A risk control system suitable for Internet rental

Abstract

The invention discloses a risk control system suitable for Internet machine rental, relates to the technical field of machine rental credit analysis, and solves the technical problem that in machine rental risk control, whether a user defaults is judged only according to a fixed threshold, ignoring the fact that the fixed threshold cannot adapt to the personalized needs of different users; the invention obtains the credit factor of the user by analyzing the number of machine rentals and the default rate; obtains the basic judgment threshold by analyzing basic information, obtains the regional influence factor based on the resident area and the credit factor, and obtains the time influence factor based on the machine rental time and the credit factor; comprehensively calculates the basic judgment threshold, the regional influence factor and the time influence factor to obtain the dynamic judgment threshold; judges the credit factor and the dynamic judgment threshold to obtain an operation instruction, and sets a deposit and a charging method based on the operation instruction and the current machine rental amount; the invention can increase the flexibility and adaptability of the credit evaluation system.

Description

Technical Field

[0001] The present invention belongs to the field of financial risk control, relates to a credit analysis technology for renting a machine, and specifically is a risk control system suitable for renting a machine on the Internet. Background Art

[0002] With the rapid development and popularization of Internet technology, online rental services have become more and more convenient, and the Internet rental market has therefore ushered in rapid growth. Users can easily rent various devices online, such as mobile phones, computers, cameras, etc. This service model provides users with great convenience and flexibility. However, due to the virtuality of the Internet and the opacity of information, there are great risks in the process of renting Internet devices. Users may breach the contract, such as failing to return the rented items on time, malicious damage, etc., which brings economic losses and credit risks to the rental platform.

[0003] At present, most risk control systems used for Internet rental of machines only judge whether a user has defaulted according to a fixed threshold in the risk control of rental of machines. This ignores the fact that the fixed threshold cannot adapt to the personalized needs of different users. Judging according to the fixed threshold will result in a one-size-fits-all situation for the credit assessment of users, and it is impossible to perform dynamic risk control based on the user's own information and environmental information, which reduces the adaptability of the risk control system.

[0004] Therefore, the present invention discloses a risk control system suitable for Internet machine rental to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a risk control system suitable for Internet rental, which is used to solve the technical problem that in the risk control of rental, whether the user defaults is judged only according to a fixed threshold, ignoring the fixed threshold and cannot adapt to the personalized needs of different users. The present invention obtains the user's credit factor by analyzing the number of rental times and the default rate; obtains the basic judgment threshold by analyzing the basic information, obtains the regional influence factor based on the resident area and the credit factor, and obtains the time influence factor based on the rental time and the credit factor; comprehensively calculates the basic judgment threshold, the regional influence factor and the time influence factor to obtain the dynamic judgment threshold; judges the credit factor and the dynamic judgment threshold to obtain an operation instruction, and sets a deposit and a charging method based on the operation instruction and the current rental amount to solve the above problems.

[0006] To achieve the above-mentioned purpose, the first aspect of the present invention provides a risk control system applicable to Internet rental, comprising: an intelligent analysis module, and a data collection module, a risk control module and a database connected thereto;

[0007] The data collection module is used to obtain the user's basic information and rental information; the basic information includes age, occupation, education and rental amount; the rental information includes the number of rentals, default rate, resident area and rental time;

[0008] The intelligent analysis module is used to analyze the number of rental times and the default rate to obtain the user's credit factor; analyze the basic information to obtain the basic judgment threshold, analyze based on the resident area and the credit factor to obtain the regional influence factor, analyze based on the rental time and the credit factor to obtain the time influence factor; and comprehensively calculate the basic judgment threshold, the regional influence factor and the time influence factor to obtain the dynamic judgment threshold;

[0009] The risk control module is used to determine the credit factor and the dynamic judgment threshold to obtain an operation instruction, and to set a deposit and a charging method based on the operation instruction and the current rental amount; wherein the payment method includes a fixed charge and a fluctuating charge.

[0010] Preferably, the obtaining of the user's basic information and rental information includes:

[0011] Obtain the user's age, occupation and education level filled in by the user or imported from third-party software through the database, and obtain the user's fixed daily rental amount and rental time from the database; third-party software includes Alipay and WeChat;

[0012] Obtain the number of times the current user rents a device and the default rate from the database; obtain the historical geographic location of the current user when using several historically rented devices based on the positioning system of several historically rented devices of the user;

[0013] Obtain the area where each historical geographical location is located, obtain the ratio of the number of historical geographical locations owned by each area in the area to the total number of historical geographical locations, and mark the ratio as the location ratio; determine in turn whether the location ratio of each area exceeds a fixed ratio; if so, mark the area whose location ratio exceeds the fixed ratio as a permanent area; if not, sort the location ratios from large to small, and mark the area corresponding to the location ratio with a sequence number in the first n% as a permanent area; wherein the area is obtained by manual setting; and n and the fixed ratio are both obtained through experience.

[0014] It should be noted that the data acquired and analyzed by the present invention are all operated on the basis of user authorization.

[0015] Preferably, the step of analyzing the number of rental times and the default rate to obtain the user's credit factor includes:

[0016] A1: Extract the user's rental times ZC and default rate WL from the database, and determine whether the rental times ZC is greater than the fixed times; if yes, jump to A2; if no, jump to A3;

[0017] A2: Determine whether the default rate WL is greater than the fixed default rate; if yes, mark the user as a low-credit user and prohibit the user from renting a device; if no, jump to A3; wherein the fixed number of times is obtained by sorting the number of times each user rents a device and selecting a number on a fixed percentile; the fixed default rate is obtained by sorting the default rate of each user and selecting a number on a fixed percentile;

[0018] A3: The user's credit factor YZ is obtained based on the formula YZ = α / exp((WL-PWL) / PWL)×ZC / BZC; where α is the amplitude adjustment factor, and the value range of α is (0,2); PWL is the average default rate of each user in the database, and BZC is the manually set standard rental number.

[0019] It should be noted that step A1 of the present application is used to prevent the situation where a user cannot rent a phone due to a breach of contract due to a small number of times the user has rented a phone.

[0020] Preferably, the analyzing the basic information to obtain the basic determination threshold comprises:

[0021] Mark users with the same age, occupation and education level as the current user as reference users from the database, and obtain the mode ZS, percentile BS and maximum value ZD of the reference user basic judgment threshold; obtain the fixed factor GZ based on the formula GZ = β1 × (ZS + β2 × BS + β3 × ZD) / 2; the percentile of the percentile is obtained by manual setting; β1, β2 and β3 are all proportional adjustment coefficients greater than 0, and β2 + β3 = 1, β2 > β3;

[0022] Extract the rental amount ZG, and obtain the basic judgment threshold CY based on the formula CY=GZ+δ / exp((ZG-BZG) / BZG); wherein BZG is the manually set standard rental amount; δ is the amplitude adjustment coefficient of the exp() function, and the value range of δ is (0,1).

[0023] It is worth noting that the present invention not only takes into account the age, occupation and education level, but also the influence of the rental amount when obtaining the basic judgment threshold of the current user; because the age, occupation and education level can indirectly indicate the quality and sense of responsibility of the current user, and further analyze the credit status of the current user; and the rental amount can indicate the economic situation of the current user. A high rental amount can indirectly indicate that the user has a good economic situation, is able to afford higher rents and has a good repayment ability, and has a relatively low credit risk. The rental amount can indirectly judge the user's economic strength and repayment ability, and further indicate the user's credit situation; therefore, the age, occupation, education level and rental amount are comprehensively considered to obtain a basic judgment threshold that can be used for the current user's credit judgment. Comprehensive consideration of these factors can provide users with a more personalized credit scoring mechanism that is more in line with the user's actual credit status.

[0024] Preferably, the regional impact factor is obtained by analyzing the resident region and the credit factor, including:

[0025] Obtain the credit factors of all users in the resident area corresponding to the current user, and combine the credit factors of all users into a regional credit library; obtain the variance of the regional credit library, and determine whether the variance is greater than the corresponding variance limit value; if yes, remove the credit factor with the largest difference from the credit factor mode in the regional credit library, and re-determine the variance until the variance of the regional credit library is not greater than the variance limit value, and retain the remaining data in the regional credit library; if no, retain the data in the regional credit library; wherein the variance limit value is obtained through experience;

[0026] Obtain the mode and average of the data retained in the regional credit database, perform proportional calculation on the mode and average to obtain the regional credit feature value YT, and obtain the credit factor YZ of the current user; obtain the regional influence factor QZ based on the formula QZ=1 / (ln(μ×(YZ-YT) / YT+1)+1); wherein μ is the amplitude adjustment factor of the ln() function, and the value range of μ is (0,1).

[0027] It is worth noting that a person's credit will change with the changes in his surrounding environment. That is to say, when the current user is in the current environment, his own credit may be affected by others. This situation is more common for users who are easily influenced by others. Whether the current user is easily influenced by others can be indirectly reflected by the credit factor YZ. The larger the credit factor YZ is, the stronger the current user's trustworthiness is. It can further indicate that the probability of the current user being influenced by others is lower. Therefore, the present invention compares the current user's credit factor YZ and the regional credit characteristic value YT to obtain a regional influence factor QZ that can indicate that the current user's credit is affected by the regional environment. In the formula calculation, as the current user's credit factor YZ increases, the value of the obtained regional influence factor QZ gradually decreases, indicating that the current user is gradually affected by the surrounding environment. This step obtains the impact of the surrounding environment on the user's credit, which can reduce the credit assessment error caused by environmental changes, thereby improving the accuracy of the assessment.

[0028] Preferably, the time impact factor is obtained by analyzing based on the rental time and the credit factor, including:

[0029] B1: Get the difference T1 between the current date and the nearest statutory holiday after the current date, and determine whether the difference T1 exceeds the maximum difference. If yes, mark the time impact factor SZ as 0. If no, jump to B2. The maximum difference is obtained through experience.

[0030] B2: Extract the number of days T2 of the nearest statutory holiday after the current date, and obtain the time impact factor SZ based on the formula SZ = ρ × ln (σ × (T2-BT2) / BT2 + 1) × T1 / CZT; where BT2 is the manually set standard number of days, CZT is the maximum difference number of days; ρ is the manually set impact control coefficient of each statutory holiday type; σ is the amplitude adjustment coefficient, and the value range of σ is (0,1).

[0031] It is worth noting that the present invention takes into account the fact that the user's credit may be affected by holidays when calculating the credit judgment threshold. When approaching holidays, some users may be more inclined to rent more expensive equipment because they pay attention to their social status and image. The present invention uses the impact caused by this phenomenon as reference data to provide data support for the subsequent calculation of dynamic judgment thresholds. Taking holiday factors into consideration can make the establishment of a credit assessment mechanism closer to the user's actual behavior pattern, thereby improving the accuracy and reliability of the assessment results.

[0032] Preferably, the step of comprehensively calculating the basic determination threshold, the regional impact factor and the time impact factor to obtain the dynamic determination threshold comprises:

[0033] Extract the basic judgment threshold CY, regional influence factor QZ and time influence factor SZ; obtain the dynamic judgment threshold DZ based on the formula DZ=CY×(R1×QZ / BQZ+R2×SZ / BSZ); wherein BQZ is the manually set standard regional influence factor, and BSZ is the manually set standard time influence factor; R1 and R2 are both proportional adjustment coefficients greater than 0.

[0034] Preferably, the step of determining the credit factor and the dynamic determination threshold to obtain the operation instruction includes:

[0035] Extract the credit factor YZ and dynamic determination threshold DZ of the current user, and determine whether the credit factor YZ is greater than the dynamic determination threshold DZ; if yes, issue operation instruction one; if no, issue operation instruction two; wherein the operation instruction includes operation instruction one and operation instruction two.

[0036] Preferably, the deposit and charging method are set based on the operation instruction and the current rental amount, including:

[0037] Receive an operation instruction, and determine whether the received operation instruction is operation instruction one; if yes, charge the user a fixed fee based on a fixed deposit and a fixed daily rental amount; if no, charge the user a fluctuating fee; wherein the payment methods include fixed fees and fluctuating fees, and the fixed deposit and the fixed daily rental amount are both obtained through manual settings.

[0038] Preferably, the fluctuating charging of fees to the user includes:

[0039] Extract the current user's credit factor YZ and dynamic judgment threshold DZ, obtain the fluctuation ratio BL based on the formula BL=DZ / YZ, and multiply the fixed deposit by the fluctuation ratio BL to obtain the fluctuation deposit;

[0040] The fixed deposit is multiplied by the fixed daily rental amount to obtain the daily fluctuating rental amount. Starting from the rental day, the rental amount is collected every day according to the fluctuating rental amount, and the collected rental amounts are summed to obtain the collected amount. The fixed rental amount for each day during the rental period is summed to obtain the receivable amount. It is determined whether the recorded difference obtained by subtracting the collected amount from the receivable amount is less than the fluctuating rental amount. If so, after the rental amount is collected according to the recorded difference on the next day, the rental amount for the current user during the current rental period is stopped; if not, the rental amount is continued to be collected according to the fluctuating rental amount.

[0041] It should be noted that collecting the rental amount in advance from users with low credit can help reduce the risk of rental default due to poor user credit.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention obtains the credit factor of the user by analyzing the number of rental times and the default rate; obtains the basic judgment threshold by analyzing the basic information, obtains the regional influence factor based on the resident area and the credit factor, and obtains the time influence factor based on the rental time and the credit factor; comprehensively calculates the basic judgment threshold, the regional influence factor and the time influence factor to obtain the dynamic judgment threshold; judges the credit factor and the dynamic judgment threshold to obtain the operation instruction, and sets the deposit and charging method based on the operation instruction and the current rental amount, thereby solving the technical problem that in the risk control of rental, whether the user defaults is judged only according to the fixed threshold, ignoring the fact that the fixed threshold cannot adapt to the personalized needs of different users; the present invention can provide personalized risk assessment according to the specific behavior and credit history of each user, rather than adopting a one-size-fits-all fixed threshold, so that the credit assessment system is more flexible and adaptable.

[0044] 2. The present invention deeply analyzes the subtle influence of environmental factors in credit assessment, and recognizes that the credit status of users does not exist in isolation, but may be affected by the social credit environment of the region where they are located. This situation is more common for users who are easily influenced by others, and whether the current user is easily influenced by others can be indirectly reflected by the credit factor. The larger the credit factor, the stronger the current user's trustworthiness, which further indicates that the probability of the current user being influenced by others is lower. Therefore, the present invention compares the credit factor of the current user with the regional credit characteristic value to obtain a regional influence factor that can indicate that the current user's credit is affected by the regional environment. In the formula calculation, as the credit factor of the current user increases, the value of the obtained regional influence factor gradually decreases, indicating that the current user is gradually less affected by the surrounding environment. The present invention obtains the influence of the surrounding environment on the user's credit, which can reduce the credit assessment error caused by environmental changes, thereby improving the accuracy of the assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is a schematic diagram of the operation steps of the present invention;

[0047] Figure 2 It is a schematic diagram of the system module of the present invention;

[0048] Figure 3 A schematic diagram of the operation steps for obtaining the regional impact factor of the present invention;

[0049] Figure 4 The figure is a schematic diagram of the operation steps for obtaining the time influence factor of the present invention. DETAILED DESCRIPTION

[0050] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. 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.

[0051] See also Figure 1-Figure 2 , the first aspect of the present invention provides a risk control system applicable to Internet rental, including: an intelligent analysis module, and a data collection module, a risk control module and a database connected thereto;

[0052] Data collection module: used to obtain basic information and rental information of users; basic information includes age, occupation, education and rental amount; rental information includes number of rentals, default rate, resident area and rental time;

[0053] Intelligent analysis module: used to analyze the number of rental times and default rate to obtain the user's credit factor; analyze the basic information to obtain the basic judgment threshold, analyze based on the resident area and credit factor to obtain the regional impact factor, analyze based on the rental time and credit factor to obtain the time impact factor; comprehensively calculate the basic judgment threshold, regional impact factor and time impact factor to obtain the dynamic judgment threshold;

[0054] Risk control module: used to judge the credit factor and dynamic judgment threshold to obtain the operation instruction, and set the deposit and charging method based on the operation instruction and the current rental amount; among them, the payment method includes fixed charge and fluctuating charge.

[0055] The basic information and rental information of the user obtained in this application include:

[0056] Obtain the user's age, occupation and education level filled in by the user or imported from third-party software through the database, and obtain the user's fixed daily rental amount and rental time from the database; third-party software includes Alipay and WeChat;

[0057] Obtain the number of times the current user rents a device and the default rate from the database; obtain the historical geographic location of the current user when using several historically rented devices based on the positioning system of several historically rented devices of the user;

[0058] Obtain the area where each historical geographical location is located, obtain the ratio of the number of historical geographical locations owned by each area in the area to the total number of historical geographical locations, and mark the ratio as the location ratio; determine in turn whether the location ratio of each area exceeds a fixed ratio; if so, mark the area where the location ratio exceeds the fixed ratio as a permanent area; if not, sort the location ratios from large to small, and mark the area corresponding to the location ratio with a sequence number in the first n% as a permanent area; wherein the area is obtained by manual setting; and n and the fixed ratio are both obtained through experience.

[0059] It should be noted that the data acquired and analyzed by the present invention are all operated on the basis of user authorization.

[0060] It should be noted that sorting the position ratios from large to small and marking the areas corresponding to the position ratios with serial numbers in the top n% as permanent areas can be understood as follows: if there are 20 position ratios in total, and the value of n is 20, since 20×20%=4, the position ratios are sorted from large to small, and the areas corresponding to the top 4 position ratios are marked as permanent areas.

[0061] In this application, the number of rental times and default rate are analyzed to obtain the user's credit factor, including:

[0062] A1: Extract the user's rental times ZC and default rate WL from the database, and determine whether the rental times ZC is greater than the fixed times; if yes, jump to A2; if no, jump to A3;

[0063] A2: Determine whether the default rate WL is greater than the fixed default rate; if yes, mark the user as a low-credit user and prohibit the user from renting a device; if no, jump to A3; the fixed number of times is obtained by sorting the number of times each user rents a device and selecting the number on the fixed percentile; the fixed default rate is obtained by sorting the default rate of each user and selecting the number on the fixed percentile;

[0064] A3: The user's credit factor YZ is obtained based on the formula YZ = α / exp((WL-PWL) / PWL)×ZC / BZC; where α is the amplitude adjustment factor, and the value range of α is (0,2); PWL is the average default rate of each user in the database, and BZC is the manually set standard rental number.

[0065] It should be noted that step A1 of the present application is used to prevent the situation where a user cannot rent a phone due to a breach of contract due to a small number of times the user has rented a phone.

[0066] In this embodiment, the fixed percentile corresponding to the fixed number of times is 10%, and the fixed percentile corresponding to the fixed default rate is 30%. The steps for obtaining the fixed number of times and the fixed default rate are:

[0067] Fixed times: Sort the rental times of each user in the database from small to large, and mark the rental times whose serial numbers account for 10% of the total serial numbers as fixed times; if there is no serial number in the 10% position, mark the rental times corresponding to the serial number closest to the 10% position as fixed times;

[0068] Fixed default rate: Sort the default rates of each user in the database from small to large, and mark the default rates of the positions whose serial numbers account for 30% of the total serial numbers as fixed times; if there is no serial number at the 30% position, the default rate corresponding to the serial number closest to the 30% position is marked as a fixed default rate.

[0069] In this embodiment, if the user's number of rental times ZC = 20 and the default rate WL = 10%, then based on the formula YZ = α / exp((WL-PWL) / PWL)×ZC / BZC=1 / exp((10%-16%) / 16%)×20 / 50=0.582, the user's credit factor YZ = 0.582 is obtained; wherein, in this embodiment, the average value of the default rate of each user PWL = 16%, the standard number of rental times BZC is 50, and the amplitude adjustment factor α is 1.

[0070] In this application, basic information is analyzed to obtain basic judgment thresholds, including:

[0071] Mark users with the same age, occupation and education level as the current user as reference users from the database, and obtain the mode ZS, percentile BS and maximum value ZD of the reference user basic judgment threshold; obtain the fixed factor GZ based on the formula GZ = β1 × (ZS + β2 × BS + β3 × ZD) / 2; the percentile of the percentile is obtained by manual setting; β1, β2 and β3 are all proportional adjustment coefficients greater than 0, and β2 + β3 = 1, β2 > β3;

[0072] Extract the rental amount ZG, and obtain the basic judgment threshold CY based on the formula CY=GZ+δ / exp((ZG-BZG) / BZG); wherein BZG is the manually set standard rental amount; δ is the amplitude adjustment coefficient of the exp() function, and the value range of δ is (0,1).

[0073] It should be noted that if there is no user with the same age, occupation and educational background as the current user in the current system, the fixed factor GZ of the current user will be obtained according to manual settings, and then the fixed factor GZ will be comprehensively calculated with the rental amount to obtain the basic judgment threshold.

[0074] It should be noted that the larger the rental amount ZG, the more stable the current user's credit is, and the basic judgment threshold is correspondingly reduced. This is because users with good credit are considered to have a lower risk of default, so more relaxed conditions can be given, and it is more difficult for the user to be judged as in default.

[0075] In this embodiment, if the mode ZS of the reference user basic determination threshold is 0.5, the percentile BS is 0.49, and the maximum value ZD is 0.65; based on the formula GZ=β1×(ZS+β2×BS+β3×ZD) / 2=0.95×(0.5+0.6×0.49+0.4×0.65) / 2=0.5, the fixed factor GZ=0.5 is obtained; wherein, in this embodiment, the value of the proportional adjustment coefficient β1 is 0.95, the value of the proportional adjustment coefficient β2 is 0.6, and the value of the proportional adjustment coefficient β3 is 0.4;

[0076] And the fixed daily rental amount ZG=20, based on the formula CY=GZ+δ / exp((ZG-BZG) / BZG)=0.5+0.06 / exp((20-50) / 50)=0.6093, the basic judgment threshold CY=0.6093 is obtained; wherein, in this embodiment, the value of the standard rental amount BZG is 50, and the value of the amplitude adjustment coefficient δ is 0.06.

[0077] See also Figure 3 In this application, regional impact factors are obtained based on the analysis of resident regions and credit factors, including:

[0078] Obtain the credit factors of all users in the resident area corresponding to the current user, and combine the credit factors of all users into a regional credit library; obtain the variance of the regional credit library, and determine whether the variance is greater than the corresponding variance threshold; if so, remove the credit factor with the largest difference from the credit factor mode in the regional credit library, and re-determine the variance until the variance of the regional credit library is not greater than the variance threshold, and retain the remaining data in the regional credit library; if not, retain the data in the regional credit library; wherein the variance threshold is obtained through experience;

[0079] Obtain the mode and average of the retained data in the regional credit database, perform proportional calculation on the mode and average to obtain the regional credit feature value YT, and obtain the credit factor YZ of the current user; obtain the regional influence factor QZ based on the formula QZ=1 / (ln(μ×(YZ-YT) / YT+1)+1); where μ is the amplitude adjustment factor of the ln() function, and the value range of μ is (0,1).

[0080] It should be noted that the variance limit value is a determination threshold used to determine whether the variance of the regional credit library exceeds a preset value.

[0081] It should be noted that in the regional credit characteristic value YT obtained by performing proportional calculation on the mode and the average, the ratio in the proportional calculation is obtained by manual setting. For example, if the ratio of the mode to the average is 3:2, then three-fifths of the mode plus two-fifths of the average is taken to obtain the regional credit characteristic value YT.

[0082] In this embodiment, the regional credit characteristic value YT=0.65, and the credit factor YZ of the current user=0.582. Therefore, based on the formula QZ=1 / (ln(μ×(YZ-YT) / YT+1)+1)=1 / (ln(0.6×(0.582-0.65) / 0.65+1)+1)=1.069, the regional influence factor QZ=1.069 is obtained; wherein, in this embodiment, the value of the amplitude adjustment factor μ is 0.6.

[0083] See also Figure 4 In this application, the time influencing factors are analyzed based on the rental time and credit factor, including:

[0084] B1: Get the difference T1 between the current date and the nearest statutory holiday after the current date, and determine whether the difference T1 exceeds the maximum difference. If yes, mark the time impact factor SZ as 0. If no, jump to B2. The maximum difference is obtained through experience.

[0085] B2: Extract the number of days T2 of the nearest statutory holiday after the current date, and obtain the time impact factor SZ based on the formula SZ = ρ × ln (σ × (T2-BT2) / BT2 + 1) × T1 / CZT; where BT2 is the manually set standard number of days, CZT is the maximum difference number of days; ρ is the manually set impact control coefficient of each statutory holiday type; σ is the amplitude adjustment coefficient, and the value range of σ is (0,1).

[0086] It should be noted that in step B1, whether the day difference T1 exceeds the maximum difference is determined in order to determine whether the nearest holiday can promote the user's rental of equipment today; for example, during holidays, when friends get together, people like to rent more expensive equipment to show off. At this time, the monthly rental amount or deposit required for the rented equipment exceeds the user's budget, which is likely to cause a breach of contract.

[0087] It should be noted that the impact control coefficient of each statutory holiday type is set according to the importance of the holiday, such as the impact control coefficient of the Spring Festival ρ=1, the impact control coefficient of the National Day ρ=1, and the impact control coefficient of the Dragon Boat Festival ρ=0.69.

[0088] In this embodiment, the difference in days T1=2 between the current date and the nearest statutory holiday after the current date is obtained. Since the difference in days T1 does not exceed the maximum difference in days, the number of days T2=7 of the nearest statutory holiday after the current date is extracted. Based on the formula SZ=ρ×ln(σ×(T2-BT2) / BT2+1)×T1 / CZT=1×ln(0.96×(7-3) / 3+1)×2 / 5=0.329, the time influence factor SZ=0.329 is obtained; wherein, in this embodiment, the value of the amplitude adjustment coefficient σ is 0.96, the value of the impact control coefficient of each manually set statutory holiday type is 1, and the value of the maximum difference in days CZT is 5.

[0089] In this application, the basic judgment threshold, regional impact factor and time impact factor are comprehensively calculated to obtain the dynamic judgment threshold, including:

[0090] Extract the basic judgment threshold CY, regional influence factor QZ and time influence factor SZ; obtain the dynamic judgment threshold DZ based on the formula DZ=CY×(R1×QZ / BQZ+R2×SZ / BSZ); wherein BQZ is the manually set standard regional influence factor, and BSZ is the manually set standard time influence factor; R1 and R2 are both proportional adjustment coefficients greater than 0.

[0091] In this embodiment, the basic determination threshold CY=0.6093, the regional influence factor QZ=1.069, and the time influence factor SZ=0.329. Therefore, based on the formula DZ=CY×(R1×QZ / BQZ+R2×SZ / BSZ)=0.6093×(0.6×1.069 / 1+0.4×0.329 / 0.3)=0.658, the dynamic determination threshold DZ=0.658 is obtained; wherein, in this embodiment, the value of the proportional adjustment coefficient R1 is 0.6, and the value of the proportional adjustment coefficient R2 is 0.4; the value of the standard regional influence factor BQZ is 1, and the value of the standard time influence factor BSZ is 0.3.

[0092] In this application, the credit factor and the dynamic determination threshold are judged to obtain the operation instruction, including:

[0093] Extract the current user's credit factor YZ and dynamic determination threshold DZ, and determine whether the credit factor YZ is greater than the dynamic determination threshold DZ; if yes, issue operation instruction one; if no, issue operation instruction two; wherein the operation instruction includes operation instruction one and operation instruction two.

[0094] In this application, the deposit and charging methods are set based on the operation instructions and the current rental amount, including:

[0095] Receive an operation instruction, and determine whether the received operation instruction is operation instruction one; if yes, charge the user a fixed fee based on a fixed deposit and a fixed daily rental amount; if no, charge the user a fluctuating fee; wherein the payment methods include fixed fees and fluctuating fees, and the fixed deposit and the fixed daily rental amount are both obtained through manual settings.

[0096] In this application, users are charged fluctuating fees, including:

[0097] Extract the current user's credit factor YZ and dynamic judgment threshold DZ, obtain the fluctuation ratio BL based on the formula BL=DZ / YZ, and multiply the fixed deposit by the fluctuation ratio BL to obtain the fluctuation deposit;

[0098] The fixed deposit is multiplied by the fixed daily rental amount to obtain the daily fluctuating rental amount. Starting from the rental day, the rental amount is collected every day according to the fluctuating rental amount, and the collected rental amounts are summed up to obtain the collected amount. The fixed rental amount for each day during the rental period is summed up to obtain the receivable amount. It is determined whether the recorded difference obtained by subtracting the collected amount from the receivable amount is less than the fluctuating rental amount. If so, after collecting the rental amount according to the recorded difference on the next day, stop collecting the rental amount from the current user during the current rental period. If not, continue to collect the rental amount according to the fluctuating rental amount.

[0099] It should be noted that collecting the rental amount in advance from users with low credit can help reduce the risk of rental default due to poor user credit.

[0100] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0101] Working principle of the present invention:

[0102] Obtain the user's basic information and rental information; analyze the number of rentals and default rate to obtain the user's credit factor; analyze the basic information to obtain the basic judgment threshold. In this step, age, occupation, education and rental amount are comprehensively considered to obtain a basic judgment threshold that can be used for the current user's credit judgment. Comprehensive consideration of these factors can provide users with a more personalized credit scoring mechanism; analyze based on the resident area and credit factor to obtain the regional influence factor. This step obtains the impact of the surrounding environment on the user's credit, which can reduce the credit assessment error caused by environmental changes, thereby improving the accuracy of the assessment; analyze based on the rental time and credit factor to obtain the time influence factor. This step takes into account the holiday factor, which can make the establishment of the credit assessment mechanism closer to the user's actual behavior pattern, thereby improving the reliability of the assessment result; comprehensively calculate the basic judgment threshold, regional influence factor and time influence factor to obtain the dynamic judgment threshold; judge the credit factor and the dynamic judgment threshold to obtain the operation instruction, and set the deposit and charging method based on the operation instruction and the current rental amount.

[0103] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A risk control system applicable to Internet rental, characterized in that: include: Intelligent analysis module, and the data collection module, risk control module and database connected to it; The data collection module is used to obtain the user's basic information and rental information; the basic information includes age, occupation, education and rental amount; the rental information includes the number of rentals, default rate, resident area and rental time; The intelligent analysis module is used to analyze the number of rental times and the default rate to obtain the user's credit factor; analyze the basic information to obtain the basic judgment threshold, analyze based on the resident area and the credit factor to obtain the regional influence factor, analyze based on the rental time and the credit factor to obtain the time influence factor; and comprehensively calculate the basic judgment threshold, the regional influence factor and the time influence factor to obtain the dynamic judgment threshold; The risk control module is used to determine the credit factor and the dynamic judgment threshold to obtain an operation instruction, and to set a deposit and a charging method based on the operation instruction and the current rental amount; wherein the payment method includes a fixed charge and a fluctuating charge.

2. A risk control system applicable to Internet rental according to claim 1, characterized in that: The obtaining of the user's basic information and rental information includes: Obtain the user's age, occupation and education level filled in by the user or imported from third-party software through the database, and obtain the user's fixed daily rental amount and rental time from the database; third-party software includes Alipay and WeChat; Obtain the number of times the current user rents a device and the default rate from the database; obtain the historical geographic location of the current user when using several historically rented devices based on the positioning system of several historically rented devices of the user; Obtain the area where each historical geographical location is located, obtain the ratio of the number of historical geographical locations owned by each area in the area to the total number of historical geographical locations, and mark the ratio as the location ratio; determine in turn whether the location ratio of each area exceeds a fixed ratio; if so, mark the area where the location ratio exceeds the fixed ratio as a permanent area; if not, sort the location ratios from large to small, and mark the areas corresponding to the location ratios with serial numbers in the top n% as permanent areas.

3. A risk control system applicable to Internet rental according to claim 1, characterized in that: The analysis of the number of rental times and the default rate to obtain the user's credit factor includes: A1: Extract the user's rental times ZC and default rate WL from the database, and determine whether the rental times ZC is greater than the fixed times; if yes, jump to A2; if no, jump to A3; A2: Determine whether the default rate WL is greater than the fixed default rate; if yes, mark the user as a low-credit user and prohibit the user from renting a device; if no, jump to A3; wherein the fixed number of times is obtained by sorting the number of times each user rents a device and selecting a number on a fixed percentile; the fixed default rate is obtained by sorting the default rate of each user and selecting a number on a fixed percentile; A3: The user's credit factor YZ is obtained based on the formula YZ = α / exp((WL-PWL) / PWL)×ZC / BZC; where α is the amplitude adjustment factor, and the value range of α is (0,2); PWL is the average default rate of each user in the database, and BZC is the standard number of rental times.

4. A risk control system applicable to Internet rental according to claim 1, characterized in that: The step of analyzing the basic information to obtain the basic determination threshold includes: Mark users with the same age, occupation and education level as the current user as reference users from the database, and obtain the mode ZS, percentile BS and maximum value ZD of the reference user basic judgment threshold; obtain the fixed factor GZ based on the formula GZ = β1 × (ZS + β2 × BS + β3 × ZD) / 2; where β1, β2 and β3 are all proportional adjustment coefficients greater than 0, and β2 + β3 = 1, β2 > β3; Extract the rental amount ZG, and obtain the basic judgment threshold CY based on the formula CY=GZ+δ / exp((ZG-BZG) / BZG); wherein BZG is the standard rental amount; δ is the amplitude adjustment coefficient of the exp() function, and the value range of δ is (0,1).

5. A risk control system applicable to Internet machine rental according to claim 1, characterized in that: The regional impact factors obtained by analyzing the resident region and credit factors include: Obtain the credit factors of all users in the resident area corresponding to the current user, and combine the credit factors of all users into a regional credit library; obtain the variance of the regional credit library, and determine whether the variance is greater than the corresponding variance limit value; if yes, remove the credit factor with the largest difference from the credit factor mode in the regional credit library, and re-determine the variance until the variance of the regional credit library is no greater than the variance limit value, and retain the remaining data in the regional credit library; if no, retain the data in the regional credit library; Obtain the mode and average of the data retained in the regional credit database, perform proportional calculation on the mode and average to obtain the regional credit feature value YT, and obtain the credit factor YZ of the current user; obtain the regional influence factor QZ based on the formula QZ=1 / (ln(μ×(YZ-YT) / YT+1)+1); wherein μ is the amplitude adjustment factor of the ln() function, and the value range of μ is (0,1).

6. A risk control system applicable to Internet rental according to claim 1, characterized in that: The time influencing factors obtained by analyzing the rental time and the credit factor include: B1: Get the difference T1 between the current date and the nearest statutory holiday after the current date, and determine whether the difference T1 exceeds the maximum difference; if yes, mark the time impact factor SZ as 0; if no, jump to B2; B2: Extract the number of days T2 of the nearest statutory holiday after the current date, and obtain the time impact factor SZ based on the formula SZ = ρ × ln (σ × (T2-BT2) / BT2 + 1) × T1 / CZT; where BT2 is the standard number of days, CZT is the maximum difference number of days; ρ is the impact control coefficient of each statutory holiday type; σ is the amplitude adjustment coefficient, and the value range of σ is (0,1).

7. A risk control system applicable to Internet rental according to claim 1, characterized in that: The dynamic determination threshold is obtained by comprehensively calculating the basic determination threshold, the regional impact factor and the time impact factor, including: Extract the basic judgment threshold CY, regional influence factor QZ and time influence factor SZ; obtain the dynamic judgment threshold DZ based on the formula DZ=CY×(R1×QZ / BQZ+R2×SZ / BSZ); among them, BQZ is the standard regional influence factor, BSZ is the standard time influence factor; R1 and R2 are both proportional adjustment coefficients greater than 0.

8. A risk control system applicable to Internet machine rental according to claim 1, characterized in that: The step of determining the credit factor and the dynamic determination threshold to obtain an operation instruction includes: Extract the current user's credit factor YZ and dynamic determination threshold DZ, and determine whether the credit factor YZ is greater than the dynamic determination threshold DZ; if yes, issue operation instruction one; if no, issue operation instruction two; wherein the operation instructions include operation instruction one and operation instruction two.

9. A risk control system applicable to Internet machine rental according to claim 8, characterized in that: The deposit and charging method are set based on the operation instruction and the current rental amount, including: Receive an operation instruction, and determine whether the received operation instruction is operation instruction one; if yes, charge the user a fixed fee based on a fixed deposit and a fixed daily rental amount; if no, charge the user a fluctuating fee; wherein the payment methods include fixed fees and fluctuating fees.

10. A risk control system applicable to Internet machine rental according to claim 9, characterized in that: The fluctuating charges to the user include: Extract the current user's credit factor YZ and dynamic judgment threshold DZ, obtain the fluctuation ratio BL based on the formula BL=DZ / YZ, and multiply the fixed deposit by the fluctuation ratio BL to obtain the fluctuation deposit; The fixed deposit is multiplied by the fixed daily rental amount to obtain the daily fluctuating rental amount. Starting from the rental day, the rental amount is collected every day according to the fluctuating rental amount, and the collected rental amounts are summed to obtain the collected amount. The fixed rental amount for each day during the rental period is summed to obtain the receivable amount. It is determined whether the recorded difference obtained by subtracting the collected amount from the receivable amount is less than the fluctuating rental amount. If so, after the rental amount is collected according to the recorded difference on the next day, the rental amount for the current user during the current rental period is stopped; if not, the rental amount is continued to be collected according to the fluctuating rental amount.

Images