify whether the target unit information is risk information based on the comparison results between the average industry data distance and the preset industry distance threshold and the comparison results between the average address data distance and the preset address distance threshold.

[0096] It should also be noted that when identifying whether the target unit information is risk information based on the average data distance and the preset distance threshold, the risk identification rules can be adaptively configured according to the actual business scenario.

[0097] For example, when there are multiple average data distances, when any average data distance exceeds the corresponding preset distance threshold, the target unit information is identified as risk information, or when all average data distances exceed the corresponding preset distance threshold, the target unit information is identified as risk information. The embodiments of the present application are not limited to this.

[0098] In an embodiment of the present application, when there are multiple related applicants, by calculating the average distance between multiple data distances with the same attribute category corresponding to the multiple related applicants, it is possible to identify risk information of the target unit information in combination with the data distances corresponding to the multiple related applicants, thereby improving the accuracy of risk information identification for the target unit information.

[0099] In some possible implementations, after identifying whether the target unit information is risk information according to the data distance, in order to achieve effective risk handling of the resource application request, a preset risk handling strategy can be set. When the target unit information is identified as risk information, the resource application request is risk handled according to the preset risk handling strategy. Correspondingly, the target unit information of the target application subject is obtained from the received resource application request of the target application subject; then after identifying whether the target unit information is risk information according to the data distance, it also includes: when the target unit information is risk information, the resource application request is risk handled according to the preset risk handling strategy, wherein the preset risk handling strategy includes at least one of the following: information verification strategy, blacklist strategy; when the preset risk handling strategy is the information verification strategy, risk handling of the resource application request includes: according to the preset information source, verifying the target unit information of the resource application request, and according to the verification result, risk handling of the resource application request; when the preset risk handling strategy is the blacklist strategy, risk handling of the resource application request includes: adding the target unit and the target application subject corresponding to the target unit information to the risk blacklist, and rejecting the resource application request of the target application subject.

[0100] Among them, the preset information source may include relevant information sources such as a business database or an official website corresponding to the resource application request, which is not limited in this embodiment of the present application.

[0101] Among them, verifying the target unit information of the resource application request includes verifying the unit credit information, unit personnel information and other contents corresponding to the target unit information, so as to determine the accuracy of risk identification of the target unit information based on the verification results, so as to perform risk processing on the resource application request.

[0102] Exemplarily, by checking the unit credit information corresponding to the target unit information, the credit rating corresponding to the target unit information is determined, and if the credit rating is less than the preset credit level, the resource application request is risk-processed. By checking the unit personnel information corresponding to the target unit information, the matching degree between the unit personnel information and the associated application object is determined, and if the matching degree exceeds the preset matching threshold, the resource application request is risk-processed.

[0103] Among them, by adding the target unit and the target applicant corresponding to the target unit information to the risk blacklist, it is used to identify the target unit and the target applicant as having potential risks, thereby reducing the risk probability of resource application by rejecting the resource application request of the target applicant.

[0104] It should be noted that the preset risk handling strategy may also include other strategies, which are not limited in the embodiments of the present application. For example, the preset risk handling strategy may also include a manual review strategy, in which the target unit information of the resource application request is sent to the target object for review, and the resource application request is risk handled according to the review result of the target object on the target unit information.

[0105] In the embodiment of the present application, when the target unit information is risk information, risk processing is performed on the resource application request by setting a preset risk processing strategy, thereby improving the reliability of risk interception of the resource application.

[0106] For ease of understanding, the following uses an example to describe the technical implementation details in the above embodiment:

[0107] In the related art, when reviewing the resource application request of the applicant, the relevant institutions mainly rely on manual review, but the above manual review method has the following disadvantages:

[0108] (1) Limited perspective: The existing solutions are centered on the applicant and mainly review the relevant basic information of the applicant, while ignoring the detailed risk review of the work unit information in the resource application request.

[0109] (2) Reliance on manual judgment: Existing solutions are highly dependent on the experience and judgment of auditors, which poses a risk of subjectivity and error. In addition, manual review limits processing efficiency and real-time performance.

[0110] (3) Insufficient interception probability: The existing scheme is not easy to be audited and discovered for information falsification, resulting in insufficient interception probability and inability to quickly and effectively identify risk information on the work unit information contained in the resource application request.

[0111] In order to solve the above problems, this example proposes a method for identifying risk information.

[0112] Figure 2 A flow chart showing a method for identifying risk information is shown in FIG. Figure 2 , the method comprising:

[0113] Step S201: Acquire the target unit information of the target applicant, and determine the associated applicant corresponding to the target unit information.

[0114] The target unit information is the unit information provided by the target applicant when making a resource application request. The target unit information of the target applicant can be obtained according to the resource application request of the target applicant, for example, by obtaining the target unit information in the resource application form corresponding to the resource application request.

[0115] The associated application subject corresponding to the target unit information may be obtained by screening from an internal business database corresponding to the resource application request or an external data source such as an official website.

[0116] The associated applicants corresponding to the target unit information may be all applicants that have an associated relationship with the target unit corresponding to the target unit information.

[0117] Step S202: Acquire information of multiple associated units of the associated applicant.

[0118] The associated unit information of the associated application subject refers to the information of the associated unit that has an associated relationship with the associated application subject. The associated unit information may include unit attribute data such as unit name and unit address.

[0119] Step S203: determining the unit attribute data corresponding to each associated unit information respectively, wherein the unit attribute data includes: industry attribute data whose attribute category is industry category and / or address attribute data whose attribute category is address category.

[0120] Step S204: Calculate the data distance between a plurality of unit attribute data having the same attribute category.

[0121] Among them, for industry attribute data whose attribute category is industry category, when calculating the data distance between multiple industry attribute data, the sequence labeling model can be used to process the industry attribute data to determine the industry category data corresponding to the industry attribute data, and then calculate the data distance between multiple industry attribute data according to the National Economic Industry Classification and Code (GB / T4754-2017) or the preset industry difference evaluation table.

[0122] Among them, the data distance between industry attribute data can be determined according to the category level differences of different industries, and can also be customized based on actual business scenarios, which is not limited in the embodiments of the present application.

[0123] Among them, when the associated applicant corresponds to multiple industry attribute data, two industry attribute data can be selected for data distance calculation. For example, the industry attribute data corresponding to the current employer of the associated applicant and the industry attribute data corresponding to the first employer are selected to calculate the data distance. Alternatively, multiple industry attribute data can be grouped in pairs to calculate the data distance, and the average data distance of each group of data distances can be selected as the data distance between the multiple industry attribute data.

[0124] Among them, for address-type attribute data whose attribute category is address category, when calculating the data distance between multiple address-type attribute data, the address-type attribute data can be parsed through a preset address parsing model to extract administrative district information, thereby comparing the administrative district information of different address-type attribute data, and matching the comparison result with the preset address distance rule to determine the data distance between multiple address-type attribute data.

[0125] Among them, the preset address distance rules can be adaptively set according to the actual comparison needs. By setting the industry difference evaluation table according to different industry characteristics and setting the preset address distance rules according to different regional characteristics, the usability of the calculated data distance is improved.

[0126] Similarly, when the associated application subject corresponds to multiple address-type attribute data, two address-type attribute data can be selected for data distance calculation. For example, the address-type attribute data corresponding to the current employer of the associated application subject and the address-type attribute data corresponding to the first employer are selected to calculate the data distance. Alternatively, multiple address-type attribute data can be grouped in pairs to calculate the data distance, so that the average data distance of each group of data distances is used as the data distance between the multiple address-type attribute data.

[0127] It should be noted that the sequence labeling model and the address resolution model are models obtained by training the machine learning or deep learning model based on the preset training data. By using the sequence labeling model and the address resolution model for information extraction, industry category information and administrative district information can be extracted quickly and accurately, improving the efficiency of risk information identification.

[0128] Step S205: Determine the first data distance corresponding to each associated application entity from the data distances.

[0129] Step S206: According to the attribute category corresponding to the first data distance, a plurality of second data distances having the same attribute category are determined from the first data distance corresponding to each associated application subject.

[0130] Step S207: Calculate the average data distance between the plurality of second data distances, and identify whether the target unit information is risk information according to the average data distance and a preset distance threshold.

[0131] In this step, multiple second data distances can be averaged to calculate the average data distance between the multiple second data distances. Different weight values ​​can also be set for different second data distances, so that the average data distance between the multiple second data distances can be calculated according to the weight values ​​corresponding to the second data distances. The embodiment of the present application is not limited to this.

[0132] Among them, when identifying whether the target unit information is risk information based on the average data distance and the preset distance threshold, the target unit information can be identified as risk information when any average data distance exceeds the corresponding preset distance threshold, or the target unit information can be identified as risk information when all average data distances exceed the corresponding preset distance threshold. The embodiment of the present application does not limit this.

[0133] Step S208: When the target unit information is risk information, risk processing is performed on the resource application request according to a preset risk processing strategy.

[0134] Among them, the preset risk handling strategy may include information verification of the target unit information of the resource application request, adding the target unit corresponding to the target unit information and the target application subject to the risk blacklist, manual review of the target unit information of the resource application request, and other processing strategies, which are not limited to the embodiments of the present application.

[0135] In summary, this example can conduct a more comprehensive risk identification of the target unit information of the target applicant by comprehensively analyzing the information of the associated applicant corresponding to the target unit information. Moreover, when identifying risk information, this example takes into account the data distance between different industry attribute data and the data distance between address attribute data, thereby effectively improving the accuracy of risk information identification.

[0136] It can be understood that the above-mentioned various method embodiments mentioned in this application can be combined with each other to form a combined embodiment without violating the principle logic. Due to space limitations, this application will not go into details. Those skilled in the art can understand that in the above-mentioned method of the specific implementation method, the specific execution order of each step should be determined by its function and possible internal logic.

[0137] In addition, the present application also provides a risk information identification device, an electronic device, and a computer-readable storage medium, all of which can be used to implement any risk information identification method provided in the present application. The corresponding technical solutions and descriptions are referred to in the corresponding records of the method part and will not be repeated here.

[0138] Figure 3 A block diagram of a risk information identification device provided in an embodiment of the present application.

[0139] Reference Figure 3 , an embodiment of the present application provides a risk information identification device, the risk information identification device comprising:

[0140] The first acquisition module 31 is used to acquire the target unit information of the target applicant and determine the associated applicant corresponding to the target unit information;

[0141] The second acquisition module 32 is used to acquire information of multiple associated units of the associated application subject;

[0142] The determination module 33 is used to respectively determine the unit attribute data corresponding to each associated unit information, wherein the unit attribute data includes: industry attribute data whose attribute category is industry category and / or address attribute data whose attribute category is address category;

[0143] The identification module 34 is used to calculate the data distance between the plurality of unit attribute data having the same attribute category, and identify whether the target unit information is risk information according to the data distance.

[0144] In some possible implementations, when the same attribute category is the industry category, the calculation of the data distance between the multiple unit attribute data with the same attribute category includes: determining the industry category data corresponding to each of the industry class attribute data according to a sequence labeling model; determining the first industry category data and the second industry category data to be compared from the industry category data corresponding to each industry class attribute data; calculating the industry category data distance between the first industry category data and the second industry category data; and determining the data distance between the multiple industry class attribute data according to the industry category data distance.

[0145] In some possible implementations, the calculating the industry category data distance between the first industry category data and the second industry category data includes: based on the first industry category data and the second industry category data, querying a preset industry difference evaluation table to determine the difference value between the first industry category data and the second industry category data; and converting the difference value into the industry category data distance between the first industry category data and the second industry category data according to a preset industry distance conversion rule.

[0146] In some possible implementations, when the same attribute category is the address category, the calculation of the data distance between the multiple unit attribute data with the same attribute category includes: extracting the administrative district information contained in each address-type attribute data according to a preset address resolution model; determining the first administrative district information and the second administrative district information to be compared from the administrative district information of each address-type attribute data; comparing the first administrative district information with the second administrative district information, matching the comparison result with a preset address distance rule, and determining the address distance corresponding to the first administrative district information and the second administrative district information; determining the data distance between the multiple address-type attribute data according to the address distance corresponding to the first administrative district information and the second administrative district information.

[0147] In some possible implementations, the comparison result is matched with a preset address distance rule to determine the address distance corresponding to the first administrative district information and the second administrative district information, including: determining the matching address type between the first administrative district information and the second administrative district information based on the comparison result, wherein the matching address type is divided according to the administrative district level; determining the address distance corresponding to the matching address type in the preset address distance rule; and using the address distance corresponding to the matching address type as the address distance corresponding to the first administrative district information and the second administrative district information.

[0148] In some possible implementations, if there are multiple associated applicants, identifying whether the target unit information is risk information based on the data distance includes: determining the first data distance corresponding to each associated applicant from the data distance; determining multiple second data distances with the same attribute category from the first data distance corresponding to each associated applicant based on the attribute category corresponding to the first data distance; calculating the average data distance between the multiple second data distances, and identifying whether the target unit information is risk information based on the average data distance and a preset distance threshold.

[0149] In some possible implementations, the target unit information of the target applicant is obtained from the resource application request received from the target applicant; then after identifying whether the target unit information is risk information according to the data distance, the method also includes: when the target unit information is risk information, performing risk processing on the resource application request according to a preset risk processing strategy, wherein the preset risk processing strategy includes at least one of the following: information verification strategy, blacklist strategy; when the preset risk processing strategy is the information verification strategy, performing risk processing on the resource application request includes: according to a preset information source, verifying the target unit information of the resource application request, and performing risk processing on the resource application request according to the verification result; when the preset risk processing strategy is the blacklist strategy, performing risk processing on the resource application request includes: adding the target unit and the target applicant corresponding to the target unit information to the risk blacklist, and rejecting the resource application request of the target applicant.

[0150] Each module in the risk information identification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0151] Figure 4 A block diagram of an electronic device provided in an embodiment of the present application.

[0152] Reference Figure 4 An embodiment of the present application provides an electronic device, which includes: at least one processor 401; at least one memory 402, and one or more I / O interfaces 403, connected between the processor 401 and the memory 402; wherein the memory 402 stores one or more computer programs that can be executed by at least one processor 401, and the one or more computer programs are executed by at least one processor 401 so that the at least one processor 401 can execute the above-mentioned risk information identification method.

[0153] Each module in the above electronic device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0154] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored, wherein the computer program implements the above-mentioned risk information identification method when executed by a processor / processing core. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0155] An embodiment of the present application also provides a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above-mentioned risk information identification method.

[0156] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable storage medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium).

[0157] As is known to those of ordinary skill in the art, the term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable program instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technology, portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. In addition, it is known to those of ordinary skill in the art that communication media typically contain computer-readable program instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium.

[0158] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0159] The computer program instructions for performing the operation of the present application can be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions can be executed completely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of a computer-readable program instruction to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA), the electronic circuit can execute a computer-readable program instruction, thereby realizing various aspects of the present application.

[0160] The computer program product described herein may be implemented in hardware, software, or a combination thereof. In one optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), etc.

[0161] Various aspects of the present application are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0162] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0163] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0164] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can also be executed in the opposite order sometimes, depending on the function involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a dedicated hardware-based system that performs the function or action of the specification, or can be realized by a combination of special-purpose hardware and computer instructions.

[0165] Example embodiments have been disclosed herein, and although specific terms are employed, they are used and should be interpreted only in a general illustrative sense and not for limiting purposes. In some instances, it will be apparent to those skilled in the art that, unless otherwise expressly noted, features, characteristics, and / or elements described in conjunction with a particular embodiment may be used alone or in combination with features, characteristics, and / or elements described in conjunction with other embodiments. Therefore, those skilled in the art will appreciate that various changes in form and detail may be made without departing from the scope of the present application as set forth in the appended claims.

Claims

1. A method for identifying risk information, characterized in that: The method comprises: Obtain target unit information of the target applicant, and determine the associated applicant corresponding to the target unit information; Obtain information on multiple associated units of the associated application subject; Determine the unit attribute data corresponding to each associated unit information respectively, wherein the unit attribute data includes: industry attribute data whose attribute category is industry category and / or address attribute data whose attribute category is address category; The data distance between the plurality of unit attribute data having the same attribute category is calculated, and whether the target unit information is risk information is identified according to the data distance.

2. The method according to claim 1, characterized in that In the case where the same attribute category is the industry category, the calculating of the data distance between the plurality of unit attribute data having the same attribute category includes: According to the sequence labeling model, the industry category data corresponding to each of the industry attribute data is determined respectively; Determine the first industry category data and the second industry category data to be compared from the industry category data corresponding to each industry attribute data; Calculating the industry category data distance between the first industry category data and the second industry category data; According to the industry category data distance, the data distance between the plurality of industry category attribute data is determined.

3. The method according to claim 2, characterized in that The calculating the industry category data distance between the first industry category data and the second industry category data includes: Based on the first industry category data and the second industry category data, querying a preset industry difference evaluation table to determine the difference value between the first industry category data and the second industry category data; According to a preset industry distance conversion rule, the difference value is converted into the industry category data distance between the first industry category data and the second industry category data.

4. The method according to claim 1, characterized in that: In the case where the same attribute category is the address category, the calculating of the data distance between the plurality of unit attribute data having the same attribute category includes: According to the preset address parsing model, the administrative district information contained in each address attribute data is extracted respectively; Determine the first administrative district information and the second administrative district information to be compared from the administrative district information of each address attribute data; Compare the first administrative district information with the second administrative district information, match the comparison result with a preset address distance rule, and determine the address distance corresponding to the first administrative district information and the second administrative district information; The data distance between the plurality of address-type attribute data is determined according to the address distance corresponding to the first administrative district information and the second administrative district information.

5. The method according to claim 4, characterized in that Matching the comparison result with a preset address distance rule to determine the address distance between the first administrative district information and the second administrative district information includes: Determine, according to the comparison result, a matching address type between the first administrative district information and the second administrative district information, wherein the matching address type is divided according to administrative district levels; Determining the address distance corresponding to the matching address type in the preset address distance rule; The address distance corresponding to the matching address type is used as the address distance corresponding to the first administrative district information and the second administrative district information.

6. The method according to claim 1, characterized in that If there are multiple associated applicants, identifying whether the target unit information is risk information based on the data distance includes: Determine respectively from the data distances a first data distance corresponding to each associated application entity; According to the attribute category corresponding to the first data distance, determining a plurality of second data distances having the same attribute category from the first data distance corresponding to each associated application subject; An average data distance between the plurality of second data distances is calculated, and whether the target unit information is risk information is identified according to the average data distance and a preset distance threshold.

7. The method according to claim 1, characterized in that The target unit information of the target application subject is obtained from the received resource application request of the target application subject; after identifying whether the target unit information is risk information according to the data distance, the method further includes: In the case where the target unit information is risk information, risk processing is performed on the resource application request according to a preset risk processing strategy, wherein the preset risk processing strategy includes at least one of the following: information verification strategy, blacklist strategy; In the case where the preset risk handling strategy is an information verification strategy, performing risk handling on the resource application request includes: verifying the target unit information of the resource application request according to a preset information source, and performing risk handling on the resource application request according to the verification result; When the preset risk handling strategy is a blacklist strategy, risk handling of the resource application request includes: adding the target unit and the target application subject corresponding to the target unit information to a risk blacklist, and rejecting the resource application request of the target application subject.

8. A risk information identification device, characterized in that: The device comprises: A first acquisition module is used to acquire target unit information of a target applicant and determine an associated applicant corresponding to the target unit information; A second acquisition module is used to acquire information of multiple associated units of the associated application subject; A determination module, used to respectively determine unit attribute data corresponding to each associated unit information, wherein the unit attribute data includes: industry attribute data whose attribute category is industry category and / or address attribute data whose attribute category is address category; The identification module is used to calculate the data distance between the plurality of unit attribute data having the same attribute category, and identify whether the target unit information is risk information according to the data distance.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs that can be executed by the at least one processor, and the one or more computer programs are executed by the at least one processor to enable the at least one processor to perform the risk information identification method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the risk information identification method according to any one of claims 1 to 7.