Automobile financial risk assessment method, system and equipment based on intelligent optimization algorithm

Abstract

The present invention discloses an automobile finance risk assessment method based on an intelligent optimization algorithm, which relates to the field of data processing technology. The method comprises: obtaining an automobile finance target task, obtaining multiple subtasks, and obtaining sub-feature values ​​corresponding to the subtasks; obtaining a first contribution degree based on an intelligent optimization algorithm and subtasks containing a first parameter, and obtaining a sub-risk index based on a risk assessment model and sub-feature values; obtaining a first comprehensive risk index based on multiple first contribution degrees and sub-risk indexes; if the first comprehensive risk index exceeds a risk threshold, the first parameter is corrected and a second parameter is formed, a second contribution degree is obtained, and a second comprehensive risk index is obtained; if the second comprehensive risk index is lower than the risk threshold, an automobile finance target task adjustment strategy is obtained based on the first parameter and the second parameter. An automobile finance risk assessment system based on an intelligent optimization algorithm is also provided. The present invention has the advantages of being scientific and accurate, dynamically adjusted, and having good auxiliary decision-making effects.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an automobile financial risk assessment method, system and device based on an intelligent optimization algorithm. Background Art

[0002] With the rapid development of the automobile industry and the increasing diversification of consumer demand, automobile financial services have become an important means to promote automobile sales and market expansion. Automobile finance not only covers traditional car purchase loans, but also extends to multiple fields such as leasing, insurance, and repair and maintenance financing, providing consumers with more flexible and diverse car purchase and use solutions. However, with the continuous expansion of automobile financial business, the risks it faces are becoming increasingly complex and changeable, including but not limited to credit risk, market risk, operational risk, etc. How to accurately and efficiently evaluate and manage these risks is crucial to the sound operation of automobile financial institutions.

[0003] Traditional auto finance risk assessment methods mostly rely on expert experience, statistical models or simple scoring systems. These methods may be more effective when dealing with small-scale, single-type data, but their accuracy and efficiency are insufficient when faced with complex scenarios with big data, multiple dimensions and nonlinear relationships. Especially when it is necessary to consider multiple subtasks (such as vehicle value, customer credit, customer income, loan interest rate, loan term and repayment method, etc.), it is often difficult to fully capture the dynamic correlation and potential impact between various factors, resulting in inaccurate risk assessment results. More importantly, it is impossible to effectively guide decisions such as adjustments to auto finance business or adjustments to customer requirements after risk assessment. Summary of the invention

[0004] In view of the defects in the prior art, the present invention provides an automobile financial risk assessment method, system and device based on an intelligent optimization algorithm.

[0005] A method for assessing automobile financial risk based on an intelligent optimization algorithm comprises: obtaining an automobile financial target task, and obtaining a plurality of subtasks according to the automobile financial target task, and obtaining sub-feature values ​​corresponding to the subtasks; obtaining a first contribution degree corresponding to each subtask based on an intelligent optimization algorithm including a first parameter and each subtask, and obtaining a sub-risk index corresponding to each subtask based on a risk assessment model and the sub-feature values ​​corresponding to each subtask; obtaining a first comprehensive risk index of the automobile financial target task according to the plurality of first contribution degrees and the plurality of sub-risk indexes; if the first comprehensive risk index exceeds a risk threshold, correcting the first parameter and forming a second parameter, and obtaining a second contribution degree corresponding to each subtask based on the intelligent optimization algorithm including a second parameter and each subtask, and obtaining a second comprehensive risk index of the automobile financial target task according to the plurality of second contribution degrees and the plurality of sub-risk indexes; if the second comprehensive risk index is lower than the risk threshold, obtaining an adjustment strategy for the automobile financial target task according to the first parameter and the second parameter.

[0006] Preferably, modifying the first parameter to form the second parameter includes: obtaining a reduction ratio according to the first comprehensive risk indicator and the risk threshold; and modifying the first parameter according to the reduction ratio to form the second parameter.

[0007] Preferably, the first parameter is corrected according to the reduction ratio and the second parameter is formed as: Among them, α1 is the first parameter, α2 is the second parameter, R1 is the first comprehensive risk indicator, and T is the risk threshold.

[0008] Preferably, obtaining the first contribution degree corresponding to each subtask based on the intelligent optimization algorithm including the first parameter and each subtask includes: obtaining the allocation index corresponding to the i-th subtask; obtaining the first contribution degree corresponding to the i-th subtask based on the intelligent optimization algorithm including the first parameter and the allocation index corresponding to the i-th subtask.

[0009] Preferably, the intelligent optimization algorithm for obtaining the first contribution corresponding to the i-th subtask based on the intelligent optimization algorithm including the first parameter and the allocation index corresponding to the i-th subtask includes: i1 =α1·A i Among them, C i1 is the first contribution corresponding to the i-th subtask, α1 is the first parameter, A i is the allocation indicator corresponding to the i-th subtask.

[0010] Preferably, the risk assessment model in which the sub-risk indicators corresponding to each sub-task are obtained based on the risk assessment model and the sub-feature values ​​corresponding to each sub-task is expressed as: i =β i ·ln(h i +1); where r iis the sub-risk indicator corresponding to the i-th sub-task, β i is the adjustment coefficient corresponding to the i-th subtask, h i is the sub-feature value corresponding to the i-th subtask.

[0011] Preferably, the first comprehensive risk index of the automobile finance target task is obtained according to the multiple first contribution degrees and the multiple sub-risk indexes as follows: Among them, R1 is the first comprehensive risk indicator, C j1 is the first contribution corresponding to the jth subtask, r j is the sub-risk indicator corresponding to the j-th subtask, and n is the number of subtasks.

[0012] A car finance risk assessment system based on an intelligent optimization algorithm is also provided. The system is used to implement a car finance risk assessment method based on an intelligent optimization algorithm. The system includes: an acquisition module, which is used to acquire a car finance target task, and acquire multiple subtasks according to the car finance target task, and acquire sub-feature values ​​corresponding to the subtasks; a first calculation module, which is used to acquire a first contribution corresponding to each subtask based on an intelligent optimization algorithm including a first parameter and each subtask, and acquire a sub-risk index corresponding to each subtask based on a risk assessment model and the sub-feature values ​​corresponding to each subtask; a second calculation module, which is used to acquire a first comprehensive risk index of the car finance target task based on multiple first contribution degrees and multiple sub-risk indicators; a risk assessment and optimization module, which, if the first comprehensive risk index exceeds a risk threshold, corrects the first parameter and forms a second parameter, and acquires a second contribution corresponding to each subtask based on the intelligent optimization algorithm including a second parameter and each subtask, and acquires a second comprehensive risk index of the car finance target task based on multiple second contribution degrees and multiple sub-risk indicators; and a risk assessment and adjustment module, which, if the second comprehensive risk index is lower than the risk threshold, acquires an adjustment strategy for the car finance target task based on the first parameter and the second parameter.

[0013] An electronic device is also provided, comprising: a memory on which a computer program is stored; and a processor for executing the computer program in the memory to implement the above-mentioned automobile financial risk assessment method based on the intelligent optimization algorithm.

[0014] A non-temporary computer-readable storage medium is also provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned automobile financial risk assessment method based on the intelligent optimization algorithm is implemented.

[0015] The beneficial effects of the present invention are embodied in:

[0016] In the entire automobile finance risk assessment method based on intelligent optimization algorithm, automobile finance target tasks are defined and subdivided into multiple subtasks. An accurate risk assessment system is constructed by extracting sub-eigenvalues. Each subtask is refined using an intelligent optimization algorithm containing parameters. Not only the characteristics of the subtask itself are considered, but also its contribution to the overall risk is quantified, so that key risk factors can be identified more clearly. Furthermore, by integrating the risk contributions of each subtask, a comprehensive risk index is formed, which provides strong support for risk management and decision-making. When the risk index exceeds the threshold, the program effectively reduces the overall risk level by correcting the parameters. Based on the corrected parameters, targeted automobile finance target task adjustment strategies are formulated, such as modifying loan approval standards, adjusting loan interest rates and terms, optimizing repayment methods, etc., to achieve a balance between risk and return, which not only improves the accuracy and efficiency of risk assessment, but also enhances the refinement of risk management and the scientific nature of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0018] Figure 1 A schematic diagram of the steps of the automobile financial risk assessment method based on the intelligent optimization algorithm of the present invention;

[0019] Figure 2 It is a schematic diagram of some steps of S4 in the automobile financial risk assessment method based on the intelligent optimization algorithm of the present invention;

[0020] Figure 3 It is a schematic diagram of some steps of S2 in the automobile financial risk assessment method based on intelligent optimization algorithm of the present invention;

[0021] Figure 4 The present invention is a block diagram of an electronic device according to an embodiment of the present invention.

[0022] Reference numerals:

[0023] 700 - electronic device, 701 - processor, 702 - memory, 703 - multimedia component, 704 - input / output (I / O) interface, 705 - communication component. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0025] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. In addition, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0027] like Figure 1 As shown, a method for assessing automobile financial risk based on an intelligent optimization algorithm is provided, including:

[0028] S1. Obtain an automobile finance target task, and obtain multiple subtasks according to the automobile finance target task, and obtain sub-feature values ​​corresponding to the subtasks;

[0029] S2. Obtaining a first contribution degree corresponding to each subtask based on the intelligent optimization algorithm including the first parameter and each subtask, and obtaining a sub-risk indicator corresponding to each subtask based on the risk assessment model and the sub-feature value corresponding to each subtask;

[0030] S3, obtaining a first comprehensive risk indicator of the automobile finance target task according to a plurality of first contribution degrees and a plurality of sub-risk indicators;

[0031] S4. If the first comprehensive risk indicator exceeds the risk threshold, the first parameter is corrected to form a second parameter, and a second contribution degree corresponding to each subtask is obtained based on the intelligent optimization algorithm including the second parameter and each subtask, and a second comprehensive risk indicator of the automobile finance target task is obtained based on multiple second contribution degrees and multiple sub-risk indicators;

[0032] S5. If the second comprehensive risk indicator is lower than the risk threshold, an automobile finance target task adjustment strategy is obtained according to the first parameter and the second parameter.

[0033] In this embodiment, it should be noted that in S1, it is first required to define the target task of automobile finance from a macro perspective, which may include but is not limited to loan approval decision, interest rate setting, loan amount determination, repayment plan formulation, etc.; then, based on this overall goal, it is necessary to deeply analyze and identify multiple subtasks that affect the achievement of this goal. For example, under the target task of loan approval decision, it can be subdivided into multiple subtasks such as vehicle value assessment, customer credit analysis, customer income stability judgment, loan interest rate and term requirements, and repayment method selection. Each subtask carries different risk assessment dimensions. For example, vehicle value assessment focuses on the market depreciation rate and accident record of the vehicle; customer credit analysis involves the customer's credit history, debt situation, repayment willingness, etc. In order to quantify the impact of these subtasks on the overall risk, the key sub-feature values ​​are further determined for each subtask. For example, in vehicle value assessment, the sub-feature value is determined by the sales price; in customer credit analysis, the sub-feature value is determined by the number of overdue payments. Through such decomposition and feature value extraction, a risk assessment system is constructed to provide accurate data input for the subsequent period.

[0034] In S2, the intelligent optimization algorithm including the first parameter is first used to perform refined processing for each subtask; specifically, the algorithm not only considers the characteristics of each subtask itself, such as the importance of each subtask, but also multiplies it with the first parameter to obtain the first contribution of the subtask to the overall risk; this processing method can make it clearer to understand which subtasks have a significant impact on the final risk results in the complex automobile financial risk assessment, and the size of their respective influence. Then, using the risk assessment model, the sub-feature values ​​of each subtask are combined with the first parameter set to calculate the specific risk indicators of each subtask. For example, in the vehicle value assessment subtask, the market price of the vehicle may be selected as the sub-feature value to accurately calculate the risk indicator of the subtask. This method can efficiently quantify the risk level of each subtask and provide strong support for subsequent risk management and decision-making.

[0035] In S3, the risk contributions of each subtask are integrated to form a comprehensive risk index of the automobile finance target task. In this process, the first contribution and sub-risk index of each subtask calculated in S2 are summarized. Then, the risk information of these subtasks is integrated through a comprehensive evaluation method, such as weighted average, fuzzy comprehensive evaluation or neural network integration. Through such processing, a first comprehensive risk index of the automobile finance target task that comprehensively considers the risks of all subtasks can be obtained.

[0036] In S4, when the first comprehensive risk index exceeds the preset risk threshold, it indicates that the current risk assessment result is unacceptable and the model parameters need to be optimized and adjusted; the risk threshold refers to a standard or limit set in risk management, which is used to evaluate and measure the degree and acceptable range of risk. It is determined based on factors such as the risk tolerance of the enterprise or individual, market conditions and risk management strategies. It is mainly used to determine whether the first comprehensive risk index reaches or exceeds the expected level and take corresponding preventive measures. Then the first parameter is corrected to form the second parameter. This correction process may be based on multiple strategies. The goal is to find a parameter configuration that can reduce the comprehensive risk index. The corrected second parameter will accurately reflect the adjustment direction of each subtask. Next, the second contribution and risk index of each subtask are recalculated using an intelligent optimization algorithm containing the second parameter, and the second comprehensive risk index based on the second parameter can be obtained. If this index is lower than the risk threshold, it means that the parameter correction is effective and the risk assessment result has been improved. Subsequent risk management and decision-making can be carried out based on the new parameter configuration.

[0037] In S5, when the second comprehensive risk indicator is lower than the risk threshold, it indicates that the risk assessment model after parameter correction has effectively reduced the overall risk level. At this time, the adjustment strategy of the auto finance target task can be formulated according to the difference between the first parameter and the second parameter. Specifically, the adjustment strategy may include modifying the loan approval standards, adjusting the loan interest rate and term, optimizing the repayment method, etc. The formulation of these adjustment strategies is based on an in-depth understanding and analysis of the risk contribution of each subtask, aiming to improve the overall benefits of the auto finance business through refined risk management.

[0038] For example, suppose that in the target task of loan approval decision, after risk assessment, it is found that the customer's credit risk and vehicle value risk are the main sources of risk. In step S4, by correcting the first parameter, the risk indicators of these two subtasks are successfully reduced, so that the second comprehensive risk indicator is lower than the risk threshold. In step S5, a specific adjustment strategy can be formulated according to the corrected parameters. For example, for customers with higher credit risks, more stringent approval standards can be adopted, such as requiring higher credit scores or providing more guarantee measures; for models with higher vehicle value risks, the loan amount can be adjusted or a higher down payment ratio can be required to reduce potential risk losses. Through such an adjustment strategy, while ensuring business benefits, the risk level can be effectively controlled to achieve a balance between risk and benefit.

[0039] In summary, in the entire automobile finance risk assessment method based on intelligent optimization algorithm, the automobile finance target task is defined and subdivided into multiple subtasks. An accurate risk assessment system is constructed by extracting sub-eigenvalues. Each subtask is refined using an intelligent optimization algorithm containing parameters. Not only the characteristics of the subtask itself are considered, but also its contribution to the overall risk is quantified, so that key risk factors can be identified more clearly. Furthermore, by integrating the risk contribution of each subtask, a comprehensive risk index is formed, which provides strong support for risk management and decision-making. When the risk index exceeds the threshold, the scheme effectively reduces the overall risk level by correcting the parameters. Based on the corrected parameters, targeted automobile finance target task adjustment strategies are formulated, such as modifying loan approval standards, adjusting loan interest rates and terms, optimizing repayment methods, etc., to achieve a balance between risk and return, which not only improves the accuracy and efficiency of risk assessment, but also enhances the refinement of risk management and the scientific nature of decision-making.

[0040] like Figure 2 As shown, in one embodiment, modifying the first parameter and forming the second parameter in S4 includes:

[0041] S41. Obtaining a reduction ratio according to the first comprehensive risk indicator and the risk threshold;

[0042] S42, modifying the first parameter according to the reduction ratio to form a second parameter.

[0043] In this embodiment, it should be noted that in S41, a reduction ratio is calculated based on the first comprehensive risk indicator and the risk threshold. This reduction ratio is used to guide the subsequent correction of the first parameter, in the hope of reducing the second comprehensive risk indicator to below the risk threshold. The calculation of the reduction ratio can be based on a variety of strategies, and the following is a possible calculation method: determine the portion of the first comprehensive risk indicator that exceeds the risk threshold, that is, the difference = the first comprehensive risk indicator-risk threshold, and then, based on the ratio of this difference to the risk threshold, or based on a preset algorithm (such as linear interpolation, exponential decay, etc.), calculate the reduction ratio, which will be directly applied to the correction of the first parameter to reduce the second comprehensive risk indicator.

[0044] In S42, the main task is to modify the first parameter according to the reduction ratio to form a new second parameter. The purpose of the modification is to adjust the parameter configuration in the model, so that the second comprehensive risk index can be reduced under the second parameter to be lower than the risk threshold, and then the adjustment strategy of the automobile financial target task is obtained through the change between the second parameter and the first parameter.

[0045] The correction method may be determined according to the specific type and nature of the first parameter. During correction, the first parameter may be adjusted accordingly according to the reduction ratio, for example, by multiplying by the inverse of the reduction ratio, subtracting a value related to the reduction ratio, etc.

[0046] In one embodiment, in S42, the first parameter is corrected according to the reduction ratio to form the second parameter, which is expressed as:

[0047] in,

[0048] α1 is the first parameter, α2 is the second parameter, R1 is the first comprehensive risk indicator, and T is the risk threshold.

[0049] In this embodiment, it should be noted that when the first comprehensive risk indicator R1 exceeds the risk threshold T, it indicates that the current risk assessment result is unacceptable and the risk needs to be reduced by adjusting the parameters. The ratio of the first comprehensive risk indicator to the risk threshold is partially calculated, that is, the reduction ratio, and it is used to adjust the first parameter α1. This adjustment method takes into account the degree of risk excess. The more the risk exceeds, the greater the adjustment. α1 is scaled by multiplying this ratio to obtain a new parameter value α2. This new parameter value is expected to make the risk assessment result closer to or lower than the risk threshold. In summary, the entire expression can dynamically adjust parameters according to the actual situation of the risk assessment results, which improves the flexibility and adaptability of the risk assessment model; through parameter correction, it helps to reduce the second comprehensive risk indicator to make it closer to or lower than the risk threshold, thereby meeting the needs of risk management.

[0050] Assume that in a certain automobile financial risk assessment scenario, the initial value of the first parameter α1 is 1.0, the first comprehensive risk index R1 is 70, and the risk threshold T is 50. According to the formula: Substitute the numerical calculation: That is, the corrected second parameter α2 is approximately 0.714.

[0051] like Figure 3 As shown, in one embodiment, obtaining the first contribution corresponding to each subtask based on the intelligent optimization algorithm including the first parameter and each subtask in S2 includes:

[0052] S21, obtaining the allocation index corresponding to the i-th subtask;

[0053] S22. Obtain a first contribution degree corresponding to the ith subtask based on an intelligent optimization algorithm including the first parameter and an allocation index corresponding to the ith subtask.

[0054] In this embodiment, it should be noted that in S21, it involves obtaining the allocation index corresponding to the i-th subtask. This allocation index is the basis for the subsequent calculation of the first contribution of each subtask, and it usually reflects the importance, complexity, resource requirements or other relevant factors of the subtask in the overall task. This allocation index can be obtained through historical data or expert experience evaluation. If there is no historical data, the importance of the subtask can be evaluated based on the realization of the overall task goal. This may require considering the goals, functions and relationships of the subtask with other subtasks; the steps, calculation amount, decision points and other factors involved in the execution of the subtask can also be evaluated to determine its complexity. Subtasks with high complexity may require more resources and time to complete; the resources required for the execution of the subtask, such as computing resources, storage resources, human resources, etc., can also be considered. Subtasks with high resource requirements may require more support.

[0055] Assuming that in similar projects in the past, the current subtask usually accounts for 20% of the total workload and has a high execution success rate (such as 90%), this information can be used as a reference for the current subtask allocation indicator.

[0056] Suppose an expert in the field of database design is invited to score or rate the current subtask. Suppose the expert gives the current subtask 8 points (out of 10 points), indicating that the expert believes that the current subtask has a high degree of importance and a certain degree of complexity. Then, the subtasks are sorted according to their scores, and the allocation indicators of each subtask are given in turn.

[0057] In S22, the allocation index of the ith subtask is obtained, the first parameter in the intelligent optimization algorithm is determined, the first parameter and the allocation index of the ith subtask are used as input, and the intelligent optimization algorithm is applied for calculation. The core of the intelligent optimization algorithm is to output a first contribution that can reflect the ith subtask under the given first parameter.

[0058] In one embodiment, the intelligent optimization algorithm in S22 for obtaining the first contribution corresponding to the i-th subtask based on the intelligent optimization algorithm including the first parameter and the allocation index corresponding to the i-th subtask includes:

[0059] C i1 =α1·A i ;in,

[0060] C i1 is the first contribution corresponding to the i-th subtask, α1 is the first parameter, A i is the allocation indicator corresponding to the i-th subtask.

[0061] In this embodiment, it should be noted that α1·A iBy directly multiplying the first parameter and the allocation index corresponding to the i-th subtask, the effect of equal increase and equal decrease is achieved, and the first contribution of each subtask can be quickly calculated.

[0062] Assume that in an automobile finance risk assessment project, there are three subtasks: credit assessment, vehicle value assessment, and repayment ability assessment. Each subtask has a corresponding allocation index, which are A1=0.3, A2=0.4, and A3=0.3. The first parameter α1 is set to 1.2 to reflect the need for risk adjustment.

[0063] Now, we can use the above expression to calculate the first contribution of each subtask:

[0064] For the credit assessment subtask: C 11 =α1·A1=1.2*0.3=0.36;

[0065] For the vehicle value assessment subtask: C 21 =α2·A1=1.2*0.4=0.48

[0066] For the repayment capacity assessment subtask: C 31 =α3·A3=1.2*0.3=0.36

[0067] The calculation results show that after considering risk adjustment, the vehicle value assessment subtask has the highest first contribution to the overall risk (0.48), while the credit assessment and repayment ability assessment subtasks have equal first contributions (0.36). This information can provide valuable reference for subsequent risk management and decision-making.

[0068] In one embodiment, the risk assessment model in S2 for obtaining the sub-risk indicators corresponding to each sub-task based on the risk assessment model and the sub-feature values ​​corresponding to each sub-task is expressed as:

[0069] r i =β i ·ln(h i +1); among them,

[0070] r i is the sub-risk indicator corresponding to the i-th sub-task, β i is the adjustment coefficient corresponding to the i-th subtask, h i is the sub-feature value corresponding to the i-th subtask.

[0071] In this embodiment, it should be noted that ln(h i +1) can handle sub-eigenvalues ​​of different magnitudes and scale them to a more reasonable range. More importantly, by ln(h i+1) calculation, it can also enhance the model's sensitivity to changes in smaller sub-eigenvalues ​​and reduce the impact of extreme sub-eigenvalues. i , the contribution of each subtask in the overall risk assessment can be flexibly adjusted, so that the model can be easily adapted to different risk preferences or business needs.

[0072] Assume that there are three subtasks, their sub-feature values ​​are h1 = 10, h2 = 5, h3 = 2, and the corresponding adjustment coefficients are β1 = 1.5, β t =1.0, β3=0.5.

[0073] According to the risk assessment model, the sub-risk index of each subtask can be calculated:

[0074] Subtask 1: r1 = β1 ln(h1+1) = 1.5*ln(10+1) = 3.5968;

[0075] Subtask 2: r2 = β2 ln(h2+1) = 1.0*ln(5+1) = 1.7918;

[0076] Subtask 3: r3=β3·ln(h3+1)=0.5*ln(2+1)=0.5493.

[0077] Therefore, the sub-risk indices of the three subtasks are 3.5968, 1.7918, and 0.5493, respectively. These indices can be used for further risk assessment or decision making.

[0078] In one embodiment, the first comprehensive risk index of the automobile finance target task is obtained according to the multiple first contribution degrees and the multiple sub-risk indexes in S3 as follows:

[0079] in,

[0080] R1 is the first comprehensive risk indicator, C j1 is the first contribution corresponding to the jth subtask, r j is the sub-risk indicator corresponding to the j-th subtask, and n is the number of subtasks.

[0081] In this embodiment, it should be noted that the automobile finance target task usually involves multiple aspects or subtasks, and each subtask has a different degree of first contribution to the overall risk. By calculating the first contribution of each subtask and multiplying it with the corresponding sub-risk index, the contribution value of each subtask to the overall risk can be obtained, and then the contribution values ​​of each subtask are added to obtain the first comprehensive risk index. The model can be easily extended to include more subtasks, just by adding the first contribution and sub-risk index of the corresponding subtask.

[0082] Assume there are three subtasks, and their first contributions are C 11 =0.5, C 21 =0.3, C 31 =0.2, and the corresponding sub-risk indicators are r1=4, r2=3, r3=2.

[0083] According to the calculation formula of the comprehensive risk index, the first comprehensive risk index of the automobile finance target task can be calculated: R1 = (0.5*4) + (0.3*3) + (0.2*2).

[0084] Therefore, the first comprehensive risk index of the auto finance target task is 3.3. This index can be used for further risk assessment, decision making or risk management.

[0085] A vehicle finance risk assessment system based on an intelligent optimization algorithm is also provided. The system is used to implement the vehicle finance risk assessment method based on an intelligent optimization algorithm in any of the above embodiments. The system includes:

[0086] An acquisition module is used to acquire an automobile finance target task, acquire multiple subtasks according to the automobile finance target task, and acquire sub-feature values ​​corresponding to the subtasks;

[0087] A first calculation module, used to obtain a first contribution degree corresponding to each subtask based on an intelligent optimization algorithm including a first parameter and each subtask, and to obtain a sub-risk indicator corresponding to each subtask based on a risk assessment model and a sub-feature value corresponding to each subtask;

[0088] A second calculation module is used to obtain a first comprehensive risk index of the automobile finance target task according to the multiple first contribution degrees and the multiple sub-risk indexes;

[0089] The risk assessment and optimization module amends the first parameter to form a second parameter if the first comprehensive risk indicator exceeds the risk threshold, obtains a second contribution degree corresponding to each subtask based on an intelligent optimization algorithm including the second parameter and each subtask, and obtains a second comprehensive risk indicator of the automobile finance target task based on multiple second contribution degrees and multiple sub-risk indicators;

[0090] The risk assessment and adjustment module obtains the automobile finance target task adjustment strategy according to the first parameter and the second parameter if the second comprehensive risk indicator is lower than the risk threshold.

[0091] In this embodiment, it should be noted that, regarding the above-mentioned automobile financial risk assessment system based on intelligent optimization algorithm, the specific method of performing operations therein has been described in detail in the implementation of the automobile financial risk assessment method based on intelligent optimization algorithm, and will not be elaborated here.

[0092] Figure 4 is a block diagram of an electronic device for an automobile financial risk assessment method based on an intelligent optimization algorithm according to an exemplary embodiment. Figure 4 As shown, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0093] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned automobile financial risk assessment method based on the intelligent optimization algorithm. The memory 702 is used to store various types of data to support the operation of the electronic device 700. These data may include, for example, instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0094] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned automobile financial risk assessment method based on intelligent optimization algorithm.

[0095] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned automobile financial risk assessment method based on the intelligent optimization algorithm are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to complete the above-mentioned automobile financial risk assessment method based on the intelligent optimization algorithm.

[0096] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned automobile financial risk assessment method based on the intelligent optimization algorithm when executed by the programmable device.

[0097] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0098] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0099] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. An automobile financial risk assessment method based on intelligent optimization algorithm, characterized in that: include: Obtain an automobile finance target task, obtain multiple subtasks according to the automobile finance target task, and obtain sub-feature values ​​corresponding to the subtasks; Obtaining a first contribution degree corresponding to each subtask based on the intelligent optimization algorithm including the first parameter and each subtask, and obtaining a sub-risk indicator corresponding to each subtask based on the risk assessment model and the sub-feature value corresponding to each subtask; Obtaining a first comprehensive risk indicator of the automobile finance target task according to a plurality of first contribution degrees and a plurality of sub-risk indicators; If the first comprehensive risk indicator exceeds the risk threshold, the first parameter is corrected to form a second parameter, and a second contribution degree corresponding to each subtask is obtained based on the intelligent optimization algorithm including the second parameter and each subtask, and a second comprehensive risk indicator of the automobile finance target task is obtained based on multiple second contribution degrees and multiple sub-risk indicators; If the second comprehensive risk indicator is lower than the risk threshold, the automobile finance target task adjustment strategy is obtained according to the first parameter and the second parameter.

2. The automobile financial risk assessment method based on intelligent optimization algorithm according to claim 1 is characterized in that: The correcting the first parameter to form the second parameter comprises: Obtaining a reduction ratio based on the first comprehensive risk indicator and the risk threshold; The first parameter is modified according to the reduction ratio and forms the second parameter.

3. The automobile financial risk assessment method based on intelligent optimization algorithm according to claim 2 is characterized in that: The method of correcting the first parameter according to the reduction ratio and forming the second parameter is expressed as: in, α1 is the first parameter, α2 is the second parameter, R1 is the first comprehensive risk indicator, and T is the risk threshold.

4. The automobile financial risk assessment method based on intelligent optimization algorithm according to claim 1 is characterized in that: Obtaining the first contribution corresponding to each subtask based on the intelligent optimization algorithm including the first parameter and each subtask includes: Get the allocation indicator corresponding to the i-th subtask; A first contribution degree corresponding to the ith subtask is obtained based on an intelligent optimization algorithm including the first parameter and an allocation index corresponding to the ith subtask.

5. The automobile financial risk assessment method based on intelligent optimization algorithm according to claim 4 is characterized in that: The intelligent optimization algorithm for obtaining the first contribution corresponding to the i-th subtask based on the intelligent optimization algorithm including the first parameter and the allocation index corresponding to the i-th subtask includes: C i1 =α1·A i ;in, C i1 is the first contribution corresponding to the i-th subtask, α1 is the first parameter, A i is the allocation indicator corresponding to the i-th subtask.

6. The automobile financial risk assessment method based on intelligent optimization algorithm according to claim 1 is characterized in that: The risk assessment model for obtaining the sub-risk indicators corresponding to each sub-task based on the risk assessment model and the sub-feature values ​​corresponding to each sub-task is expressed as: r i =β i ·ln(h i +1); among them, r i is the sub-risk indicator corresponding to the i-th sub-task, β i is the adjustment coefficient corresponding to the i-th subtask, h i is the sub-feature value corresponding to the i-th subtask.

7. The automobile financial risk assessment method based on intelligent optimization algorithm according to claim 1 is characterized in that: The first comprehensive risk index of the automobile finance target task is obtained according to multiple first contribution degrees and multiple sub-risk indicators as follows: in, R1 is the first comprehensive risk indicator, C j1 is the first contribution corresponding to the jth subtask, r j is the sub-risk indicator corresponding to the j-th subtask, and n is the number of subtasks.

8. An automobile financial risk assessment system based on intelligent optimization algorithm, characterized in that: The system is used to implement the automobile financial risk assessment method based on the intelligent optimization algorithm as described in any one of claims 1 to 7, and the system includes: An acquisition module is used to acquire an automobile finance target task, acquire multiple subtasks according to the automobile finance target task, and acquire sub-feature values ​​corresponding to the subtasks; A first calculation module, used to obtain a first contribution degree corresponding to each subtask based on an intelligent optimization algorithm including a first parameter and each subtask, and to obtain a sub-risk indicator corresponding to each subtask based on a risk assessment model and a sub-feature value corresponding to each subtask; A second calculation module is used to obtain a first comprehensive risk index of the automobile finance target task according to the multiple first contribution degrees and the multiple sub-risk indexes; The risk assessment and optimization module amends the first parameter to form a second parameter if the first comprehensive risk indicator exceeds the risk threshold, obtains a second contribution degree corresponding to each subtask based on an intelligent optimization algorithm including the second parameter and each subtask, and obtains a second comprehensive risk indicator of the automobile finance target task based on multiple second contribution degrees and multiple sub-risk indicators; The risk assessment and adjustment module obtains the automobile finance target task adjustment strategy according to the first parameter and the second parameter if the second comprehensive risk indicator is lower than the risk threshold.

9. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the automobile financial risk assessment method based on the intelligent optimization algorithm as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the automobile financial risk assessment method based on the intelligent optimization algorithm described in any one of claims 1 to 7 is implemented.

Images