Application review method, device, electronic device and storage medium

Abstract

The embodiment of the present invention discloses an application review method, device, electronic device and storage medium. The method includes: determining the personal review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph; determining other members of the group to which the applicant belongs based on the knowledge graph, and determining the group application status based on the application information submitted by the other members; determining the application result of the applicant based on the personal review result of the applicant and the group application status. By running the technical solution provided by the embodiment of the present invention, it is possible to solve the problem that the review only targets the information of a single applicant, making it difficult to discover group fraud related to a single application, thereby reducing the accuracy of the application review, thereby achieving the effect of improving the efficiency and accuracy of the application review.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer technology, and more particularly to an application review method, device, electronic device and storage medium. Background Art

[0002] With the development of the economy, more and more people use credit cards for consumption, so the review of credit card applications is particularly important.

[0003] The current process for reviewing credit card applications is to manually verify the basic information filled out by the applicant in different systems after receiving it to determine whether the applicant's information meets the application criteria.

[0004] However, reviewing a single person's information requires entering multiple systems for information verification, which reduces the efficiency of application review. In addition, the current review only reviews the applicant's individual information, making it difficult to detect group fraud related to a single application, thereby reducing the accuracy of the application review. Summary of the invention

[0005] The embodiments of the present invention provide an application review method, device, electronic device and storage medium to achieve the effect of improving the efficiency and accuracy of application review.

[0006] In a first aspect, an embodiment of the present invention provides an application review method, the method comprising:

[0007] Determine the individual review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph;

[0008] Determine other members of the group to which the applicant belongs based on the knowledge graph, and determine the group application status based on the application information submitted by the other members;

[0009] The application result of the applicant is determined based on the individual review result of the applicant and the group application status.

[0010] In a second aspect, an embodiment of the present invention further provides an application review device, the device comprising:

[0011] A personal review result determination module, used to determine the personal review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph;

[0012] A group application status determination module, used to determine other members of the group to which the applicant belongs based on the knowledge graph, and determine the group application status based on the application information submitted by the other members;

[0013] The application result determination module is used to determine the application result of the applicant according to the individual review result of the applicant and the group application status.

[0014] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0015] one or more processors;

[0016] a storage device for storing one or more programs,

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the application review method as described above.

[0018] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the application review method as described above.

[0019] The embodiment of the present invention determines the personal review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph; determines other members of the group to which the applicant belongs based on the knowledge graph, and determines the group application status based on the application information submitted by the other members; determines the application result of the applicant based on the personal review result of the applicant and the group application status, thereby solving the problem that the review only audits the information of a single applicant, making it difficult to discover group fraud related to a single application, thereby reducing the accuracy of the application review, and achieving the effect of improving the efficiency and accuracy of the application review. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A flowchart of an application review method provided in Embodiment 1 of the present invention;

[0021] Figure 2 A flowchart of an application review method provided in Embodiment 2 of the present invention;

[0022] Figure 3 A schematic diagram of the structure of an application review device provided in Embodiment 3 of the present invention;

[0023] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0025] Embodiment 1

[0026] Figure 1 This is a flow chart of an application review method provided in the first embodiment of the present invention. This embodiment can be used to review whether the application information submitted by the applicant is correct. The method can be executed by the application review device provided in the embodiment of the present invention. The device can be implemented in software and / or hardware. Figure 1 The application review method provided in this embodiment includes:

[0027] Step 110: Determine the personal review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph.

[0028] The application information submitted by the applicant may include the applicant's basic information and application type. The applicant's basic information may include the applicant's name, ID number, and other information. The application type may be a credit card application, etc. The applicant data in the knowledge graph is the data related to the applicant in the pre-built knowledge graph. By comparing the application information with the applicant data in the knowledge graph, it is determined whether the applicant's personal review result is qualified.

[0029] In this embodiment, optionally, the applicant data includes:

[0030] At least one of illegal list data, credit data and personal data; wherein the illegal list data includes blacklist data and grey list data.

[0031] Among them, blacklist data refers to the data of users who have been blacklisted for long-term overdue payments, repeated non-repayment, illegal cash withdrawal, etc. Graylist data refers to the data of users whose relatives within the second generation are blacklist members. Credit data can be the credit report of the user. Personal data can be the name, ID number and other data submitted by the user when performing other operations before.

[0032] In this embodiment, optionally, obtaining the gray list data includes:

[0033] Determine a first relative set according to the blacklist data and the family relationships in the knowledge graph;

[0034] Determine a second relative set according to the first relative set and the family relationship in the knowledge graph;

[0035] The gray list data is obtained by performing a deduplication operation on the second relative set.

[0036] The first relative set is a set consisting of the immediate family members of the blacklisted users and the blacklisted users. The second user set is a set consisting of the immediate family members of the members in the first relative set obtained by the first relative set through the family relationships in the knowledge graph. The duplicate members in the second relative set and the relevant data of the blacklisted users are removed to obtain the graylist data. The graylist data is obtained through the knowledge graph, thereby improving the accuracy and efficiency of obtaining the graylist data, thereby improving the accuracy of obtaining the personal review results.

[0037] In this embodiment, optionally, the personal review result of the applicant is determined based on the application information submitted by the applicant and the applicant data in the knowledge graph, including at least one of the following:

[0038] According to the applicant information and the illegal list data, determine whether the applicant is a member of the illegal list; if so, the personal review result is unqualified;

[0039] According to the applicant information and the credit data, determine whether the applicant's credit data meets the application qualifications; if not, the personal review result is unqualified;

[0040] Based on the applicant information and the personal data, determine whether the applicant information is false data; if so, the personal review result is unqualified.

[0041] Based on the applicant information and illegal list data, determine whether the applicant is a member of the illegal list. If the applicant is a member of the illegal list, the personal review result is unqualified.

[0042] Based on the applicant information and credit data, determine whether the applicant's credit situation meets the application qualifications. For example, if the applicant has a bad credit record due to failure to repay loans or credit cards on time, the personal review result will be unqualified.

[0043] Based on the applicant's information and personal data, determine whether there are obvious changes in the applicant's information compared to the personal data, such as a change in gender, etc. If there is an obvious difference, the applicant's information is judged to be false data, and the personal review result is unqualified.

[0044] By determining the applicant's personal review result based on at least one of the illegal list data, credit data and personal data, the accuracy of personal application results is improved. At the same time, by integrating the applicant's data into the knowledge graph, manual verification of application information with applicant data in different systems is avoided, which reduces the review efficiency.

[0045] Step 120: Determine other members of the group to which the applicant belongs based on the knowledge graph, and determine the group application status based on the application information submitted by the other members.

[0046] Determine other members of the group to which the applicant belongs based on the applicant's relationships in the knowledge graph.

[0047] In this embodiment, optionally, the group related to the applicant includes at least one of an applicant's family group and an applicant's company group.

[0048] The other members of the family group to which the applicant belongs are determined based on the family relationships of the applicant in the knowledge graph, or the other members of the company group to which the applicant belongs are determined based on the colleague relationships of the applicant in the knowledge graph.

[0049] The group application status is determined based on the application information submitted by other members. The group application status is determined based on the application information submitted by group members related to the application type submitted by the applicant.

[0050] In this embodiment, optionally, determining the group application status according to the application information submitted by the other members includes:

[0051] Acquire application information submitted by the other members; wherein the application information submitted by the other members includes the application frequency and application time of the other members;

[0052] Determine whether the application frequency is greater than a preset frequency and whether the application time is within a preset time range;

[0053] If the application frequency is greater than a preset frequency and the application time is within a preset time range, it is determined that the group application status is abnormal.

[0054] If the application frequency is greater than the preset frequency and the application time is within the preset time range, the group application status is abnormal, and other situations are normal.

[0055] Obtain application information submitted by other members; wherein, the application information submitted by other members includes the application frequency and application time of other members. Exemplarily, when the group is an applicant company group, determine the application frequency and application time of other members in the company. When there are company members whose application frequency is greater than the preset frequency within a preset time range, such as seven days, for example, ten applications are submitted, the group application status is determined to be abnormal. Group information that meets the requirements of an application frequency greater than the preset frequency and an application time within the preset time range may also be transmitted to the risk control department, which will further determine whether the group application status is abnormal. This embodiment does not limit this.

[0056] When applying for a credit card, avoid criminals from setting up shell companies and using company employees to frequently apply for credit cards to obtain illegal benefits. Or avoid criminals from frequently applying for credit cards as a family unit to obtain illegal benefits.

[0057] Step 130: Determine the application result of the applicant according to the individual review result of the applicant and the group application status.

[0058] The applicant's final application result will be determined based on the applicant's personal review results and group application status.

[0059] In this embodiment, optionally, determining the application result of the applicant according to the individual review result of the applicant and the group application status includes:

[0060] If the individual review result of the applicant is qualified and the group application status is normal, the application result of the applicant is approved;

[0061] If the individual review result of the applicant is qualified and the group application status is abnormal, the application result of the applicant is approved and the group application status is recorded;

[0062] If the individual review result of the applicant is unqualified and the group application status is normal, the application result of the applicant will be rejected and the individual application status will be recorded;

[0063] If the individual review result of the applicant is unqualified and the group application status is abnormal, the application result of the applicant will be rejected, and the individual application status and group application status will be recorded.

[0064] If the applicant's personal review result is qualified and the group application status is abnormal, the applicant's application result will be approved, which will not affect the applicant's application result, but the group application situation will be recorded in the applicant's risk data for subsequent personal risk control analysis.

[0065] If the applicant's individual review result is unqualified and the group application status is normal, the applicant's application result will be rejected, the applicant can be added to the blacklist, and the individual application situation will be recorded in the group's relevant risk data for subsequent group risk control analysis.

[0066] If the individual review result of the applicant is unqualified and the group application status is abnormal, the applicant's application result will be rejected, and the individual application status and group application status will be recorded. The applicant and the company can be added to the blacklist, and the individual application status and group application status can be recorded in the relevant risk data for subsequent group and individual risk control analysis. By jointly determining the applicant's application result based on the applicant's individual review result and group application status, the ability to prevent group fraud and the accuracy of individual application review are improved.

[0067] The technical solution provided in this embodiment determines the personal review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph; determines other members of the group to which the applicant belongs based on the knowledge graph, and determines the group application status based on the application information submitted by the other members; and determines the application result of the applicant based on the personal review result of the applicant and the group application status, thereby solving the problem that the review only targets the information of a single applicant, making it difficult to discover group fraud related to a single application, thereby reducing the accuracy of the application review, and achieving the effect of improving the efficiency and accuracy of the application review.

[0068] Embodiment 2

[0069] Figure 2 This is a flowchart of an application review method provided in Embodiment 2 of the present invention. This technical solution is to supplement the process before determining the personal review result of the applicant. Compared with the above solution, this solution is specifically optimized to include: before determining the personal review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph, the following is also included:

[0070] By extracting data from the business party's internal data and / or the business party's external data according to a first preset period, the relationship between entities is obtained;

[0071] According to the relationship between the entities, a knowledge graph is determined. Specifically, the flowchart of the application review method is as follows: Figure 2 As shown:

[0072] Step 210: Extract the internal data of the business party and / or the external data of the business party according to a first preset period to obtain the relationship between entities.

[0073] Among them, the business party's internal data refers to the data that can be obtained internally by the business party, such as personal and corporate customer information tables, family relationship tables, credit card product tables, internal blacklist information tables, etc. The business party's external data refers to the data that cannot be obtained internally by the business party and needs to be obtained from the outside, such as credit data, peer blacklist data, etc. Among them, the credit card product table can include information such as card information, credit limit information, currency information, etc.

[0074] Exemplarily, the first preset period may be every day, and the newly added business party internal data and / or business party external data of the day are extracted to obtain entities and the relationships between entities. Exemplary entities may be private customer entities, corporate customer entities, credit card entities, etc., and the relationships between entities may be application relationships, family relationships, work relationships, etc.

[0075] Step 220: Determine a knowledge graph based on the entities and the relationships between entities.

[0076] The initial knowledge graph can be determined based on the entities extracted for the first time and the relationships between the entities, and then data extraction is performed according to the first preset cycle to obtain the relationships between the current entities and entities, and the initial knowledge graph is updated to determine the knowledge graph.

[0077] In this embodiment, optionally, determining a knowledge graph according to the relationship between the entities includes:

[0078] storing the entities and the relationships between the entities in a first storage area;

[0079] adding the relationships between entities in the first storage area to the second storage area according to a second preset period;

[0080] According to entities and relationships between entities in the second storage area, a knowledge graph in the second storage area is determined.

[0081] The acquired entities and the relationships between them will be stored in the first storage area, and the relationships between them will be added to the second storage area every second preset period, such as every day. The first storage area is used to temporarily store the recently acquired entities and the relationships between them, and to record the data acquired at different times for the same entity separately, and to keep them for a certain period of time, such as one week, and then delete them to avoid occupying too much memory. The second storage area is used to store the relationships between all entities, merge the records of the data acquired at different times for the same entity, and generate a knowledge graph. This ensures data synchronization and avoids useless data occupying memory.

[0082] In this embodiment, optionally, the first storage area is a Hive data warehouse, and the second storage area is an Hbase database. Hive is a data warehouse tool based on Hadoop, which is used to extract, transform, and load data. It is a mechanism that can store, query, and analyze large-scale data stored in Hadoop. HBase is a distributed, column-oriented open source database. By combining the Hive data warehouse with the Hbase database, the efficiency of acquiring and storing data is improved.

[0083] Step 230: Determine the personal review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph.

[0084] In this embodiment, optionally, according to the application information submitted by the applicant and the applicant data in the knowledge graph, the personal review result of the applicant is determined, including:

[0085] Determine the applicant data index according to the application information submitted by the applicant;

[0086] According to the applicant data index, obtaining the applicant data in the knowledge graph;

[0087] The individual review result of the applicant is determined based on the application information and the applicant data.

[0088] Among them, according to the application information submitted by the applicant, the applicant data to be obtained is determined, and according to the applicant data index, the corresponding applicant data in the knowledge graph is obtained from the designated storage area, such as the second storage area mentioned above, and then the personal review result of the applicant is determined based on the application information and the applicant data. It avoids the problem of storing all data in the database in the prior art, resulting in a large amount of data and directly accessing the database during query, which reduces the query efficiency, thereby improving the efficiency of obtaining applicant data. It should be noted that in this embodiment, when obtaining data in the knowledge graph, the above scheme can be adopted, not limited to applicant data.

[0089] In this embodiment, the applicant data index is optionally stored in Elasticsearch. Elasticsearch is a Lucene-based search server that provides a distributed multi-user full-text search engine, which improves the stability, reliability and efficiency of applicant data search.

[0090] Step 240: Determine other members of the group to which the applicant belongs based on the knowledge graph, and determine the group application status based on the application information submitted by the other members.

[0091] Step 250: Determine the application result of the applicant according to the individual review result of the applicant and the group application status.

[0092] The embodiment of the present invention extracts the internal data of the business party and / or the external data of the business party according to a first preset period to obtain the relationship between entities, thereby solving the problem of multiple queries caused by the need to verify the application information in sequence according to the information type in the prior art, and improving the efficiency of application review.

[0093] Embodiment 3

[0094] Figure 3 This is a schematic diagram of the structure of an application review device provided in the third embodiment of the present invention. The device can be implemented by hardware and / or software, can execute an application review method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. Figure 3 As shown, the device comprises:

[0095] A personal review result determination module 310 is used to determine the personal review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph;

[0096] A group application status determination module 320, configured to determine other members of the group to which the applicant belongs based on the knowledge graph, and determine the group application status based on the application information submitted by the other members;

[0097] The application result determination module 330 is used to determine the application result of the applicant according to the individual review result of the applicant and the group application status.

[0098] The embodiment of the present invention determines the personal review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph; determines other members of the group to which the applicant belongs based on the knowledge graph, and determines the group application status based on the application information submitted by the other members; determines the application result of the applicant based on the personal review result of the applicant and the group application status, thereby solving the problem that the review only audits the information of a single applicant, making it difficult to discover group fraud related to a single application, thereby reducing the accuracy of the application review, and achieving the effect of improving the efficiency and accuracy of the application review.

[0099] On the basis of the above technical solutions, optionally, the personal review result determination module includes:

[0100] An applicant data index determination unit, used to determine the applicant data index according to the application information submitted by the applicant;

[0101] An applicant data acquisition unit, configured to acquire the applicant data in the knowledge graph according to the applicant data index;

[0102] The personal review result determination unit is used to determine the personal review result of the applicant based on the application information and the applicant data.

[0103] Based on the above technical solutions, optionally, the group application status determination module includes:

[0104] An application information acquisition unit, used to acquire the application information submitted by the other members; wherein the application information submitted by the other members includes the application frequency and application time of the other members;

[0105] An application frequency and time judgment unit, used to judge whether the application frequency is greater than a preset frequency and whether the application time is within a preset time range;

[0106] The group application status determination unit is used to determine that the group application status is abnormal if the application frequency is greater than a preset frequency and the application time is within a preset time range.

[0107] On the basis of the above technical solutions, optionally, the application result determination module includes:

[0108] A first application result determination unit, configured to determine that the application result of the applicant is passed if the individual review result of the applicant is qualified and the group application status is normal;

[0109] A second application result determination unit, configured to determine that if the individual review result of the applicant is qualified and the group application status is abnormal, the application result of the applicant is passed and the group application status is recorded;

[0110] A third application result determination unit, configured to determine that if the individual review result of the applicant is unqualified and the group application status is normal, the application result of the applicant is rejected and the individual application status is recorded;

[0111] The fourth application result determination unit is used to determine if the individual review result of the applicant is unqualified and the group application status is abnormal, then the application result of the applicant is rejected, and the individual application status and the group application status are recorded.

[0112] On the basis of the above technical solutions, optionally, the device further includes:

[0113] An entity relationship acquisition module is used before the individual review result determination module to extract data from the business party's internal data and / or the business party's external data according to a first preset period to acquire the relationship between entities;

[0114] The knowledge graph determination module is used to determine the knowledge graph based on the entities and the relationships between the entities.

[0115] On the basis of the above technical solutions, optionally, the knowledge graph determination module includes:

[0116] A first storage area storage unit, used to store the entities and the relationships between the entities in a first storage area;

[0117] a second storage area adding unit, configured to add the relationships between entities in the first storage area to the second storage area according to a second preset period;

[0118] A knowledge graph determination unit is used to determine the knowledge graph in the second storage area based on the entities and the relationships between the entities in the second storage area.

[0119] Based on the above technical solutions, optionally, the first storage area is a Hive data warehouse, and the second storage area is an Hbase database.

[0120] Based on the above technical solutions, optionally, the applicant data includes:

[0121] At least one of illegal list data, credit data and personal data; wherein the illegal list data includes blacklist data and grey list data.

[0122] On the basis of the above technical solutions, optionally, the personal review result determination module includes at least one of the following:

[0123] A first individual audit result determination unit is used to determine whether the applicant is a member of the illegal list based on the applicant information and the illegal list data; if so, the individual audit result is unqualified;

[0124] A second individual review result determination unit is used to determine whether the applicant's credit data meets the application qualifications based on the applicant information and the credit data; if not, the individual review result is unqualified;

[0125] The third individual review result determination unit is used to determine whether the applicant information is false data based on the applicant information and the individual data; if so, the individual review result is unqualified.

[0126] Based on the above technical solutions, the optional grey list data acquisition module includes:

[0127] A first relative set determining unit, configured to determine a first relative set according to the blacklist data and the family relationships in the knowledge graph;

[0128] A second relative set determining unit, configured to determine a second relative set according to the first relative set and the family relationship in the knowledge graph;

[0129] The grey list data acquisition unit is used to acquire the grey list data by performing a deduplication operation on the second relative set.

[0130] On the basis of the above-mentioned technical solutions, optionally, the group related to the applicant includes at least one of the applicant's family group and the applicant's company group.

[0131] Based on the above technical solutions, optionally, the applicant data index is stored in Elasticsearch.

[0132] Embodiment 4

[0133] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention is shown in FIG. Figure 4 As shown, the electronic device includes a processor 40, a memory 41, an input device 42 and an output device 43; the number of processors 40 in the electronic device can be one or more. Figure 4 A processor 40 is taken as an example; the processor 40, the memory 41, the input device 42 and the output device 43 in the electronic device can be connected by a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0134] The memory 41 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the application review method in the embodiment of the present invention. The processor 40 executes various functional applications and data processing of the electronic device by running the software programs, instructions and modules stored in the memory 41, that is, implements the above-mentioned application review method.

[0135] The memory 71 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 71 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 71 may further include a memory remotely arranged relative to the processor 70, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0136] Embodiment 5

[0137] Embodiment 5 of the present invention further provides a storage medium including computer executable instructions, wherein the computer executable instructions are used to execute an application review method when executed by a computer processor, the method comprising:

[0138] Determine the individual review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph;

[0139] Determine other members of the group to which the applicant belongs based on the knowledge graph, and determine the group application status based on the application information submitted by the other members;

[0140] The application result of the applicant is determined based on the individual review result of the applicant and the group application status.

[0141] Of course, the computer executable instructions of a storage medium containing computer executable instructions provided by an embodiment of the present invention are not limited to the method operations described above, and can also execute related operations in the application review method provided by any embodiment of the present invention.

[0142] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0143] It is worth noting that in the embodiment of the above-mentioned application review device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0144] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An application review method, characterized in that: include: Determine the individual review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph; Determine other members of the group to which the applicant belongs based on the knowledge graph, and determine the group application status based on the application information submitted by the other members; Determine the application result of the applicant according to the individual review result of the applicant and the group application status; Wherein, the applicant data includes at least one of illegal list data, credit data and personal data; wherein, the illegal list data includes blacklist data and grey list data; Wherein, obtaining the grey list data includes: Determine a first relative set according to the blacklist data and the family relationships in the knowledge graph; Determine a second relative set according to the first relative set and the family relationship in the knowledge graph; Obtaining the gray list data by performing a deduplication operation on the second relative set; Wherein, determining the group application status according to the application information submitted by the other members includes: Acquire application information submitted by the other members; wherein the application information submitted by the other members includes application frequency and application time of the other members; Determine whether the application frequency is greater than a preset frequency and whether the application time is within a preset time range; If the application frequency is greater than a preset frequency and the application time is within a preset time range, it is determined that the group application status is abnormal.

2. The method according to claim 1, characterized in that Based on the application information submitted by the applicant and the applicant data in the knowledge graph, determine the individual review result of the applicant, including: Determine the applicant data index according to the application information submitted by the applicant; According to the applicant data index, obtaining the applicant data in the knowledge graph; The individual review result of the applicant is determined based on the application information and the applicant data.

3. The method according to claim 1, characterized in that Determine the applicant's application result based on the applicant's individual review result and the group application status, including: If the individual review result of the applicant is qualified and the group application status is normal, the application result of the applicant is approved; If the individual review result of the applicant is qualified and the group application status is abnormal, the application result of the applicant is approved and the group application status is recorded; If the individual review result of the applicant is unqualified and the group application status is normal, the application result of the applicant will be rejected and the individual application status will be recorded; If the individual review result of the applicant is unqualified and the group application status is abnormal, the application result of the applicant will be rejected, and the individual application status and group application status will be recorded.

4. The method according to claim 1, characterized in that Before determining the individual review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph, it also includes: By extracting data from the business party's internal data and / or the business party's external data according to a first preset period, the relationship between entities is obtained; A knowledge graph is determined based on the entities and the relationships between them.

5. The method according to claim 4, characterized in that According to the entities and the relationships between the entities, a knowledge graph is determined, including: storing the entities and the relationships between the entities in a first storage area; adding the relationships between entities in the first storage area to the second storage area according to a second preset period; According to entities and relationships between entities in the second storage area, a knowledge graph in the second storage area is determined.

6. The method according to claim 5, characterized in that The first storage area is a Hive data warehouse, and the second storage area is an Hbase database.

7. The method according to claim 1, characterized in that Determine the personal review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph, including at least one of the following: According to the applicant information and the illegal list data, determine whether the applicant is a member of the illegal list; if so, the personal review result is unqualified; According to the applicant information and the credit data, determine whether the applicant's credit data meets the application qualifications; if not, the personal review result is unqualified; Determining whether the applicant information is false data based on the applicant information and the personal data; If so, the individual review result is unqualified.

8. The method according to claim 1, characterized in that: The group related to the applicant includes at least one of the applicant's family group and the applicant's company group.

9. The method according to claim 1, characterized in that: The applicant data index is stored in Elasticsearch.

10. An application review device, characterized in that: include: A personal review result determination module, used to determine the personal review result of the applicant based on the application information submitted by the applicant and the applicant data in the knowledge graph; A group application status determination module, used to determine other members of the group to which the applicant belongs based on the knowledge graph, and determine the group application status based on the application information submitted by the other members; An application result determination module, used to determine the application result of the applicant according to the individual review result of the applicant and the group application status; Wherein, the applicant data includes at least one of illegal list data, credit data and personal data; wherein, the illegal list data includes blacklist data and grey list data; Among them, the grey list data acquisition module includes: A first relative set determining unit, configured to determine a first relative set according to the blacklist data and the family relationships in the knowledge graph; A second relative set determining unit, configured to determine a second relative set according to the first relative set and the family relationship in the knowledge graph; A grey list data acquisition unit, configured to acquire the grey list data by performing a deduplication operation on the second relative set; Wherein, the group application status determination module includes: An application information acquisition unit, used to acquire the application information submitted by the other members; wherein the application information submitted by the other members includes the application frequency and application time of the other members; An application frequency and time judgment unit, used to judge whether the application frequency is greater than a preset frequency and whether the application time is within a preset time range; The group application status determination unit is used to determine that the group application status is abnormal if the application frequency is greater than a preset frequency and the application time is within a preset time range.

11. The device according to claim 10, characterized in that The individual audit result determination module includes: An applicant data index determination unit, used to determine the applicant data index according to the application information submitted by the applicant; An applicant data acquisition unit, configured to acquire the applicant data in the knowledge graph according to the applicant data index; The personal review result determination unit is used to determine the personal review result of the applicant based on the application information and the applicant data.

12. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the application review method as described in any one of claims 1-9.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the application review method as described in any one of claims 1 to 9 is implemented.

Images