Investor screening method, investor screening device, and computer-readable storage medium

Abstract

The embodiments of the present application disclose a method for screening investors, an investor screening device, and a computer-readable storage medium for screening out target investors for processing a current order. The method of the embodiments of the present application includes: obtaining an order risk value and a preset risk threshold value of a current order, determining multiple alternative investors, each of which has a corresponding investor risk value, and for each alternative investor, using a fuzzy logic inference algorithm to perform fuzzy logic processing on the current order risk value, the preset risk threshold value, and the investor risk value of the alternative investor to obtain a corresponding rejection probability of the alternative investor, the rejection probability being used to represent the likelihood that the alternative investor will reject the current order, and selecting an alternative investor whose rejection probability does not exceed the preset rejection probability threshold as the target investor for processing the current order.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of investor screening, and more specifically, to an investor screening method, an investor screening device, and a computer-readable storage medium. Background Art

[0002] The loan assistance platform has a pool of investors, which includes multiple investors. The loan assistance platform can receive orders and match them to investors. The contract between the investor and the loan assistance platform stipulates a preset risk threshold. If the investor's investor risk value exceeds the preset risk threshold, the loan assistance platform needs to pay a penalty to the investor. In order to increase the overall market profit, it is necessary to reduce the situation where the loan assistance platform pays penalties to the investor. Therefore, it is necessary to screen out the target investor to process the order from the alternative investors in the investor pool, so that the investor risk value of the target investor after processing the order is as small as possible or equal to the preset risk threshold.

[0003] The existing investor screening method is to obtain the order risk value of the current order, the preset risk threshold, and the investor risk value of each investor. It can first determine whether the order risk value is less than or equal to the preset risk threshold. If so, it can then determine whether the investor risk value of each alternative investor is less than or equal to the preset risk threshold, obtain the judgment result, and based on the judgment result, use the alternative investor whose investor risk value is less than or equal to the preset risk threshold as the target investor for processing the current order.

[0004] However, for this investor screening method, under the condition that the order risk is less than the preset risk threshold, the alternative investor can be used as the target investor for processing the current order as long as the investor risk value is less than or equal to the preset risk threshold. Therefore, if the investor risk value of the alternative investor is about to reach the preset risk threshold, the current order can still be processed. After the loan is successfully issued, the probability that the investor risk of the target investor is greater than the preset risk threshold is increased, and the probability that the loan assistance platform needs to pay a penalty to the target investor is increased, thereby reducing the profit of the overall market. Summary of the Invention

[0005] Embodiments of the present application provide a method for screening investors, an investor screening device, and a computer-readable storage medium, which can screen out target investors for processing a current order.

[0006] In a first aspect, an embodiment of the present application provides a method for screening investors, comprising:

[0007] Obtain the order risk value and preset risk threshold of the current order;

[0008] Determining a plurality of candidate investors, each of the plurality of candidate investors having a corresponding investor risk value;

[0009] For each candidate sponsor, a fuzzy logic inference algorithm is used to perform fuzzy logic processing on the current order risk value, the preset risk threshold, and the sponsor risk value of the candidate sponsor to obtain a rejection probability corresponding to the candidate sponsor; the rejection probability is used to indicate the likelihood that the candidate sponsor will reject the current order;

[0010] The candidate sponsor whose rejection probability does not exceed the preset rejection probability threshold is used as the target sponsor for processing the current order.

[0011] Optionally, before performing fuzzy logic processing on the investor risk value, the current order risk value, and the preset risk threshold using a fuzzy logic inference algorithm, the method further includes:

[0012] Obtaining the historical order amount and historical order risk value of each of the alternative investors;

[0013] For each candidate investor, the investor risk value of the candidate investor is obtained according to the historical order amount and historical order risk value of the candidate investor.

[0014] Optionally, determining the investor risk value of the candidate investor based on the historical order amount and historical order risk of the candidate investor includes:

[0015] The historical order amount and the historical order risk value of the alternative investor are weighted averaged to obtain the investor risk value of the alternative investor.

[0016] Optionally, the using of a fuzzy logic inference algorithm to perform fuzzy logic processing on the investor risk value, the current order risk value, and the preset risk threshold to obtain a rejection probability of the candidate investor rejecting the current order includes:

[0017] The difference between the investor risk value and the preset risk threshold is used as a first input, and the difference between the current order risk value and the investor risk value is used as a second input;

[0018] Inputting the first input quantity into a first membership function to obtain the membership of the first input quantity, and inputting the second input quantity into a second membership function to obtain the membership of the second input quantity;

[0019] Determining, based on the membership degree of the first input quantity and the membership degree of the second input quantity, target rejection intention fuzzy labels corresponding to the first input quantity and the second input quantity and the membership degree of each target rejection intention fuzzy label;

[0020] The rejection probability is obtained by performing a weighted average of the membership degree of each target rejection intention fuzzy mark and the preset weight corresponding to each target rejection intention fuzzy mark.

[0021] Optionally, determining, based on the membership of the first input quantity and the membership of the second input quantity, the target rejection intention fuzzy marks corresponding to the first input quantity and the second input quantity and the membership of each target rejection intention fuzzy mark includes:

[0022] In a preset fuzzy rule base, the rejection intention fuzzy marks corresponding to the membership degree of the first input quantity and the membership degree of the second input quantity are used as target rejection intention fuzzy marks;

[0023] determining a strength value of the target rejection intention fuzzy mark according to the membership degree of the first input quantity and the membership degree of the second input quantity corresponding to the target rejection intention fuzzy mark;

[0024] The membership degree of each target rejection intention fuzzy mark is determined according to the strength value of at least one target rejection intention fuzzy mark.

[0025] Optionally, determining the strength value of the target rejection intention fuzzy mark according to the membership degree of the first input quantity and the membership degree of the second input quantity corresponding to the target rejection intention fuzzy mark includes:

[0026] The smaller degree of membership between the first input quantity and the second input quantity corresponding to the target rejection intention fuzzy mark is used as the strength value of the target rejection intention fuzzy mark.

[0027] Optionally, determining the membership of each target rejection intention fuzzy mark according to the strength value of at least one target rejection intention fuzzy mark includes:

[0028] determining, among at least one of the target rejection intention fuzzy marks, target rejection intention fuzzy marks belonging to the same type;

[0029] The maximum value among the intensity values ​​of the fuzzy mark of the same target rejection intention is taken as the membership degree of the fuzzy mark of the target rejection intention.

[0030] In a second aspect, an embodiment of the present application provides a funding screening device, comprising:

[0031] An obtaining unit, used to obtain the order risk value and the preset risk threshold of the current order;

[0032] a determining unit, configured to determine a plurality of candidate investors, each of which has a corresponding investor risk value;

[0033] a processing unit configured to perform fuzzy logic processing on the current order risk value, the preset risk threshold, and the funder risk value of each candidate funder using a fuzzy logic inference algorithm to obtain a rejection probability corresponding to the candidate funder; the rejection probability is used to indicate the likelihood that the candidate funder will reject the current order;

[0034] As a unit, it is used to take the candidate sponsor whose rejection probability does not exceed a preset rejection probability threshold as the target sponsor for processing the current order.

[0035] In a third aspect, an embodiment of the present application provides a funding screening device, comprising:

[0036] CPU, memory, input and output interfaces, wired or wireless network interfaces, and power supply;

[0037] The memory is a transient storage memory or a persistent storage memory;

[0038] The central processing unit is configured to communicate with the memory and execute instructions in the memory to perform the aforementioned investor screening method.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which includes instructions. When the instructions are executed on a computer, the computer executes the aforementioned investor screening method.

[0040] In a fifth aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the aforementioned investor screening method.

[0041] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages: for each alternative investor, a fuzzy logic inference algorithm can be used to perform fuzzy logic processing on the current order risk value, the preset risk threshold, and the investor risk value of the alternative investor, to obtain the corresponding rejection probability of the alternative investor. The rejection probability is used to indicate the possibility that the alternative investor will reject the current order, and the alternative investor whose rejection probability does not exceed the preset rejection probability threshold is used as the target investor for processing the current order. The requirement that the alternative investor can be used as the target investor for processing the current order is improved. After the loan is successfully issued, the probability that the investor risk of the target investor is greater than the preset risk threshold is reduced, the probability that the loan assistance platform needs to pay a penalty to the target investor is reduced, and the profit of the market profit is increased. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic flow chart of a method for screening investors disclosed in an embodiment of the present application;

[0043] Figure 2A flowchart of a fuzzy logic processing method disclosed in an embodiment of the present application;

[0044] Figure 3 A schematic diagram of a first membership function disclosed in an embodiment of the present application;

[0045] Figure 4 A schematic diagram of a second membership function disclosed in an embodiment of the present application;

[0046] Figure 5 A schematic diagram of a rejection intention membership function disclosed in an embodiment of the present application;

[0047] Figure 6 A schematic diagram of a fuzzy logic reasoning surface disclosed in an embodiment of the present application;

[0048] Figure 7 This is a schematic structural diagram of a capital screening device disclosed in an embodiment of the present application;

[0049] Figure 8 This is a schematic structural diagram of another investor screening device disclosed in an embodiment of the present application;

[0050] Figure 9 This is a structural schematic diagram of another investor screening device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The embodiments of the present application provide a method for screening investors, an investor screening device, and a computer-readable storage medium for screening out target investors for processing current orders. The investor screening device is also known as an investor risk control device.

[0052] See also Figure 1 , Figure 1 This is a flow chart of a method for screening investors disclosed in an embodiment of the present application, the method comprising:

[0053] 101. Obtain the order risk value and preset risk threshold of the current order.

[0054] In this embodiment, when screening investors, the order risk value and the preset risk threshold of the current order can be obtained.

[0055] 102. Determine multiple alternative investors, each of which has a corresponding investor risk value.

[0056] Multiple alternative investors may be determined, each having a corresponding investor risk value.

[0057] 103. For each alternative investor, a fuzzy logic inference algorithm is used to perform fuzzy logic processing on the current order risk value, the preset risk threshold, and the investor risk value of the alternative investor to obtain the corresponding rejection probability of the alternative investor; the rejection probability is used to indicate the possibility that the alternative investor will reject the current order.

[0058] After identifying multiple alternative investors, a fuzzy logic inference algorithm can be used to perform fuzzy logic processing on the current order risk value, the preset risk threshold, and the alternative investor's risk value for each alternative investor to obtain the corresponding rejection probability of the alternative investor. The rejection probability represents the likelihood that the alternative investor will reject the current order. It can be understood that using a fuzzy logic inference algorithm to perform fuzzy logic processing on the current order risk value, the preset risk threshold, and the alternative investor's risk value can yield a rejection probability that more accurately reflects the likelihood that the alternative investor will reject the current order. The rejection probability can then be used as a screening basis for investor selection. Therefore, using a fuzzy logic inference algorithm to perform fuzzy logic processing on the current order risk value, the preset risk threshold, and the alternative investor's risk value is of considerable significance.

[0059] 104. The alternative investor whose rejection probability does not exceed the preset rejection probability threshold is selected as the target investor for processing the current order.

[0060] After obtaining the rejection probabilities corresponding to the candidate investors, the candidate investors whose rejection probabilities do not exceed the preset rejection probability threshold can be used as the target investors for processing the current order.

[0061] In an embodiment of the present application, a fuzzy logic inference algorithm can be used for each alternative investor to perform fuzzy logic processing on the current order risk value, the preset risk threshold, and the investor risk value of the alternative investor to obtain the corresponding rejection probability of the alternative investor. The rejection probability is used to indicate the possibility that the alternative investor will reject the current order, and the alternative investor whose rejection probability does not exceed the preset rejection probability threshold is used as the target investor for processing the current order. This increases the requirements for alternative investors to be used as target investors for processing the current order. After the loan is successfully issued, the probability that the investor risk of the target investor is greater than the preset risk threshold is reduced, the probability that the loan assistance platform needs to pay a penalty to the target investor is reduced, and the profit of the overall market is increased.

[0062] In an embodiment of the present application, a fuzzy logic inference algorithm is used to perform fuzzy logic processing on the investor risk value, the current order risk value, and the preset risk threshold. There are multiple methods for obtaining the rejection probability of the alternative investor rejecting the current order, one of which is described below.

[0063] In this embodiment, there are multiple alternative investors in the investor pool of the loan assistance platform. The alternative investors can be alternative institutions that can provide funds, or other investors that can provide funds. The specific details are not limited here. When the loan assistance platform receives the current order, the artificial intelligence matching model can screen the alternative investors in the investor pool before deciding the matching order of the alternative investors, and use the alternative investors that meet the conditions as the target investors for processing the current order to prevent the investor risk value from exceeding the preset risk threshold, thereby causing losses. When screening investors, the order risk value and preset risk threshold of the current order can be obtained. The current order can be formed based on user information, order amount, account period and interest rate and other information. The specific formation method of the current order is not limited here.

[0064] Multiple alternative investors can be determined, and multiple alternative investors have corresponding investor risk values. Among them, the investor risk values ​​of multiple alternative investors are predetermined, and the determination method can be to obtain the historical order amount and historical order risk value of each alternative investor, and for each alternative investor, obtain the investor risk value of the alternative investor based on the historical order amount and historical order risk value of the alternative investor. It can also be determined based on other relevant information of the historical orders processed by the alternative investor, or it can be determined based on other relevant information of the alternative investor. The specific method for determining the investor risk value of the alternative investor is not limited here. Among them, the method for obtaining the investor risk value of the alternative investor based on the historical order amount and historical order risk value of the alternative investor can be to take a weighted average of the historical order amount and historical order risk value of the alternative investor to obtain the investor risk value of the alternative investor. The specific formula is as follows:

[0065]

[0066] Formula 1

[0067] Where Zr is the investor risk value, od_amt is the historical order amount, and od_lc is the historical order risk. It is understood that in addition to the above method for obtaining the investor risk value, other methods can also be used to obtain the investor risk value of the candidate investor based on the candidate investor's historical order amount and historical order risk value, and the specific methods are not limited here.

[0068] After obtaining the risk value of the alternative investors, we can use the fuzzy logic inference algorithm to perform fuzzy logic processing on the current order risk value, the preset risk threshold, and the risk value of the alternative investors for each alternative investor to obtain the corresponding rejection probability of the alternative investor. The rejection probability is used to indicate the possibility that the alternative investor will reject the current order. There are many ways to perform fuzzy logic processing to obtain the rejection probability. One method is described below. Figure 2 , Figure 2This is a flow chart of a fuzzy logic processing method disclosed in an embodiment of the present application, the method comprising:

[0069] 201. The difference between the investor's risk value and the preset risk threshold is used as a first input, and the difference between the current order risk value and the investor's risk value is used as a second input.

[0070] The difference between the investor's risk value and a preset risk threshold may be used as the first input, and the difference between the current order risk value and the investor's risk value may be used as the second input.

[0071] It is understood that the first input value and the second input value may have corresponding numerical ranges, and the specific numerical ranges are not limited. For this embodiment, for example, the numerical range of the first input value is (-0.5 to 0.5), and the numerical range of the second input value is (-1 to 1).

[0072] 202. Input the first input quantity into a first membership function to obtain the membership of the first input quantity, and input the second input quantity into a second membership function to obtain the membership of the second input quantity.

[0073] After obtaining the first input quantity and the second input quantity, the first input quantity may be input into a first membership function to obtain the membership of the first input quantity, and the second input quantity may be input into a second membership function to obtain the membership of the second input quantity.

[0074] It is worth mentioning that the first membership function and the second membership function are predetermined. Specifically, the numerical range of the first input and the numerical range of the second input can be obtained in advance. A preset number of fuzzy marks can be set for the first input and the second input. For example, 5 fuzzy marks are set for the first input and the second input, namely much higher, a little higher, almost equal, a little lower, and much lower. Please refer to Figure 3 , Figure 3 This is a schematic diagram of a first membership function disclosed in an embodiment of the present application. Figure 3 Different lines represent different fuzzy labels, the x-axis represents the first input quantity, and the y-axis represents the membership degree of the first input quantity. Figure 4 , Figure 4 This is a schematic diagram of a second membership function disclosed in an embodiment of the present application. Figure 4 Different lines represent different fuzzy labels. The x-axis represents the second input quantity, and the y-axis represents the membership of the second input quantity. For example, if the first input quantity is 0.015, inputting 0.015 into the first membership function will yield the membership of the first input quantity. See Table 1, which shows a membership of the first input quantity disclosed in the embodiments of this application.

[0075] First input: Investor risk value - preset risk threshold 0.015

[0076]

[0077]

[0078] Table 1

[0079] The second input quantity is -0.01. Inputting -0.01 into the second membership function can obtain the membership of the second input quantity. Please refer to Table 2, which shows a membership of the second input quantity disclosed in the embodiment of this application.

[0080] Second input: Order risk value - Investor risk value - 0.01

[0081]

[0082] Table 2

[0083] 203. Determine the target rejection intention fuzzy labels corresponding to the first input and the second input, and the membership of each target rejection intention fuzzy label, based on the membership of the first input and the membership of the second input.

[0084] After obtaining the membership of the first input quantity and the membership of the second input quantity, the target rejection intention fuzzy tags corresponding to the first input quantity and the second input quantity and the membership of each target rejection intention fuzzy tag can be determined based on the membership of the first input quantity and the membership of the second input quantity. Specifically, there are multiple methods for determining the target rejection intention fuzzy tags corresponding to the first input quantity and the second input quantity and the membership of each target rejection intention fuzzy tag based on the membership of the first input quantity and the membership of the second input quantity. The method can be to use the rejection intention fuzzy tags corresponding to the membership of the first input quantity and the membership of the second input quantity as the target rejection intention fuzzy tags in a preset fuzzy rule base, determine the strength value of the target rejection intention fuzzy tag based on the membership of the first input quantity and the membership of the second input quantity corresponding to the target rejection intention fuzzy tag, and determine the membership of each target rejection intention fuzzy tag based on the strength value of at least one target rejection intention fuzzy tag.

[0085] It is worth mentioning that the preset fuzzy rule base is predetermined, and the determination method is determined based on the first input fuzzy mark, the second input fuzzy mark, the predetermined rejection intention fuzzy mark, business experience, and the actual value distribution. Among them, the method for determining the rejection intention fuzzy mark can be to obtain the numerical range of rejection intention in advance, and the numerical range of rejection intention can be (0-1). A preset number of rejection intention fuzzy marks can be set, for example, three rejection intention fuzzy marks, namely strong rejection intention, medium rejection intention, and weak rejection intention. Please refer to Figure 5 , Figure 5This is a schematic diagram of a rejection intention membership function disclosed in an embodiment of the present application. Figure 5 Different lines represent different fuzzy marks, the x-axis represents the rejection intention, and the y-axis represents the membership of the first input. Please refer to Table 3, which is a preset fuzzy rule library disclosed in the embodiment of this application. For Table 3, the first input is the difference between the investor risk value and the preset risk threshold, and the second input is the difference between the current order risk value and the investor risk value. If the investor risk of the alternative investor exceeds the preset risk threshold, the order risk value is much lower than the investor risk value, and it can still be used as the target investor for processing the current order. Because the order risk value is lower than the investor risk value, after processing the order, the asset risk value can be lowered.

[0086]

[0087] Table 3

[0088] See also Figure 6 , Figure 6 This is a schematic diagram of a fuzzy logic reasoning surface disclosed in an embodiment of the present application. Figure 6 The coordinate system is a three-dimensional coordinate system with the first input as the x-axis, the second input as the y-axis, and the rejection intention as the z-axis.

[0089] It should be understood that, among others, the method for determining the strength value of the target rejection intention fuzzy tag based on the membership of the first input quantity and the membership of the second input quantity corresponding to the target rejection intention fuzzy tag may be to use the smaller membership of the membership of the first input quantity and the membership of the second input quantity corresponding to the target rejection intention fuzzy tag as the strength value of the target rejection intention fuzzy tag, or other methods for determining the strength value of the target rejection intention fuzzy tag based on the membership of the first input quantity and the membership of the second input quantity corresponding to the target rejection intention fuzzy tag, which are not specifically limited here. Among others, the method for determining the membership of each target rejection intention fuzzy tag based on the strength value of at least one target rejection intention fuzzy tag may be to determine the target rejection intention fuzzy tags belonging to the same type among at least one target rejection intention fuzzy tag, and use the maximum value among the strength values ​​of the target rejection intention fuzzy tags of the same type as the membership of the target rejection intention fuzzy tag of that type, or other methods for determining the membership of each target rejection intention fuzzy tag based on the strength value of at least one target rejection intention fuzzy tag, which are not specifically limited here. For example, the first input is 0.015, and the second input is -0.01. The membership of the first input is "much higher membership is 0.0102, slightly higher membership is 0.9444, almost equal membership is 0, slightly lower membership is 0, and much lower membership is 0", and the membership of the second input is "much higher membership is 0, slightly higher membership is 0, almost equal membership is 0.9800, slightly lower membership is 0.0200, and much lower membership is 0". According to the membership of the first input and the membership of the second input, please continue to refer to Table 1. In the preset fuzzy rule library, the target fuzzy rules corresponding to the membership of the first input of 0.015 and the membership of the second input of -0.01 can be determined. The target fuzzy rules are as follows:

[0090] Target fuzzy rule a: The membership degree of the investor risk value that is much higher than the preset risk threshold is 0.0102, and the membership degree of the order risk value that is almost equal to the investor risk value is 0.9800. The target rejection intention fuzzy mark is strong rejection intention;

[0091] Target fuzzy rule b: The membership degree of the investor risk value that is much higher than the preset risk threshold is 0.0102, and the membership degree of the order risk value that is slightly lower than the investor risk value is 0.0200. The target rejection intention fuzzy mark is medium rejection intention;

[0092] Target fuzzy rule c: The membership degree of the investor risk value being slightly higher than the preset risk threshold is 0.9444, and the membership degree of the order risk value being almost equal to the investor risk value is 0.9800. The target rejection intention fuzzy mark is medium rejection intention;

[0093] Target fuzzy rule d: The membership degree of the investor risk value that is much higher than the preset risk threshold is 0.9444, and the membership degree of the order risk value that is almost equal to the investor risk value is 0.0200. The target rejection intention is fuzzy marked as weak rejection intention.

[0094] After obtaining the target fuzzy rule, it can be determined that the target rejection intention fuzzy labels corresponding to the membership of the first input quantity of 0.015 and the membership of the second input quantity of -0.01 are strong rejection intention, medium rejection intention and weak rejection intention. The smaller membership of the membership of the first input quantity and the membership of the second input quantity corresponding to the target rejection intention fuzzy label can be used as the strength value of the target rejection intention fuzzy label. Therefore, the strength of the target fuzzy rule a is 0.0102, the strength of the target fuzzy rule b is 0.0102, and the strength of the target fuzzy rule c is 0.0102. The strength of target fuzzy rule d is 0.9444, and the strength of target fuzzy rule d is 0.0200. Among these four target fuzzy rules, the rejection intention fuzzy labels of target fuzzy rule b and target fuzzy rule c are both medium. The maximum value among the strength values ​​can be used as the membership of medium. Therefore, for the first input quantity of 0.015 and the second input quantity of -0.01, the membership of the rejection intention fuzzy label of medium is 0.9444, the membership of the rejection intention fuzzy label of high is 0.0102, and the membership of the rejection intention fuzzy label of low is 0.0200. It can be understood that in addition to the method described above for determining the target rejection intention fuzzy labels corresponding to the first input quantity and the second input quantity and the membership of each target rejection intention fuzzy label, other methods can also be used to determine the target rejection intention fuzzy labels corresponding to the first input quantity and the second input quantity and the membership of each target rejection intention fuzzy label based on the membership of the first input quantity and the membership of the second input quantity, which are not limited to the specific methods here.

[0095] 204. Perform a weighted average of the membership degree of each target rejection intention fuzzy mark and the preset weight corresponding to each target rejection intention fuzzy mark to obtain a rejection probability.

[0096] After determining the target rejection intention fuzzy labels corresponding to the first and second input quantities and the membership of each target rejection intention fuzzy label, the membership of each target rejection intention fuzzy label and the preset weight corresponding to each target rejection intention fuzzy label can be weighted averaged to obtain the rejection probability. Continuing with the example of the first input quantity being 0.015 and the second input quantity being -0.01, the membership of the rejection intention medium is 0.9444, the membership of the rejection intention high fuzzy is 0.0102, and the membership of the rejection intention low is 0.0200. After the preset weights corresponding to each target rejection intention fuzzy label are, for example, a weight of 1 for a strong rejection intention, a weight of 0.5 for a medium rejection intention, and a weight of 0.001 for a weak rejection intention, the rejection probability can be calculated for a first input quantity of 0.015 and a second input quantity of -0.01 using the following formula:

[0097]

[0098] Formula 2

[0099] The rejection probability is 0.4950 when the first input is 0.015 and the second input is -0.01. Figure 2 In addition to the fuzzy logic processing method shown, other methods for performing fuzzy logic processing to obtain rejection probability may also be used, and the specific methods are not limited here.

[0100] After obtaining the rejection probabilities for the candidate investors, the candidate with a rejection probability that does not exceed the preset rejection probability threshold can be selected as the target investor for processing the current order. Continuing with the example of a first input of 0.015 and a second input of -0.01, if the rejection probability for the first input of 0.015 and the second input of -0.01 is 0.4950, and the preset rejection probability threshold is 0.6, then this candidate investor can be selected as the target investor for processing the current order because 0.4950 is less than 0.6.

[0101] It is understood that the alternative investor can be a profit-sharing investor under the profit-sharing model or an investor under another model, and the specific details are not limited here. It is also understood that the target investor for processing the current order can be the investor directly processing the current order or an alternative investor for processing the current order, and the specific details are not limited here. It is also understood that the fuzzy logic reasoning algorithm is transferable and can be used in business scenarios other than screening investors, as well as other business scenarios requiring decision-making, and the specific details are not limited here.

[0102] In this embodiment, a fuzzy logic inference algorithm can be used for each candidate investor to perform fuzzy logic processing on the current order risk value, the preset risk threshold, and the candidate investor's risk value. This yields a corresponding rejection probability for the candidate investor. The rejection probability represents the likelihood that the candidate investor will reject the current order, and the candidate investor whose rejection probability does not exceed the preset rejection probability threshold is selected as the target investor for processing the current order. This increases the requirements for candidate investors to be selected as target investors for processing the current order. After a loan is successfully disbursed, the probability that the target investor's risk exceeds the preset risk threshold is reduced, reducing the probability that the loan facilitation platform will need to pay a penalty to the target investor, thereby increasing the overall market profit. Secondly, it can be understood that the introduced fuzzy logic inference algorithm, namely, the application of the investor risk control in asset allocation, makes the entire investor risk control simple and effective by inputting variables. Based on the investor risk value, order risk value, and the preset risk threshold, the control module can output the final decision strength value. This can not only fuzzify the precise value for reasoning, but also output an accurate decision strength value to assist in decision making. Furthermore, the first membership function, the second membership function and the preset fuzzy rule base are all obtained through business experience and continuous online debugging. The entire process is controlled, and the control module is effective under any circumstances, which improves the real-time performance of investor screening and investor risk control.

[0103] The above describes the investor screening method in the embodiment of the present application. The following describes the investor screening device in the embodiment of the present application. Figure 7 One embodiment of the investor screening device in the embodiment of the present application includes:

[0104] An obtaining unit 701 is used to obtain an order risk value and a preset risk threshold value of a current order;

[0105] A determining unit 702 is configured to determine a plurality of candidate investors, each of which has a corresponding investor risk value;

[0106] Processing unit 703 is configured to perform fuzzy logic processing on the current order risk value obtained by obtaining unit 701, the preset risk threshold, and the funder risk value of the alternative funder determined by determining unit 702 for each of the alternative funders using a fuzzy logic inference algorithm to obtain a rejection probability corresponding to the alternative funder; the rejection probability is used to indicate the likelihood that the alternative funder will reject the current order;

[0107] As unit 704, it is used to use the candidate sponsor whose rejection probability obtained by the processing unit 703 does not exceed the preset rejection probability threshold as the target sponsor for processing the current order.

[0108] In an embodiment of the present application, a fuzzy logic inference algorithm can be used for each alternative investor to perform fuzzy logic processing on the current order risk value, the preset risk threshold, and the investor risk value of the alternative investor to obtain the corresponding rejection probability of the alternative investor. The rejection probability is used to indicate the possibility that the alternative investor will reject the current order, and the alternative investor whose rejection probability does not exceed the preset rejection probability threshold is used as the target investor for processing the current order. This increases the requirements for alternative investors to be used as target investors for processing the current order. After the loan is successfully issued, the probability that the investor risk of the target investor is greater than the preset risk threshold is reduced, the probability that the loan assistance platform needs to pay a penalty to the target investor is reduced, and the profit of the overall market is increased.

[0109] The following is a detailed description of the capital screening device in the embodiment of the present application, please refer to Figure 8 Another embodiment of the investor screening device in the embodiment of the present application includes:

[0110] An obtaining unit 801 is used to obtain an order risk value and a preset risk threshold value of a current order;

[0111] A determining unit 802 is configured to determine a plurality of candidate investors, each of which has a corresponding investor risk value;

[0112] The processing unit 803 is configured to perform fuzzy logic processing on the current order risk value obtained by the obtaining unit 801, the preset risk threshold, and the funder risk value of the alternative funder determined by the determining unit 802 using a fuzzy logic inference algorithm for each of the alternative funders, thereby obtaining a rejection probability corresponding to the alternative funder; the rejection probability is used to indicate the likelihood that the alternative funder will reject the current order;

[0113] As unit 804, it is used to take the candidate sponsor whose rejection probability obtained by the processing unit 803 does not exceed the preset rejection probability threshold as the target sponsor for processing the current order.

[0114] The investor screening device further includes: an obtaining unit 805;

[0115] The obtaining unit 801 is further configured to obtain the historical order amount and historical order risk value of each candidate investor;

[0116] The obtaining unit 805 is specifically configured to obtain, for each candidate investor, the investor risk value of the candidate investor according to the historical order amount and historical order risk value of the candidate investor obtained by the obtaining unit 801 .

[0117] The determining unit 802 is specifically configured to perform weighted averaging on the historical order amounts and historical order risk values ​​of the candidate investor obtained by the obtaining unit 801 to obtain the investor risk value of the candidate investor.

[0118] The obtaining unit 805 is specifically used to take the difference between the investor risk value determined by the determining unit 802 and the preset risk threshold obtained by the obtaining unit 801 as the first input, and the difference between the current order risk value and the investor risk value as the second input, input the first input into the first membership function to obtain the membership of the first input, and input the second input into the second membership function to obtain the membership of the second input, determine the target rejection intention fuzzy mark corresponding to the first input and the second input and the membership of each target rejection intention fuzzy mark according to the membership of the first input and the membership of the second input, perform weighted averaging on the membership of each target rejection intention fuzzy mark and the preset weight corresponding to each target rejection intention fuzzy mark, and obtain the rejection probability.

[0119] The determination unit 802 is specifically used to use the rejection intention fuzzy marks corresponding to the membership of the first input quantity and the membership of the second input quantity as the target rejection intention fuzzy marks in the preset fuzzy rule base, determine the strength value of the target rejection intention fuzzy marks according to the membership of the first input quantity and the membership of the second input quantity corresponding to the target rejection intention fuzzy marks, and determine the membership of each target rejection intention fuzzy mark according to the strength value of at least one of the target rejection intention fuzzy marks.

[0120] The determining unit 802 is specifically configured to use the smaller of the membership of the first input quantity and the membership of the second input quantity obtained by the obtaining unit 805 corresponding to the target rejection intention fuzzy mark as the strength value of the target rejection intention fuzzy mark.

[0121] The determination unit 802 specifically determines target rejection intention fuzzy marks belonging to the same type among at least one of the target rejection intention fuzzy marks, and takes the maximum value of the strength values ​​determined by the determination unit 802 of the target rejection intention fuzzy marks of the same type as the membership of the target rejection intention fuzzy mark.

[0122] In this embodiment, each unit in the capital screening device performs the above Figure 1 and Figure 2 The operation of the capital screening equipment in the illustrated embodiment will not be described in detail here.

[0123] See below Figure 9 Another embodiment of the vehicle sharing device 900 in the embodiment of the present application includes:

[0124] CPU 901, memory 905, input / output interface 904, wired or wireless network interface 903 and power supply 902;

[0125] The memory 905 is a temporary storage memory or a permanent storage memory;

[0126] The CPU 901 is configured to communicate with the memory 905 and execute the instructions in the memory 905 to perform the aforementioned Figure 1 and Figure 2 The method in the embodiment shown.

[0127] The embodiment of the present application also provides a computer-readable storage medium, which includes instructions. When the instructions are executed on a computer, the computer executes the aforementioned Figure 1 and Figure 2 The method in the embodiment shown.

[0128] The present application also provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the aforementioned Figure 1 and Figure 2 The method in the embodiment shown.

[0129] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0130] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0131] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0133] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0134] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk, and other media that can store program code.

Claims

1. A method for screening investors, characterized in that: Applied to capital screening equipment, including: Obtain the order risk value and preset risk threshold of the current order; Determining a plurality of candidate investors, each of the plurality of candidate investors having a corresponding investor risk value; For each candidate sponsor, a fuzzy logic inference algorithm is used to perform fuzzy logic processing on the order risk value of the current order, the preset risk threshold, and the sponsor risk value of the candidate sponsor to obtain a corresponding rejection probability of the candidate sponsor; the rejection probability is used to represent the likelihood that the candidate sponsor will reject the current order; The alternative sponsor whose rejection probability does not exceed the preset rejection probability threshold is selected as the target sponsor for processing the current order; The method of using a fuzzy logic inference algorithm to perform fuzzy logic processing on the order risk value of the current order, the preset risk threshold, and the capital risk value of the alternative capital provider to obtain a rejection probability corresponding to the alternative capital provider includes: The difference between the investor risk value and the preset risk threshold is used as a first input, and the difference between the order risk value of the current order and the investor risk value is used as a second input; Inputting the first input quantity into a first membership function to obtain the membership of the first input quantity, and inputting the second input quantity into a second membership function to obtain the membership of the second input quantity; Determining, based on the membership degree of the first input quantity and the membership degree of the second input quantity, target rejection intention fuzzy labels corresponding to the first input quantity and the second input quantity and the membership degree of each target rejection intention fuzzy label; The rejection probability is obtained by performing a weighted average of the membership degree of each target rejection intention fuzzy mark and the preset weight corresponding to each target rejection intention fuzzy mark.

2. The method according to claim 1, characterized in that Before performing fuzzy logic processing on the order risk value of the current order, the preset risk threshold, and the investor risk value of the candidate investor using the fuzzy logic inference algorithm, the method further includes: Obtaining the historical order amount and historical order risk value of each of the alternative investors; For each candidate investor, the investor risk value of the candidate investor is obtained according to the historical order amount and historical order risk value of the candidate investor.

3. The method according to claim 2, characterized in that The determining of the investor risk value of the candidate investor based on the historical order amount and historical order risk value of the candidate investor includes: The historical order amount and the historical order risk value of the alternative investor are weighted averaged to obtain the investor risk value of the alternative investor.

4. The method according to claim 1, wherein The determining, based on the membership of the first input quantity and the membership of the second input quantity, the target rejection intention fuzzy labels corresponding to the first input quantity and the second input quantity and the membership of each target rejection intention fuzzy label includes: In a preset fuzzy rule base, the rejection intention fuzzy marks corresponding to the membership degree of the first input quantity and the membership degree of the second input quantity are used as target rejection intention fuzzy marks; determining a strength value of the target rejection intention fuzzy mark according to the membership degree of the first input quantity and the membership degree of the second input quantity corresponding to the target rejection intention fuzzy mark; The membership degree of each target rejection intention fuzzy mark is determined according to the strength value of at least one target rejection intention fuzzy mark.

5. The method according to claim 4, characterized in that The determining the strength value of the target rejection intention fuzzy mark according to the membership degree of the first input quantity and the membership degree of the second input quantity corresponding to the target rejection intention fuzzy mark includes: The smaller degree of membership between the first input quantity and the second input quantity corresponding to the target rejection intention fuzzy mark is used as the strength value of the target rejection intention fuzzy mark.

6. The method according to claim 4, characterized in that Determining the membership of each target rejection intention fuzzy mark according to the strength value of at least one target rejection intention fuzzy mark includes: determining, among at least one of the target rejection intention fuzzy marks, target rejection intention fuzzy marks belonging to the same type; The maximum value among the intensity values ​​of the fuzzy mark of the same target rejection intention is taken as the membership degree of the fuzzy mark of the target rejection intention.

7. A capital screening device, characterized in that: include: An obtaining unit, used to obtain the order risk value and the preset risk threshold of the current order; a determining unit, configured to determine a plurality of candidate investors, each of which has a corresponding investor risk value; a processing unit configured to perform fuzzy logic processing on the order risk value of the current order, the preset risk threshold, and the capital risk value of the alternative capital provider using a fuzzy logic inference algorithm for each of the alternative capital providers, to obtain a corresponding rejection probability of the alternative capital provider; the rejection probability is used to indicate the likelihood that the alternative capital provider will reject the current order; as a unit, configured to select the candidate sponsor whose rejection probability does not exceed a preset rejection probability threshold as the target sponsor for processing the current order; The processing unit is specifically used to take the difference between the investor risk value and the preset risk threshold as the first input, and the difference between the order risk value of the current order and the investor risk value as the second input, input the first input into the first membership function to obtain the membership of the first input, and input the second input into the second membership function to obtain the membership of the second input, determine the target rejection intention fuzzy mark corresponding to the first input and the second input and the membership of each target rejection intention fuzzy mark according to the membership of the first input and the membership of the second input, and perform weighted averaging on the membership of each target rejection intention fuzzy mark and the preset weight corresponding to each target rejection intention fuzzy mark to obtain the rejection probability.

8. A capital screening device, characterized in that: include: CPU, memory, input and output interfaces, wired or wireless network interfaces, and power supply; The memory is a transient storage memory or a persistent storage memory; The central processing unit is configured to communicate with the memory and execute instructions in the memory to perform the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium comprises instructions, and when the instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 6.

Images