CN110458697A - Method and apparatus for assessing risk - Google Patents

Abstract

The embodiments of the present disclosure relate to the field of cloud computing, and disclose a method and an apparatus for evaluating risks. The method includes: determining the basic information of the enterprise based on the entered application information; generating a knowledge map of the enterprise based on the association relationship between the enterprise identification information in the basic information and the enterprise identification information in the enterprise information database; querying the business of the enterprise based on the basic information Data and public opinion information of the enterprise; input the basic information, the knowledge map of the enterprise, business data and public opinion information into the risk control model to obtain the risk assessment information of the enterprise. The method improves the efficiency and accuracy of obtaining risk assessment information.

Description

Method and apparatus for assessing risk

technical field

The present disclosure relates to the field of computer technology, in particular to the field of risk assessment technology, and in particular to a method and apparatus for assessing risks.

Background technique

With the development of economy, there are more and more enterprises in the market. These enterprises can obtain external loans to pave the way for the future development of the enterprises, so there is a great demand for external loans. For loan providers, corporate loan application is an important part of loan providers' business sources. With the increase in the business of enterprises obtaining external loans, loan providers have higher and higher requirements for risk control of enterprises obtaining loans. How to accurately assess the risk situation when providing loans to enterprises has become a difficult problem in the work of loan providers.

At present, the loan risk assessment of enterprises is mainly conducted manually by business personnel.

SUMMARY OF THE INVENTION

Embodiments of the present disclosure provide methods and apparatus for assessing risk.

In a first aspect, an embodiment of the present disclosure provides a method for assessing risks, including: determining basic information of an enterprise based on entered application information; based on enterprise identification information in the basic information and enterprise identification information in an enterprise information database Based on the basic information, query the business data of the enterprise and the public opinion information of the enterprise; input the basic information, the knowledge graph, business data and public opinion information of the enterprise into the risk control model to obtain the risk assessment information of the enterprise .

In some embodiments, the risk control model includes: a risk relationship model and a risk scoring model; the risk assessment information includes: the risk probability of establishing a service relationship with the enterprise, the risk score of the enterprise, and service prompt information; the basic information, the knowledge map of the enterprise And business data is input into the risk control model, and the risk assessment information of the enterprise is obtained, including: input the basic information, the knowledge map of the enterprise and the public opinion information into the risk relationship model to obtain the risk probability of establishing a service relationship with the enterprise; input the business data and public opinion information into the risk Scoring model, get enterprise risk score and service prompt information.

In some embodiments, the method further includes at least one of the following: the risk relationship model is a relationship network model obtained based on RFM, NLP, and graph mining technology; the risk scoring model is a multiple regression model; the risk probability includes fraud probability, default probability and overdue probability Probability; and business data including: number of hires, hiring time, operations and liabilities.

In some embodiments, determining the basic information of the enterprise based on the entered application information includes: identifying the entered paper version of the application information to obtain the identification result; using an intelligent correction algorithm to correct the identification result to obtain a text sequence; Entity, get tagged entity data; and based on tagged named entity data, output structured basic information of the enterprise.

In some embodiments, determining the basic information of the enterprise based on the entered application information includes: based on the entered application information, retrieving benchmark information corresponding to the enterprise in the application information; wherein the benchmark information includes official information and/or historical information ; Based on the benchmark information, the application information is verified; in response to the result of the verification indicating that the preset information fails the verification, a prompt message for returning the application is presented; in response to the result of the verification indicating that the enterprise in the application information conforms to the blacklist rules, the The companies in the application information are added to the blacklist.

In some embodiments, the verification result indicates that the enterprise in the application information conforms to the blacklist, including at least one of the following: the number of times that there is untrue information in the application information exceeds a predetermined threshold; the number of historical verifications exceeds a preset threshold.

In some embodiments, the method further includes: inputting the risk assessment information into the risk control decision model to obtain a decision result output by the risk control decision model.

In some embodiments, the risk control decision model is a rule model formed by connecting multiple rules in series or in parallel.

In some embodiments, when the risk assessment information includes: the risk probability of establishing a service relationship with the enterprise, the risk score of the enterprise, and the service prompt information, the plurality of rules at least include: if the fraud probability or default probability in the risk probability is higher than the expected probability Set the probability, the output decision result is to return the application; if the credit score in the risk score is lower than the preset score, the income in the risk score is lower than the income threshold, or the debt ratio in the risk score is higher than the debt ratio threshold, the output The decision result is to return the application.

In some embodiments, the method further includes: in response to receiving the service indication, establishing a service relationship with the enterprise, monitoring business data of the enterprise that has established the service relationship after receiving the service; optimizing the risk control model based on the business data after receiving the service .

In a second aspect, an embodiment of the present disclosure provides an apparatus for assessing risks of an enterprise, including: an information determination unit configured to determine basic information of the enterprise based on the entered application information; a graph generation unit configured to The association relationship between the enterprise identification information in the basic information and the enterprise identification information in the enterprise information database generates the knowledge map of the enterprise; the information query unit is configured to query the business data of the enterprise and the public opinion information of the enterprise based on the basic information; the evaluation output The unit is configured to input basic information, enterprise knowledge graph, business data and public opinion information into the risk control model to obtain enterprise risk assessment information.

In some embodiments, the risk control model in the assessment output unit includes: a risk relationship model and a risk scoring model; the risk assessment information in the assessment output unit includes: a risk probability of establishing a service relationship with the enterprise, a risk score of the enterprise, and a service prompt information; the evaluation output unit is further configured to: input basic information, enterprise knowledge map and public opinion information into the risk relationship model to obtain the risk probability of establishing a service relationship with the enterprise; input business data and public opinion information into the risk scoring model to obtain the enterprise’s risk probability. Risk score and service reminder information.

In some embodiments, the apparatus further includes at least one of the following: the risk relationship model is a relationship network model obtained based on RFM, NLP, and graph mining technology; the risk scoring model is a multiple regression model; the risk probability includes fraud probability, default probability and overdue probability Probability; and business data including: number of hires, hiring time, operations and liabilities.

In some embodiments, the information determination unit includes: a result identification subunit, configured to identify the entered paper version of the application information, and obtain the identification result; the result correction subunit, configured to use an intelligent correction algorithm to correct the identification result to obtain a text sequence; an entity identification subunit configured to identify entities in the text sequence to obtain tagged entity data; and an information output subunit configured to output structured basic information of the enterprise based on the tagged named entity data .

In some embodiments, the information determination unit includes: an information retrieval subunit, configured to retrieve benchmark information corresponding to the enterprise in the application information based on the entered application information; wherein the benchmark information includes official information and/or history information; an information verification subunit, configured to verify application information based on the reference information; a prompt presentation subunit, configured to present a prompt message for returning the application in response to the verification result indicating that the preset information fails the verification; The list adding subunit is configured to add the enterprise in the application information to the blacklist in response to the verification result indicating that the enterprise in the application information conforms to the blacklist rule.

In some embodiments, the verification result in the information determination unit indicates that the enterprise in the application information conforms to the blacklist, including at least one of the following: the number of times that there is untrue information in the application information exceeds a predetermined threshold; the number of historical verifications exceeds a predetermined threshold .

In some embodiments, the apparatus further includes: a result determination unit configured to input the risk assessment information into the risk control decision model to obtain a decision result output by the risk control decision model.

In some embodiments, the risk control decision model in the result determination unit is a rule model formed by connecting a plurality of rules in series or in parallel.

In some embodiments, when the risk assessment information in the assessment output unit includes: a risk probability of establishing a service relationship with an enterprise, a risk score of the enterprise, and service prompt information, the plurality of rules in the result determination unit at least include: if the risk probability If the fraud probability or default probability in the risk score is higher than the preset probability, the output decision result is to return the application; if the credit score in the risk score is lower than the preset score, the income in the risk score is lower than the income threshold or the liability in the risk score If the debt ratio is higher than the debt ratio threshold, the output decision result is to return the application.

In some embodiments, the apparatus further includes: a data monitoring unit, configured to establish a service relationship with the enterprise in response to receiving the service indication, and monitor the business data of the enterprise that has established the service relationship after receiving the service; a model optimization unit, configured to be It is configured to optimize the risk control model based on the business data after receiving the service.

In a third aspect, embodiments of the present disclosure provide an electronic device/terminal/server, including: one or more processors; a storage device for storing one or more programs; The processors execute such that the one or more processors implement a method for assessing risk as described in any of the above.

In a fourth aspect, an embodiment of the present disclosure provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, implements the method for assessing risk as described above.

The method and device for evaluating risks provided by the embodiments of the present disclosure firstly determine the basic information of the enterprise based on the entered application information; then, based on the association relationship between the enterprise identification information in the basic information and the enterprise identification information in the enterprise information database , to generate the knowledge map of the enterprise; then, based on the basic information, query the business data of the enterprise and the public opinion information of the enterprise; finally, input the basic information, the knowledge map of the enterprise, the business data and the public opinion information into the risk control model to obtain the risk assessment of the enterprise information. In this process, since the input data of the risk control model adopts multi-dimensional data such as basic information, enterprise knowledge map, business data and public opinion information, the accuracy of the risk assessment information output by the risk control model is higher, and Since the risk control model is adopted to replace the manual evaluation to obtain the risk assessment information, the efficiency and accuracy of obtaining the risk assessment information are improved.

Description of drawings

Other features, objects and advantages of the present disclosure will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings:

FIG. 1 is an exemplary system architecture diagram to which the present disclosure may be applied;

FIG. 2 is a schematic flowchart of one embodiment of a method for assessing risk according to an embodiment of the present disclosure;

FIG. 3 is an exemplary application scenario of the method for assessing risk according to an embodiment of the present disclosure;

FIG. 4 is a schematic flowchart of yet another embodiment of a method for assessing risk according to an embodiment of the present disclosure;

FIG. 5 is an exemplary structural diagram of one embodiment of the apparatus for assessing risk of the present disclosure;

FIG. 6 is a schematic structural diagram of a computer system suitable for implementing a server of an embodiment of the present disclosure.

Detailed ways

The present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the related invention, but not to limit the invention. In addition, it should be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

It should be noted that the embodiments of the present disclosure and the features of the embodiments may be combined with each other under the condition of no conflict. The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

FIG. 1 illustrates an exemplary system architecture 100 to which embodiments of a method for assessing risk or an apparatus for assessing risk of the present disclosure may be applied.

As shown in FIG. 1 , the system architecture 100 may include terminal devices 101 , 102 , and 103 , a network 104 and a server 105 . The network 104 is a medium used to provide a communication link between the terminal devices 101 , 102 , 103 and the server 105 . The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages and the like. Various communication client applications may be installed on the terminal devices 101 , 102 and 103 , such as browser applications, shopping applications, search applications, instant communication tools, email clients, social platform software, and the like.

The terminal devices 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, and 103 are hardware, they can be various electronic devices that support browser applications, including but not limited to tablet computers, laptop computers, desktop computers, and the like. When the terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. It can be implemented, for example, as multiple software or software modules for providing distributed services, or as a single software or software module. There is no specific limitation here.

The server 105 may be a server that provides various services, such as a background server that provides support for browser applications performed on the terminal devices 101 , 102 , and 103 . The background server can analyze and process the received request and other data, and feed back the processing result to the terminal device.

It should be noted that the server may be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or can be implemented as a single server. When the server is software, it may be implemented as multiple software or software modules for providing distributed services, or may be implemented as a single software or software module. There is no specific limitation here.

In practice, the method for assessing risks provided by the embodiments of the present disclosure may be executed by terminal devices 101 , 102 , 103 and/or servers 105 , 106 , and the apparatus for assessing risks may also be set on terminal devices 101 , 102 , 103 and/or servers 105 , 106 .

It should be understood that the numbers of terminal devices, networks and servers in FIG. 1 are merely illustrative. There can be any number of terminal devices, networks and servers according to implementation needs.

With continued reference to Figure 2, Figure 2 illustrates a flow 200 of one embodiment of a method for assessing risk in accordance with the present disclosure. The method for assessing risk includes the following steps:

Step 201, based on the entered application information, determine the basic information of the enterprise.

In this embodiment, the execution body of the method for risk assessment (for example, the terminal or the server shown in FIG. 1 ) may receive the application information submitted by the user through a local or remote human-computer interaction device.

Specifically, the above-mentioned execution body may acquire the electronic version application information entered by the user from the front end. The electronic version of the application information includes the basic information of the enterprise, the recent operation of the enterprise, etc. The information entry layer provides a front-end interface for enterprises that need to apply to enter their basic information.

Alternatively or additionally, the above-mentioned executive body may obtain the paper version application information entered by the user. When entering the application information, the paper application information mainly includes: legal person valid certificate, business license, tax registration certificate, paper application form, etc.

In some optional implementations of this embodiment, determining the basic information of the enterprise based on the entered application information includes: identifying the entered application information in paper version, and obtaining the identification result; using an intelligent correction algorithm to correct the identification result to obtain a text sequence ; Recognize entities in text sequences to obtain tagged entity data; and output structured basic information of enterprises based on tagged named entity data.

In this implementation manner, the application information in the paper version can be identified by the method used to identify the text in the picture in the existing technology or the technology developed in the future, which is not limited in this application. For example, OCR identification can be used. The technical identification paper version of the application information.

The recognition result obtained by the recognition usually has many typos. Therefore, it is necessary to perform data processing on the recognition results to obtain text sequences. In the data processing here, the intelligent correction algorithm can be used to correct the text in the recognition result to prepare for further analysis. The intelligent correction algorithm may adopt the method for correcting sentence errors in the existing technology or the technology developed in the future, which is not limited in this application. For example, a Chinese typo correction tool (pycorrector) or a recurrent neural network (RNNLM) language model can be used to correct errors in text.

In addition, for the revised text sequence, entity recognition algorithms can be combined to ensure the correctness of entity recognition. The entity identification algorithm here may be an algorithm used to identify an entity in the existing technology or a technology developed in the future, which is not limited in this application. For example, Named Entity Recognition (NER) task can be employed to identify entities in text sequences.

Specifically, the identified named entities may include:

(1) Relevant entities applying for the company, such as the application name, pre-approved document number for the name, domicile, place of production and operation, postal code, company type, etc.;

(2) Personnel related entities, such as legal representatives, supervisors, directors, managers, financial directors, shareholder promoters, liaisons, etc.;

(3) Personnel information related attribute entities, such as name, fixed phone, mobile phone, ID card type, ID card number, etc.; and other related entities. These entities can provide relevant domain terminology for subsequent establishment approvals.

In the method for determining the basic information of an enterprise in this implementation manner, since an intelligent correction algorithm is used to correct the recognition result of the paper version of the application information, the accuracy of the text sequence obtained according to the recognition result can be improved; The basic information of the enterprise improves the accuracy and efficiency of obtaining the basic information of the enterprise.

In some optional implementations of this embodiment, determining the basic information of the enterprise based on the entered application information includes: retrieving benchmark information corresponding to the enterprise in the application information based on the entered application information; wherein the benchmark information includes official information and/or historical information; based on the benchmark information, verify the application information; in response to the result of the verification indicating that the preset information fails the verification, a prompt message for returning the application is presented; in response to the result of the verification, the enterprise in the application information is indicated In line with the blacklist rules, the companies in the application information will be added to the blacklist.

In this implementation manner, in order to check whether the data in the application information is correct, the entered application information may be checked. For example, do a check on the company address in the application information. Once it is found that the company's actual business address is inconsistent with the company's registered address in the official information, the application will be returned directly. This step will automatically retrieve the historical information data of the applicant company, and compare it with the information in the application materials in detail, including the corporate legal person, corporate registered capital and other information.

In addition, verifying the entered application information can avoid malicious submission. The verification result may be compared with a preset blacklist, and if the comparison result indicates that the verification result hits the blacklist rule, the enterprise in the application information will be added to the blacklist.

Exemplarily, the verification result indicating that the enterprise in the application information conforms to the blacklist may include: the number of times that there is untrue information in the application information exceeds a predetermined threshold; the number of historical verifications exceeds a predetermined threshold.

Specifically, the above-mentioned execution body may obtain the historical verification times of the applicant, and compare the historical verification times with a preset threshold. If the number of historical verification exceeds the preset threshold, the applied enterprise user will be added to the blacklist, and the blacklist addition prompt message will be output.

Alternatively or additionally, the above-mentioned executive body can check the number of times that the basic information provided by the applicant is not real information, and compare the number of times of non-real information with a predetermined threshold, if the number of times of non-real information exceeds the predetermined threshold, then Add the applied enterprise users to the blacklist, and output the blacklist addition prompt information.

In the method for determining the basic information of the enterprise in this implementation manner, since the data in the application information is verified, the authenticity and accuracy of the determined basic information of the enterprise can be improved, and bad applications and malicious applications can be avoided.

Step 202: Generate a knowledge map of the enterprise based on the association relationship between the enterprise identification information in the basic information and the enterprise identification information in the enterprise information database.

In this embodiment, the above-mentioned execution subject may query the enterprise identification information in the enterprise information database for the enterprise identification information in the basic information that has an associated relationship with the enterprise identification information in the basic information according to the enterprise identification information in the basic information of the enterprise. Afterwards, the above-mentioned executive body may generate a knowledge graph of the enterprise according to the enterprise identification information in the basic information, the enterprise identification information having an associated relationship with the enterprise identification information in the basic information, and the association between the two.

The enterprise identification information here can identify the enterprise so that the outside world can identify the enterprise. Specifically, the enterprise identification information may include at least one of the following: an enterprise name, an enterprise legal person, an enterprise trademark, and the like.

In a specific example, according to the enterprise name in the basic information, the enterprise name associated with the enterprise name in the enterprise information database and the association relationship between these enterprises can be queried. At the same time, the legal person in the basic information and other companies controlled by it can be queried from the enterprise information database.

After acquiring the association relationship between the enterprise identification information in the basic information and the enterprise identification information in the enterprise information database, the above-mentioned execution body can organize the acquired data into an intuitive enterprise knowledge graph. For example, the basic information of each enterprise and the basic information of each legal person can be organized into an enterprise knowledge map.

It should be understood that after obtaining the enterprise knowledge graph, the enterprise knowledge graph can be presented on the interactive interface, and the information in the enterprise knowledge graph can be output.

Step 203 , based on the basic information, query the business data of the enterprise and the public opinion information of the enterprise.

In this embodiment, the business data of the enterprise and the public opinion information of the enterprise can be obtained from various channels. For example, the business data of the enterprise and the public opinion information of the enterprise can be obtained from a network platform, a database, a third party, etc.

The business data of an enterprise refers to data that can indicate the business operation status of the enterprise. For example, the business data of an enterprise may at least include: number of recruits, recruiting time, operating conditions, liabilities, and the like.

The public opinion information of the enterprise refers to the reflection form of the public opinion of the enterprise. For example, media information for enterprises, government information, etc.

Step 204: Input the basic information, the knowledge graph of the enterprise, the business data and the public opinion information into the risk control model to obtain the risk assessment information of the enterprise.

In this embodiment, the risk control model mainly evaluates the situation of the enterprise, and outputs the score to the interactive interface or for use in the next decision.

The risk control model here may be a rule-based model, wherein the rules are rules obtained according to historical data statistics. Alternatively or additionally, the risk control model may be a model based on a machine learning algorithm obtained based on learning from historical data. This application does not limit this.

After the basic information, enterprise knowledge map, business data and public opinion information are input into the risk control model, the risk control model can analyze the input data and estimate the risk assessment information corresponding to the input data based on the input data.

In some optional implementations of this embodiment, the risk control model includes: a risk relationship model and a risk scoring model; the risk assessment information includes: a risk probability of establishing a service relationship with an enterprise, a risk score of the enterprise, and service prompt information; Information, the knowledge map of the enterprise and the business data are input into the risk control model, and the risk assessment information of the enterprise is obtained, including: input the basic information, the knowledge map of the enterprise and the public opinion information into the risk relationship model to obtain the risk probability of establishing a service relationship with the enterprise; Data and public opinion information are input into the risk scoring model to obtain the enterprise's risk score and service prompt information.

In this implementation manner, the risk relationship model is used to estimate the risk probability of establishing a service relationship with the enterprise based on the input basic information, the enterprise's knowledge map and public opinion information. Risk probability may indicate the risk of establishing a service relationship with a business.

Here, the risk relationship model may be a relationship network model. A relational network is a graph-based data structure consisting of nodes and edges. Each node represents an individual, and each edge is a relationship between individuals. Relational networks connect different individuals according to their relationships, thereby providing the ability to analyze problems from the perspective of "relationships". A network of relationships facilitates the identification of abnormal gang fraud from normal behavior.

The application scenarios of relational network in anti-fraud are mainly divided into two cases: supervised model and unsupervised model. The so-called supervised model refers to trying to dig out the typical characteristics and behavior patterns of fraudulent gangs from historical data under the premise of known “good” and “bad” labels, so as to effectively identify fraudulent gangs. Although supervised models have good performance in prediction accuracy, in practice, "good" and "bad" labels are often difficult to obtain. Therefore, unsupervised model analysis also becomes particularly important when there is no label information.

The risk scoring model is used to estimate the risk score of the enterprise and output service prompt information based on the business data of the enterprise. The risk score may indicate the overall score of the enterprise, and the service prompt information may indicate the level of the service provided to the enterprise.

Here, the risk scoring model can be a simple multiple regression model or a neural network regression model. In a specific example, the risk scoring model may be a linear regression model obtained by training. The value of the dependent variable in the linear regression model is the risk score. The independent variables are business data and public opinion information. Specifically, the business data may include: profit growth rate, recruiting number growth rate, recruiting number, company debt ratio, and the like. The model can be a simple multiple regression model or a neural network regression model

In the risk control model in this implementation, by setting a risk relationship model and a risk scoring model in the risk control model, the risk relationship model can be used to determine the risk probability of establishing a service relationship with the enterprise, and the risk scoring model can be used to obtain the enterprise's risk score and Service prompt information, so that for different input data, different models are used for special processing, which improves the accuracy of the output results.

In some optional implementations of this embodiment, the method for evaluating risks of the present disclosure further includes at least one of the following: the risk relationship model is a relationship network model obtained based on RFM, NLP, and graph mining technology; the risk scoring model is Multiple regression model; risk probability includes fraud probability, default probability and overdue probability; and business data includes: number of recruits, recruitment time, operating conditions and liabilities.

In this implementation, the RFM model is a customer relationship management model, the NLP is a natural language processing model, and the graph mining technology refers to the process of using graph models to discover and extract useful knowledge and information from massive data. After building a relational network model based on RFM, NLP, and graph mining technology, basic information, enterprise knowledge graphs and business data can be input into the relational network model to obtain the fraud probability and default probability of establishing a service relationship with the enterprise output by the relational network model. and overdue probability.

The multiple regression model can use the number of recruits, recruiting time, operating conditions and liabilities in the business data as independent variables, and the risk score of the enterprise as the dependent variable, and generate service prompt information based on the dependent variable.

The method for assessing risk in the above embodiments of the present disclosure makes the risk assessment information output by the risk control model more accurate, and improves the efficiency and accuracy of obtaining the risk assessment information.

An exemplary application scenario of the method for assessing risk of the present disclosure is described below with reference to FIG. 3 .

As shown in FIG. 3 , FIG. 3 shows an exemplary application scenario of the method for assessing risk according to the present disclosure.

As shown in FIG. 3 , the method 300 for assessing risk runs in the electronic device 310 and may include:

First, based on the entered application information 301, determine the basic information 302 of the enterprise;

Based on the association relationship 305 between the entity 303 in the basic information 302 and the entity 304 in the enterprise information base, a knowledge graph 306 of the enterprise is generated;

Based on the basic information 302, query the business data 307 of the enterprise and the public opinion information 308 of the enterprise;

The basic information 302 , the knowledge map 306 of the enterprise, the business data 307 and the public opinion information 308 are input into the risk control model 309 to obtain the risk assessment information 310 of the enterprise.

It should be understood that the application scenario of the method for assessing risk shown in FIG. 3 above is only an exemplary description of the method for assessing risk, and does not represent a limitation to the method. For example, each step shown in FIG. 3 above may further adopt a more detailed implementation method. It is also possible to further add other steps for assessing risks on the basis of FIG. 3 above.

With further reference to FIG. 4, FIG. 4 shows a schematic flow diagram of yet another embodiment of a method for assessing risk according to the present disclosure.

As shown in FIG. 4 , the method 400 for assessing risk in this embodiment may include the following steps:

Step 401, based on the entered application information, determine the basic information of the enterprise.

In this embodiment, the execution body of the method for risk assessment (for example, the terminal or server shown in FIG. 1 ) may receive the application information submitted by the user through a local or remote human-computer interaction device.

Step 402 , based on the association relationship between the entities in the basic information and the entities in the enterprise information base, generate a knowledge graph of the enterprise.

In this embodiment, the above-mentioned execution subject may, according to the enterprise identification information in the basic information of the enterprise, query the enterprise identification information in the enterprise information database that has an associated relationship with the enterprise identification information in the basic information. Afterwards, the above-mentioned executive body may generate a knowledge graph of the enterprise according to the enterprise identification information in the basic information, the enterprise identification information having an associated relationship with the enterprise identification information in the basic information, and the association between the two.

Step 403 , based on the basic information, query the business data of the enterprise and the public opinion information of the enterprise.

In this embodiment, the business data of the enterprise and the public opinion information of the enterprise can be obtained from various channels. For example, the business data of the enterprise and the public opinion information of the enterprise can be obtained from a network platform, a database, a third party, etc.

Step 404: Input the basic information, the knowledge graph of the enterprise, the business data and the public opinion information into the risk control model to obtain the risk assessment information of the enterprise.

In this embodiment, the risk control model mainly evaluates the situation of the enterprise, and outputs the score to the interactive interface or for use in the next decision.

The risk control model here may be a rule-based model, wherein the rules are rules obtained according to historical data statistics. Alternatively or additionally, the risk control model may be a model based on a machine learning algorithm obtained based on learning from historical data. This application does not limit this.

After the basic information, enterprise knowledge map, business data and public opinion information are input into the risk control model, the risk control model can analyze the input data and estimate the risk assessment information corresponding to the input data based on the input data.

It should be understood that the above steps 401 to 404 correspond to the steps 201 to 204 in the embodiment shown in FIG. 2 respectively. Therefore, the operations and features described for steps 201 to 204 in the above embodiment shown in FIG. 2 are also applicable to steps 401 to 404, and are not repeated here.

Step 405: Input the risk assessment information into the risk control decision model to obtain the decision result output by the risk control decision model.

In this embodiment, the risk control decision model can make intelligent decisions according to the risk assessment information, and output decision results. The entire decision-making process of the risk control decision-making model is completed by the model without manual participation. After the decision is completed, the risk control decision model will output the decision result to the interactive interface for manual reference.

The risk control decision model is a rule model formed by multiple rules in series or parallel.

For example, the rules included in the risk control decision model may be that the enterprise fraud probability or default probability obtained by the risk relationship model cannot be higher than the preset probability. The risk control decision model considers that the enterprise has a strong fraud tendency when the enterprise fraud probability or default probability obtained by the risk relationship model is higher than the preset probability, and the output decision result is: it is recommended to return the application.

For another example, other rules included in the risk control decision model may also include limitations on credit score, income situation, debt ratio and other situations in the risk score. When the credit score is lower than the preset score, the income is lower than the income threshold, or the debt ratio is higher than the debt ratio threshold, the output decision result is: It is recommended to return the application.

It will be appreciated that these rules may be set manually via the interactive interface.

After the risk control decision model generates the decision results, the decision results can be presented on the interactive interface. Further, the application information or intermediate data for generating the decision result can also be presented on the interactive interface.

In optional step 406, in response to receiving the service indication, establish a service relationship with the enterprise, and monitor business data of the enterprise that has established the service relationship after receiving the service.

In this embodiment, the above-mentioned executive body may directly use the decision result as a service instruction to establish a service relationship with the enterprise when the decision result is to suggest establishing a service relationship with the enterprise. Alternatively, the above-mentioned executive body may present the decision result to the user, receive a service instruction to establish a service relationship with the enterprise input by the user based on the decision result, and establish a service relationship with the enterprise.

After establishing a service relationship with the enterprise, the above-mentioned executive body can monitor the business data of the enterprise that has established the service relationship after receiving the service, so as to adjust the service provided to the enterprise according to the business data after receiving the service.

In optional step 407, the risk control model is optimized based on the business data after receiving the service.

In this embodiment, after monitoring the business data of the enterprise that has established the service relationship after receiving the service, the execution body may analyze the monitored business data, so as to adjust and optimize the risk control model.

The method for assessing risk in the embodiment in FIG. 4 of the present disclosure, on the basis of the method for assessing risk shown in FIG. 2 , the risk assessment information can be input into a risk control decision model to obtain a risk control decision model The output decision result, compared with the manual review in the prior art, reduces the repetitive and redundant work of the reviewers, improves the work efficiency of risk assessment, and can shorten the approval process to avoid the audit caused by the difference in the level of the reviewers. The occurrence of phenomena such as different standards and large differences in approval results. In some embodiments, due to the addition of optional step 406 and optional step 407, the business data of the enterprise can be monitored, and the risk of providing services to the enterprise but failing to recover the service benefits can be reduced.

With further reference to FIG. 5 , as an implementation of the methods shown in the above figures, an embodiment of the present disclosure provides an embodiment of an apparatus for assessing risks, which is similar to the methods shown in FIGS. 2 to 4 . Corresponding to the embodiment, the apparatus may be specifically applied to an apparatus including a publishing end and a server.

As shown in FIG. 5 , the apparatus 500 for evaluating risks in this embodiment may include: an information determination unit 510 configured to determine basic information of an enterprise based on the entered application information; a graph generation unit 520 configured to The association relationship between the enterprise identification information in the information and the enterprise identification information in the enterprise information database, to generate the knowledge map of the enterprise; the information query unit 530 is configured to query the business data of the enterprise and the public opinion information of the enterprise based on the basic information; evaluation output The unit 540 is configured to input the basic information, the knowledge graph of the enterprise, the business data and the public opinion information into the risk control model to obtain the risk assessment information of the enterprise.

In some optional implementations of this embodiment, the risk control model in the evaluation output unit 540 includes: a risk relationship model and a risk scoring model; the risk evaluation information in the evaluation output unit 540 includes: a risk probability of establishing a service relationship with an enterprise , the enterprise's risk score and service prompt information; the evaluation output unit 540 is further configured to: input the basic information, the enterprise's knowledge map and public opinion information into the risk relationship model to obtain the risk probability of establishing a service relationship with the enterprise; Enter the information into the risk scoring model to obtain the enterprise's risk score and service prompt information.

In some optional implementations of this embodiment, the apparatus 500 further includes at least one of the following: the risk relationship model is a relationship network model obtained based on RFM, NLP, and graph mining technology; the risk scoring model is a multiple regression model; the risk probability includes Fraud probability, default probability and overdue probability; and business data including: number of hires, hiring time, operations and liabilities.

In some optional implementations of this embodiment, the information determination unit 510 includes (not shown in the figure): a result identification subunit, configured to identify the entered application information in paper version, and obtain the identification result; a unit configured to use an intelligent correction algorithm to correct the recognition result to obtain a text sequence; an entity identification subunit configured to identify entities in the text sequence to obtain tagged entity data; and an information output subunit configured to Label named entity data, output structured basic information of the enterprise.

In some optional implementations of this embodiment, the information determination unit 510 includes (not shown in the figure): an information retrieval subunit, configured to retrieve an information corresponding to the enterprise in the application information based on the entered application information. Reference information; wherein the reference information includes official information and/or historical information; an information verification sub-unit is configured to verify application information based on the benchmark information; a prompt presentation sub-unit is configured to indicate a predetermined If the information fails the verification, a prompt message for returning the application is presented; the list adding subunit is configured to add the enterprise in the application information to the blacklist in response to the verification result indicating that the enterprise in the application information conforms to the blacklist rule.

In some optional implementations of this embodiment, the result of verification in the information determining unit 510 indicates that the enterprises in the application information conform to the blacklist, including at least one of the following: the number of times that there is untrue information in the application information exceeds a predetermined threshold; the history The number of verifications exceeds the preset threshold.

In some optional implementations of this embodiment, the apparatus further includes: a result determination unit 550 configured to input the risk assessment information into the risk control decision model to obtain a decision result output by the risk control decision model.

In some optional implementations of this embodiment, the risk control decision model in the result determination unit 550 is a rule model formed by connecting multiple rules in series or in parallel.

In some optional implementations of this embodiment, when the risk assessment information in the assessment output unit 540 includes: the risk probability of establishing a service relationship with the enterprise, the risk score of the enterprise, and the service prompt information, the result determination unit 550 contains multiple risk assessment information. Each rule includes at least: if the fraud probability or default probability in the risk probability is higher than the preset probability, the output decision result is to return the application; if the credit score in the risk score is lower than the preset score, and the income in the risk score is lower than If the debt ratio in the income threshold or risk score is higher than the debt ratio threshold, the output decision result is to return the application.

In some optional implementations of this embodiment, the apparatus further includes: a data monitoring unit 560, configured to, in response to receiving the service indication, establish a service relationship with the enterprise, and monitor the business of the enterprise that has established the service relationship after receiving the service Data; the model optimization unit 570 is configured to optimize the risk control model based on the service data after receiving the service.

It should be understood that each unit recorded in the apparatus 500 corresponds to each step recorded in the method described with reference to FIGS. 2-4 . Therefore, the operations and features described above with respect to the method are also applicable to the apparatus 500 and each unit included therein, and details are not described herein again.

Referring next to FIG. 6 , it shows a schematic structural diagram of an electronic device (eg, the server or terminal device in FIG. 1 ) 600 suitable for implementing the embodiments of the present disclosure. Terminal devices in the embodiments of the present disclosure may include, but are not limited to, notebook computers, desktop computers, and the like. The terminal device/server shown in FIG. 6 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.

As shown in FIG. 6, an electronic device 600 may include a processing device (eg, a central processing unit, a graphics processor, etc.) 601 that may be loaded into random access according to a program stored in a read only memory (ROM) 602 or from a storage device 608 Various appropriate actions and processes are executed by the programs in the memory (RAM) 603 . In the RAM 603, various programs and data necessary for the operation of the electronic device 600 are also stored. The processing device 601 , the ROM 602 , and the RAM 603 are connected to each other through a bus 604 . An input/output (I/O) interface 605 is also connected to bus 604 .

Typically, the following devices can be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration An output device 607 of a computer, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. Communication means 609 may allow electronic device 600 to communicate wirelessly or by wire with other devices to exchange data. While FIG. 6 shows electronic device 600 having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in FIG. 6 may represent one device, or may represent multiple devices as required.

In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication device 609 , or from the storage device 608 , or from the ROM 602 . When the computer program is executed by the processing apparatus 601, the above-described functions defined in the methods of the embodiments of the present disclosure are executed. It should be noted that the computer-readable medium described in the embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Rather, in embodiments of the present disclosure, a computer-readable signal medium may include a data signal in baseband or propagated as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device . Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or may exist alone without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: determines the basic information of the enterprise based on the entered application information; The relationship between the identification information and the enterprise identification information in the enterprise information database, and the knowledge map of the enterprise is generated; based on the basic information, the business data of the enterprise and the public opinion information of the enterprise are inquired; the basic information, the knowledge map of the enterprise, business data and public opinion information Enter the risk control model to get the risk assessment information of the enterprise.

Computer program code for carrying out operations of embodiments of the present disclosure may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, or a combination thereof, Also included are conventional procedural programming languages - such as the "C" 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 (eg, using an Internet service provider to via Internet connection).

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.

The units involved in the embodiments of the present disclosure may be implemented in a software manner, and may also be implemented in a hardware manner. The described unit can also be provided in the processor, for example, it can be described as: a processor includes an information determination unit, a map generation unit, an information query unit and an evaluation output unit. Wherein, the names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the information determination unit may also be described as "a unit for determining the basic information of an enterprise based on the entered application information".

The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the present disclosure is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, and should also cover, without departing from the above-mentioned inventive concept, the above-mentioned technical features or Other technical solutions formed by any combination of its equivalent features. For example, a technical solution is formed by replacing the above features with the technical features disclosed in the present disclosure (but not limited to) with similar functions.

Claims (22)

1. A method for assessing the risk of an enterprise, comprising: Based on the entered application information, determine the basic information of the enterprise; Generate a knowledge map of the enterprise based on the association relationship between the enterprise identification information in the basic information and the enterprise identification information in the enterprise information database; Based on the basic information, query the business data of the enterprise and the public opinion information of the enterprise; The basic information, the knowledge graph of the enterprise, the business data and the public opinion information are input into the risk control model to obtain the risk assessment information of the enterprise. 2. The method according to claim 1, wherein the risk control model comprises: a risk relationship model and a risk scoring model; The risk assessment information includes: the risk probability of establishing a service relationship with the enterprise, the enterprise's risk score and service prompt information; The inputting the basic information, the knowledge graph of the enterprise and the business data into the risk control model to obtain the risk assessment information of the enterprise includes: inputting the basic information, the knowledge graph of the enterprise and the public opinion information into a risk relationship model to obtain the risk probability of establishing a service relationship with the enterprise; input the business data and the public opinion information into a risk scoring model to obtain the enterprise's risk score and service prompt information. 3. The method of claim 2, wherein the method further comprises at least one of the following: The risk relationship model is a relationship network model obtained based on RFM, NLP, and graph mining technology; The risk scoring model is a multiple regression model; The probability of risk includes probability of fraud, probability of default and probability of overdue; and The business data includes: number of recruits, recruiting time, operating conditions and liabilities. 4. The method according to claim 1, wherein, determining the basic information of the enterprise based on the entered application information comprises: Identify the application information entered in the paper version, and obtain the identification result; Adopt intelligent correction algorithm to correct the recognition result and get the text sequence; identifying entities in the text sequence to obtain tagged entity data; and Based on the tagged named entity data, structured basic information of the enterprise is output. 5. The method according to any one of claims 1-4, wherein the determining the basic information of the enterprise based on the entered application information comprises: Based on the entered application information, retrieve the benchmark information corresponding to the enterprise in the application information; wherein, the benchmark information includes official information and/or historical information; based on the reference information, verifying the application information; In response to the result of the verification indicating that the preset information fails the verification, a prompt message for returning the application is presented; In response to the verification result indicating that the enterprise in the application information complies with the blacklist rule, the enterprise in the application information is added to the blacklist. 6. The method according to claim 5, wherein the result of the verification indicates that the enterprise in the application information conforms to the blacklist including at least one of the following: The number of times that there is untrue information in the application information exceeds a predetermined threshold; The number of historical verifications exceeds the preset threshold. 7. The method according to any one of claims 1-6, wherein the method further comprises: The risk assessment information is input into the risk control decision-making model, and the decision-making result output by the risk control decision-making model is obtained. 8. The method according to claim 7, wherein the risk control decision model is a rule model formed by connecting a plurality of rules in series or in parallel. 9. The method according to claim 8, wherein, when the risk assessment information includes: a risk probability of establishing a service relationship with the enterprise, a risk score of the enterprise, and service prompt information, the plurality of rules at least include: If the probability of fraud or the probability of default in the risk probability is higher than the preset probability, the output decision result is to return the application; If the credit score in the risk score is lower than the preset score, the income in the risk score is lower than the income threshold, or the debt ratio in the risk score is higher than the debt ratio threshold, the output decision result is to return the application. 10. The method according to any one of claims 1-9, wherein the method further comprises: In response to receiving the service indication, establish a service relationship with the enterprise, and monitor the business data of the enterprise that has established the service relationship after receiving the service; Based on the service data after receiving the service, the risk control model is optimized. 11. An apparatus for assessing risk to an enterprise, comprising: an information determination unit, configured to determine the basic information of the enterprise based on the entered application information; a graph generation unit, configured to generate a knowledge graph of an enterprise based on the association relationship between the enterprise identification information in the basic information and the enterprise identification information in the enterprise information database; an information query unit, configured to query the business data of the enterprise and the public opinion information of the enterprise based on the basic information; The evaluation output unit is configured to input the basic information, the knowledge graph of the enterprise, the business data and the public opinion information into a risk control model to obtain risk evaluation information of the enterprise. 12. The apparatus according to claim 11, wherein the risk control model in the evaluation output unit includes: a risk relationship model and a risk scoring model; the risk evaluation information in the evaluation output unit includes: with The risk probability of the enterprise establishing a service relationship, the enterprise's risk score, and service prompt information; The evaluation output unit is further configured to: input the basic information, the knowledge graph of the enterprise and the public opinion information into a risk relationship model to obtain a risk probability of establishing a service relationship with the enterprise; The public opinion information is input into a risk scoring model to obtain the enterprise's risk score and service prompt information. 13. The apparatus of claim 12, wherein the apparatus further comprises at least one of: The risk relationship model is a relationship network model obtained based on RFM, NLP, and graph mining technology; The risk scoring model is a multiple regression model; The probability of risk includes probability of fraud, probability of default and probability of overdue; and The business data includes: number of recruits, recruiting time, operating conditions and liabilities. 14. The apparatus of claim 11, wherein the information determination unit comprises: The result identification subunit is configured to identify the application information entered in the paper version, and obtain the identification result; The result correction subunit is configured to use an intelligent correction algorithm to correct the recognition result to obtain a text sequence; an entity identification subunit configured to identify entities in the text sequence to obtain tagged entity data; and The information output subunit is configured to output the structured basic information of the enterprise based on the tagged named entity data. 15. The apparatus according to any one of claims 11-14, wherein the information determination unit comprises: an information retrieval subunit, configured to retrieve benchmark information corresponding to the enterprise in the application information based on the entered application information; wherein the benchmark information includes official information and/or historical information; an information verification subunit, configured to verify the application information based on the reference information; a prompt presentation subunit, configured to present prompt information for returning the application in response to the result of the verification indicating that the preset information fails the verification; The list adding subunit is configured to add the enterprise in the application information to the blacklist in response to the verification result indicating that the enterprise in the application information complies with the blacklist rule. 16. The apparatus according to claim 15, wherein the result of the verification in the information determination unit indicates that the enterprise in the application information complies with the blacklist including at least one of the following: The number of times that there is untrue information in the application information exceeds a predetermined threshold; The number of historical verifications exceeds the preset threshold. 17. The apparatus of any one of claims 11-16, wherein the apparatus further comprises: The result determination unit is configured to input the risk assessment information into the risk control decision model to obtain the decision result output by the risk control decision model. 18. The apparatus according to claim 17, wherein the risk control decision model in the result determination unit is a rule model formed by connecting a plurality of rules in series or in parallel. 19. The apparatus according to claim 18, wherein when the risk assessment information in the assessment output unit includes: a risk probability of establishing a service relationship with the enterprise, a risk score of the enterprise, and service prompt information, the The multiple rules in the result determination unit include at least: If the probability of fraud or the probability of default in the risk probability is higher than the preset probability, the output decision result is to return the application; If the credit score in the risk score is lower than the preset score, the income in the risk score is lower than the income threshold, or the debt ratio in the risk score is higher than the debt ratio threshold, the output decision result is to return the application. 20. The apparatus of any one of claims 11-19, wherein the apparatus further comprises: a data monitoring unit, configured to, in response to receiving the service indication, establish a service relationship with the enterprise, and monitor the business data of the enterprise that has established the service relationship after receiving the service; The model optimization unit is configured to optimize the risk control model based on the service data after receiving the service. 21. An electronic device/terminal/server, comprising: one or more processors; a storage device 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 method of any one of claims 1-10. 22. A computer-readable medium having stored thereon a computer program which, when executed by a processor, implements the method of any one of claims 1-10.