Loan product recommendation method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a loan product recommendation method and device, equipment, a storage medium and a program product, and relates to the field of financial science and technology or other related fields. The method comprises the following steps: acquiring at least one piece of user information; the user information comprises at least one influence factor influencing loan; for each user, determining at least one factor target weight according to the at least one influence factor; for each user, determining at least one product target weight corresponding to each influence factor according to the at least one loan product; and according to the at least one factor target weight and the at least one product target weight, performing multilevel analysis to determine a loan product of the corresponding user. According to the method and the device, a more reasonable loan product can be determined, and in addition, the efficiency of determining the loan product is improved.

Description

Technical Field

[0001] The present application relates to financial technology or other related fields, and in particular to a method, device, equipment, storage medium and program product for recommending loan products. Background Art

[0002] At present, major financial institutions have introduced a variety of loan products. Different loan products can serve different users, thereby solving the user's financial difficulties.

[0003] Currently, after a financial institution contacts a user, it uses face-to-face interviews to manually determine a loan product for the user from a variety of loan products.

[0004] However, currently, major financial institutions have introduced a large number of loan products, and sales staff cannot be familiar with every loan product, which may lead to sales staff selling inappropriate loan products to users. In addition, manually determining loan products for users results in low efficiency and increased labor costs. Summary of the invention

[0005] The present application provides a loan product recommendation method, device, equipment, storage medium and product, which are used to solve the technical problems of salesmen promoting inappropriate loan products to users and low efficiency.

[0006] In a first aspect, the present application provides a method for recommending a loan product, the method comprising:

[0007] Acquire at least one user information; the user information includes at least one factor affecting the loan;

[0008] For each user, determining at least one factor target weight according to at least one influencing factor;

[0009] For each user, determining at least one product target weight corresponding to each influencing factor according to at least one loan product;

[0010] The loan product corresponding to the user is determined through multi-level analysis based on the at least one factor target weight and the at least one product target weight.

[0011] In a second aspect, the present application provides a loan product recommendation device, comprising:

[0012] An acquisition module, used to acquire at least one user information; the user information includes at least one factor affecting the loan;

[0013] A determination module, configured to determine at least one factor target weight for each user according to at least one influencing factor;

[0014] The determination module is further used to determine at least one product target weight corresponding to each influencing factor according to at least one loan product for each user;

[0015] The determination module is also used to determine the loan product corresponding to the user through multi-level analysis based on the at least one factor target weight and the at least one product target weight.

[0016] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0017] The memory stores computer-executable instructions;

[0018] The processor executes the computer-executable instructions stored in the memory to implement any one of the methods described in the first aspect.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement any of the methods described in the first aspect.

[0020] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the methods in the first aspect above.

[0021] The loan product recommendation method, device, equipment, storage medium and program product provided by the present application, in the present application, at least one user information is first obtained, and the user information includes at least one influencing factor, which is a factor affecting the loan, and then for each user, at least one factor target weight is determined according to the influencing factor, and at least one product target weight corresponding to each influencing factor is determined according to the loan product, so as to determine the loan product corresponding to the user through multi-level analysis based on the factor target weight and the product target weight. In the present application, the weight occupied by the influencing factor corresponding to the loan (i.e., the factor target weight) and the weight occupied by each loan product under each influencing factor (i.e., the product target weight) are taken into account, so that the present application realizes multi-level analysis, comprehensively considers the weight occupied by the influencing factor and the loan product at the time of the loan, that is, considers both the factor side and the product side, wherein the product side also combines the weight occupied by the loan product under different influencing factors, so the product target weight is more appropriate and more in line with the corresponding influencing factor, so as to determine a reasonable loan product for the user; in addition, the present application adopts a device to realize the recommendation of loan products, so as to improve efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0023] Figure 1 This is a schematic diagram of the application scenario of this application;

[0024] Figure 2 A flowchart of a method for recommending a loan product provided in Example 1;

[0025] Figure 3 A flowchart of a method for recommending a loan product provided in Example 2;

[0026] Figure 4 A flowchart of a method for recommending a loan product provided in Example 3;

[0027] Figure 5 A flowchart of a method for recommending a loan product provided in Example 4;

[0028] Figure 6 A method for recommending loan products provided in Example 8;

[0029] Figure 7 A schematic diagram of a loan product recommendation device structure provided in Example 9;

[0030] Figure 8 A schematic diagram of the structure of an electronic device provided in Example 10.

[0031] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0032] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0033] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0034] In addition, this application involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and the use of artificial intelligence technology for automated decision-making, and a technical solution for making decisions that have a significant impact on personal rights and interests based on the results of automated decision-making. The application provides users with corresponding operation entrances for them to choose to agree or reject the results of automated decision-making; if the user chooses to reject, the expert decision-making process will be entered.

[0035] It should be noted that the recommended methods, devices, equipment, storage media and products for the loan products provided in this application can be used in the field of financial technology, and can also be used in any field other than financial technology. The application fields of the recommended methods, devices, equipment, storage media and products for the loan products in this application are not limited.

[0036] Currently, after financial institutions contact a user, they manually determine a loan product for the user through face-to-face interviews.

[0037] However, currently, major financial institutions have introduced a large number of loan products, and sales staff cannot be familiar with every loan product, which may lead to sales staff selling inappropriate loan products to users. In addition, manually determining loan products for users results in low efficiency and increased labor costs.

[0038] In order to solve the defects of the prior art, the inventor of the present invention has designed a new solution after creative research. The present invention provides a method for recommending loan products. In order to understand the problem of salesmen promoting inappropriate loan products to users and the low efficiency, after the electronic device obtains at least one user information, the user information includes at least one influencing factor affecting the loan. Furthermore, the electronic device determines the factor target weight corresponding to the influencing factor based on the at least one influencing factor, so as to obtain the weights of all influencing factors at the time of loan (i.e., factor target weights). The factor target weights reflect the importance of the corresponding influencing factors on the loan at the time of loan, and play a decisive role at the time of loan. Furthermore, the electronic device determines the weight of each loan under each influencing factor based on at least one loan product. The weight of the product at the time of loan (i.e., the product target weight), and then the factor target weight and product target weight are used to determine the user's loan product. This solution considers both the factor side and the product side, and the product side is the weight of at least one loan product at the time of loan under each influencing factor, so the product side is diversified and targeted according to the influencing factors, and the product target weight obtained is more in line with the user, so based on the influencing target weight and product target weight, a more suitable loan product can be determined for the user; in addition, electronic devices are used in this application to realize the recommendation of loan products, and loan products can also be determined for multiple users, so this application can provide efficiency. The following is a specific application scenario of this application.

[0039] Figure 1 This is a schematic diagram of the application scenario of this application. Figure 1 As shown, an electronic device 101 is included.

[0040] The electronic device 101 may be a mobile phone, a computer or other device with computing functions, which is not limited here.

[0041] The electronic device 101 includes a device for recommending loan products.

[0042] Specifically, the electronic device 101 obtains at least one piece of user information; the user information includes at least one factor affecting the loan.

[0043] Furthermore, the electronic device 101 determines at least one factor target weight for each user according to at least one influencing factor. Furthermore, the electronic device 101 determines at least one product target weight corresponding to each influencing factor according to at least one loan product.

[0044] Furthermore, the electronic device 101 determines the loan product for the user through a multi-level analysis based on at least one factor target weight and at least one product target weight.

[0045] It should be noted that if there are multiple pieces of user information, they correspond to multiple users, so that the electronic device can determine the loan products corresponding to the multiple users.

[0046] The recommendation method for loan products provided in this application is intended to solve the above technical problems of the prior art.

[0047] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0048] Embodiment 1

[0049] The executing entity of Embodiments 1 to 8 of the present application is a loan product recommendation device, wherein the loan product recommendation device is located in an electronic device.

[0050] Figure 2 This is a flowchart of a method for recommending a loan product provided in Example 1. Figure 2 As shown, including:

[0051] S201, obtaining at least one piece of user information; the user information includes at least one factor affecting the loan.

[0052] Among them, influencing factors refer to factors that affect loans.

[0053] The user information refers to information related to the user. The user information may include identity information, asset information, and credit information. The influencing factors may include identity influencing factors, asset influencing factors, and information influencing factors.

[0054] Among them, one user corresponds to one user information, and in this embodiment, the electronic device can obtain multiple user information, and then determine the loan products for multiple users. Therefore, this embodiment can improve efficiency.

[0055] S202: For each user, determine at least one factor target weight according to at least one influencing factor.

[0056] Among them, the factor target weight refers to the weight of the influencing factor at the time of loan, which plays a decisive role in the time of loan. If the factor target weight is larger, it means that the corresponding influencing factor has a greater degree of influence at the time of loan.

[0057] For example, assuming that the electronic device obtains three user information, corresponding to the first user, the second user, and the third user respectively. For the first user, the electronic device determines at least one factor target weight according to at least one influencing factor corresponding to the first user. Assuming that the first user information includes five influencing factors, the electronic device determines the factor target weights corresponding to the five influencing factors, which are W1, W2, W3, W4, and W5 respectively.

[0058] S203: For each user, determine at least one product target weight corresponding to each influencing factor according to at least one loan product.

[0059] Among them, the product target weight refers to the weight of the loan product under each influencing factor when making a loan. The larger the product target weight, the greater the degree to which the loan product affects the loan under the influencing factor.

[0060] Exemplarily, assume that there are three loan products, namely the first loan product, the second loan product and the third loan product, and five influencing factors, namely the first influencing factor, the second influencing factor, the third influencing factor, the third influencing factor and the fifth influencing factor. For each influencing factor, the electronic device determines the product target weight corresponding to each loan product.

[0061] For example, the first loan product is taken as an example, as shown in Table 1.

[0062] Table 1

[0063] First Loan Product Second loan product Third loan products The first influencing factor A1W1 A2W1 A3W1 The second influencing factor A1W2 A2W2 A3W2 The third influencing factor A1W3 A2W3 A3W3 The fourth influencing factor A1W4 A2W4 A3W4 The fifth influencing factor A1W5 A2W5 A3W5

[0064] As shown in Table 1, taking the first loan product (B1) as an example, the electronic device determines the corresponding product target weights under the five influencing factors, which are A1W1, A1W2, A1W3, A1W4 and A1W5. Among them, Ai refers to the i-th influencing factor.

[0065] It should be noted that the product importance level corresponding to the same loan product under different influencing factors may be different. It is understandable that the product importance level of the same loan product under different influencing factors may be different due to aspects such as the performance and type of the loan product. Therefore, in this embodiment, it is more appropriate to determine at least one product target weight corresponding to each loan product according to different influencing factors.

[0066] S204, determining a loan product corresponding to the user through a multi-level analysis based on at least one factor target weight and at least one product target weight.

[0067] Furthermore, the electronic device determines the loan product for the first user by performing a multi-level analysis on the five factor target weights (W1, W2, W3, W4 and W5) of the first user and the product target weights of the three loan products under the five influencing factors.

[0068] The present embodiment provides a method for recommending loan products. In the present embodiment, the electronic device determines the factor target weight corresponding to the influencing factor according to at least one influencing factor, so as to obtain the weights occupied by all influencing factors when making loans (i.e., factor target weights). The factor target weights reflect the importance of the corresponding influencing factors on the loan when making loans, and play a decisive role in making loans. Further, the electronic device determines the weights occupied by each loan product under each influencing factor when making loans (i.e., product target weights) according to at least one loan product, and then uses the factor target weights and product target weights to determine the user's loan product. In the present solution, both the factor side and the product side are considered, and the product side is the weight occupied by at least one loan product under each influencing factor when making loans, so the product side is diversified and targeted according to the influencing factors, and the product target weights obtained are more in line with the user, so a more suitable loan product can be determined for the user based on the influencing target weights and product target weights. In addition, the electronic device is used in the present application to realize the recommendation of loan products, and loan products can also be determined for multiple users at the same time, so the present application can provide efficiency.

[0069] Embodiment 2

[0070] This embodiment is a further refinement of any of the above embodiments. This embodiment is an optional method for determining at least one factor target weight according to at least one influencing factor for each user.

[0071] Figure 3 This is a flowchart of a method for recommending a loan product provided in Example 2. Figure 3 As shown, specifically including:

[0072] S301: Obtain a factor importance level corresponding to at least one preset influencing factor.

[0073] Exemplarily, it is assumed that the five influencing factors corresponding to the first user are "having a stable income", "having property rights", "having bad credit", "not married" and "having no loans".

[0074] It should be noted that the electronic device pre-stores the importance level of each influencing factor.

[0075] Among them, the factor importance level refers to the degree of influence of the influencing factor on the loan.

[0076] For example, assume that the importance level of the factor "having stable income" is a1, the importance level of the factor "having property rights" is a2, the importance level of the factor "having bad credit" is a3, the importance level of the factor "not married" is a4, and the importance level of the factor "not having loans" is a5. Among them, a1>a2>a3>a4>a5.

[0077] S302, establishing an influencing factor matrix based on the matrix comparison standard and the factor importance level.

[0078] Among them, the matrix comparison standard is a pre-set comparison table used to generate an influencing factor matrix.

[0079] Exemplarily, in the matrix comparison standard, the judgment value of the importance level of each factor in the influencing factor matrix can be determined, and then the influencing factor matrix is ​​established using the judgment value.

[0080] Specifically, assuming that when a1 is compared with a2, it is determined that a1 is slightly more important than a2, then a standard value is determined in the matrix comparison standard, and then the reciprocal of the standard value is taken as the judgment value P12. This method is used to determine each judgment value in turn, thereby obtaining an influencing factor matrix. As shown in Table 2. Among them, A1 is equally important compared with A1, so P11 is 1, and other influencing factors are similarly compared with themselves, which will not be repeated here.

[0081] Table 2

[0082]

[0083]

[0084] As shown in Table 2, the judgment value of P12 is the judgment value after comparing the importance levels of factors corresponding to A1 and A2. A1 is the first influencing factor, A2 is the second influencing factor, and so on.

[0085] Exemplarily, the matrix comparison criteria are shown in Table 2.

[0086] S303: Using a preset weighting method to perform weight calculation on the influencing factor matrix to determine at least one factor target weight.

[0087] The preset weight method may be any one of the sum method, the sum-product method and the square root method.

[0088] For example, assuming that the preset weight method is the sum method, according to the above Table 2, the factor target weights can be calculated as Table 3.

[0089] Table 3

[0090]

[0091] As shown in Table 3, SUM refers to a sum value. Table 3 includes five sum values, namely S1 to S5. Each sum value is the sum of all judgment values ​​in each column. Exemplarily, S1=1+P12+P13+P14+P15.

[0092] Wherein, W refers to the factor weight, and Table 3 includes five factor weights, namely W1 to W5. The factor weight is the average weight ratio corresponding to the influencing factor, wherein the weight ratio is the ratio of the judgment value to the corresponding sum value. Exemplarily, the weight ratios of the influencing factors are Q1 to Q5, wherein Q1=P11 / S1, Q2=P21 / S2, Q3=P31 / S3, Q4=P41 / S4, and Q4=P51 / S5, wherein W1=(Q1+Q2+Q3+Q4+Q5) / 5, wherein P11=1, and by analogy, the weights of other factors can be calculated, thereby determining the target weights of the five factors.

[0093] In one approach, the factor weights are determined as factor target weights.

[0094] In another way, the five factor weights are determined as the factor pending weights, and the five factor pending weights are verified. If the verification passes, the factor pending weights are determined as the factor target weights.

[0095] It should be noted that, in the exemplary example of this embodiment, at least one factor target weight corresponding to the first user can be determined. The electronic device can also determine at least one factor target weight corresponding to the second user and the third user in the same way.

[0096] The present embodiment provides a method for recommending loan products. In the present embodiment, for each user, the electronic device obtains the factor importance level corresponding to at least one pre-set influencing factor, and then establishes an influencing factor matrix based on the matrix comparison standard and the factor importance level, and then uses the preset weight method to calculate the weight of the influencing factor matrix, and then determines at least one factor target weight. In the present embodiment, collecting the factor importance level and the matrix comparison standard can achieve accuracy comparison, thereby realizing hierarchical analysis. Furthermore, using the preset weight method to obtain the factor target weight can obtain a more accurate factor target weight.

[0097] Embodiment 3

[0098] This embodiment is a further refinement of any of the above embodiments. This embodiment is an optional way to use a preset weight method to calculate the weight of the influencing factor matrix to determine the target weight of at least one factor.

[0099] Figure 4 This is a flowchart of a method for recommending a loan product provided in Example 3. Figure 4 As shown, specifically including:

[0100] S401, using a preset weight method to calculate and obtain a pending weight of at least one factor; the preset weight method includes any one of a sum method, a sum-product method, and a square root method.

[0101] According to the above-mentioned second embodiment, the five factor weights obtained are the factor weights to be determined.

[0102] Among them, the undetermined weight of the factor refers to the undetermined weight corresponding to the influencing factor.

[0103] In the above embodiment, the sum-product method may also be used to calculate the undetermined weight of at least one factor, as shown in Table 4.

[0104] Table 4

[0105]

[0106] Among them, W' is the undetermined weight of the factor determined by the sum-product method. W' is the sum of all weight ratios corresponding to the influencing factors, that is, W'=Q1+Q2+Q3+Q4+Q5.

[0107] S402, verifying at least one pending factor weight by using consistency verification, and in response to the verification passing, determining the pending factor weight as the factor target weight.

[0108] Specifically, the random consistency index RI is determined according to the number of influencing factors.

[0109] For example, the sum method is used to obtain the undetermined weights of the factors. Table 5 is a schematic table of consistency check, as shown in Table 5:

[0110] Table 5

[0111]

[0112] As shown in Table 5, the DW corresponding to each influencing factor is calculated, and the consistency index CI is calculated using the following formula:

[0113] (1)

[0114] Among them, (DW) i is the vector corresponding to the i-th influencing factor, n represents the number of influencing factors, … max is the maximum eigenvalue, W is the factor weight, and in this embodiment, W may be the undetermined weight of the factor.

[0115] (2)

[0116] Among them, CI is the consistency index.

[0117] (3)

[0118] Among them, CR is the degree of consistency.

[0119] Exemplarily, the electronic device calculates DW1 to DW5 using at least one factor with a weight to be determined, further calculates the maximum eigenvalue, thereby calculating the consistency index CI, and determines RI according to the number of influencing factors, and then calculates the consistency degree CR according to formula (3).

[0120] Furthermore, if the consistency degree CR is less than a preset verification threshold, it is determined that the verification is passed, and then the undetermined weight of the factor is determined as the target weight of the factor.

[0121] The preset verification threshold is a preset verification consistency threshold. Exemplarily, the setting of the preset verification threshold is important, and the preset verification threshold may be 0.1, which is not limited here.

[0122] This embodiment provides a method for recommending loan products. In this embodiment, consistency verification is used to verify the undetermined weights of factors, so that more consistent factor target weights can be determined.

[0123] Embodiment 4

[0124] This embodiment is a further refinement of any of the above embodiments. This embodiment is an optional way of determining at least one product target weight corresponding to each influencing factor according to at least one loan product for each user.

[0125] Figure 5 This is a flowchart of a method for recommending a loan product provided in Example 4. Figure 5 As shown, specifically including:

[0126] S501, under each influencing factor, obtain the product importance level corresponding to all loan products under each influencing factor.

[0127] It should be noted that the product importance level of each loan product may be different under different influencing factors, so in this embodiment, the product target weight under different influencing factors should be considered from the product side. For example, the product importance level b11=X1 corresponding to the first loan product (B1) under the first influencing factor, and the product importance level b21=X2 corresponding to the first loan product (B1) under the second influencing factor, so the product importance level in this embodiment is more comprehensive and in line with the actual situation.

[0128] Among them, the product importance level is pre-set, and the product importance level can be represented by bij, where bij refers to the product importance level corresponding to the jth loan product under the ith influencing factor. For example, b12 refers to the product importance level corresponding to the second loan product under the first influencing factor.

[0129] For example, there are three loan products, namely the first loan product, the second loan product and the third loan product. The jth loan product can be represented by Bj, where B1 refers to the first loan product.

[0130] Exemplarily, the electronic device obtains B11 to B13, B21 to B23, B31 to B33, B41 to B43 and B51 to B53 corresponding to B1.

[0131] S502, establishing a loan product matrix under various influencing factors based on the matrix comparison standard and product importance level.

[0132] Similarly, a loan product matrix is ​​established according to the description in the second embodiment.

[0133] It should be noted that the corresponding loan product matrices are established under different influencing factors. According to the above exemplary embodiment, the electronic device needs to establish loan product matrices corresponding to five influencing factors for the first user.

[0134] S503, using a preset weight method to calculate the weight of the loan product matrix to determine at least one product target weight corresponding to each influencing factor.

[0135] According to the description in the second embodiment, the same method is used to determine at least one product target weight corresponding to the five influencing factors.

[0136] This embodiment provides a method for recommending loan products. In this embodiment, the different product importance levels corresponding to various loan products under different influencing factors are taken into consideration, so as to determine at least one product target weight corresponding to each influencing factor, which has stronger pertinence and accuracy.

[0137] Embodiment 5

[0138] This embodiment is a further refinement of any of the above embodiments. This embodiment is an optional method of using a preset weight method to calculate the weight of a loan product matrix to determine at least one product target weight corresponding to each influencing factor.

[0139] Under each influencing factor, at least one product pending weight is calculated using a preset weight method; the preset weight method includes any one of the sum method, the sum-product method and the square root method, and a consistency check is used to verify at least one product pending weight. In response to the verification passing, the product pending weight is determined as the product target weight.

[0140] In this embodiment, the pending product weight is determined as the product target weight according to the description in the above-mentioned embodiment three and embodiment four.

[0141] This embodiment provides a method for recommending loan products. In this embodiment, a consistency check is used to check the pending product weight. Only when the check passes is the pending product weight determined as the product target weight, so that the determined product target weight is more reasonable.

[0142] Embodiment 6

[0143] This embodiment is a further refinement of any of the above embodiments. This embodiment is an optional method for determining the loan product corresponding to the user based on a multi-level analysis of at least one factor target weight and at least one product target weight.

[0144] At least one target value of a loan product is obtained by multi-level analysis using at least one factor target weight and at least one product target weight, and the loan product corresponding to the largest target value is determined as the loan product recommended to the user.

[0145] The target value of the loan product refers to the degree to which the loan product is determined to be the loan product of the user. The larger the target value of the loan product, the greater the degree to which the loan product is determined to be the loan product of the user.

[0146] For example, as shown in Table 6.

[0147] Table 6

[0148]

[0149] Among them, Z1 refers to the sum of the products of all factor target weights and the corresponding product target weights.

[0150] As shown in Table 6, Z1=W1*A1W1+W2*A1W2+W3*A1W3+W4*A1W4+W5*A1W5, and so on, to determine Z2 and Z3, where Zj refers to the loan product target value corresponding to the j-th loan product.

[0151] Further, the electronic device determines a maximum loan product target value, namely Zmax, from at least one loan product target value, and further determines the loan product corresponding to Zmax as the loan product recommended to the user.

[0152] Exemplarily, if Z1 is Zmax, the first loan product (B1) corresponding to Z1 is determined as the loan product recommended to the user.

[0153] The present embodiment provides a method for recommending loan products. In the present embodiment, a target value of a loan product is determined. The target value of the loan product symbolizes the rationality of recommending the loan product to a user, and reflects the degree of determining that the loan product is the loan product for the user. In the present embodiment, the loan product corresponding to the maximum loan product target value is the loan product recommended to the user. Because it is the maximum loan product, its rationality is the largest among multiple loan product target values, so that a more reasonable loan product can be recommended to the user.

[0154] Embodiment 7

[0155] This embodiment is a further refinement of any of the above embodiments, and this embodiment also includes:

[0156] In response to the verification failing, an influencing factor matrix is ​​established using the re-acquired factor importance level corresponding to the at least one influencing factor to determine at least one factor target weight.

[0157] In this embodiment, if the verification fails when determining the factor target weight, the factor importance level corresponding to at least one influencing factor is obtained again, so as to re-establish the influencing factor matrix, and at least one factor pending weight is re-determined based on the new influencing factor matrix according to the same method as above, until the verification of the re-determined factor pending weight passes, then the factor pending weight is determined as the factor target weight.

[0158] This embodiment provides a method for recommending loan products. In this embodiment, if the verification fails, it is necessary to re-acquire the factor importance level and establish a new influencing factor matrix, so as to re-determine at least one factor target weight. Therefore, the factor target weight determined in this embodiment is more reasonable.

[0159] Embodiment 8

[0160] This embodiment is a further refinement of any of the above embodiments, and this embodiment also includes:

[0161] In response to the verification failing, a loan product matrix is ​​established using the re-acquired product importance levels corresponding to each influencing factor to determine at least one product target weight.

[0162] Similarly, in this embodiment, if the verification fails when determining the product target weight, at least one product importance level corresponding to each influencing factor is re-acquired, thereby re-establishing the loan product matrix, and at least one product pending weight is re-determined based on the new loan product matrix according to the same method as above, until the verification of the re-determined product pending weight passes, then the product pending weight is determined as the product target weight.

[0163] This embodiment provides a method for recommending loan products. In this embodiment, if the verification fails, the corresponding product importance level under each influencing factor is re-acquired to establish a loan product matrix, thereby more reasonably determining at least one product target weight.

[0164] Figure 6 A method for recommending loan products is provided in Example 8. Figure 6 As shown, the electronic device performs the following steps:

[0165] S601: The electronic device obtains user information corresponding to a first user, wherein the user information includes at least one influencing factor.

[0166] S602: The electronic device determines at least one factor to be determined weight according to at least one influencing factor.

[0167] S603, the electronic device uses consistency verification to verify the pending weight of at least one factor to determine whether the verification passes. If so, execute S604, if not, execute S608.

[0168] S604: The electronic device determines the undetermined weight of the factor as the target weight of the factor.

[0169] S605, the electronic device determines at least one product pending weight corresponding to each loan product under each influencing factor.

[0170] S606, the electronic device uses consistency verification to verify at least one product's pending weight, and checks whether the verification passes. If so, execute S607, if not, execute S609.

[0171] S607, the electronic device determines the pending weight of the product as the target weight of the product.

[0172] S608: The electronic device reacquires at least one factor importance level and determines the factor target weight.

[0173] S609, the electronic device reacquires at least one product importance level and determines a product target weight.

[0174] S610, the electronic device determines a loan product to be recommended to the first user according to the factor target weights and the product target weights.

[0175] Embodiment 9

[0176] Figure 7 This is a schematic diagram of a loan product recommendation device structure provided in Example 9. The loan product recommendation device 700 includes:

[0177] The acquisition module 701 is used to acquire at least one user information; the user information includes at least one factor affecting the loan;

[0178] A determination module 702, configured to determine at least one factor target weight for each user according to at least one influencing factor;

[0179] The determination module 702 is further configured to determine, for each user, at least one product target weight corresponding to each influencing factor according to at least one loan product;

[0180] The determination module 702 is further used to determine the loan product corresponding to the user through multi-level analysis based on at least one factor target weight and at least one product target weight.

[0181] In one embodiment, when determining at least one factor target weight according to at least one influencing factor for each user, the determination module 702 is specifically configured to:

[0182] Obtaining a factor importance level corresponding to at least one preset influencing factor;

[0183] Establish an influencing factor matrix based on the matrix comparison criteria and the importance of factors;

[0184] The weight of the influencing factor matrix is ​​calculated using a preset weight method to determine at least one factor target weight.

[0185] In one embodiment, when the determination module 702 uses a preset weight method to perform weight calculation on the influencing factor matrix to determine at least one factor target weight, it is specifically used to:

[0186] The preset weight method is used to calculate the undetermined weight of at least one factor; the preset weight method includes any one of the sum method, the sum-product method and the square root method;

[0187] A consistency check is used to check at least one of the pending weights of the factor, and in response to the check passing, the pending weight of the factor is determined as the factor target weight.

[0188] In one embodiment, when determining at least one product target weight corresponding to each influencing factor according to at least one loan product for each user, the determination module 702 is specifically configured to:

[0189] Under each influencing factor, obtain the product importance level corresponding to all loan products under each influencing factor;

[0190] Establish a loan product matrix under various influencing factors based on matrix comparison criteria and product importance levels;

[0191] The preset weight method is used to calculate the weight of the loan product matrix to determine at least one product target weight corresponding to each influencing factor.

[0192] In one embodiment, when the determination module 702 uses a preset weight method to perform weight calculation on the loan product matrix to determine at least one product target weight corresponding to each influencing factor, it is specifically used to:

[0193] Under each influencing factor, at least one product pending weight is calculated using a preset weight method; the preset weight method includes any one of a sum method, a sum-product method, and a square root method;

[0194] A consistency check is performed on at least one product pending weight, and in response to the check passing, the product pending weight is determined as the product target weight.

[0195] In one embodiment, when determining the loan product corresponding to the user through multi-level analysis based on at least one factor target weight and at least one product target weight, the determination module 702 is specifically configured to:

[0196] Obtain at least one loan product target value by using at least one factor target weight and at least one product target weight for multi-level analysis;

[0197] The loan product corresponding to the largest target value is determined as the loan product recommended to the user.

[0198] In one embodiment, the determination module 702 is further configured to:

[0199] In response to the verification failing, an influencing factor matrix is ​​established using the re-acquired factor importance level corresponding to the at least one influencing factor to determine at least one factor target weight.

[0200] In one embodiment, the determination module 702 is further configured to: in response to failure of verification, establish a loan product matrix using the re-acquired product importance levels corresponding to each influencing factor to determine at least one product target weight.

[0201] Embodiment 10

[0202] This embodiment also provides an electronic device, Figure 8 This is a schematic diagram of the structure of an electronic device provided in Example 10. Figure 8 As shown, the electronic device 800 may include: a processor 801, and a memory 802 in communication with the processor 801. The memory 802 stores computer-executable instructions; the processor 801 executes the computer-executable instructions stored in the memory 802 to implement any one of the method embodiments in the above-mentioned embodiments 1 to 8, and the specific implementation methods and technical effects are similar, which will not be repeated here.

[0203] In this embodiment, the transceiver 803, the storage 802 and the processor 801 are connected via a bus. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0204] Embodiment 11

[0205] The present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement any one of the method embodiments of Embodiments 1 to 8 above. The specific implementation methods and technical effects are similar and will not be repeated here.

[0206] Embodiment 12

[0207] The present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements any one of the method embodiments of Embodiments 1 to 8 above. The specific implementation methods and technical effects are similar and will not be repeated here.

[0208] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0209] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-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 the sub-steps or stages of other steps.

[0210] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0211] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0212] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0213] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for recommending loan products, characterized in that: The method comprises: Acquire at least one user information; the user information includes at least one factor affecting the loan; For each user, determining at least one factor target weight according to at least one influencing factor; For each user, determining at least one product target weight corresponding to each influencing factor according to at least one loan product; The loan product corresponding to the user is determined through multi-level analysis based on the at least one factor target weight and the at least one product target weight.

2. The method according to claim 1, characterized in that The step of determining at least one factor target weight for each user according to at least one influencing factor includes: Obtaining a factor importance level corresponding to the at least one preset influencing factor; Establishing an influencing factor matrix based on the matrix comparison criteria and the importance levels of the factors; The influencing factor matrix is ​​weighted by using a preset weight method to determine at least one factor target weight.

3. The method according to claim 2, characterized in that The step of using a preset weight method to perform weight calculation on the influencing factor matrix to determine at least one factor target weight includes: The preset weight method is used to calculate and obtain the undetermined weight of at least one factor; the preset weight method includes any one of the sum method, the sum-product method and the square root method; The at least one factor pending weight is verified by using a consistency check, and in response to the verification passing, the factor pending weight is determined as the factor target weight.

4. The method according to claim 1, characterized in that: The step of determining at least one product target weight corresponding to each influencing factor according to at least one loan product for each user includes: Under each influencing factor, obtain the product importance level corresponding to all loan products under each influencing factor; Establish a loan product matrix under various influencing factors based on the matrix comparison criteria and the product importance level; The loan product matrix is ​​weighted by using a preset weight method to determine at least one product target weight corresponding to each influencing factor.

5. The method according to claim 4, characterized in that The method of using a preset weight method to calculate the weight of the loan product matrix to determine at least one product target weight corresponding to each influencing factor includes: Under each influencing factor, at least one product pending weight is calculated using the preset weight method; the preset weight method includes any one of the sum method, the sum-product method and the square root method; The at least one product pending weight is verified by using a consistency check, and in response to the verification passing, the product pending weight is determined as the product target weight.

6. The method according to claim 1, characterized in that The step of determining the loan product corresponding to the user according to the multi-level analysis of the at least one factor target weight and the at least one product target weight comprises: Obtaining at least one loan product target value by multi-level analysis using the at least one factor target weight and the at least one product target weight; The loan product corresponding to the largest target value is determined as the loan product recommended to the user.

7. The method according to claim 3, characterized in that The method further comprises: In response to the verification failing, an influencing factor matrix is ​​established using the re-acquired factor importance level corresponding to the at least one influencing factor to determine at least one factor target weight.

8. The method according to claim 5, characterized in that The method further comprises: In response to the verification failing, a loan product matrix is ​​established using the re-acquired product importance levels corresponding to each influencing factor to determine at least one product target weight.

9. A device for recommending loan products, characterized in that: The device comprises: An acquisition module, used to acquire at least one user information; the user information includes at least one factor affecting the loan; A determination module, configured to determine at least one factor target weight for each user according to at least one influencing factor; The determination module is further used to determine at least one product target weight corresponding to each influencing factor according to at least one loan product for each user; The determination module is also used to determine the loan product corresponding to the user through multi-level analysis based on the at least one factor target weight and the at least one product target weight.

10. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when being executed by a processor.

Images