CN111429255B - Risk assessment method, apparatus, device and storage medium - Google Patents
Risk assessment method, apparatus, device and storage medium Download PDFInfo
- Publication number
- CN111429255B CN111429255B CN202010196148.2A CN202010196148A CN111429255B CN 111429255 B CN111429255 B CN 111429255B CN 202010196148 A CN202010196148 A CN 202010196148A CN 111429255 B CN111429255 B CN 111429255B
- Authority
- CN
- China
- Prior art keywords
- risk
- target
- risk assessment
- data
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 308
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012512 characterization method Methods 0.000 claims abstract description 149
- 238000011156 evaluation Methods 0.000 claims description 46
- 210000000056 organ Anatomy 0.000 claims description 21
- 230000008014 freezing Effects 0.000 claims description 11
- 238000007710 freezing Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 6
- 238000011002 quantification Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 230000003287 optical effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000013500 data storage Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000010200 validation analysis Methods 0.000 description 3
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a risk assessment method, a risk assessment device, risk assessment equipment and a storage medium, wherein the risk assessment method comprises the following steps: establishing a knowledge graph of a target client and a right authority, wherein the target client comprises a target enterprise and/or a target individual; determining target risk characterization data of a target client according to the knowledge graph and a preset risk assessment index system, wherein the preset risk assessment index system is determined based on the knowledge graph; and carrying out risk assessment on the target client according to the target risk characterization data to obtain a target risk assessment result of the target client. The technical scheme of the embodiment of the invention improves the accuracy of the customer risk assessment.
Description
Technical Field
The embodiment of the invention relates to the technical field of risk assessment, in particular to a risk assessment method, a risk assessment device, a risk assessment terminal and a risk assessment storage medium.
Background
Financial institutions (e.g., banks) need to perform risk assessment of their customers, particularly those that are judicially checked for freezing by a right authority, to avoid unnecessary losses.
At present, a banking system carries out risk assessment on judicial clients looking up the freezing knot, the risk of the clients involved in a case is identified mainly through a sample training model method, the quality comparison of the model depends on the quality of sample data, and if the sample data is selected improperly, the accuracy of risk assessment is greatly reduced.
Disclosure of Invention
The invention provides a risk assessment method, a risk assessment device, a risk assessment terminal and a risk assessment storage medium, which improve the accuracy of customer risk assessment.
In a first aspect, an embodiment of the present invention provides a risk assessment method, where the method includes:
establishing a knowledge graph of a target client and a right authority, wherein the target client comprises a target enterprise and/or a target individual;
determining target risk characterization data of a target client according to the knowledge graph and a preset risk assessment index system, wherein the preset risk assessment index system is determined based on the knowledge graph;
and carrying out risk assessment on the target client according to the target risk characterization data to obtain a target risk assessment result of the target client.
In a second aspect, an embodiment of the present invention further provides a risk assessment apparatus, where the apparatus includes:
the knowledge graph establishing module is used for establishing knowledge graphs of target clients and authorized institutions, wherein the target clients comprise target enterprises and/or target individuals;
the target risk representation data determining module is used for determining target risk representation data of a target client according to the knowledge graph and a preset risk assessment index system, wherein the preset risk assessment index system is determined based on the knowledge graph;
And the target risk assessment result determining module is used for carrying out risk assessment on the target client according to the target risk representation data to obtain a target risk assessment result of the target client.
In a third aspect, an embodiment of the present invention further provides a computer apparatus, including:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the risk assessment method according to any of the embodiments of the present invention.
In a fourth aspect, embodiments of the present invention further provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a risk assessment method according to any of the embodiments of the present invention.
According to the embodiment of the invention, the knowledge graph of the target clients and the authorized authorities is established, and the target clients comprise target enterprises and/or target individuals; determining target risk characterization data of a target client according to the knowledge graph and a preset risk assessment index system, wherein the preset risk assessment index system is determined based on the knowledge graph; according to the target risk characterization data, performing risk assessment on the target client to obtain a target risk assessment result of the target client, overcoming the defect of low risk assessment accuracy caused by improper sample data selection when the risk of the financial crime related case of the client is identified through a sample training model method, and improving the accuracy of the risk assessment of the client.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a risk assessment method according to a first embodiment of the present invention;
FIG. 2 is a flow chart of a risk assessment method according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram of a risk assessment apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device in a fourth embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Example 1
Fig. 1 is a flowchart of a risk assessment method according to an embodiment of the present invention, where the method may be implemented by a risk assessment device, and the device may be implemented in software and/or hardware, and the device may be configured in a computer device. As shown in fig. 1, the method in this embodiment specifically includes:
s110, establishing a knowledge graph of a target client and a right authority, wherein the target client comprises a target enterprise and/or a target individual.
Knowledge graph nature is a semantic network that describes objective things in a graph consisting of nodes and edges. Nodes in the knowledge graph represent entities and concepts, wherein the entities can be concrete things, and the concepts can be abstract things; edges in the knowledge graph represent relationships and attributes of things, where the relationships may be external connections to the things and the attributes may be internal features of the things. In general, a simplified description is generally performed on a knowledge graph, that is, an entity and a concept are collectively referred to as an entity, and a relationship and an attribute are collectively referred to as a relationship, that is, the knowledge graph is used to describe a relationship between entities. The entity may be a person, a place, an organization, a concept, etc., and the relationship may be more various, such as a relationship between persons, a relationship between a person and an organization, a relationship between a concept and an object, etc.
The target customer is an enterprise or individual who opens accounts in the relevant financial institution system, for example, the financial institution may include a bank or the like. The authority refers to a judicial authority, an administrative authority, a military authority, and a business entity that performs administrative functions, which have the authority to inquire, freeze, withhold the deposit of an enterprise or person at a financial institution, in accordance with the clear regulations of laws and administrative laws. The authority may include 14 authorities and departments such as public security, national security, inspection, court, tax, customs, army guard, prison, smuggling crime investigation, supervision, army supervision, audit, business administration, securities administration, etc. as specified by the current law and administrative laws. . When a target enterprise or a target person possibly has a problem related to a financial crime-related case, the authority is entitled to perform operations such as inquiring, freezing, deducting and the like on a corresponding target enterprise account or target personal account, and at this time, an association relationship exists between the authority and the target enterprise or the target person. There may also be an association relationship between the target enterprise and the target enterprise, for example, the target enterprise a is a subsidiary of the target enterprise B, or the target enterprise a is a branch office of the target enterprise B, or the target enterprise a and the target enterprise B have a cooperative relationship, and so on. There may also be an association between the target enterprise and the target person, for example, target person a is a legal representative of target enterprise a, or target person a is a senior manager (e.g., may be a manager, a secondary manager, etc.) of target enterprise a. There may also be an association between the target person and the target person, for example, there is a blood relationship between the target person a and the target person b, or there is a couple relationship between the target person a and the target person b, or the like.
In this embodiment, the entity in the knowledge graph may be preferably a target enterprise, a target individual, a right authority, and the like, and the relationship in the knowledge graph may be preferably an association relationship between any two of the target enterprise, the target individual, and the right authority.
Preferably, establishing a knowledge graph of the target client and the authority includes:
acquiring target customer data and authority data from a target database;
determining the association relationship among the target enterprise, the target individual and the authorized organ and the entity attribute of the target client and the authorized organ according to the target client data and the authorized organ data;
and establishing a knowledge graph according to the association relation and the entity attribute.
The target database may include a data storage database in a financial institution system, an enterprise business database, a public security agency database, etc., for example, the data storage database in the financial institution system may be a data storage database of a banking system. The target customer data may include the name and unified credit code of the target business, the name, identity document type, and identity document number of the target individual, the association between target customers, and the like. The rights authority data may include names and types of rights authorities, etc. Preferably, the name and the unified credit code of the target enterprise and the association relationship between the target clients, for example, the association relationship between the target enterprise and the target enterprise, the association relationship between the target enterprise and the target person, and the like, may be obtained from an enterprise business database. The name, identity document type and identity document number of the target person, the association relationship between the target person and the target person, and the like can be obtained from the public security authority database. Target enterprise account data and/or target personal account data, authority data, association relation of target clients and authority and the like can be obtained from a data storage database of the banking system.
After the target client data and the authorized organ data are obtained, the association relation among the target enterprise, the target individual and the authorized organ and the entity attribute of the target client and the authorized organ can be determined according to the target client data and the authorized organ data, and the knowledge graph related to the target client, the target individual and the authorized organ can be established according to the association relation and the entity attribute.
By way of example, the entities may include target enterprises, target individuals, and rights authorities; the entity attributes may include a target business attribute including a business name and a unified credit code, a target person attribute including a target person name, an identity document type, and an identity document number, and a rights authority attribute including a rights authority name and type. The association between the target enterprise, the target individual, and the authority may include a legal representative of the target enterprise as the target individual, a senior manager of the target enterprise as the target individual, a branch of the target enterprise as the target enterprise, a subsidiary of the target enterprise as the target enterprise, the authority querying the target individual, the authority freezing the target individual, the authority detaining the target individual, the authority querying the target customer, the authority freezing the target customer, the authority detaining the target customer, and the like.
S120, determining target risk characterization data of a target client according to the knowledge graph and a preset risk assessment index system, wherein the preset risk assessment index system is determined based on the knowledge graph.
In this embodiment, the risk refers to a risk of a target enterprise or a target individual related to a financial crime case (hereinafter referred to as a case related risk), and the preset risk assessment index system is used for assessing the level of the case related risk of the target enterprise or the target individual. The preset risk assessment index system may include a preset risk assessment index and index risk characterization data corresponding to the preset risk assessment index, where the risk assessment index may be various factors that cause a target enterprise or a target individual to have a case-related risk. The case-related risk corresponding to the risk assessment index determines corresponding index risk representation data, and the same can be effectively reflected by the index risk representation data. Taking the index risk characterization data as an example of the risk score corresponding to the corresponding risk assessment index, if the case-related risk corresponding to the risk assessment index is high, the risk score corresponding to the risk assessment index is high, and if the case-related risk corresponding to the risk assessment index is low, the risk score corresponding to the risk assessment index is low. It should be noted that the risk score may be set according to practical situations, and is not limited herein.
The target risk representation data of the target client can be determined based on the preset risk assessment index in the preset risk assessment index system and the index risk representation data corresponding to the preset risk assessment index by a four-rule operation method. The target risk characterization data can be used for characterizing the case-related risk of the target client.
Preferably, before determining the target risk characterization data of the target client according to the knowledge graph and the preset risk assessment index system, the method further comprises:
and determining a preset risk assessment index system based on the association relationship among the target enterprise, the target individual and the authorized organ in the knowledge graph.
In this embodiment, a preset risk assessment index system may be determined based on the knowledge graph, and specifically, risk assessment indexes in the preset risk assessment index system may be determined according to various association relations in the knowledge graph. Since various associations may exist among the target enterprise, the target individual, and the authorized entity, the risk assessment index may include a plurality of items, for example, a case-related type (e.g., civil and criminal, etc.) of the target client, a type of instruction executed by the authorized entity in association with the target client, a target enterprise or target individual in association with the target client, and the like.
Taking a target enterprise as an example, risk assessment indicators that may cause the target enterprise to be at risk for a case may include the target enterprise itself, a legal representative of the target enterprise, a senior manager of the target enterprise, a branch office of the target enterprise, a child of the target enterprise, criminal cases related to the target enterprise, civil cases related to the target enterprise, one or more operations of querying, freezing, and withholding performed by a authority were accepted by the target enterprise, and the like.
And S130, performing risk assessment on the target client according to the target risk characterization data to obtain a target risk assessment result of the target client.
The target risk assessment result may be that the target client has risk or does not have risk, or that the target client has low risk or has high risk, or may be a risk level of the target client, etc.
If the target risk assessment result is that the target client has low risk or high risk, performing risk assessment on the target client according to the target risk characterization data, which may be to preset a target risk characterization data threshold, comparing the target risk characterization data with the target risk characterization data threshold, if the target risk characterization data is lower than the target risk characterization data threshold, determining that the target client has low risk, and if the target risk characterization data is higher than the target risk characterization data threshold, determining that the target risk assessment result is that the target client has high risk.
If the target risk assessment result is the risk level of the target client, performing risk assessment on the target client according to the target risk characterization data, namely performing grading on possible risk characterization data in advance, so as to obtain a preset corresponding relation table between the risk level and the risk characterization data. And comparing the target risk representation data with a preset corresponding relation table to obtain a risk grade corresponding to the target risk representation data. For example, the possible risk characterization data is a value in the range of 0-100, the possible risk characterization data is graded to obtain a preset corresponding relation table between the risk grade and the risk characterization data, the preset corresponding relation table may be that the risk characterization data is 0-20 corresponding to a first-level risk, the risk characterization data is 21-40 corresponding to a second-level risk, the risk characterization data is 41-60 corresponding to a third-level risk, the risk characterization data is 61-80 corresponding to a fourth-level risk, and the risk characterization data is 81-100 corresponding to a fifth-level risk. If the target risk representation data is 88, the preset corresponding relation table can determine that the risk level corresponding to the target risk representation data is five-level risk, that is, the target risk assessment result of the target client is five-level risk.
According to the risk assessment method provided by the embodiment, a knowledge graph of a target client and a right authority is established, and the target client comprises a target enterprise and/or a target individual; determining target risk characterization data of a target client according to the knowledge graph and a preset risk assessment index system, wherein the preset risk assessment index system is determined based on the knowledge graph; according to the target risk characterization data, performing risk assessment on the target client to obtain a target risk assessment result of the target client, overcoming the defect of low risk assessment accuracy caused by improper sample data selection when the risk of the financial crime related case of the client is identified through a sample training model method, and improving the accuracy of the risk assessment of the client.
Example two
Fig. 2 is a flowchart of a risk assessment method according to a second embodiment of the present invention. Based on the above embodiments, the determining the preset risk assessment index system according to the association relationship among the target enterprise, the target individual and the authorized authority in the knowledge graph includes:
determining a risk assessment index in a preset risk assessment index system according to the association relationship among the target enterprise, the target individual and the authorized authorities in the knowledge graph;
determining a risk influence weight determining rule corresponding to the risk assessment index;
performing risk quantification on the risk assessment index to obtain initial risk characterization data corresponding to the risk assessment index;
the preset risk assessment index system comprises a risk assessment index, a risk influence weight determining rule and initial risk representation data.
And determining target risk characterization data of the target client according to the knowledge graph and a preset risk assessment index system, wherein the target risk characterization data comprises:
determining a risk influence weight corresponding to each risk assessment index according to a risk influence weight determining rule;
determining risk assessment index characterization data corresponding to each risk assessment index according to each risk influence weight and corresponding initial risk characterization data;
Based on each risk assessment indicator characterization data, target risk characterization data for the target customer is determined.
As shown in fig. 2, the method in this embodiment specifically includes:
s210, establishing a knowledge graph of a target client and a right authority, wherein the target client comprises a target enterprise and/or a target individual.
S220, determining a risk assessment index in a preset risk assessment index system according to the association relationship among the target enterprise, the target individual and the authorized authorities in the knowledge graph.
By way of example, the risk assessment indicator may include a case-related type of the target client, a type of instructions executed by a rights authority in association with the target client, a target enterprise or target individual in association with the target client, and so forth. The crime related type may include a specific crime related type, an uncertain crime or civil type, and the like, wherein the specific crime related type refers to an instruction source being a public security department and a characteristic description conforming to ten kinds of case types, the specific crime related type refers to an instruction source being a court and being recognized as a civil case type, the uncertain crime or civil type refers to an uncertainty not conforming to a specific crime related type and a specific civil case type, and the instruction source being an authorized authority other than public security and court.
The instruction types may include inquiry, freezing, withholding, and the like, and if the target client is a target enterprise, the risk assessment index may further include a legal representative of the target enterprise, an advanced manager, a branch office, and a subsidiary, and if the target client is a target individual, the risk assessment index may further include a target individual having a couple relationship or blood relationship with the target individual, the target individual being a target enterprise represented by the legal representative, the target individual being a target enterprise of the advanced manager, and the like.
S230, determining a risk influence weight determining rule corresponding to the risk assessment index.
In this embodiment, the risk assessment index system may further include a risk impact weight determining rule. Different risk assessment indexes can correspond to different risk influence weights, and the same risk assessment index can also correspond to different risk influence weights under different conditions. For example, if the risk assessment indicator is an instruction type, the risk impact weight determining rule may be determined according to an effective time and/or an ineffective time corresponding to the instruction type, if the risk assessment indicator is a legal representative or an advanced manager, the risk impact weight determining rule may be determined according to a six-degree relationship theory, and a case-related enterprise served or being served by the legal representative or the advanced manager, and if the risk assessment indicator is a branch office or a subsidiary, the risk impact weight determining rule may be determined according to an actual relevance of the branch office or the subsidiary to the target client. It should be noted that, if the risk impact of the risk assessment index on the target client does not change with time, environment, or any other situation, the risk impact weight determination rule may set the risk impact weight to 1. For example, if the risk assessment indicator is a case-related type of the target client, the risk impact weight corresponding to the case-related type may be set to 1.
S240, risk quantification is carried out on the risk assessment indexes, and initial risk representation data corresponding to the risk assessment indexes are obtained.
In this embodiment, the risk assessment index system may further include initial risk characterization data. The initial risk characterization data may be determined according to actual conditions, and is not particularly limited herein. It can be appreciated that if the risk assessment index is determined to have a smaller influence on the case-related risk of the target client, the initial risk characterization data is smaller, and if the risk assessment index is determined to have a larger influence on the case-related risk of the target client, the initial risk characterization data is larger. For example, if the risk assessment indicator is specifically related to a criminal case type, the initial risk characterization data corresponding to the risk assessment indicator may preferably be larger than the initial risk characterization data corresponding to the risk assessment indicator being specifically related to a civil case type.
S250, determining the risk influence weight corresponding to each risk assessment index according to the risk influence weight determining rule.
According to the risk influence weight determining rule and the value corresponding to the variable in the risk influence weight determining rule determined according to the actual situation, the risk influence weight corresponding to each risk assessment index can be determined.
S260, determining the risk assessment index characterization data corresponding to each risk assessment index according to each risk influence weight and the corresponding initial risk characterization data.
Preferably, the risk impact weight and the corresponding initial risk characterization data may be multiplied to determine risk assessment indicator characterization data corresponding to each risk assessment indicator.
S270, determining target risk characterization data of the target client based on each risk assessment index characterization data.
And determining target risk characterization data of the target client by using a four-rule operation method according to the relation between each risk assessment index. For example, the risk assessment index may include a case-related type of the target client, a type of instruction executed by a right authority having an association relationship with the target client, a target enterprise or a target individual having an association relationship with the target client, and the like, and the target risk characterization data may include instruction characterization data and enterprise business characterization data, where the instruction risk score may be a product between the case-related type characterization data and the instruction type characterization data, and the enterprise business characterization data may be characterization data corresponding to the target enterprise or the target individual having the association relationship with the target client, for example, legal representation characterization data, advanced manager characterization data, branch office characterization data, and sub-company characterization data, and the like.
And S280, performing risk assessment on the target client according to the target risk characterization data to obtain a target risk assessment result of the target client.
Table 1 is a preset risk assessment index system in this embodiment, where the preset risk assessment index system may include a risk assessment index, a risk impact weight determination rule, and initial risk characterization data. It should be noted that, in the preset risk assessment index system in table 1, the risk impact weight determining rule and the initial risk characterization data may be adjusted according to actual situations, which is only an example in the embodiment and cannot play a limiting role.
As shown in table 1, the risk impact weight determination rule corresponding to the risk assessment index "query" is (730+the instruction validation date-system date)/730, which takes two years (365×2) as a term, if the instruction validation date is more than two years away from the current system time, the instruction can be considered to have no impact on the final target risk assessment result, if the instruction validation date is not more than two years away from the current system time, the instruction can be considered to have an impact on the final target risk assessment result, and the closer the instruction is to the current system time, the greater the impact on the final target risk assessment result is, which is expressed as the corresponding risk impact weight is greater.
The risk impact weight determination rule corresponding to the risk assessment index "scratch" is that the risk weight is (1826+the effective date of the instruction—the system date)/1826, which takes five years (365×4+366) as a term, if the effective date of the instruction is more than five years away from the current system time, the instruction can be considered to have no impact on the final target risk assessment result, if the effective date of the instruction is not more than five years away from the current system time, the instruction can be considered to have an impact on the final target risk assessment result, and the closer the instruction is to the current system time, the greater the impact on the final target risk assessment result is, which is expressed as the corresponding risk impact weight is greater.
The risk evaluation index "legal representative" corresponds to a risk impact weight determination rule that if a legal representative relationship exists for a public customer, the risk weight is (6-relationship hierarchy)/5. It means that if the legal representative is the "relationship hierarchy" level legal representative of other involved enterprises, the risk weight thereof may be (6-relationship hierarchy)/5, wherein the relationship hierarchy may include 0, 1, 2, 3, 4, 5, 6.
The risk influence weight determination rule corresponding to the risk assessment index of 'high-level manager' is that if a high-level relationship exists with a public customer, the risk weight is (6-relationship level)/5. It means that if the legal person represents the "relationship hierarchy" level high-level manager of other involved enterprises, the risk weight may be (6-relationship hierarchy)/5, where the relationship hierarchy may include 0, 1, 2, 3, 4, 5, and 6.
TABLE 1 preset Risk assessment index System
Taking a preset risk assessment index system in table 1 as an example, a solving process of the risk assessment index characterization data corresponding to the risk assessment index is specifically described below:
the risk evaluation index is characterized in that the risk evaluation index characterization data corresponding to crime is 1×10=10, the risk evaluation index characterization data corresponding to civil case is 1×1=1, and the risk evaluation index characterization data corresponding to uncertain crime or civil case is 1×2=2. The risk assessment index "inquires" about the corresponding instruction effective date-system effective date= -365 (i.e. distance from system time), then its corresponding risk impact weight= (730-365)/730=0.5, and then the risk assessment index characterization data corresponding to the risk assessment index "inquires" about 0.5×10=5. And if the effective date of the instruction corresponding to the risk assessment index freezing is not more than the system date and the failure date is not less than the system date, the characterization data of the risk assessment index corresponding to the risk assessment index freezing is 5. The risk evaluation index characterization data corresponding to the risk evaluation index "snap" is 0.8x10=8, if the corresponding risk impact weight= (1826-365)/1826=0.8 is the instruction effective date-system effective date= -365 (i.e. the distance from the system time). The risk evaluation index "legal representative" corresponds to a relationship level of 3, and if the corresponding risk influence weight= (6-3)/5=0.6, the risk evaluation index "legal representative" corresponds to a risk evaluation index characterization data of 0.6x10=6. The corresponding relation level of the risk assessment index of the high-level manager is 3, the corresponding risk influence weight of the risk assessment index is= (6-3)/5=0.6, and the corresponding risk assessment index characterization data of the risk assessment index of the legal representative is 0.6x10=6. Risk assessment index "branch" corresponds to branch risk characterization data=self risk characterization data 10+its branch risk characterization data 16×0.5=18, and then risk assessment index "branch" corresponds to risk assessment index characterization data of 0.5×18=9. If the risk evaluation index "subsidiary" corresponds to the subsidiary risk characterization data=self risk characterization data 20+its subsidiary risk characterization data 12×0.5=26, the risk evaluation index characterization data corresponding to the risk evaluation index "subsidiary" is 0.5×26=13. In a specific embodiment, if the target client is a target enterprise and the crime-related type is explicitly related to crime, and the instruction type includes query, freeze and withhold, then the target risk characterization data=risk assessment index "explicitly related to crime" corresponding to risk assessment index characterization data 10×risk assessment index "query" corresponding to risk assessment index characterization data 5+ risk assessment index "explicitly related to crime" corresponding to risk assessment index characterization data 10×risk assessment index "freeze" corresponding to risk assessment index characterization data 5+ risk assessment index "explicitly related to crime" corresponding to risk assessment index characterization data 10×risk assessment index "withhold" corresponding to crime risk assessment index characterization data 8+ risk assessment index "legal representative" corresponding to risk assessment index characterization data 6+ risk assessment index "branch office" corresponding to risk assessment index characterization data 9+ risk assessment index "sub-company" corresponding to risk assessment index=13+.
If the target risk representation data threshold is preset to be 200, the target risk representation data is lower than the target risk representation data threshold 200, the target risk assessment result is determined that the target client has low risk, and if the target risk representation data is higher than the target risk representation data threshold 200, the target risk assessment result is determined that the target client has high risk. In this example, the target risk characterization data is 214, and if the target risk characterization data 214 is higher than the target risk characterization data threshold 200, it may be determined that the target customer has a high risk.
According to the risk assessment method provided by the embodiment, a knowledge graph of a target client and a right authority is established, and the target client comprises a target enterprise and/or a target individual; determining a risk assessment index in a preset risk assessment index system according to the association relationship among the target enterprise, the target individual and the authorized authorities in the knowledge graph; determining a risk influence weight determining rule corresponding to the risk assessment index; carrying out risk quantification on the risk assessment index to obtain initial risk characterization data corresponding to the risk assessment index; the preset risk assessment index system comprises a risk assessment index, a risk influence weight determining rule and initial risk representation data; determining a risk influence weight corresponding to each risk assessment index according to a risk influence weight determining rule; determining risk assessment index characterization data corresponding to each risk assessment index according to each risk influence weight and corresponding initial risk characterization data; determining target risk characterization data of the target client based on each risk assessment indicator characterization data; according to the target risk characterization data, carrying out risk assessment on the target client to obtain a target risk assessment result of the target client, overcoming the defect of low risk assessment accuracy caused by improper sample data selection when the risk of the financial crime related case of the client is identified through a sample training model method, and further improving the accuracy of the risk assessment of the client.
Based on the above embodiments, further, after performing risk assessment on the target client according to the target risk characterization data to obtain a target risk assessment result, the method further includes:
based on a preset evaluation index, determining evaluation index characterization data corresponding to a preset risk evaluation index system according to the received actual risk evaluation result and target risk evaluation result of the target client;
the preset evaluation index includes any one of Precision, recall and F1-score (F1 value). The preset evaluation index Precision refers to a ratio between the data of the positive example evaluated correctly and the data evaluated as the positive example. By way of example, by using the method in this embodiment to perform risk assessment on each target client, the number of assessments of the target clients with low risk or without risk (i.e., the data assessed as positive examples) is 100, the target risk assessment results corresponding to these target clients are compared with the actual risk assessment results of the corresponding target clients, and if the actual number of target clients with correct assessment (i.e., the data assessed as correct positive examples) is 98, the Precision characterization data corresponding to the preset risk assessment index system is 98/100=0.98. The preset evaluation index Recall refers to the ratio between the data evaluated as positive examples and the data actually as positive examples. For example, by using the method in this embodiment to perform risk assessment on each target client, the number of assessed low-risk or non-risk target clients is 100, and according to the received actual risk assessment result of the target clients, it is determined that the actual number of target clients actually having low risk or non-risk is 104, and then it is determined that Recall characterization data corresponding to the preset risk assessment index system is 100/104=0.96. The preset evaluation index F1-score comprehensively considers the indexes of precision and recovery. In the case of multi-category classification, it includes both macro-average (macro-average) and micro-average (micro-average).
And if the evaluation index characterization data accords with the preset adjustment conditions, adjusting the risk influence weight determination rule and/or the initial risk characterization data.
Preferably, if the evaluation index characterization data is lower than the preset evaluation index characterization data threshold, the risk impact weight determination rule and/or the initial risk characterization data may be adjusted. The adjusting mode may be to automatically adjust the risk influence weight determining rule and the initial risk characterization data according to a preset adjusting rule, or manually adjust the risk influence weight determining rule and the initial risk characterization data.
Example III
Fig. 3 is a schematic structural diagram of a risk assessment apparatus according to a third embodiment of the present invention. As shown in fig. 3, the apparatus of this embodiment includes:
a knowledge graph creation module 310, configured to create a knowledge graph of a target client and a right authority, where the target client includes a target enterprise and/or a target individual;
the target risk characterization data determining module 320 is configured to determine target risk characterization data of a target client according to a knowledge graph and a preset risk assessment index system, where the preset risk assessment index system is determined based on the knowledge graph;
the target risk assessment result determining module 330 is configured to perform risk assessment on the target client according to the target risk characterization data, so as to obtain a target risk assessment result of the target client.
The risk assessment device provided by the embodiment establishes a knowledge graph of a target client and a right authority by utilizing a knowledge graph establishing module, wherein the target client comprises a target enterprise and/or a target individual; determining target risk characterization data of a target client by using a target risk characterization data determination module according to the knowledge graph and a preset risk assessment index system, wherein the preset risk assessment index system is determined based on the knowledge graph; the target risk assessment result determining module is used for carrying out risk assessment on the target client according to the target risk representation data to obtain a target risk assessment result of the target client, so that the defect of low risk assessment accuracy caused by improper sample data selection when the risk of the financial crime related case is identified by a sample training model method is overcome, and the accuracy of the risk assessment of the client is improved.
Based on the above technical solutions, optionally, the knowledge graph building module 310 may specifically include:
the data acquisition unit is used for acquiring target client data and right authority data from a target database;
the entity attribute determining unit is used for determining the association relationship among the target enterprise, the target personal and the authorized organ and the entity attribute of the target client and the authorized organ according to the target client data and the authorized organ data;
And the knowledge graph establishing unit is used for establishing a knowledge graph according to the association relation and the entity attribute.
On the basis of the above technical solutions, optionally, the risk assessment device may specifically further include a preset risk assessment indicator system determining module, configured to determine, before determining the target risk characterization data of the target client according to the knowledge graph and the preset risk assessment indicator system, a preset risk assessment indicator system based on an association relationship among the target enterprise, the target individual and the authorized authority in the knowledge graph.
Based on the above technical solutions, optionally, the determining module of the preset risk assessment indicator system may specifically include:
the risk assessment index determining unit is used for determining a risk assessment index in a preset risk assessment index system according to the association relationship among the target enterprise, the target individual and the authorized organ in the knowledge graph;
the risk influence weight determining rule determining unit is used for determining a risk influence weight determining rule corresponding to the risk evaluation index;
the initial risk representation data determining unit is used for carrying out risk quantification on the risk assessment indexes to obtain initial risk representation data corresponding to the risk assessment indexes;
The preset risk assessment index system comprises a risk assessment index, a risk influence weight determining rule and initial risk representation data.
Based on the above technical solutions, optionally, the target risk characterization data determining module 320 may specifically include:
the risk influence weight determining unit is used for determining the risk influence weight corresponding to each risk assessment index according to the risk influence weight determining rule;
the risk assessment index characterization data determining unit is used for determining risk assessment index characterization data corresponding to each risk assessment index according to each risk influence weight and corresponding initial risk characterization data;
and the target risk characterization data determining unit is used for determining target risk characterization data of the target client based on each risk assessment index characterization data.
On the basis of the above technical solutions, optionally, the risk assessment device may specifically further include an evaluation index characterization data determining module, configured to perform risk assessment on the target client according to the target risk characterization data, and determine, based on a preset evaluation index, evaluation index characterization data corresponding to a preset risk assessment index system according to the received actual risk assessment result and the target risk assessment result of the target client after obtaining the target risk assessment result;
And the adjusting module is used for adjusting the risk influence weight determining rule and/or the initial risk representation data if the evaluation index representation data accords with the preset adjusting conditions.
Based on the above technical solutions, optionally, the preset evaluation index includes any one of Precision, recall and F1-score.
The risk assessment device provided by the embodiment of the invention can execute the risk assessment method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. Fig. 4 illustrates a block diagram of an exemplary computer device 412 suitable for use in implementing embodiments of the invention. The computer device 412 shown in fig. 4 is only an example and should not be construed as limiting the functionality and scope of use of embodiments of the invention.
As shown in FIG. 4, computer device 412 is in the form of a general purpose computing device. Components of computer device 412 may include, but are not limited to: one or more processors 416, a memory 428, a bus 418 that connects the various system components (including the memory 428 and the processor 416).
Bus 418 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Computer device 412 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 412 and includes both volatile and nonvolatile media, removable and non-removable media.
Memory 428 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 430 and/or cache memory 432. The computer device 412 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage 434 may be used to read from or write to non-removable, non-volatile magnetic media (not shown in FIG. 4, commonly referred to as a "hard disk drive"). Although not shown in fig. 4, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 418 via one or more data medium interfaces. Memory 428 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the invention.
A program/utility 440 having a set (at least one) of program modules 442 may be stored in, for example, memory 428, such program modules 442 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 442 generally perform the functions and/or methodologies in the described embodiments of the invention.
The computer device 412 may also communicate with one or more external devices 414 (e.g., keyboard, pointing device, display 424, etc., wherein the display 424 may be configured as desired), with one or more devices that enable a user to interact with the computer device 412, and/or with any device (e.g., network card, modem, etc.) that enables the computer device 412 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 422. Moreover, computer device 412 may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through network adapter 420. As shown, network adapter 420 communicates with other modules of computer device 412 over bus 418. It should be appreciated that although not shown in fig. 4, other hardware and/or software modules may be used in connection with computer device 412, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage, and the like.
Processor 416 executes various functional applications and risk assessment by running programs stored in memory 428, such as implementing the risk assessment methods provided by embodiments of the present invention.
Example five
A fifth embodiment of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a risk assessment method as provided by the embodiments of the present invention, including:
establishing a knowledge graph of a target client and a right authority, wherein the target client comprises a target enterprise and/or a target individual;
determining target risk characterization data of a target client according to the knowledge graph and a preset risk assessment index system, wherein the preset risk assessment index system is determined based on the knowledge graph;
and carrying out risk assessment on the target client according to the target risk characterization data to obtain a target risk assessment result of the target client.
Of course, the computer-readable storage medium provided by the embodiments of the present invention, on which the computer program is stored, is not limited to performing the method operations described above, but may also perform related operations in the risk assessment method based on a computer device provided by any embodiment of the present invention.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (4)
1. A risk assessment method, comprising:
establishing a knowledge graph of a target client and a right authority, wherein the target client comprises a target enterprise and/or a target individual;
determining a risk assessment index in a preset risk assessment index system according to the association relationship among the target enterprise, the target individual and the authorized authorities in the knowledge graph; the risk assessment index comprises a case-related type of a target client, an instruction type executed by a right authority with an association relationship with the target client and a target enterprise or target person with the association relationship with the target client, wherein the instruction type comprises inquiry, freezing and withholding;
determining a risk influence weight determining rule corresponding to the risk assessment index;
performing risk quantification on the risk assessment index to obtain initial risk characterization data corresponding to the risk assessment index; the preset risk assessment index system comprises a risk assessment index, a risk influence weight determining rule and initial risk representation data, wherein the initial risk representation data is used for reflecting the influence of the risk assessment index on the case-related risk of the target client;
Determining a risk influence weight corresponding to each risk assessment index according to a risk influence weight determining rule;
determining risk assessment index characterization data corresponding to each risk assessment index according to the risk influence weight corresponding to each risk assessment index and corresponding initial risk characterization data; the risk assessment index characterization data are determined by multiplying the risk influence weights and corresponding initial risk characterization data;
determining target risk representation data of a target client based on the risk assessment index representation data corresponding to each risk assessment index; the preset risk assessment index system is determined based on the knowledge graph, and the target risk representation data are used for representing the case-related risk of the target client;
performing risk assessment on the target client according to the target risk characterization data to obtain a target risk assessment result of the target client;
the establishing the knowledge graph of the target client and the authorized organ comprises the following steps:
acquiring target customer data and authority data from a target database;
determining the association relationship among the target enterprise, the target individual and the authorized organ and the entity attribute of the target client and the authorized organ according to the target client data and the authorized organ data;
Establishing the knowledge graph according to the association relationship and the entity attribute;
wherein, after performing risk assessment on the target client according to the target risk characterization data to obtain a target risk assessment result of the target client, the method further comprises:
based on a preset evaluation index, determining preset evaluation index characterization data corresponding to a preset risk evaluation index system according to a received actual risk evaluation result of a target client and the target risk evaluation result; wherein the preset evaluation index comprises any one of an accuracy rate, a recall rate and an F1 value;
and if the preset evaluation index representation data is lower than a preset evaluation index representation data threshold, adjusting the risk influence weight determining rule and/or the initial risk representation data.
2. A risk assessment apparatus, comprising:
the knowledge graph establishing module is used for establishing knowledge graphs of target clients and authorized institutions, wherein the target clients comprise target enterprises and/or target individuals;
the preset risk assessment index system determining module comprises:
the risk assessment index determining unit is used for determining a risk assessment index in a preset risk assessment index system according to the association relationship among the target enterprise, the target individual and the authorized organ in the knowledge graph; the risk assessment index comprises a case-related type of a target client, an instruction type executed by a right authority with an association relationship with the target client and a target enterprise or target person with the association relationship with the target client, wherein the instruction type comprises inquiry, freezing and withholding;
The risk influence weight determining rule determining unit is used for determining a risk influence weight determining rule corresponding to the risk evaluation index;
the initial risk representation data determining unit is used for carrying out risk quantification on the risk assessment indexes to obtain initial risk representation data corresponding to the risk assessment indexes; the preset risk assessment index system comprises a risk assessment index, a risk influence weight determining rule and initial risk representation data, wherein the initial risk representation data is used for reflecting the influence of the risk assessment index on the case-related risk of the target client;
a target risk characterization data determination module comprising:
the risk influence weight determining unit is used for determining the risk influence weight corresponding to each risk assessment index according to the risk influence weight determining rule;
the risk assessment index characterization data determining unit is used for determining risk assessment index characterization data corresponding to each risk assessment index according to the risk influence weight corresponding to each risk assessment index and the corresponding initial risk characterization data; the risk assessment index characterization data are determined by multiplying the risk influence weights and corresponding initial risk characterization data;
The target risk representation data determining unit is used for determining target risk representation data of a target client based on the risk assessment index representation data corresponding to each risk assessment index; the preset risk assessment index system is determined based on the knowledge graph, and the target risk representation data are used for representing the case-related risk of the target client;
the target risk assessment result determining module is used for carrying out risk assessment on the target client according to the target risk characterization data to obtain a target risk assessment result of the target client;
the knowledge graph building module comprises:
the data acquisition unit is used for acquiring target client data and right authority data from a target database;
the entity attribute determining unit is used for determining the association relationship among the target enterprise, the target personal and the authorized organ and the entity attribute of the target client and the authorized organ according to the target client data and the authorized organ data;
the knowledge graph establishing unit is used for establishing the knowledge graph according to the association relation and the entity attribute;
wherein the apparatus further comprises:
the evaluation index characterization data determining module is used for performing risk assessment on the target client according to the target risk characterization data to obtain a target risk assessment result of the target client, and determining preset evaluation index characterization data corresponding to a preset risk assessment index system according to the received actual risk assessment result and the target risk assessment result of the target client based on a preset evaluation index; wherein the preset evaluation index comprises any one of an accuracy rate, a recall rate and an F1 value;
And the adjusting module is used for adjusting the risk influence weight determining rule and/or the initial risk representation data if the preset evaluation index representation data is lower than a preset evaluation index representation data threshold value.
3. A computer device, comprising:
one or more processing devices;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processing devices, the one or more processing devices are caused to implement the risk assessment method as claimed in claim 1.
4. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the risk assessment method as claimed in claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010196148.2A CN111429255B (en) | 2020-03-19 | 2020-03-19 | Risk assessment method, apparatus, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010196148.2A CN111429255B (en) | 2020-03-19 | 2020-03-19 | Risk assessment method, apparatus, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111429255A CN111429255A (en) | 2020-07-17 |
| CN111429255B true CN111429255B (en) | 2024-02-20 |
Family
ID=71549604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010196148.2A Active CN111429255B (en) | 2020-03-19 | 2020-03-19 | Risk assessment method, apparatus, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111429255B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861281A (en) * | 2020-08-05 | 2020-10-30 | 中国银行股份有限公司 | Knowledge graph-based risk employee discovery method and device |
| CN111966912B (en) * | 2020-09-02 | 2023-03-10 | 深圳壹账通智能科技有限公司 | Recommendation method and device based on knowledge graph, computer equipment and storage medium |
| CN112732804B (en) * | 2020-12-23 | 2024-04-26 | 北京金堤征信服务有限公司 | Cooperative data evaluation method and device, electronic equipment and readable storage medium |
| CN112559774B (en) * | 2021-03-01 | 2021-06-04 | 北京金睛云华科技有限公司 | Extended knowledge graph for information security risk assessment and construction method and system |
| CN113205408A (en) * | 2021-05-28 | 2021-08-03 | 中国工商银行股份有限公司 | Customer manager capacity map generation method and device |
| CN113674081B (en) * | 2021-07-30 | 2023-12-19 | 浙江创邻科技有限公司 | System and method for wind control management of middle and small enterprises based on graph database |
| CN113850665B (en) * | 2021-09-14 | 2023-09-12 | 江苏中交车旺科技有限公司 | Method and system for preventing and controlling fraud based on logistic finance knowledge graph |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109858740A (en) * | 2018-12-21 | 2019-06-07 | 中化资本有限公司 | Appraisal procedure, device, computer equipment and the storage medium of business risk |
| CN110162976A (en) * | 2019-02-20 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Methods of risk assessment, device and terminal |
| CN110163741A (en) * | 2019-04-16 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Credit decisions method, apparatus, equipment and medium based on credit air control model |
| CN110362689A (en) * | 2019-06-21 | 2019-10-22 | 深圳壹账通智能科技有限公司 | A kind of methods of risk assessment, device, storage medium and server |
| CN110458697A (en) * | 2019-08-19 | 2019-11-15 | 北京百度网讯科技有限公司 | Method and apparatus for assessing risk |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160071035A1 (en) * | 2014-09-05 | 2016-03-10 | International Business Machines Corporation | Implementing socially enabled business risk management |
-
2020
- 2020-03-19 CN CN202010196148.2A patent/CN111429255B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109858740A (en) * | 2018-12-21 | 2019-06-07 | 中化资本有限公司 | Appraisal procedure, device, computer equipment and the storage medium of business risk |
| CN110162976A (en) * | 2019-02-20 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Methods of risk assessment, device and terminal |
| CN110163741A (en) * | 2019-04-16 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Credit decisions method, apparatus, equipment and medium based on credit air control model |
| CN110362689A (en) * | 2019-06-21 | 2019-10-22 | 深圳壹账通智能科技有限公司 | A kind of methods of risk assessment, device, storage medium and server |
| CN110458697A (en) * | 2019-08-19 | 2019-11-15 | 北京百度网讯科技有限公司 | Method and apparatus for assessing risk |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111429255A (en) | 2020-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111429255B (en) | Risk assessment method, apparatus, device and storage medium | |
| US10467631B2 (en) | Ranking and tracking suspicious procurement entities | |
| US8489479B2 (en) | Risk scoring system and method for risk-based data assessment | |
| US11593811B2 (en) | Fraud detection based on community change analysis using a machine learning model | |
| US20160063644A1 (en) | Computer program, method, and system for detecting fraudulently filed tax returns | |
| AU2021353095A1 (en) | Predicting data tampering using augmented machine learning models | |
| US20190294786A1 (en) | Intelligent Security Risk Assessment | |
| US11574360B2 (en) | Fraud detection based on community change analysis | |
| Srivastava et al. | Bayesian fraud risk formula for financial statement audits | |
| AU2016201953A1 (en) | System and method for candidate profile screening | |
| US10482542B1 (en) | Tax fraud detection through linked relationships | |
| CN112819611A (en) | Fraud identification method, device, electronic equipment and computer-readable storage medium | |
| CN112950359B (en) | User identification method and device | |
| CN112702410B (en) | Evaluation system, method and related equipment based on blockchain network | |
| CN110766547A (en) | Method, device, equipment and storage medium for determining credibility grade | |
| Dhurandhar et al. | Robust system for identifying procurement fraud | |
| CN114708090A (en) | Bank payment business risk identification device based on big data | |
| CN114202409A (en) | Guarantee map construction method, device, equipment and storage medium | |
| CN112598499A (en) | Method and device for determining credit limit | |
| Huang et al. | Time Series Analysis and Prediction on Bitcoin | |
| CN112669039A (en) | Client risk control system and method based on knowledge graph | |
| US20230012408A1 (en) | Systems and methods for client intake and management using hierarchal conflict analysis | |
| US20220300977A1 (en) | Real-time malicious activity detection using non-transaction data | |
| US20230274371A1 (en) | Data ferret | |
| CN111768299A (en) | Method, device, equipment and storage medium for determining loan amount |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220921 Address after: 25 Financial Street, Xicheng District, Beijing 100033 Applicant after: CHINA CONSTRUCTION BANK Corp. Address before: 25 Financial Street, Xicheng District, Beijing 100033 Applicant before: CHINA CONSTRUCTION BANK Corp. Applicant before: Jianxin Financial Science and Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |