Collateral risk level prediction method and device, electronic equipment and storage medium
By obtaining the user risk level and portrait data of users associated with the mortgage, and combining the expected user risk level, the mortgage risk level is determined, which solves the problem of inaccurate risk assessment of loan users in the existing technology, and realizes the risk of mortgaged property Accurate judgment and reduction of financial institutions' losses.
Patent Information
- Application Number
- CN202310754165.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-25
- Publication Date
- 2024-12-27
AI Technical Summary
The existing machine learning model is not accurate enough to predict the risk level of loan users, resulting in financial institutions facing high risk of loss when loans cannot be repaid on time.
By obtaining the user risk level and portrait data of the user associated with the collateral, input the pre-trained risk level prediction model, determine the collateral risk level based on the user risk level and the expected user risk level, and then perform preset operations to reduce the financial institution's Risk of capital loss.
Accurate judgment of the risk level of collateral is achieved, and the risk of capital loss of financial institutions is reduced. By timely correcting the risk level with the user's current risk level and portrait data, the degree of loan default is identified.
Smart Images
Figure CN119205294A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of risk prediction, and in particular to a method, device, electronic device and storage medium for predicting the risk level of collateral. Background Art
[0002] For financial institutions such as banks and pawnshops, when the loans they have lent cannot be repaid on time, they will suffer losses. Therefore, it is necessary to conduct real-time risk assessment on loan users to understand the asset changes and repayment ability of loan users as much as possible, and reduce the default risk of financial institutions.
[0003] At present, financial institutions assess the risk level of loan users by predicting the risk level of customers through machine learning models. However, the prediction results of machine learning models on customer risk levels are not accurate enough. Summary of the invention
[0004] In order to solve the problems in the related art, the embodiments of the present disclosure provide a method, device, electronic device and storage medium for predicting the risk level of collateral.
[0005] In a first aspect, the present disclosure provides a method for predicting the risk level of collateral, including:
[0006] Obtain the user risk level of the user associated with the collateral;
[0007] Acquire the portrait data of the associated user, input the portrait data into a pre-trained risk level prediction model, and predict the expected user risk level of the associated user at the target time;
[0008] The risk level of the collateral is determined based on the user risk level and the expected user risk level.
[0009] According to an embodiment of the present disclosure, obtaining the user risk level of the user associated with the collateral includes:
[0010] Receiving a prediction request; wherein the prediction request carries an identifier of the associated user;
[0011] The user risk level is obtained from a risk control database according to the identifier of the associated user.
[0012] According to an embodiment of the present disclosure, obtaining the user risk level of the user associated with the collateral includes:
[0013] Receiving a prediction request; wherein the prediction request carries an identifier of the associated user;
[0014] The user risk level is obtained from a risk control database according to the identifier of the associated user.
[0015] According to an embodiment of the present disclosure, the method further includes:
[0016] Determine the user risk level based on the configuration information of the risk assessment questionnaire;
[0017] The corresponding relationship between the user risk level and the user identification is stored in the risk control database.
[0018] According to an embodiment of the present disclosure, the associated user's portrait data includes at least one of consumption portrait data, behavior portrait data, and interest portrait data;
[0019] The step of inputting the portrait data into a pre-trained risk level prediction model to predict the expected user risk level of the associated user at the target time includes:
[0020] Inputting the consumption profile data into a pre-trained first prediction model to predict a first expected user risk level of the associated user at a target time; and / or
[0021] Inputting the behavior profile data into a pre-trained second prediction model to predict a second expected user risk level of the associated user at a target time; and / or
[0022] Inputting the interest portrait data into a pre-trained third prediction model to predict a third expected user risk level of the associated user at a target time;
[0023] The expected user risk level of the associated user at the target moment is calculated based on the first expected user risk level and / or the second expected user risk level and / or the third expected user risk level and corresponding configured weight parameters.
[0024] According to an embodiment of the present disclosure, determining the risk level of collateral according to the user risk level and the expected user risk level includes:
[0025] If the user risk level and the expected user risk level are the same, the collateral risk level is set to medium;
[0026] If the user risk level and the expected user risk level are different, the collateral risk level is set to a low level or a high level accordingly.
[0027] According to an embodiment of the present disclosure, the method further includes:
[0028] Execute a preset operation based on the risk level of the collateral.
[0029] In a second aspect, an embodiment of the present disclosure provides a collateral risk level prediction device, comprising:
[0030] An acquisition module configured to acquire a user risk level of a user associated with the collateral;
[0031] A prediction module is configured to obtain the portrait data of the associated user, input the portrait data into a pre-trained risk level prediction model, and predict the expected user risk level of the associated user at a target time;
[0032] The determination module is configured to determine the risk level of the collateral according to the user risk level and the expected user risk level.
[0033] According to an embodiment of the present disclosure, the part of the acquisition module that acquires the user risk level of the user associated with the collateral is configured as follows:
[0034] Receiving a prediction request; wherein the prediction request carries an identifier of the associated user;
[0035] The user risk level is obtained from a risk control database according to the identifier of the associated user.
[0036] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer instructions, and wherein the one or more computer instructions are executed by the processor to implement a method as described in any one of the first aspects.
[0037] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium on which computer instructions are stored. When the computer instructions are executed by a processor, the method described in any one of the first aspects is implemented.
[0038] According to the technical solution provided by the embodiment of the present disclosure, the user risk level of the user associated with the collateral is obtained; the portrait data of the associated user is obtained, and the portrait data is input into the pre-trained risk level prediction model to predict the expected user risk level of the associated user at the target time; the risk level of the collateral is determined according to the user risk level and the expected user risk level. When determining the risk level of the collateral, the above technical solution uses the user risk level of the user associated with the collateral in combination with the expected user risk level at the target time to make a judgment. The expected user risk level is related to the user's portrait data, so that the user's current risk level can be corrected in time, and then the degree of loan default can be identified according to the user's current risk level, which helps to achieve accurate judgment of the risk level of the collateral and reduces the risk of financial institution capital loss.
[0039] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:
[0041] Figure 1 A flow chart of a method for predicting the risk level of collateral according to an embodiment of the present disclosure is shown.
[0042] Figure 2 A structural block diagram of a device for predicting risk level of collateral according to an embodiment of the present disclosure is shown.
[0043] Figure 3 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown.
[0044] Figure 4 A schematic diagram showing the structure of a computer system suitable for implementing the method according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0045] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.
[0046] In the present disclosure, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, numbers, steps, behaviors, components, parts, or a combination thereof disclosed in the present specification, and are not intended to exclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or a combination thereof exist or are added.
[0047] It should also be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0048] In the present disclosure, if it involves operations of obtaining user information or user data or displaying user information or user data to others, the operations are all authorized and confirmed by the user, or actively selected by the user.
[0049] For financial institutions such as banks and pawnshops, when the loans they have lent cannot be repaid on time, they will suffer losses. Therefore, it is necessary to conduct real-time risk assessment on loan users to understand the asset changes and repayment ability of loan users as much as possible, and reduce the default risk of financial institutions.
[0050] At present, financial institutions assess the risk level of loan users by predicting the risk level of customers through machine learning models. However, the prediction results of machine learning models on customer risk levels are not accurate enough.
[0051] In order to solve the above technical problems, the present application discloses a method for predicting the risk level of collateral, including: obtaining the user risk level of the user associated with the collateral; obtaining the portrait data of the associated user, inputting the portrait data into a pre-trained risk level prediction model, and predicting the expected user risk level of the associated user at the target time; determining the risk level of the collateral according to the user risk level and the expected user risk level. When determining the risk level of the collateral, the above technical solution uses the user risk level of the user associated with the collateral in combination with the expected user risk level at the target time to make a judgment. The expected user risk level is related to the user's portrait data, so that the user's current risk level can be corrected in time, and then the degree of loan default can be identified according to the user's current risk level, which helps to achieve accurate judgment of the risk level of the collateral and reduces the risk of capital loss of financial institutions.
[0052] Figure 1 A flow chart showing a method for predicting the risk level of collateral according to an embodiment of the present disclosure is shown. Figure 1 As shown, the collateral risk level prediction method includes the following steps S101-S103:
[0053] In step S101, the user risk level of the user associated with the collateral is obtained;
[0054] In step S102, the portrait data of the associated user is obtained, and the portrait data is input into a pre-trained risk level prediction model to predict the expected user risk level of the associated user at the target time;
[0055] In step S103, the risk level of the collateral is determined according to the user risk level and the expected user risk level.
[0056] According to an embodiment of the present disclosure, obtaining the user risk level of the user associated with the collateral includes:
[0057] Receiving a prediction request; wherein the prediction request carries an identifier of the associated user;
[0058] The user risk level is obtained from a risk control database according to the identifier of the associated user.
[0059] In the disclosed method, the identifier of the associated user may be the user's identity code, bank card number, contract number, etc.
[0060] In the present disclosure, the user risk level is the risk level assessed on the user when the user handles a mortgage business.
[0061] According to an embodiment of the present disclosure, the collateral risk level prediction method further includes:
[0062] Determine the user risk level based on the configuration information of the risk assessment questionnaire;
[0063] The corresponding relationship between the user risk level and the user identification is stored in the risk control database.
[0064] In the present disclosure, the user risk level is determined based on the configuration information of the risk assessment questionnaire, and the configuration information is pre-set survey information, including the user's historical consumption data, historical income data, historical asset information, job position, etc., which is used to investigate the user's assets and credit background.
[0065] According to an embodiment of the present disclosure, the associated user's portrait data includes at least one of consumption portrait data, behavior portrait data, and interest portrait data;
[0066] The step of inputting the portrait data into a pre-trained risk level prediction model to predict the expected user risk level of the associated user at the target time includes:
[0067] Inputting the consumption profile data into a pre-trained first prediction model to predict a first expected user risk level of the associated user at a target time; and / or
[0068] Inputting the behavior profile data into a pre-trained second prediction model to predict a second expected user risk level of the associated user at a target time; and / or
[0069] Inputting the interest portrait data into a pre-trained third prediction model to predict a third expected user risk level of the associated user at a target time;
[0070] The expected user risk level of the associated user at the target moment is calculated based on the first expected user risk level and / or the second expected user risk level and / or the third expected user risk level and corresponding configured weight parameters.
[0071] In the present disclosure method, the consumption profile data refers to the historical consumption data of the user from the date of the previous risk assessment to the time of this prediction, including the total consumption amount, the maximum single consumption amount, the average monthly consumption amount, the place where the consumption behavior occurred, and other data of the user during this time period. The behavior profile data refers to the historical behavior data of the user from the date of the previous risk assessment to the time of this prediction, including the total loan amount, the maximum single loan amount, the place where the loan behavior occurred, the loan collateral, and other data of the user during this time period. The interest profile data refers to the historical income source and expenditure destination data of the user from the date of the previous risk assessment to the time of this prediction, including data such as work unit, salary income, income interval time, and consumer object category.
[0072] In the disclosed method, the first prediction model, the second prediction model, and the third prediction model are pre-trained machine learning models, such as naive Bayes model, decision tree model, support vector machine model, etc., wherein the first prediction model uses the user's consumption profile data as a training sample and outputs the first expected user risk level; similarly, the second prediction model uses the user's behavior profile data as a training sample and outputs the second expected user risk level; the first prediction model uses the user's interest profile data as a training sample and outputs the third expected user risk level. For relevant content about model training, please refer to the prior art, and this disclosure will not elaborate on it here.
[0073] In the disclosed method, the expected risk level of the associated user at the target moment can be calculated according to the first expected user risk level, the second expected user risk level, the third expected user risk level and the corresponding configured weight parameters. For example, the low risk score is 1, the medium risk score is 2, and the high risk score is 3. The first expected user risk level of user A is low risk, the weight parameter is 20%, the second expected user risk level is high risk, the weight is 45%, and the third expected user risk level is medium risk, the weight parameter is 30%, then the expected user risk level score is 1*20%+3*45%+2*30%=2.15, and the preset user risk level score is: low risk 1-1.6, medium risk 1.6-2.4, high risk 2.4-3, then the expected user risk level of the associated user at the target moment is medium risk.
[0074] According to an embodiment of the present disclosure, determining the risk level of collateral according to the user risk level and the expected user risk level includes:
[0075] If the user risk level and the expected user risk level are the same, the collateral risk level is set to medium;
[0076] If the user risk level and the expected user risk level are different, the collateral risk level is set to a low level or a high level accordingly.
[0077] In the disclosed method, if the user risk level and the expected user risk level are the same, the collateral risk level is set to a medium level. For example, if the user risk level is high and the expected user risk level is also high, it means that the user's risk level at the target time has not changed compared with when handling financial business, and the repayment of the collateral left in the financial institution may be large, and the probability of causing financial institution losses is small, so the collateral risk level is set to medium risk; if the user risk level is medium and the expected user risk level is high, it means that the user's risk level at the target time is higher than when handling financial business, and the collateral left in the financial institution may not be repaid, which may cause financial institution losses, so the collateral risk level is set to high risk; if the user risk level is high and the expected user risk level is medium, it means that the user's risk level at the target time is lower than when handling financial business, and the overpayment of the collateral left in the financial institution will not cause financial institution losses, so the collateral risk level is set to low risk.
[0078] According to an embodiment of the present disclosure, the collateral risk level prediction method further includes:
[0079] Execute a preset operation based on the risk level of the collateral.
[0080] In the disclosed method, the preset operations include: when the collateral risk level is medium or low, the financial institution maintains the collateral amount unchanged or reduces the collateral amount; when the collateral risk level is high, the financial institution requires the user to increase the collateral amount.
[0081] Figure 2 The structural block diagram of the collateral risk level prediction device according to the embodiment of the present disclosure is shown. The device can be implemented as part or all of the electronic device through software, hardware or a combination of both.
[0082] like Figure 2 As shown, the collateral risk level prediction device 200 includes an acquisition module 210 , a prediction module 220 , and a determination module 230 .
[0083] An acquisition module 210 is configured to acquire a user risk level of a user associated with the collateral;
[0084] The prediction module 220 is configured to obtain the portrait data of the associated user, input the portrait data into a pre-trained risk level prediction model, and predict the expected user risk level of the associated user at the target time;
[0085] The determination module 230 is configured to determine the risk level of the collateral according to the user risk level and the expected user risk level.
[0086] According to the technical solution provided by the embodiment of the present disclosure, when determining the risk level of the collateral, the user risk level of the user associated with the collateral is combined with the expected user risk level at the target moment for judgment. The expected user risk level is related to the user's portrait data, so that the user's current risk level can be corrected in time, and then the degree of loan default can be identified based on the user's current risk level, which helps to achieve accurate judgment of the risk level of the collateral and reduce the risk of capital loss for financial institutions.
[0087] According to an embodiment of the present disclosure, obtaining the user risk level of the user associated with the collateral includes:
[0088] Receiving a prediction request; wherein the prediction request carries an identifier of the associated user;
[0089] The user risk level is obtained from a risk control database according to the identifier of the associated user.
[0090] In the disclosed method, the identifier of the associated user may be the user's identity code, bank card number, contract number, etc.
[0091] In the present disclosure, the user risk level is the risk level assessed on the user when the user handles a mortgage business.
[0092] According to an embodiment of the present disclosure, the collateral risk level prediction device further includes:
[0093] A second determination module is configured to determine the user risk level according to the configuration information of the risk assessment questionnaire;
[0094] The corresponding relationship between the user risk level and the user identification is stored in the risk control database.
[0095] In the present disclosure, the user risk level is determined based on the configuration information of the risk assessment questionnaire, and the configuration information is pre-set survey information, including the user's historical consumption data, historical income data, historical asset information, job position, etc., which is used to investigate the user's assets and credit background.
[0096] According to an embodiment of the present disclosure, the associated user's portrait data includes at least one of consumption portrait data, behavior portrait data, and interest portrait data;
[0097] The step of inputting the portrait data into a pre-trained risk level prediction model to predict the expected user risk level of the associated user at the target time includes:
[0098] Inputting the consumption profile data into a pre-trained first prediction model to predict a first expected user risk level of the associated user at a target time; and / or
[0099] Inputting the behavior profile data into a pre-trained second prediction model to predict a second expected user risk level of the associated user at a target time; and / or
[0100] Inputting the interest portrait data into a pre-trained third prediction model to predict a third expected user risk level of the associated user at a target time;
[0101] The expected user risk level of the associated user at the target time is calculated based on the first expected user risk level and / or the second expected user risk level and / or the third expected user risk level and corresponding configured weight parameters.
[0102] In the present disclosure method, the consumption profile data refers to the historical consumption data of the user from the date of the previous risk assessment to the time of this prediction, including the total consumption amount, the maximum single consumption amount, the average monthly consumption amount, the place where the consumption behavior occurred, and other data of the user during this time period. The behavior profile data refers to the historical behavior data of the user from the date of the previous risk assessment to the time of this prediction, including the total loan amount, the maximum single loan amount, the place where the loan behavior occurred, the loan collateral, and other data of the user during this time period. The interest profile data refers to the historical income source and expenditure destination data of the user from the date of the previous risk assessment to the time of this prediction, including data such as work unit, salary income, income interval time, and consumer object category.
[0103] In the disclosed method, the expected risk level of the associated user at the target moment can be calculated according to the first expected user risk level, the second expected user risk level, the third expected user risk level and the corresponding configured weight parameters. For example, the low risk score is 1, the medium risk score is 2, and the high risk score is 3. The first expected user risk level of user A is low risk, the weight parameter is 20%, the second expected user risk level is high risk, the weight is 45%, and the third expected user risk level is medium risk, the weight parameter is 30%, then the expected user risk level score is 1*20%+3*45%+2*30%=2.15, and the preset user risk level score is: low risk 1-1.6, medium risk 1.6-2.4, high risk 2.4-3, then the expected user risk level of the associated user at the target moment is medium risk.
[0104] According to an embodiment of the present disclosure, determining the risk level of collateral according to the user risk level and the expected user risk level includes:
[0105] If the user risk level and the expected user risk level are the same, the collateral risk level is set to medium;
[0106] If the user risk level and the expected user risk level are different, the collateral risk level is set to a low level or a high level accordingly.
[0107] In the disclosed method, if the user risk level and the expected user risk level are the same, the collateral risk level is set to a medium level. For example, if the user risk level is high and the expected user risk level is also high, it means that the user's risk level at the target time has not changed compared with when handling financial business, and the repayment of the collateral left in the financial institution may be large, and the probability of causing financial institution losses is small, so the collateral risk level is set to medium risk; if the user risk level is medium and the expected user risk level is high, it means that the user's risk level at the target time is higher than when handling financial business, and the collateral left in the financial institution may not be repaid, which may cause financial institution losses, so the collateral risk level is set to high risk; if the user risk level is high and the expected user risk level is medium, it means that the user's risk level at the target time is lower than when handling financial business, and the overpayment of the collateral left in the financial institution will not cause financial institution losses, so the collateral risk level is set to low risk.
[0108] According to an embodiment of the present disclosure, the collateral risk level prediction device further includes:
[0109] The execution module is configured to execute a preset operation based on the risk level of the collateral.
[0110] In the disclosed method, the preset operations include: when the collateral risk level is medium or low, the financial institution maintains the collateral amount unchanged or reduces the collateral amount; when the collateral risk level is high, the financial institution requires the user to increase the collateral amount.
[0111] The present disclosure also discloses an electronic device, Figure 3 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown.
[0112] like Figure 3 As shown, the electronic device includes a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method according to an embodiment of the present disclosure.
[0113] A method for predicting the risk level of collateral, comprising:
[0114] Obtain the user risk level of the user associated with the collateral;
[0115] Acquire the portrait data of the associated user, input the portrait data into a pre-trained risk level prediction model, and predict the expected user risk level of the associated user at the target time;
[0116] The risk level of the collateral is determined based on the user risk level and the expected user risk level.
[0117] According to an embodiment of the present disclosure, obtaining the user risk level of the user associated with the collateral includes:
[0118] Receiving a prediction request; wherein the prediction request carries an identifier of the associated user;
[0119] The user risk level is obtained from a risk control database according to the identifier of the associated user.
[0120] According to an embodiment of the present disclosure, the collateral risk level prediction method further includes:
[0121] Determine the user risk level based on the configuration information of the risk assessment questionnaire;
[0122] The corresponding relationship between the user risk level and the user identification is stored in the risk control database.
[0123] According to an embodiment of the present disclosure, the associated user's portrait data includes at least one of consumption portrait data, behavior portrait data, and interest portrait data;
[0124] The step of inputting the portrait data into a pre-trained risk level prediction model to predict the expected user risk level of the associated user at the target time includes:
[0125] Inputting the consumption profile data into a pre-trained first prediction model to predict a first expected user risk level of the associated user at a target time; and / or
[0126] Inputting the behavior profile data into a pre-trained second prediction model to predict a second expected user risk level of the associated user at a target time; and / or
[0127] Inputting the interest portrait data into a pre-trained third prediction model to predict a third expected user risk level of the associated user at a target time;
[0128] The expected user risk level of the associated user at the target moment is calculated based on the first expected user risk level and / or the second expected user risk level and / or the third expected user risk level and corresponding configured weight parameters.
[0129] According to an embodiment of the present disclosure, determining the risk level of collateral according to the user risk level and the expected user risk level includes:
[0130] If the user risk level and the expected user risk level are the same, the collateral risk level is set to medium;
[0131] If the user risk level and the expected user risk level are different, the collateral risk level is set to a low level or a high level accordingly.
[0132] According to an embodiment of the present disclosure, the collateral risk level prediction method further includes:
[0133] Execute a preset operation based on the risk level of the collateral.
[0134] Figure 4 A schematic diagram showing the structure of a computer system suitable for implementing the method according to an embodiment of the present disclosure is shown.
[0135] like Figure 4 As shown, the computer system includes a processing unit, which can perform the various methods in the above-mentioned embodiments according to the program stored in the read-only memory (ROM) or the program loaded from the storage part into the random access memory (RAM). In the RAM, various programs and data required for the operation of the computer system are also stored. The processing unit, ROM and RAM are connected to each other through a bus. The input / output (I / O) interface is also connected to the bus.
[0136] The following components are connected to the I / O interface: an input part including a keyboard, a mouse, etc.; an output part including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage part including a hard disk, etc.; and a communication part including a network interface card such as a LAN card, a modem, etc. The communication part performs a communication process via a network such as the Internet. The drive is also connected to the I / O interface as needed. Removable media, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on the drive as needed so that the computer program read therefrom is installed into the storage part as needed. Among them, the processing unit can be implemented as a processing unit such as a CPU, a GPU, a TPU, an FPGA, an NPU, etc.
[0137] In particular, according to an embodiment of the present disclosure, the method described above can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes a program code for executing the above method. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium.
[0138] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0139] The units or modules involved in the embodiments described in the present disclosure may be implemented by software or by programmable hardware. The units or modules described may also be set in a processor, and the names of these units or modules do not constitute limitations on the units or modules themselves in some cases.
[0140] As another aspect, the present disclosure further provides a computer-readable storage medium, which may be a computer-readable storage medium included in the electronic device or computer system in the above embodiment; or a computer-readable storage medium that exists independently and is not assembled into a device. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the method described in the present disclosure.
[0141] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. 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 a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.
Claims
1. A method for predicting the risk level of collateral, characterized in that: include: Obtain the user risk level of the user associated with the collateral; Acquire the portrait data of the associated user, input the portrait data into a pre-trained risk level prediction model, and predict the expected user risk level of the associated user at the target time; The risk level of the collateral is determined based on the user risk level and the expected user risk level.
2. The method for predicting the risk level of collateral according to claim 1, characterized in that: The obtaining of the user risk level of the user associated with the collateral includes: Receiving a prediction request; wherein the prediction request carries an identifier of the associated user; The user risk level is obtained from a risk control database according to the identifier of the associated user.
3. The method for predicting the risk level of collateral according to claim 2, characterized in that: The method further comprises: Determine the user risk level based on the configuration information of the risk assessment questionnaire; The corresponding relationship between the user risk level and the user identification is stored in the risk control database.
4. The method for predicting the risk level of collateral according to claim 1, characterized in that: The associated user's portrait data includes at least one of consumption portrait data, behavior portrait data, and interest portrait data; The step of inputting the portrait data into a pre-trained risk level prediction model to predict the expected user risk level of the associated user at the target time includes: Inputting the consumption profile data into a pre-trained first prediction model to predict a first expected user risk level of the associated user at a target time; and / or Inputting the behavior profile data into a pre-trained second prediction model to predict a second expected user risk level of the associated user at a target time; and / or Inputting the interest portrait data into a pre-trained third prediction model to predict a third expected user risk level of the associated user at a target time; The expected user risk level of the associated user at the target time is calculated based on the first expected user risk level and / or the second expected user risk level and / or the third expected user risk level and corresponding configured weight parameters.
5. The method for predicting the risk level of collateral according to claim 1, characterized in that: Determining the risk level of the collateral according to the user risk level and the expected user risk level includes: If the user risk level and the expected user risk level are the same, the collateral risk level is set to medium; If the user risk level and the expected user risk level are different, the collateral risk level is set to a low level or a high level accordingly.
6. The method for predicting the risk level of collateral according to any one of claims 1 to 5, characterized in that: The method further comprises: Execute a preset operation based on the risk level of the collateral.
7. A device for predicting the risk level of collateral, characterized in that: include: An acquisition module configured to acquire a user risk level of a user associated with the collateral; A prediction module is configured to obtain the portrait data of the associated user, input the portrait data into a pre-trained risk level prediction model, and predict the expected user risk level of the associated user at a target time; The determination module is configured to determine the risk level of the collateral according to the user risk level and the expected user risk level.
8. The device for predicting the risk level of collateral according to claim 7, characterized in that: The part of the acquisition module that acquires the user risk level of the user associated with the collateral is configured as follows: Receiving a prediction request; wherein the prediction request carries an identifier of the associated user; The user risk level is obtained from a risk control database according to the identifier of the associated user.
9. An electronic device, characterized in that: The method comprises a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method steps described in any one of claims 1-6.
10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, the method steps described in any one of claims 1 to 6 are implemented.