WO2019100852A1

WO2019100852A1 - Method and apparatus for implementing risk assessment

Info

Publication number: WO2019100852A1
Application number: PCT/CN2018/108918
Authority: WO
Inventors: 宋雨龙
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2017-11-22
Filing date: 2018-09-30
Publication date: 2019-05-31
Also published as: TW201926202A; CN108022167A; CN108022167B

Abstract

A method for implementing risk assessment, applied to a server. The method comprises: receiving a risk assessment request sent by a terminal of a user, and obtaining a risk assessment question of the user (110); obtaining assessment basic data of the user, and generating a recommended answer to at least one risk assessment question by using the assessment basic data (120); obtaining a risk model characteristic value of the user, based on the recommended answer (130); and generating a risk assessment result of the user according to the risk model characteristic value of the user, and returning the risk assessment result to the terminal of the user (140).

Description

Method and device for implementing risk assessment

Technical field

The present specification relates to the field of network communication technologies, and in particular, to a method and apparatus for implementing risk assessment.

Background technique

The continuous advancement of high technology has promoted financial innovation while promoting economic development. As a product of the combination of finance and technology, Internet finance plays an increasingly important role in daily life. Users can manage accounts, make payments, purchase various financial products, and more through the network.

Some financial products have certain requirements on the buyer's risk tolerance, and the user will conduct risk assessment before selling the financial products to the users. Risk assessment through the network is usually performed by displaying multiple questions to the user on the terminal, and the user gives an answer based on which the user's risk tolerance level is evaluated. Too many questions can cause a burden on the user, while too few problems can cause deviations in the evaluation results.

Summary of the invention

In view of this, the present specification provides a method for implementing risk assessment, which is applied to a server, and the method includes:

Receiving a risk assessment request sent by the user terminal, and acquiring a risk assessment question of the user;

Obtaining the evaluation basic data of the user, and using the evaluation basic data to generate at least one recommended answer of the risk assessment topic;

Obtaining a risk model feature value of the user based on the recommended answer;

Generating a risk assessment result of the user according to the risk model feature value of the user, and returning the result to the terminal of the user.

The method for implementing the risk assessment provided by the present specification is applied to a user terminal, and the method includes:

Sending the user's risk assessment request to the server according to the user's instruction;

Receiving, by the server, the risk assessment result of the user returned by the server to the user; the risk assessment result of the user is generated by the server after acquiring the risk assessment topic and the evaluation basic data of the user, and using the basic data of the assessment to generate at least one The recommended answer of the risk assessment topic is generated based on the user risk model feature value obtained based on the recommended answer.

The present specification also provides an apparatus for implementing risk assessment, which is applied to a server, and the apparatus includes:

a risk assessment request receiving unit, configured to receive a risk assessment request sent by the user terminal, and obtain a risk assessment question of the user;

a recommendation answer generating unit, configured to acquire the evaluation basic data of the user, and generate at least one recommended answer of the risk assessment topic by using the evaluation basic data;

a risk model feature value unit, configured to obtain a risk model feature value of the user based on the recommended answer;

The risk assessment result generating unit is configured to generate a risk assessment result of the user according to the risk model feature value of the user, and return the result to the terminal of the user.

The apparatus for implementing risk assessment provided by the present specification is applied to a terminal of a user, and the apparatus includes:

a risk assessment request sending unit, configured to send, according to an instruction of the user, the risk assessment request of the user to the server;

The risk assessment result receiving unit is configured to receive the risk assessment result of the user returned by the server, and display the result to the user; the risk assessment result of the user is obtained by the server after acquiring the risk assessment topic and the evaluation basic data of the user. A recommendation answer of at least one risk assessment topic is generated by using the evaluation basic data, and is generated according to the user risk model feature value obtained based on the recommended answer.

The computer device provided by the present specification includes: a memory and a processor; the memory stores a computer program executable by the processor; and when the processor runs the computer program, performing the risk assessment of the application on the server Implement the steps described in the method.

The present specification also provides a terminal comprising: a memory and a processor; the memory storing a computer program executable by the processor; and when the processor runs the computer program, performing risk assessment of the application on the terminal The steps described in the implementation method.

The present specification provides a computer readable storage medium having stored thereon a computer program that, when executed by a processor, performs the steps described above for implementing the risk assessment of the application at the server.

The present specification also provides a computer readable storage medium having stored thereon a computer program that, when executed by a processor, performs the steps described above for implementing the risk assessment on the terminal.

It can be seen from the above technical solution that in the embodiment of the present specification, the server generates a recommended answer of the user risk assessment topic according to the available evaluation basic data, and generates a user risk according to the risk model feature value based on the recommended answer. As a result of the evaluation, the user does not need to answer the question with the recommended answer, which reduces the user's operation and improves the efficiency of the risk assessment. At the same time, the recommended answer from the basic data of the evaluation usually accurately reflects the user's situation and avoids the user's memory. Errors caused by inaccuracies, operational errors, etc., improve the accuracy of risk assessment.

DRAWINGS

1 is a flowchart of a method for implementing risk assessment applied to a server in an embodiment of the present specification;

2 is a flowchart of a method for implementing risk assessment applied to a terminal in an embodiment of the present specification;

3 is a flowchart of processing of a server-side user risk assessment request in an application example of the present specification;

4 is a hardware structure diagram of a device where a terminal or a server is located;

5 is a logical structural diagram of an apparatus for implementing risk assessment applied to a server in an embodiment of the present specification;

FIG. 6 is a logical structural diagram of an apparatus for implementing risk assessment applied to a terminal in an embodiment of the present specification.

Detailed ways

The embodiment of the present specification proposes a new method for implementing risk assessment. After receiving the risk assessment request from the user terminal, the server obtains the user's risk assessment topic and the evaluation basic data, and uses the evaluation basic data to generate a recommendation answer, and The risk model evaluation result based on the recommended answer is used to generate the user's risk assessment result. The recommended answer can reduce the user's need to answer the question and answer the operation, and reduce the burden on the user, and the recommended answer generated by the evaluation basic data avoids the cause. Errors in the user's memory or incorrect operation result in the accuracy of risk assessment and increase the accuracy of risk assessment.

In the embodiment of the present specification, the user uses the service of a certain network service provider through his own terminal. The server of the network service provider and the terminal of the user are mutually accessible through the network, and the user can access the server through the client software installed on the terminal, or access the server through the browser or other application level of the terminal. The user's terminal may be a mobile phone, a tablet computer, a PC (Personal Computer), a notebook, etc.; the server may run on one device, or may be two or more devices sharing different responsibilities, The functions of the server in the embodiment of the present specification are implemented in cooperation with each other, and are not limited.

In the embodiment of the present specification, the flow of the risk assessment implementation method applied to the server is as shown in FIG. 1 , and the process applied to the user terminal is as shown in FIG. 2 .

On the terminal, in step 210, the user's risk assessment request is sent to the server according to the user's instruction.

At the server, step 110, receiving a risk assessment request sent by the user terminal, and acquiring the risk assessment topic of the user.

In the embodiment of the present specification, according to the service rule of the network service provider in the actual application scenario, when the user's risk assessment result is lacking to perform the service, the server informs the user through the terminal that the risk assessment needs to be performed; the user may also be on the terminal. Proactively initiate a risk assessment request. After receiving the indication of the user's risk assessment, the terminal sends the user's risk assessment request to the server.

After receiving the risk assessment request sent by the terminal, the server obtains the risk assessment question of the user. According to the risk assessment needs of the actual application scenario, the user's risk assessment topic may be different depending on the business to be performed, the characteristics of the user, and the like. In addition, the server can read the user's risk assessment topic from the predetermined network storage location, and can also request the risk assessment topic from other server terminals. The embodiments of the present specification do not limit the above two points.

On the server side, in step 120, the evaluation basic data of the user is obtained, and at least one recommended answer of the risk assessment topic is generated by using the evaluation basic data.

After obtaining the user's risk assessment topic, the server obtains the basic data of the user's evaluation. The evaluation basic data may be any data related to the user's risk assessment, and may include, for example, one or more of the user's registration information, the user's historical behavior data, and the evaluation conclusions of the user using various models.

In the embodiment of the present specification, the source of the evaluation basic data is not limited. For example, the server can be extracted from the system of the network service provider, or can be queried by other network service providers, government agencies, and the like. In some application scenarios, the server can obtain the data related to the topic as the basic data of the assessment according to the specific risk assessment topic.

In some application scenarios, the server may obtain user data as the basic data for evaluation after obtaining the permission of the user. Specifically, after receiving the risk assessment request of the terminal, the server may send a user data usage request to the terminal, and the terminal displays the user data usage request to the user; after receiving the user's confirmation operation, the terminal sends the user data usage permission to the server; After receiving the user data license, the server obtains the user's evaluation basic data.

The server uses the basic data of the assessment to automatically generate a recommended answer for at most one risk assessment topic. According to the specific risk assessment topic and the evaluation basic data, the server can use various methods to generate the recommended answers of the risk assessment topic, without limitation. The server can directly use some of the evaluation basic data as the answers to some risk assessment questions (such as the user's gender); some of the evaluation basic data can be statistically or calculated to obtain the answers to some risk assessment questions (eg, based on the assessment) The ID number in the basic data is used to calculate the age of the user, and the average stock holding duration of the user is calculated according to the transaction record of the user buying and selling stocks in the basic data of the evaluation; some basic data of the evaluation can also be used as a machine learning model for training completion. The input is based on the output of the model to obtain the recommended answer (such as the user's purchase of various financial assets in the evaluation basic data, browsing the history of various financial information into the trained model to assess the user's familiarity with the investment).

On the server side, in step 130, the risk model feature value of the user is obtained based on the recommended answer.

The risk model eigenvalue is all the input information of the user required to make a risk assessment conclusion for a certain user by using a certain risk model, and may include, for example, the user's gender, age, annual income, annual consumption, Asset quota, debt limit, and/or credit card limit, etc. The risk model can be any form that matches the needs of the actual application scenario and is not limited.

When the server generates a recommended answer for all the risk assessment questions, the server may generate some or all of the risk model feature values of the user by using the recommended answer (eg, directly recommend the answer as part or all of the risk model feature values) Instead of having to answer the risk assessment questions by the user.

When the server cannot generate a recommended answer for a risk assessment topic, or in some application scenarios, if it is desired to use the answer of the user-recognized risk assessment topic to perform risk assessment on the user, the following process may be used to obtain the user's Risk model eigenvalues:

The user's risk assessment topic and at least one recommended answer are sent by the server to the user's terminal. The terminal displays the risk assessment topic and at least one recommended answer delivered by the server to the user, and uses the recommended answer as the current answer of the corresponding risk assessment topic. The terminal modifies the current answer of the risk assessment topic according to the input of the user; and may include obtaining the current answer of the risk assessment topic according to the user input when receiving the input operation of the risk assessment topic without the recommended answer by the user; or may include When the user inputs the risk assessment topic with the recommended answer, the current answer of the risk assessment topic is modified according to the user's input. After receiving the uploading instruction of the user, the terminal uploads the current answer as the confirmation answer corresponding to the risk assessment topic to the server; wherein the confirmation answer is determined by the user according to the risk assessment topic and the recommended answer displayed by the terminal. After receiving the confirmation answer uploaded by the terminal, the server uses the confirmation answer to generate some or all of the risk model feature values of the user.

In some application scenarios, the risk model feature value may include other variables in addition to the risk assessment question answer (confirmed answer or recommended answer), and may include the user's historical behavior data in the evaluation basic data, and adopt the user's historical behavior data. Generate other risk model eigenvalues of the user other than the answer to the risk assessment topic. For example, according to the historical behavior data of the user accessing the stock forum included in the evaluation basic data, speaking in the stock forum, etc., the characteristic value of the participation degree of the user to the stock forum may be counted.

On the server side, in step 140, the risk assessment result of the user is generated according to the user's risk model feature value, and returned to the user's terminal.

On the terminal, in step 220, the risk assessment result of the user returned by the server is received and displayed to the user. The user's risk assessment result is obtained by the server after obtaining the user's risk assessment topic and the evaluation basic data, and uses the evaluation basic data to generate at least one recommended answer of the risk assessment topic, according to the user risk model eigenvalue obtained based on the recommended answer. generate.

The server takes the user's risk model feature value as the input of the risk model, and the output of the risk model is the user's risk assessment result. In one example, the risk model sets a predetermined weight for each risk model eigenvalue, and sets a predetermined score for each value interval of each risk model eigenvalue; when inputting a user's risk model eigenvalue The score of the eigenvalue of the risk model is obtained according to the value interval of the eigenvalue of the risk model of the user, and the weighted sum of the eigenvalue scores of the plurality of risk models is used as the risk assessment result of the user.

The risk assessment result can be a single assessment result, and can also include the user's evaluation results in two or more different aspects. The evaluation results of each aspect can be input with some or all of the risk model eigenvalues, based on different risks. Model to come.

In some application scenarios, it may be divided into several feature categories according to the characteristics and uses of the risk model feature values, and the risk model feature values of different categories may be used to generate different aspects of the evaluation results.

In one example, the risk model feature value includes at least one of the following feature categories: identity information, property status, and personal preference; wherein the identity information category includes at least one of the following risk model feature values: age, gender, education level, family structure; The status category includes at least one of the following risk model eigenvalues: financial assets, non-financial assets, credit card quotas, consumption levels, income levels, travel, debt levels, occupations and insurance, and debt repayment; when the user has an investment behavior, the individual The preference category includes at least one of the following risk model eigenvalues: the length of time the financial asset is held, the breadth of information browsing before the financial asset is purchased, the depth of information browsing before the financial asset is purchased, the speech of the investment community, the number of times the investment business is used, and the number of credit cards. When the user has no investment behavior, the personal preference includes at least one of the following risk model characteristic values: interest in financial asset investment, activity of financial business The number of credit cards, the number of public utility payments, and the number of donations. The risk assessment results in this example include two aspects: the risk tolerance assessment result and the preference assessment result, wherein the risk tolerance assessment result is based on at least one risk model characteristic value belonging to the identity information category, and at least one belonging to the property status category. The risk model feature value generation; the preference evaluation result is generated according to at least one risk model feature value belonging to the identity information category and at least one risk model feature value belonging to the personal preference category.

It can be seen that, in the embodiment of the present specification, the user terminal sends a risk assessment request to the server, and the server generates a recommended answer of the user risk assessment topic according to the available evaluation basic data, and adopts the risk model feature based on the recommended answer. The value generates the user's risk assessment result, and the recommended answer can reduce the user's need to answer the question and answer the operation, and improve the efficiency of the risk assessment; the recommended answer generated by the evaluation basic data avoids the wrong answer caused by the user's memory error or improper operation. Improve the accuracy of risk assessment.

The foregoing description of the specific embodiments of the specification has been described. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than the embodiments and still achieve the desired results. In addition, the processes depicted in the figures are not necessarily in a particular order or in a sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In an application example of this specification, a user may purchase a financial product sold by a financial product sales platform online, including funds, bonds, and financial management, through an App (application) of a financial product sales platform installed on the terminal. Products, etc. For some financial products with certain degree of risk, the financial product sales platform can only be sold to users whose risk tolerance and preference are in line with the requirements of each financial product. The financial product sales platform needs to risk the users who purchase these financial products for the first time. Evaluation. Users can also initiate risk assessments in the client app of the financial product sales platform.

When the user starts the application or requests the transaction to place an order, the server of the financial product sales platform queries whether the risk tolerance score and the preference score of the user are saved in the database, and if not, the user can perform risk assessment on the user. . The server sends a message to the user's terminal asking the user to confirm the risk assessment, and the terminal displays the message to the user. If the user agrees to conduct a risk assessment, the App sends a risk assessment request to the server. The user can also initiate risk assessment in the App, and the App sends a risk assessment request to the server according to the user's instructions.

The processing flow after the server receives the risk assessment request from the App is shown in Figure 3.

Step 305: Query a risk assessment topic applicable to the user from a database of risk assessment topics.

Step 310: Send a request message to the App for using the user data for answer recommendation.

In step 315, the response returned by the App is received. If the user agrees to use the user data, step 320 is performed; otherwise, step 335 is performed.

Step 320: Obtain historical behavior data of the browsing history, forum speech record, transaction record, and the like of the user on the platform, and the registration information of the user on the platform, as the basic data of the evaluation of the user.

Step 325, using the basic data of the evaluation to obtain a recommended answer of several risk assessment questions. For example, for the user's age topic, the user's age may be calculated according to the user's ID number; for example, the recommended answer of the user's interest in which financial products may be given according to the user's browsing history on the platform.

In step 330, the risk assessment topic and the recommended answer are sent to the App. For the risk assessment question that cannot be used to obtain the recommended answer by using the basic data of the evaluation, only the risk assessment topic itself is sent, and the user answers. Go to step 340.

The App displays the risk assessment title and the recommended answer to the user. The user can answer the question without the recommended answer, or modify the recommended answer. After confirming the answers to all the questions, the App is instructed to submit. The app sends the user's confirmation answer to the server.

In step 335, the risk assessment topic is sent to the App.

The App displays the risk assessment topic to the user, and the user answers each question and instructs the App to submit. The app sends the user's confirmation answer to the server.

Step 340, receiving a confirmation answer from the user from the App.

Step 345: using the user's confirmation answer as the partial risk model feature value, and generating other risk model feature values according to the user's historical behavior record.

Step 350: Enter the risk model feature value of the user into the risk tolerance model and the preference model to obtain the user's risk tolerance score and preference score.

In one example, the risk tolerance model is shown in Table 1:

Table 1

Table 2

In this example, the scores of the identity dimension, the asset dimension, the consumption dimension, and the income dimension may be determined according to the value range in which the user's individual risk model feature values are located in Table 2, and the highest score is used as the wealth level score of the user in Table 1. Then, the score of the eigenvalue of the risk model is determined according to the interval of the eigenvalues of each risk model in Table 1, and then the weighted sum of the scores is taken as the risk tolerance score of the user.

In this example, the risk model eigenvalues in the preference model are shown in Table 3:

table 3

According to the interval of the eigenvalues of each risk model in Table 3, the scores of the eigenvalues of the risk model are determined, and the scores of the eigenvalues of all the risk models are summed to obtain X, and then the user's preference score can be obtained according to Equation 1:

Exp(x)/(exp(x)+1)*100 Equation 1

Step 355, returning the user's risk tolerance score and preference score to the App, which is displayed to the user by the App.

Corresponding to the foregoing process implementation, the embodiment of the present specification further provides an apparatus for implementing risk assessment applied to a server, and an apparatus for implementing risk assessment applied to the terminal. Both devices can be implemented by software or by hardware or a combination of hardware and software. Taking the software implementation as an example, as a logical means, the CPU (Central Process Unit) of the device where the terminal or the server is located reads the corresponding computer program instructions into the memory. From the hardware level, in addition to the CPU, memory and memory shown in FIG. 4, the terminal in which the device for implementing the risk assessment usually includes other hardware such as a chip for transmitting and receiving wireless signals, and the device for implementing the risk assessment is located. The server device usually also includes other hardware such as a board for implementing network communication functions.

FIG. 5 is a schematic diagram of an apparatus for implementing risk assessment according to an embodiment of the present disclosure, which is applied to a server, where the apparatus includes a risk assessment request receiving unit, a recommended answer generating unit, a risk model feature value unit, and a risk assessment result generating unit. The risk assessment request receiving unit is configured to receive the risk assessment request sent by the user terminal, and obtain the risk assessment topic of the user; the recommended answer generation unit is configured to acquire the basic data of the assessment of the user, and generate at least one basic data by using the assessment basic data. a recommended answer of the risk assessment topic; a risk model feature value unit is configured to obtain a risk model feature value of the user based on the recommended answer; and a risk assessment result generating unit is configured to generate the user according to the risk model feature value of the user Risk assessment results are returned to the user's terminal.

Optionally, the risk model feature value unit is specifically used to generate one or all risk model feature values of the user by using a recommended answer; or send the user's risk assessment topic and at least one recommended answer. After receiving the confirmation answer uploaded by the terminal, the terminal of the user generates part or all of the risk model feature values of the user by using the confirmation answer, and the confirmation answer is determined by the user according to the risk assessment question and the recommended answer displayed by the terminal. .

Optionally, the evaluation basic data includes: historical behavior data of the user; the risk model feature value unit is specifically configured to: obtain a partial risk model feature value of the user based on the recommended answer, and adopt the history of the user Behavior data generates other risk model feature values for the user.

Optionally, the risk assessment result generating unit is specifically configured to: obtain a score of the eigenvalue of the risk model according to a value interval in which the eigenvalue of the risk model of the user is located, and weight the eigenvalue scores of the plurality of risk models And as a result of the risk assessment of the user.

In one example, the risk model feature value includes at least one feature category: identity information, property status, and personal preference; the identity information category includes at least one of the following risk model feature values: age, gender, education level, family structure; The property status category includes at least one of the following risk model characteristic values: financial assets, non-financial assets, credit card quota, consumption level, income level, travel status, debt level, occupation and insurance status, and debt repayment situation; In the case of investment behavior, the personal preference category includes at least one of the following risk model characteristic values: duration of holding the financial asset, breadth of information browsing before purchasing the financial asset, depth of information browsing before purchasing the financial asset, speech of the investment community, investment The number of times the business is used, the number of credit cards, the number of public utility contributions, and the number of donations; when the user has no investment behavior, the personal preferences include at least one of the following risk model characteristic values: interest in financial asset investment, and active financial business Degree, non-gold Interest of asset investment, credit card number, the number of public utilities payment, the number of donations.

In the above example, the risk assessment result may include: a risk tolerance evaluation result and a preference evaluation result; the risk tolerance evaluation result is based on at least one risk model characteristic value belonging to the identity information category, and at least one belonging to the property status category. The risk model feature value is generated; the preference evaluation result is generated according to at least one risk model feature value belonging to the identity information category and at least one risk model feature value belonging to the personal preference category.

FIG. 6 is a schematic diagram of an apparatus for implementing risk assessment according to an embodiment of the present disclosure, which is applied to a user terminal, where the apparatus includes a risk assessment request sending unit and a risk assessment result receiving unit, where the risk assessment request sending unit is used. Sending, by the user, the risk assessment request of the user to the server; the risk assessment result receiving unit is configured to receive the risk assessment result of the user returned by the server, and display the result to the user; the risk assessment result of the user is served by the service After obtaining the risk assessment topic and the evaluation basic data of the user, the terminal uses the evaluation basic data to generate a recommendation answer of at least one risk assessment topic, and generates the feature value of the user risk model obtained based on the recommended answer.

Optionally, the device further includes a recommended answer receiving unit, a current answer modifying unit, and a confirmation answer uploading unit, wherein: the recommended answer receiving unit is configured to receive the risk assessment topic of the user and at least one recommended answer delivered by the server And displaying to the user, using the recommended answer as the current answer of the corresponding risk assessment topic; the current answer modification unit is configured to modify the current answer of the risk assessment topic according to the user input; the confirmation answer uploading unit is configured to receive the upload instruction of the user, Upload the current answer as a confirmation answer to the corresponding risk assessment topic to the server.

Optionally, the risk assessment result includes: a risk tolerance evaluation result and a preference evaluation result.

Embodiments of the present specification provide a computer device including a memory and a processor. Wherein, the computer stores a computer program executable by the processor; when the processor runs the stored computer program, the processor executes the steps of the implementation method of the risk assessment applied to the server in the embodiment of the present specification. For a detailed description of each step of the implementation method of the risk assessment applied to the server, please refer to the previous content, and will not be repeated.

Embodiments of the present specification provide a terminal that includes a memory and a processor. Wherein, the computer stores a computer program executable by the processor; and when the processor runs the stored computer program, the processor executes the steps of the method for implementing the risk assessment applied to the terminal in the embodiment of the present specification. For a detailed description of each step of the implementation method of the risk assessment applied to the terminal, please refer to the previous content, and will not be repeated.

Embodiments of the present specification provide a computer readable storage medium having stored thereon computer programs that, when executed by a processor, perform an implementation method of risk assessment applied to a server in an embodiment of the present specification. Each step. For a detailed description of each step of the implementation method of the risk assessment applied to the server, please refer to the previous content, and will not be repeated.

Embodiments of the present specification provide a computer readable storage medium having stored thereon computer programs that, when executed by a processor, perform an implementation method of risk assessment applied to a terminal in an embodiment of the present specification The various steps. For a detailed description of each step of the implementation method of the risk assessment applied to the terminal, please refer to the previous content, and will not be repeated.

The above description is only the preferred embodiment of the present specification, and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc., which are made within the spirit and principles of the present application, should be included in the present application. Within the scope of protection.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory. Memory is an example of a computer readable medium.

Computer readable media includes both permanent and non-persistent, removable and non-removable media. Information storage can be implemented by any method or technology. The information can be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.

It is also to be understood that the terms "comprises" or "comprising" or "comprising" or any other variations are intended to encompass a non-exclusive inclusion, such that a process, method, article, Other elements not explicitly listed, or elements that are inherent to such a process, method, commodity, or equipment. An element defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, method, item, or device including the element.

Those skilled in the art will appreciate that embodiments of the present specification can be provided as a method, system, or computer program product. Thus, embodiments of the present specification can take the form of an entirely hardware embodiment, an entirely software embodiment or a combination of software and hardware. Moreover, embodiments of the present specification can take the form of a computer program product embodied on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer usable program code embodied therein. .

Claims

A method for implementing risk assessment is applied to a server, and the method includes:

Receiving a risk assessment request sent by the user terminal, and acquiring a risk assessment question of the user;

Obtaining the evaluation basic data of the user, and using the evaluation basic data to generate at least one recommended answer of the risk assessment topic;

Obtaining a risk model feature value of the user based on the recommended answer;

Generating a risk assessment result of the user according to the risk model feature value of the user, and returning the result to the terminal of the user.
The method according to claim 1, wherein the risk model feature value of the user is obtained based on a recommended answer, including one of the following:

Generating some or all of the risk model feature values of the user using the recommended answer; or,

Sending the risk assessment topic of the user and the at least one recommended answer to the terminal of the user, and after receiving the confirmation answer uploaded by the terminal, generating a partial or total risk model feature value of the user by using the confirmation answer, the confirmation The answer is determined by the user based on the risk assessment topic and the recommended answer displayed by the terminal.
The method according to claim 1, wherein the evaluation basic data comprises: historical behavior data of the user;

The obtaining the risk model feature value of the user based on the recommended answer comprises: obtaining a partial risk model feature value of the user based on the recommended answer, and generating other risk model feature values of the user by using the historical behavior data of the user.
The method according to claim 1, wherein the generating the risk assessment result of the user according to the risk model feature value of the user and returning to the terminal of the user comprises: according to a certain risk model feature of the user The value interval in which the value is located obtains the score of the eigenvalue of the risk model, and the weighted sum of the eigenvalue scores of the plurality of risk models is used as the risk assessment result of the user.
The method according to claim 1, wherein the risk model feature value comprises at least one of the following feature categories: identity information, property status, personal preference;

The identity information category includes at least one of the following risk model feature values: age, gender, education level, family structure;

The property status category includes at least one of the following risk model characteristic values: financial assets, non-financial assets, credit card quota, consumption level, income level, travel status, debt level, occupation and insurance status, and debt service;

When the user has an investment behavior, the personal preference category includes at least one risk model characteristic value: length of holding the financial asset, breadth of information browsing before purchasing the financial asset, depth of information browsing before purchasing the financial asset, investment community The status of the speech, the number of times the investment business is used, the number of credit cards, the number of public utility contributions, and the number of donations; when the user has no investment behavior, the personal preferences include at least one of the following risk model characteristic values: interest in financial asset investment , the level of activity of financial business, interest in investment in non-financial assets, the number of credit cards, the number of public utility payments, and the number of donations.
The method according to claim 5, wherein the risk assessment result comprises: a risk tolerance evaluation result and a preference evaluation result;

The risk tolerance evaluation result is generated according to at least one risk model feature value belonging to the identity information category and at least one risk model feature value belonging to the property status category;

The preference evaluation result is generated according to at least one risk model feature value belonging to the identity information category and at least one risk model feature value belonging to the personal preference category.
A method for implementing risk assessment is applied to a user terminal, and the method includes:

Sending the user's risk assessment request to the server according to the user's instruction;

Receiving, by the server, the risk assessment result of the user returned by the server to the user; the risk assessment result of the user is generated by the server after acquiring the risk assessment topic and the evaluation basic data of the user, and using the basic data of the assessment to generate at least one The recommended answer of the risk assessment topic is generated based on the user risk model feature value obtained based on the recommended answer.
The method of claim 7 further comprising:

Receiving, by the server, the risk assessment topic of the user and at least one recommended answer and displaying the recommended answer to the user, and using the recommended answer as the current answer of the corresponding risk assessment topic;

Modify the current answer to the risk assessment topic based on the user's input;

After receiving the upload instruction of the user, the current answer is uploaded to the server as the confirmation answer corresponding to the risk assessment question.
The method according to claim 7, wherein the risk assessment result comprises: a risk tolerance evaluation result and a preference evaluation result.
A device for implementing risk assessment is applied to a server, and the device includes:

a risk assessment request receiving unit, configured to receive a risk assessment request sent by the user terminal, and obtain a risk assessment question of the user;

a recommendation answer generating unit, configured to acquire the evaluation basic data of the user, and generate at least one recommended answer of the risk assessment topic by using the evaluation basic data;

a risk model feature value unit, configured to obtain a risk model feature value of the user based on the recommended answer;

The risk assessment result generating unit is configured to generate a risk assessment result of the user according to the risk model feature value of the user, and return the result to the terminal of the user.
The apparatus according to claim 10, wherein the risk model feature value unit is specifically used for one of the following:

Generating some or all of the risk model feature values of the user using the recommended answer; or,

Sending the risk assessment topic of the user and the at least one recommended answer to the terminal of the user, and after receiving the confirmation answer uploaded by the terminal, generating a partial or total risk model feature value of the user by using the confirmation answer, the confirmation The answer is determined by the user based on the risk assessment topic and the recommended answer displayed by the terminal.
The apparatus according to claim 10, wherein the evaluation basic data comprises: historical behavior data of the user;

The risk model feature value unit is specifically configured to: obtain a partial risk model feature value of the user based on the recommended answer, and generate other risk model feature values of the user by using the historical behavior data of the user.
The apparatus according to claim 10, wherein the risk assessment result generating unit is configured to: obtain a score of the eigenvalue of the risk model according to a value interval in which the risk value of the risk model of the user is located, and use a plurality of risk models The weighted sum of the feature value scores is used as the risk assessment result of the user.
The apparatus according to claim 10, wherein the risk model feature value comprises at least one of the following feature categories: identity information, property status, personal preference;

The identity information category includes at least one of the following risk model feature values: age, gender, education level, family structure;

The property status category includes at least one of the following risk model characteristic values: financial assets, non-financial assets, credit card quota, consumption level, income level, travel status, debt level, occupation and insurance status, and debt service;

When the user has an investment behavior, the personal preference category includes at least one risk model characteristic value: length of holding the financial asset, breadth of information browsing before purchasing the financial asset, depth of information browsing before purchasing the financial asset, investment community The status of the speech, the number of times the investment business is used, the number of credit cards, the number of public utility contributions, and the number of donations; when the user has no investment behavior, the personal preferences include at least one of the following risk model characteristic values: interest in financial asset investment , the level of activity of financial business, interest in investment in non-financial assets, the number of credit cards, the number of public utility payments, and the number of donations.
The apparatus according to claim 14, wherein the risk assessment result comprises: a risk tolerance evaluation result and a preference evaluation result;

The risk tolerance evaluation result is generated according to at least one risk model feature value belonging to the identity information category and at least one risk model feature value belonging to the property status category;

The preference evaluation result is generated according to at least one risk model feature value belonging to the identity information category and at least one risk model feature value belonging to the personal preference category.
A device for implementing risk assessment is applied to a user terminal, and the device includes:

a risk assessment request sending unit, configured to send, according to an instruction of the user, the risk assessment request of the user to the server;

The risk assessment result receiving unit is configured to receive the risk assessment result of the user returned by the server, and display the result to the user; the risk assessment result of the user is obtained by the server after acquiring the risk assessment topic and the evaluation basic data of the user. A recommendation answer of at least one risk assessment topic is generated by using the evaluation basic data, and is generated according to the user risk model feature value obtained based on the recommended answer.
The apparatus of claim 16 further comprising:

a recommended answer receiving unit, configured to receive the risk assessment topic of the user and at least one recommended answer delivered by the server, and display the recommended answer to the user, and use the recommended answer as the current answer of the corresponding risk assessment topic;

The current answer modification unit is configured to modify the current answer of the risk assessment topic according to the user input;

The confirmation answer uploading unit is configured to upload the current answer as a confirmation answer corresponding to the risk assessment topic to the server after receiving the upload instruction of the user.
The apparatus according to claim 16, wherein the risk assessment result comprises: a risk tolerance evaluation result and a preference evaluation result.
A computer device comprising: a memory and a processor; wherein the memory stores a computer program executable by the processor; and when the processor runs the computer program, performing the method of any one of claims 1 to step.
A terminal comprising: a memory and a processor; wherein the memory stores a computer program executable by a processor; and when the processor runs the computer program, performing the steps of any one of claims 7 to 9. .
A computer readable storage medium having stored thereon a computer program, the computer program being executed by a processor, performing the steps of any one of claims 1 to 6.
A computer readable storage medium having stored thereon a computer program, the computer program being executed by a processor, performing the steps of any one of claims 7 to 9.